weaviate.collections.classes

weaviate.collections.classes.aggregate

class weaviate.collections.classes.aggregate.AggregateInteger(count, maximum, mean, median, minimum, mode, sum_)

Bases: object

The aggregation result for an int property.

Parameters:

• count (int | None)

• maximum (int | None)

• mean (float | None)

• median (float | None)

• minimum (int | None)

• mode (int | None)

• sum_ (int | None)

count: int | None

maximum: int | None

mean: float | None

median: float | None

minimum: int | None

mode: int | None

sum_: int | None

class weaviate.collections.classes.aggregate.AggregateNumber(count, maximum, mean, median, minimum, mode, sum_)

Bases: object

The aggregation result for a number property.

Parameters:

• count (int | None)

• maximum (float | None)

• mean (float | None)

• median (float | None)

• minimum (float | None)

• mode (float | None)

• sum_ (float | None)

count: int | None

maximum: float | None

mean: float | None

median: float | None

minimum: float | None

mode: float | None

sum_: float | None

class weaviate.collections.classes.aggregate.TopOccurrence(count, value)

Bases: object

The top occurrence of a text property.

Parameters:

• count (int | None)

• value (str | None)

count: int | None

value: str | None

class weaviate.collections.classes.aggregate.AggregateText(count, top_occurrences)

Bases: object

The aggregation result for a text property.

Parameters:

• count (int | None)

• top_occurrences (List[TopOccurrence])

count: int | None

top_occurrences: List[TopOccurrence]

class weaviate.collections.classes.aggregate.AggregateBoolean(count, percentage_false, percentage_true, total_false, total_true)

Bases: object

The aggregation result for a boolean property.

Parameters:

• count (int | None)

• percentage_false (float | None)

• percentage_true (float | None)

• total_false (int | None)

• total_true (int | None)

count: int | None

percentage_false: float | None

percentage_true: float | None

total_false: int | None

total_true: int | None

class weaviate.collections.classes.aggregate.AggregateReference(pointing_to)

Bases: object

The aggregation result for a cross-reference property.

Parameters:

pointing_to (List[str] | None)

pointing_to: List[str] | None

class weaviate.collections.classes.aggregate.AggregateDate(count, maximum, median, minimum, mode)

Bases: object

The aggregation result for a date property.

Parameters:

• count (int | None)

• maximum (str | None)

• median (str | None)

• minimum (str | None)

• mode (str | None)

count: int | None

maximum: str | None

median: str | None

minimum: str | None

mode: str | None

class weaviate.collections.classes.aggregate.AggregateReturn(properties, total_count)

Bases: object

The aggregation result for a collection.

Parameters:

• properties (Dict[str, AggregateInteger | AggregateNumber | AggregateText | AggregateBoolean | AggregateDate | AggregateReference])

• total_count (int | None)

properties: Dict[str, AggregateInteger | AggregateNumber | AggregateText | AggregateBoolean | AggregateDate | AggregateReference]

total_count: int | None

class weaviate.collections.classes.aggregate.GroupedBy(prop, value)

Bases: object

The property that the collection was grouped by.

Parameters:

• prop (str)

• value (str | int | float | bool | List[str] | List[int] | List[float] | List[bool] | GeoCoordinate | None)

prop: str

value: str | int | float | bool | List[str] | List[int] | List[float] | List[bool] | GeoCoordinate | None

class weaviate.collections.classes.aggregate.AggregateGroup(grouped_by, properties, total_count)

Bases: object

The aggregation result for a collection grouped by a property.

Parameters:

• grouped_by (GroupedBy)

• properties (Dict[str, AggregateInteger | AggregateNumber | AggregateText | AggregateBoolean | AggregateDate | AggregateReference])

• total_count (int | None)

grouped_by: GroupedBy

properties: Dict[str, AggregateInteger | AggregateNumber | AggregateText | AggregateBoolean | AggregateDate | AggregateReference]

total_count: int | None

class weaviate.collections.classes.aggregate.AggregateGroupByReturn(groups)

Bases: object

The aggregation results for a collection grouped by a property.

Parameters:

groups (List[AggregateGroup])

groups: List[AggregateGroup]

class weaviate.collections.classes.aggregate._MetricsBase(*, property_name, count)

Bases: BaseModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• property_name (str)

• count (bool)

property_name: str

count: bool

to_gql()

Return type:

str

to_grpc()

Return type:

Aggregation

_abc_impl = <_abc._abc_data object>

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.aggregate._MetricsText(*, property_name, count, top_occurrences_count, top_occurrences_value, limit)

Bases: _MetricsBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• property_name (str)

• count (bool)

• top_occurrences_count (bool)

• top_occurrences_value (bool)

• limit (int | None)

top_occurrences_count: bool

top_occurrences_value: bool

limit: int | None

to_gql()

Return type:

str

to_grpc()

Return type:

Aggregation

_abc_impl = <_abc._abc_data object>

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.aggregate._MetricsNum(*, property_name, count, maximum, mean, median, minimum, mode, sum_)

Bases: _MetricsBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• property_name (str)

• count (bool)

• maximum (bool)

• mean (bool)

• median (bool)

• minimum (bool)

• mode (bool)

• sum_ (bool)

maximum: bool

mean: bool

median: bool

minimum: bool

mode: bool

sum_: bool

to_gql()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.aggregate._MetricsInteger(*, property_name, count, maximum, mean, median, minimum, mode, sum_)

Bases: _MetricsNum

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• property_name (str)

• count (bool)

• maximum (bool)

• mean (bool)

• median (bool)

• minimum (bool)

• mode (bool)

• sum_ (bool)

to_grpc()

Return type:

Aggregation

_abc_impl = <_abc._abc_data object>

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.aggregate._MetricsNumber(*, property_name, count, maximum, mean, median, minimum, mode, sum_)

Bases: _MetricsNum

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• property_name (str)

• count (bool)

• maximum (bool)

• mean (bool)

• median (bool)

• minimum (bool)

• mode (bool)

• sum_ (bool)

to_grpc()

Return type:

Aggregation

_abc_impl = <_abc._abc_data object>

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.aggregate._MetricsBoolean(*, property_name, count, percentage_false, percentage_true, total_false, total_true)

Bases: _MetricsBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• property_name (str)

• count (bool)

• percentage_false (bool)

• percentage_true (bool)

• total_false (bool)

• total_true (bool)

percentage_false: bool

percentage_true: bool

total_false: bool

total_true: bool

to_gql()

Return type:

str

to_grpc()

Return type:

Aggregation

_abc_impl = <_abc._abc_data object>

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.aggregate._MetricsDate(*, property_name, count, maximum, median, minimum, mode)

Bases: _MetricsBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• property_name (str)

• count (bool)

• maximum (bool)

• median (bool)

• minimum (bool)

• mode (bool)

maximum: bool

median: bool

minimum: bool

mode: bool

to_gql()

Return type:

str

to_grpc()

Return type:

Aggregation

_abc_impl = <_abc._abc_data object>

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.aggregate._MetricsReference(*, property_name, pointing_to)

Bases: BaseModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• property_name (str)

• pointing_to (bool)

property_name: str

pointing_to: bool

to_gql()

Return type:

str

to_grpc()

Return type:

Aggregation

_abc_impl = <_abc._abc_data object>

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.aggregate.GroupByAggregate(*, prop, limit=None)

Bases: _WeaviateInput

Define how the aggregations’s group-by operation should be performed.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• prop (str)

• limit (int | None)

prop: str

limit: int | None

_to_grpc()

Return type:

GroupBy

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.aggregate.Metrics(property_)

Bases: object

Define the metrics to be returned based on a property when aggregating over a collection.

Use the __init__ method to define the name to the property to be aggregated on. Then use the text, integer, number, boolean, date_, or reference methods to define the metrics to be returned.

See the docs for more details!

Parameters:

property_ (str)

text(count: bool = False, top_occurrences_count: bool = False, top_occurrences_value: bool = False, limit: int | None = None) → _MetricsText

text(count: bool = False, top_occurrences_count: bool = False, top_occurrences_value: bool = False, limit: int | None = None, min_occurrences: int | None = None) → _MetricsText

Define the metrics to be returned for a TEXT or TEXT_ARRAY property when aggregating over a collection.

If none of the arguments are provided then all metrics will be returned.

Parameters:

• count (bool) – Whether to include the number of objects that contain this property.

• top_occurrences_count (bool) – Whether to include the number of the top occurrences of a property’s value.

• top_occurrences_value (bool) – Whether to include the value of the top occurrences of a property’s value.

• min_occurrences (int | None) – (Deprecated) The maximum number of top occurrences to return. Use limit instead.

• limit (int | None) – The maximum number of top occurrences to return.

Returns:

A _MetricsStr object that includes the metrics to be returned.

Return type:

_MetricsText

integer(count=False, maximum=False, mean=False, median=False, minimum=False, mode=False, sum_=False)

Define the metrics to be returned for an INT or INT_ARRAY property when aggregating over a collection.

If none of the arguments are provided then all metrics will be returned.

Parameters:

• count (bool) – Whether to include the number of objects that contain this property.

• maximum (bool) – Whether to include the maximum value of this property.

• mean (bool) – Whether to include the mean value of this property.

• median (bool) – Whether to include the median value of this property.

• minimum (bool) – Whether to include the minimum value of this property.

• mode (bool) – Whether to include the mode value of this property.

• sum – Whether to include the sum of this property.

• sum_ (bool)

Returns:

A _MetricsInteger object that includes the metrics to be returned.

Return type:

_MetricsInteger

number(count=False, maximum=False, mean=False, median=False, minimum=False, mode=False, sum_=False)

Define the metrics to be returned for a NUMBER or NUMBER_ARRAY property when aggregating over a collection.

If none of the arguments are provided then all metrics will be returned.

Parameters:

• count (bool) – Whether to include the number of objects that contain this property.

• maximum (bool) – Whether to include the maximum value of this property.

• mean (bool) – Whether to include the mean value of this property.

• median (bool) – Whether to include the median value of this property.

• minimum (bool) – Whether to include the minimum value of this property.

• mode (bool) – Whether to include the mode value of this property.

• sum – Whether to include the sum of this property.

• sum_ (bool)

Returns:

A _MetricsNumber object that includes the metrics to be returned.

Return type:

_MetricsNumber

boolean(count=False, percentage_false=False, percentage_true=False, total_false=False, total_true=False)

Define the metrics to be returned for a BOOL or BOOL_ARRAY property when aggregating over a collection.

If none of the arguments are provided then all metrics will be returned.

Parameters:

• count (bool) – Whether to include the number of objects that contain this property.

• percentage_false (bool) – Whether to include the percentage of objects that have a false value for this property.

• percentage_true (bool) – Whether to include the percentage of objects that have a true value for this property.

• total_false (bool) – Whether to include the total number of objects that have a false value for this property.

• total_true (bool) – Whether to include the total number of objects that have a true value for this property.

Returns:

A _MetricsBoolean object that includes the metrics to be returned.

Return type:

_MetricsBoolean

date_(count=False, maximum=False, median=False, minimum=False, mode=False)

Define the metrics to be returned for a DATE or DATE_ARRAY property when aggregating over a collection.

If none of the arguments are provided then all metrics will be returned.

Parameters:

• count (bool) – Whether to include the number of objects that contain this property.

• maximum (bool) – Whether to include the maximum value of this property.

• median (bool) – Whether to include the median value of this property.

• minimum (bool) – Whether to include the minimum value of this property.

• mode (bool) – Whether to include the mode value of this property.

Returns:

A _MetricsDate object that includes the metrics to be returned.

Return type:

_MetricsDate

reference(pointing_to=False)

Define the metrics to be returned for a cross-reference property when aggregating over a collection.

If none of the arguments are provided then all metrics will be returned.

Parameters:

pointing_to (bool) – The UUIDs of the objects that are being pointed to.

Returns:

A _MetricsReference object that includes the metrics to be returned.

Return type:

_MetricsReference

weaviate.collections.classes.batch

class weaviate.collections.classes.batch._BatchObject(collection: str, vector: Mapping[str, Sequence[int | float] | Sequence[Sequence[int | float]]] | Sequence[int | float] | NoneType, uuid: str, properties: Dict[str, NoneType | str | bool | int | float | datetime.datetime | uuid.UUID | weaviate.collections.classes.types.GeoCoordinate | weaviate.collections.classes.types.PhoneNumber | weaviate.collections.classes.types._PhoneNumber | Mapping[str, ForwardRef('WeaviateField')] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime.datetime] | Sequence[uuid.UUID] | Sequence[Mapping[str, ForwardRef('WeaviateField')]]] | None, tenant: str | None, references: Mapping[str, str | uuid.UUID | Sequence[str | uuid.UUID] | weaviate.collections.classes.internal.ReferenceToMulti] | None, index: int, retry_count: int = 0)

Bases: object

Parameters:

• collection (str)

• vector (Mapping[str, Sequence[int | float] | Sequence[Sequence[int | float]]] | Sequence[int | float] | None)

• uuid (str)

• properties (Dict[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, WeaviateField] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, WeaviateField]]] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, WeaviateField] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, WeaviateField]]]]] | None)

• tenant (str | None)

• references (Mapping[str, str | UUID | Sequence[str | UUID] | ReferenceToMulti] | None)

• index (int)

• retry_count (int)

collection: str

vector: Mapping[str, Sequence[int | float] | Sequence[Sequence[int | float]]] | Sequence[int | float] | None

uuid: str

properties: Dict[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, WeaviateField] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, WeaviateField]]] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, WeaviateField] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, WeaviateField]]]]] | None

tenant: str | None

references: Mapping[str, str | UUID | Sequence[str | UUID] | ReferenceToMulti] | None

index: int

retry_count: int = 0

class weaviate.collections.classes.batch._BatchReference(from_: str, to: str, tenant: str | None, from_uuid: str, to_uuid: str | None, index: int)

Bases: object

Parameters:

• from_ (str)

• to (str)

• tenant (str | None)

• from_uuid (str)

• to_uuid (str | None)

• index (int)

from_: str

to: str

tenant: str | None

from_uuid: str

to_uuid: str | None

index: int

class weaviate.collections.classes.batch.BatchObject(*, collection, properties=None, references=None, uuid=None, vector=None, tenant=None, index, retry_count=0)

Bases: BaseModel

A Weaviate object to be added to the database.

Performs validation on the class name and UUID, and automatically generates a UUID if one is not provided. Also converts the vector to a list of floats if it is provided as a numpy array.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• collection (Annotated[str, MinLen(min_length=1)])

• properties (Dict[str, Any] | None)

• references (Mapping[str, str | UUID | Sequence[str | UUID] | ReferenceToMulti] | None)

• uuid (str | UUID | None)

• vector (Mapping[str, Sequence[int | float] | Sequence[Sequence[int | float]]] | Sequence[int | float] | None)

• tenant (str | None)

• index (int)

• retry_count (int)

collection: str

properties: Dict[str, Any] | None

references: Mapping[str, str | UUID | Sequence[str | UUID] | ReferenceToMulti] | None

uuid: str | UUID | None

vector: Mapping[str, Sequence[int | float] | Sequence[Sequence[int | float]]] | Sequence[int | float] | None

tenant: str | None

index: int

retry_count: int

_to_internal()

Return type:

_BatchObject

classmethod _from_internal(obj)

Parameters:

obj (_BatchObject)

Return type:

BatchObject

classmethod _validate_collection(v)

Parameters:

v (str)

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.batch.Shard(*, collection, tenant=None)

Bases: BaseModel

Use this class when defining a shard whose vector indexing process will be awaited for in a sync blocking fashion.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• collection (str)

• tenant (str | None)

collection: str

tenant: str | None

_abc_impl = <_abc._abc_data object>

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.batch.BatchReference(*, from_object_collection, from_object_uuid, from_property_name, to_object_uuid, to_object_collection=None, tenant=None, index)

Bases: BaseModel

A reference between two objects in Weaviate.

Performs validation on the class names and UUIDs.

Converts provided data to an internal object containing beacons for insertion into Weaviate.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• from_object_collection (Annotated[str, MinLen(min_length=1)])

• from_object_uuid (str | UUID)

• from_property_name (str)

• to_object_uuid (str | UUID)

• to_object_collection (str | None)

• tenant (str | None)

• index (int)

from_object_collection: str

from_object_uuid: str | UUID

from_property_name: str

to_object_uuid: str | UUID

to_object_collection: str | None

tenant: str | None

index: int

classmethod _validate_from_object_collection(v)

Parameters:

v (str)

Return type:

str

classmethod _validate_to_object_collection(v)

Parameters:

v (str | None)

Return type:

str | None

classmethod _validate_uuids(v)

Parameters:

v (str | UUID)

Return type:

str

_to_internal()

Return type:

_BatchReference

classmethod _from_internal(ref)

Parameters:

ref (_BatchReference)

Return type:

BatchReference

_to_beacon()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.batch.ErrorObject(message, object_, original_uuid=None)

Bases: object

This class contains the error information for a single object in a batch operation.

Parameters:

• message (str)

• object_ (BatchObject)

• original_uuid (str | UUID | None)

message: str

object_: BatchObject

original_uuid: str | UUID | None = None

class weaviate.collections.classes.batch.ErrorReference(message, reference)

Bases: object

This class contains the error information for a single reference in a batch operation.

Parameters:

• message (str)

• reference (BatchReference)

message: str

reference: BatchReference

class weaviate.collections.classes.batch.BatchObjectReturn(_all_responses=<factory>, elapsed_seconds=0.0, errors=<factory>, uuids=<factory>, has_errors=False)

Bases: object

This class contains the results of a batch insert_many operation.

Since the individual objects within the batch can error for differing reasons, the data is split up within this class for ease use when performing error checking, handling, and data revalidation.

Note

Due to concerns over memory usage, this object will only ever store the last MAX_STORED_RESULTS uuids in the uuids dictionary and MAX_STORED_RESULTS in the all_responses list. If more than MAX_STORED_RESULTS uuids are added to the dictionary, the oldest uuids will be removed. If the number of objects inserted in this batch exceeds MAX_STORED_RESULTS, the all_responses list will only contain the last MAX_STORED_RESULTS objects. The keys of the errors and uuids dictionaries will always be equivalent to the original_index of the objects as you added them to the batching loop but won’t necessarily be the same as the indices in the all_responses list because of this.

Parameters:

• _all_responses (List[UUID | ErrorObject])

• elapsed_seconds (float)

• errors (Dict[int, ErrorObject])

• uuids (Dict[int, UUID])

• has_errors (bool)

elapsed_seconds

The time taken to perform the batch operation.

Type:

float

errors

A dictionary of all the failed responses from the batch operation. The keys are the indices of the objects in the batch, and the values are the Error objects.

Type:

Dict[int, weaviate.collections.classes.batch.ErrorObject]

uuids

A dictionary of all the successful responses from the batch operation. The keys are the indices of the objects in the batch, and the values are the uuid_package.UUID objects.

Type:

Dict[int, uuid.UUID]

has_errors

A boolean indicating whether or not any of the objects in the batch failed to be inserted. If this is True, then the errors dictionary will contain at least one entry.

Type:

bool

_all_responses: List[UUID | ErrorObject]

elapsed_seconds: float = 0.0

errors: Dict[int, ErrorObject]

uuids: Dict[int, UUID]

has_errors: bool = False

property all_responses: List[UUID | ErrorObject]

A list of all the responses from the batch operation. Each response is either a uuid_package.UUID object or an Error object.

WARNING: This only stores the last MAX_STORED_RESULTS objects. If more than MAX_STORED_RESULTS objects are added to the batch, the oldest objects will be removed from this list.

Type:

@deprecated

add_uuids(uuids)

Add a list of uuids to the batch return object.

Parameters:

uuids (Dict[int, UUID])

Return type:

None

add_errors(errors)

Add a list of errors to the batch return object.

Parameters:

errors (Dict[int, ErrorObject])

Return type:

None

class weaviate.collections.classes.batch.BatchReferenceReturn(elapsed_seconds=0.0, errors=<factory>, has_errors=False)

Bases: object

This class contains the results of a batch insert_many_references operation.

Since the individual references within the batch can error for differing reasons, the data is split up within this class for ease use when performing error checking, handling, and data revalidation.

Parameters:

• elapsed_seconds (float)

• errors (Dict[int, ErrorReference])

• has_errors (bool)

elapsed_seconds

The time taken to perform the batch operation.

Type:

float

errors

A dictionary of all the failed responses from the batch operation. The keys are the indices of the references in the batch, and the values are the Error objects.

Type:

Dict[int, weaviate.collections.classes.batch.ErrorReference]

has_errors

A boolean indicating whether or not any of the references in the batch failed to be inserted. If this is True, then the errors dictionary will contain at least one entry.

Type:

bool

elapsed_seconds: float = 0.0

errors: Dict[int, ErrorReference]

has_errors: bool = False

add_errors(errors)

Add a list of errors to the batch return object.

Parameters:

errors (Dict[int, ErrorReference])

Return type:

None

class weaviate.collections.classes.batch.BatchResult

Bases: object

This class contains the results of a batch operation.

Since the individual objects and references within the batch can error for differing reasons, the data is split up within this class for ease use when performing error checking, handling, and data revalidation.

objs

The results of the batch object operation.

Type:

weaviate.collections.classes.batch.BatchObjectReturn

refs

The results of the batch reference operation.

Type:

weaviate.collections.classes.batch.BatchReferenceReturn

objs: BatchObjectReturn

refs: BatchReferenceReturn

class weaviate.collections.classes.batch.DeleteManyObject(uuid, successful, error=None)

Bases: object

This class contains the objects of a delete_many operation.

Parameters:

• uuid (UUID)

• successful (bool)

• error (str | None)

uuid: UUID

successful: bool

error: str | None = None

class weaviate.collections.classes.batch.DeleteManyReturn(failed, matches, objects, successful)

Bases: Generic[T]

This class contains the results of a delete_many operation..

Parameters:

• failed (int)

• matches (int)

• objects (T)

• successful (int)

failed: int

matches: int

objects: T

successful: int

weaviate.collections.classes.cluster

class weaviate.collections.classes.cluster.Shard(collection, name, node, object_count, vector_indexing_status, vector_queue_length, compressed, loaded)

Bases: object

The properties of a single shard of a collection.

Parameters:

• collection (str)

• name (str)

• node (str)

• object_count (int)

• vector_indexing_status (Literal['READONLY', 'INDEXING', 'READY', 'LAZY_LOADING'])

• vector_queue_length (int)

• compressed (bool)

• loaded (bool | None)

collection: str

name: str

node: str

object_count: int

vector_indexing_status: Literal['READONLY', 'INDEXING', 'READY', 'LAZY_LOADING']

vector_queue_length: int

compressed: bool

loaded: bool | None

class weaviate.collections.classes.cluster.Stats(object_count, shard_count)

Bases: object

The statistics of a collection.

Parameters:

• object_count (int)

• shard_count (int)

object_count: int

shard_count: int

class weaviate.collections.classes.cluster.Node(git_hash, name, shards, stats, status, version)

Bases: Generic[Sh, St]

The properties of a single node in the cluster.

Parameters:

• git_hash (str)

• name (str)

• shards (Sh)

• stats (St)

• status (str)

• version (str)

git_hash: str

name: str

shards: Sh

stats: St

status: str

version: str

class weaviate.collections.classes.cluster._ConvertFromREST

Bases: object

static nodes_verbose(nodes)

Parameters:

nodes (List[Node])

Return type:

List[Node[List[Shard], Stats]]

static nodes_minimal(nodes)

Parameters:

nodes (List[Node])

Return type:

List[Node[None, None]]

weaviate.collections.classes.config

class weaviate.collections.classes.config.ConsistencyLevel(*values)

Bases: str, BaseEnum

The consistency levels when writing to Weaviate with replication enabled.

ALL

Wait for confirmation of write success from all, N, replicas.

ONE

Wait for confirmation of write success from only one replica.

QUORUM

Wait for confirmation of write success from a quorum: N/2+1, of replicas.

ALL = 'ALL'

ONE = 'ONE'

QUORUM = 'QUORUM'

class weaviate.collections.classes.config.DataType(*values)

Bases: str, BaseEnum

The available primitive data types in Weaviate.

TEXT

Text data type.

TEXT_ARRAY

Text array data type.

INT

Integer data type.

INT_ARRAY

Integer array data type.

BOOL

Boolean data type.

BOOL_ARRAY

Boolean array data type.

NUMBER

Number data type.

NUMBER_ARRAY

Number array data type.

DATE

Date data type.

DATE_ARRAY

Date array data type.

UUID

UUID data type.

UUID_ARRAY

UUID array data type.

GEO_COORDINATES

Geo coordinates data type.

BLOB

Blob data type.

BLOB_HASH

Blob hash data type.

PHONE_NUMBER

Phone number data type.

OBJECT

Object data type.

OBJECT_ARRAY

Object array data type.

TEXT = 'text'

TEXT_ARRAY = 'text[]'

INT = 'int'

INT_ARRAY = 'int[]'

BOOL = 'boolean'

BOOL_ARRAY = 'boolean[]'

NUMBER = 'number'

NUMBER_ARRAY = 'number[]'

DATE = 'date'

DATE_ARRAY = 'date[]'

UUID = 'uuid'

UUID_ARRAY = 'uuid[]'

GEO_COORDINATES = 'geoCoordinates'

BLOB = 'blob'

BLOB_HASH = 'blobHash'

PHONE_NUMBER = 'phoneNumber'

OBJECT = 'object'

OBJECT_ARRAY = 'object[]'

class weaviate.collections.classes.config.Tokenization(*values)

Bases: str, BaseEnum

The available inverted index tokenization methods for text properties in Weaviate.

WORD

Tokenize by word.

WHITESPACE

Tokenize by whitespace.

LOWERCASE

Tokenize by lowercase.

FIELD

Tokenize by field.

GSE

Tokenize using GSE (for Chinese and Japanese).

TRIGRAM

Tokenize into trigrams.

KAGOME_JA

Tokenize using the ‘Kagome’ tokenizer (for Japanese).

KAGOME_KR

Tokenize using the ‘Kagome’ tokenizer and a Korean MeCab dictionary (for Korean).

GSE_CH

Tokenize using GSE (for Chinese).

WORD = 'word'

WHITESPACE = 'whitespace'

LOWERCASE = 'lowercase'

FIELD = 'field'

GSE = 'gse'

TRIGRAM = 'trigram'

KAGOME_JA = 'kagome_ja'

KAGOME_KR = 'kagome_kr'

GSE_CH = 'gse_ch'

class weaviate.collections.classes.config.GenerativeSearches(*values)

Bases: str, BaseEnum

The available generative search modules in Weaviate.

These modules generate text from text-based inputs. See the docs for more details.

AWS

Weaviate module backed by AWS Bedrock generative models.

ANTHROPIC

Weaviate module backed by Anthropic generative models.

ANYSCALE

Weaviate module backed by Anyscale generative models.

COHERE

Weaviate module backed by Cohere generative models.

CONTEXTUALAI

Weaviate module backed by ContextualAI generative models.

DATABRICKS

Weaviate module backed by Databricks generative models.

FRIENDLIAI

Weaviate module backed by FriendliAI generative models.

MISTRAL

Weaviate module backed by Mistral generative models.

NVIDIA

Weaviate module backed by NVIDIA generative models.

OLLAMA

Weaviate module backed by generative models deployed on Ollama infrastructure.

OPENAI

Weaviate module backed by OpenAI and Azure-OpenAI generative models.

PALM

Weaviate module backed by PaLM generative models.

AWS = 'generative-aws'

ANTHROPIC = 'generative-anthropic'

ANYSCALE = 'generative-anyscale'

COHERE = 'generative-cohere'

CONTEXTUALAI = 'generative-contextualai'

DATABRICKS = 'generative-databricks'

DUMMY = 'generative-dummy'

FRIENDLIAI = 'generative-friendliai'

MISTRAL = 'generative-mistral'

NVIDIA = 'generative-nvidia'

OLLAMA = 'generative-ollama'

OPENAI = 'generative-openai'

PALM = 'generative-palm'

XAI = 'generative-xai'

class weaviate.collections.classes.config.Rerankers(*values)

Bases: str, BaseEnum

The available reranker modules in Weaviate.

These modules rerank the results of a search query. See the docs for more details.

NONE

No reranker.

COHERE

Weaviate module backed by Cohere reranking models.

CONTEXTUALAI

Weaviate module backed by ContextualAI reranking models.

TRANSFORMERS

Weaviate module backed by Transformers reranking models.

VOYAGEAI

Weaviate module backed by VoyageAI reranking models.

JINAAI

Weaviate module backed by JinaAI reranking models.

NVIDIA

Weaviate module backed by NVIDIA reranking models.

NONE = 'none'

COHERE = 'reranker-cohere'

CONTEXTUALAI = 'reranker-contextualai'

TRANSFORMERS = 'reranker-transformers'

VOYAGEAI = 'reranker-voyageai'

JINAAI = 'reranker-jinaai'

NVIDIA = 'reranker-nvidia'

class weaviate.collections.classes.config.StopwordsPreset(*values)

Bases: str, BaseEnum

Preset stopwords to use in the Stopwords class.

EN

English stopwords.

NONE

No stopwords.

NONE = 'none'

EN = 'en'

class weaviate.collections.classes.config.ReplicationDeletionStrategy(*values)

Bases: str, BaseEnum

How object deletions in multi node environments should be resolved.

PERMANENT_DELETION

Once an object has been deleted on one node it will be deleted on all nodes in case of conflicts.

NO_AUTOMATED_RESOLUTION

No deletion resolution.

DELETE_ON_CONFLICT = 'DeleteOnConflict'

NO_AUTOMATED_RESOLUTION = 'NoAutomatedResolution'

TIME_BASED_RESOLUTION = 'TimeBasedResolution'

class weaviate.collections.classes.config._ShardingConfigCreate(*, virtualPerPhysical, desiredCount, desiredVirtualCount, key='_id', strategy='hash', function='murmur3')

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• virtualPerPhysical (int | None)

• desiredCount (int | None)

• desiredVirtualCount (int | None)

• key (str)

• strategy (str)

• function (str)

virtualPerPhysical: int | None

desiredCount: int | None

desiredVirtualCount: int | None

key: str

strategy: str

function: str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._AsyncReplicationConfigCreate(*, maxWorkers, hashtreeHeight, frequency, frequencyWhilePropagating, aliveNodesCheckingFrequency, loggingFrequency, diffBatchSize, diffPerNodeTimeout, prePropagationTimeout, propagationTimeout, propagationLimit, propagationDelay, propagationConcurrency, propagationBatchSize)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• maxWorkers (int | None)

• hashtreeHeight (int | None)

• frequency (int | None)

• frequencyWhilePropagating (int | None)

• aliveNodesCheckingFrequency (int | None)

• loggingFrequency (int | None)

• diffBatchSize (int | None)

• diffPerNodeTimeout (int | None)

• prePropagationTimeout (int | None)

• propagationTimeout (int | None)

• propagationLimit (int | None)

• propagationDelay (int | None)

• propagationConcurrency (int | None)

• propagationBatchSize (int | None)

maxWorkers: int | None

hashtreeHeight: int | None

frequency: int | None

frequencyWhilePropagating: int | None

aliveNodesCheckingFrequency: int | None

loggingFrequency: int | None

diffBatchSize: int | None

diffPerNodeTimeout: int | None

prePropagationTimeout: int | None

propagationTimeout: int | None

propagationLimit: int | None

propagationDelay: int | None

propagationConcurrency: int | None

propagationBatchSize: int | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._AsyncReplicationConfigUpdate(*, maxWorkers, hashtreeHeight, frequency, frequencyWhilePropagating, aliveNodesCheckingFrequency, loggingFrequency, diffBatchSize, diffPerNodeTimeout, prePropagationTimeout, propagationTimeout, propagationLimit, propagationDelay, propagationConcurrency, propagationBatchSize)

Bases: _ConfigUpdateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• maxWorkers (int | None)

• hashtreeHeight (int | None)

• frequency (int | None)

• frequencyWhilePropagating (int | None)

• aliveNodesCheckingFrequency (int | None)

• loggingFrequency (int | None)

• diffBatchSize (int | None)

• diffPerNodeTimeout (int | None)

• prePropagationTimeout (int | None)

• propagationTimeout (int | None)

• propagationLimit (int | None)

• propagationDelay (int | None)

• propagationConcurrency (int | None)

• propagationBatchSize (int | None)

maxWorkers: int | None

hashtreeHeight: int | None

frequency: int | None

frequencyWhilePropagating: int | None

aliveNodesCheckingFrequency: int | None

loggingFrequency: int | None

diffBatchSize: int | None

diffPerNodeTimeout: int | None

prePropagationTimeout: int | None

propagationTimeout: int | None

propagationLimit: int | None

propagationDelay: int | None

propagationConcurrency: int | None

propagationBatchSize: int | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._ReplicationConfigCreate(*, factor, asyncEnabled, asyncConfig, deletionStrategy)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• factor (int | None)

• asyncEnabled (bool | None)

• asyncConfig (_AsyncReplicationConfigCreate | None)

• deletionStrategy (ReplicationDeletionStrategy | None)

factor: int | None

asyncEnabled: bool | None

asyncConfig: _AsyncReplicationConfigCreate | None

deletionStrategy: ReplicationDeletionStrategy | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._ReplicationConfigUpdate(*, factor, asyncEnabled, asyncConfig, deletionStrategy)

Bases: _ConfigUpdateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• factor (int | None)

• asyncEnabled (bool | None)

• asyncConfig (_AsyncReplicationConfigUpdate | None)

• deletionStrategy (ReplicationDeletionStrategy | None)

factor: int | None

asyncEnabled: bool | None

asyncConfig: _AsyncReplicationConfigUpdate | None

deletionStrategy: ReplicationDeletionStrategy | None

merge_with_existing(schema)

Parameters:

schema (Dict[str, Any])

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._BM25ConfigCreate(*, b, k1)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• b (float)

• k1 (float)

b: float

k1: float

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._BM25ConfigUpdate(*, b, k1)

Bases: _ConfigUpdateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• b (float | None)

• k1 (float | None)

b: float | None

k1: float | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._StopwordsCreate(*, preset, additions, removals)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• preset (StopwordsPreset | None)

• additions (List[str] | None)

• removals (List[str] | None)

preset: StopwordsPreset | None

additions: List[str] | None

removals: List[str] | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._StopwordsUpdate(*, preset, additions, removals)

Bases: _ConfigUpdateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• preset (StopwordsPreset | None)

• additions (List[str] | None)

• removals (List[str] | None)

preset: StopwordsPreset | None

additions: List[str] | None

removals: List[str] | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._InvertedIndexConfigCreate(*, bm25, cleanupIntervalSeconds, indexTimestamps, indexPropertyLength, indexNullState, stopwords, stopwordPresets=None)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• bm25 (_BM25ConfigCreate | None)

• cleanupIntervalSeconds (int | None)

• indexTimestamps (bool | None)

• indexPropertyLength (bool | None)

• indexNullState (bool | None)

• stopwords (_StopwordsCreate)

• stopwordPresets (Dict[str, List[str]] | None)

bm25: _BM25ConfigCreate | None

cleanupIntervalSeconds: int | None

indexTimestamps: bool | None

indexPropertyLength: bool | None

indexNullState: bool | None

stopwords: _StopwordsCreate

stopwordPresets: Dict[str, List[str]] | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._InvertedIndexConfigUpdate(*, bm25, cleanupIntervalSeconds, stopwords, stopwordPresets=None)

Bases: _ConfigUpdateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• bm25 (_BM25ConfigUpdate | None)

• cleanupIntervalSeconds (int | None)

• stopwords (_StopwordsUpdate | None)

• stopwordPresets (Dict[str, List[str]] | None)

bm25: _BM25ConfigUpdate | None

cleanupIntervalSeconds: int | None

stopwords: _StopwordsUpdate | None

stopwordPresets: Dict[str, List[str]] | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._MultiTenancyConfigCreate(*, enabled, autoTenantCreation, autoTenantActivation)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• enabled (bool)

• autoTenantCreation (bool | None)

• autoTenantActivation (bool | None)

enabled: bool

autoTenantCreation: bool | None

autoTenantActivation: bool | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._MultiTenancyConfigUpdate(*, autoTenantCreation, autoTenantActivation)

Bases: _ConfigUpdateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• autoTenantCreation (bool | None)

• autoTenantActivation (bool | None)

autoTenantCreation: bool | None

autoTenantActivation: bool | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeProvider(*, generative)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

generative (GenerativeSearches | _EnumLikeStr)

generative: GenerativeSearches | _EnumLikeStr

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeAnyscale(*, generative=GenerativeSearches.ANYSCALE, baseURL, temperature, model)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• baseURL (str | None)

• temperature (float | None)

• model (str | None)

generative: GenerativeSearches | _EnumLikeStr

baseURL: str | None

temperature: float | None

model: str | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeCustom(*, generative, module_config)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• module_config (Dict[str, Any] | None)

module_config: Dict[str, Any] | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeDatabricks(*, generative=GenerativeSearches.DATABRICKS, endpoint, maxTokens, temperature, topK, topP)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• endpoint (str)

• maxTokens (int | None)

• temperature (float | None)

• topK (int | None)

• topP (float | None)

generative: GenerativeSearches | _EnumLikeStr

endpoint: str

maxTokens: int | None

temperature: float | None

topK: int | None

topP: float | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeMistral(*, generative=GenerativeSearches.MISTRAL, temperature, model, maxTokens, baseURL)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• temperature (float | None)

• model (str | None)

• maxTokens (int | None)

• baseURL (str | None)

generative: GenerativeSearches | _EnumLikeStr

temperature: float | None

model: str | None

maxTokens: int | None

baseURL: str | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeNvidia(*, generative=GenerativeSearches.NVIDIA, temperature, model, maxTokens, baseURL)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• temperature (float | None)

• model (str | None)

• maxTokens (int | None)

• baseURL (str | None)

generative: GenerativeSearches | _EnumLikeStr

temperature: float | None

model: str | None

maxTokens: int | None

baseURL: str | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeXai(*, generative=GenerativeSearches.XAI, temperature, model, maxTokens, baseURL, topP)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• temperature (float | None)

• model (str | None)

• maxTokens (int | None)

• baseURL (str | None)

• topP (float | None)

generative: GenerativeSearches | _EnumLikeStr

temperature: float | None

model: str | None

maxTokens: int | None

baseURL: str | None

topP: float | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeFriendliai(*, generative=GenerativeSearches.FRIENDLIAI, temperature, model, maxTokens, baseURL)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• temperature (float | None)

• model (str | None)

• maxTokens (int | None)

• baseURL (str | None)

generative: GenerativeSearches | _EnumLikeStr

temperature: float | None

model: str | None

maxTokens: int | None

baseURL: str | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeOllama(*, generative=GenerativeSearches.OLLAMA, model, apiEndpoint)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• model (str | None)

• apiEndpoint (str | None)

generative: GenerativeSearches | _EnumLikeStr

model: str | None

apiEndpoint: str | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeOpenAIConfigBase(*, generative=GenerativeSearches.OPENAI, baseURL, frequencyPenalty, presencePenalty, maxTokens, temperature, topP)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• baseURL (AnyHttpUrl | None)

• frequencyPenalty (float | None)

• presencePenalty (float | None)

• maxTokens (int | None)

• temperature (float | None)

• topP (float | None)

generative: GenerativeSearches | _EnumLikeStr

baseURL: AnyHttpUrl | None

frequencyPenalty: float | None

presencePenalty: float | None

maxTokens: int | None

temperature: float | None

topP: float | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeOpenAIConfig(*, generative=GenerativeSearches.OPENAI, baseURL, frequencyPenalty, presencePenalty, maxTokens, temperature, topP, model, verbosity, reasoningEffort)

Bases: _GenerativeOpenAIConfigBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• baseURL (AnyHttpUrl | None)

• frequencyPenalty (float | None)

• presencePenalty (float | None)

• maxTokens (int | None)

• temperature (float | None)

• topP (float | None)

• model (str | None)

• verbosity (str | None)

• reasoningEffort (str | None)

model: str | None

verbosity: str | None

reasoningEffort: str | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeAzureOpenAIConfig(*, generative=GenerativeSearches.OPENAI, baseURL, frequencyPenalty, presencePenalty, maxTokens, temperature, topP, resourceName, deploymentId)

Bases: _GenerativeOpenAIConfigBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• baseURL (AnyHttpUrl | None)

• frequencyPenalty (float | None)

• presencePenalty (float | None)

• maxTokens (int | None)

• temperature (float | None)

• topP (float | None)

• resourceName (str)

• deploymentId (str)

resourceName: str

deploymentId: str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeCohereConfig(*, generative=GenerativeSearches.COHERE, baseURL, k, model, maxTokens, stopSequences, temperature)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• baseURL (AnyHttpUrl | None)

• k (int | None)

• model (str | None)

• maxTokens (int | None)

• stopSequences (List[str] | None)

• temperature (float | None)

generative: GenerativeSearches | _EnumLikeStr

baseURL: AnyHttpUrl | None

k: int | None

model: str | None

maxTokens: int | None

stopSequences: List[str] | None

temperature: float | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeContextualAIConfig(*, generative=GenerativeSearches.CONTEXTUALAI, model, temperature, topP, maxNewTokens, systemPrompt, avoidCommentary, knowledge)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• model (str | None)

• temperature (float | None)

• topP (float | None)

• maxNewTokens (int | None)

• systemPrompt (str | None)

• avoidCommentary (bool | None)

• knowledge (List[str] | None)

generative: GenerativeSearches | _EnumLikeStr

model: str | None

temperature: float | None

topP: float | None

maxNewTokens: int | None

systemPrompt: str | None

avoidCommentary: bool | None

knowledge: List[str] | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeGoogleConfig(*, generative=GenerativeSearches.PALM, apiEndpoint, endpointId, region, maxOutputTokens, modelId, projectId, temperature, topK, topP, stopSequences, frequencyPenalty, presencePenalty)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• apiEndpoint (str | None)

• endpointId (str | None)

• region (str | None)

• maxOutputTokens (int | None)

• modelId (str | None)

• projectId (str)

• temperature (float | None)

• topK (int | None)

• topP (float | None)

• stopSequences (list[str] | None)

• frequencyPenalty (float | None)

• presencePenalty (float | None)

generative: GenerativeSearches | _EnumLikeStr

apiEndpoint: str | None

endpointId: str | None

region: str | None

maxOutputTokens: int | None

modelId: str | None

projectId: str

temperature: float | None

topK: int | None

topP: float | None

stopSequences: list[str] | None

frequencyPenalty: float | None

presencePenalty: float | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeAWSConfig(*, generative=GenerativeSearches.AWS, region, service, model, endpoint, temperature, targetModel, targetVariant, topK, topP, stopSequences, maxTokens)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• region (str)

• service (str)

• model (str | None)

• endpoint (str | None)

• temperature (float | None)

• targetModel (str | None)

• targetVariant (str | None)

• topK (int | None)

• topP (float | None)

• stopSequences (List[str] | None)

• maxTokens (int | None)

generative: GenerativeSearches | _EnumLikeStr

region: str

service: str

model: str | None

endpoint: str | None

temperature: float | None

targetModel: str | None

targetVariant: str | None

topK: int | None

topP: float | None

stopSequences: List[str] | None

maxTokens: int | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._GenerativeAnthropicConfig(*, generative=GenerativeSearches.ANTHROPIC, model, maxTokens, stopSequences, temperature, topK, topP)

Bases: _GenerativeProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• generative (GenerativeSearches | _EnumLikeStr)

• model (str | None)

• maxTokens (int | None)

• stopSequences (List[str] | None)

• temperature (float | None)

• topK (int | None)

• topP (float | None)

generative: GenerativeSearches | _EnumLikeStr

model: str | None

maxTokens: int | None

stopSequences: List[str] | None

temperature: float | None

topK: int | None

topP: float | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._RerankerProvider(*, reranker)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

reranker (Rerankers | _EnumLikeStr)

reranker: Rerankers | _EnumLikeStr

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._RerankerCohereConfig(*, reranker=Rerankers.COHERE, model=None, baseURL)

Bases: _RerankerProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• reranker (Rerankers | _EnumLikeStr)

• model (Literal['rerank-english-v2.0', 'rerank-multilingual-v2.0'] | str | None)

• baseURL (AnyHttpUrl | None)

reranker: Rerankers | _EnumLikeStr

model: Literal['rerank-english-v2.0', 'rerank-multilingual-v2.0'] | str | None

baseURL: AnyHttpUrl | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._RerankerCustomConfig(*, reranker, module_config)

Bases: _RerankerProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• reranker (Rerankers | _EnumLikeStr)

• module_config (Dict[str, Any] | None)

module_config: Dict[str, Any] | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._RerankerTransformersConfig(*, reranker=Rerankers.TRANSFORMERS)

Bases: _RerankerProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

reranker (Rerankers | _EnumLikeStr)

reranker: Rerankers | _EnumLikeStr

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._RerankerJinaAIConfig(*, reranker=Rerankers.JINAAI, model=None)

Bases: _RerankerProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• reranker (Rerankers | _EnumLikeStr)

• model (Literal['jina-reranker-v2-base-multilingual', 'jina-reranker-v1-base-en', 'jina-reranker-v1-turbo-en', 'jina-reranker-v1-tiny-en', 'jina-colbert-v1-en'] | str | None)

reranker: Rerankers | _EnumLikeStr

model: Literal['jina-reranker-v2-base-multilingual', 'jina-reranker-v1-base-en', 'jina-reranker-v1-turbo-en', 'jina-reranker-v1-tiny-en', 'jina-colbert-v1-en'] | str | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._RerankerVoyageAIConfig(*, reranker=Rerankers.VOYAGEAI, model=None)

Bases: _RerankerProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• reranker (Rerankers | _EnumLikeStr)

• model (Literal['rerank-2', 'rerank-2-lite', 'rerank-lite-1', 'rerank-1'] | str | None)

reranker: Rerankers | _EnumLikeStr

model: Literal['rerank-2', 'rerank-2-lite', 'rerank-lite-1', 'rerank-1'] | str | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._RerankerNvidiaConfig(*, reranker=Rerankers.NVIDIA, model=None, baseURL)

Bases: _RerankerProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• reranker (Rerankers | _EnumLikeStr)

• model (str | None)

• baseURL (AnyHttpUrl | None)

reranker: Rerankers | _EnumLikeStr

model: str | None

baseURL: AnyHttpUrl | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._RerankerContextualAIConfig(*, reranker=Rerankers.CONTEXTUALAI, model=None, instruction=None, topN=None)

Bases: _RerankerProvider

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• reranker (Rerankers | _EnumLikeStr)

• model (Literal['ctxl-rerank-v2-instruct-multilingual', 'ctxl-rerank-v2-instruct-multilingual-mini', 'ctxl-rerank-v1-instruct'] | str | None)

• instruction (str | None)

• topN (int | None)

reranker: Rerankers | _EnumLikeStr

model: Literal['ctxl-rerank-v2-instruct-multilingual', 'ctxl-rerank-v2-instruct-multilingual-mini', 'ctxl-rerank-v1-instruct'] | str | None

instruction: str | None

topN: int | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._Generative

Bases: object

Use this factory class to create the correct object for the generative_config argument in the collections.create() method.

Each staticmethod provides options specific to the named generative search module in the function’s name. Under-the-hood data validation steps will ensure that any mis-specifications will be caught before the request is sent to Weaviate.

static anyscale(model=None, temperature=None, base_url=None)

Create a _GenerativeAnyscale object for use when generating using the generative-anyscale module.

Parameters:

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• base_url (str | None) – The base URL where the API request should go. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static custom(module_name, module_config=None)

Create a _GenerativeCustom object for use when generating using a custom specification.

Parameters:

• module_name (str) – The name of the module to use, REQUIRED.

• module_config (Dict[str, Any] | None) – The configuration to use for the module. Defaults to None, which uses the server-defined default.

Return type:

_GenerativeProvider

static databricks(*, endpoint, max_tokens=None, temperature=None, top_k=None, top_p=None)

Create a _GenerativeDatabricks object for use when performing AI generation using the generative-databricks module.

Parameters:

• endpoint (str) – The URL where the API request should go. Defaults to None, which uses the server-defined default

• max_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• top_k (int | None) – The top K value to use. Defaults to None, which uses the server-defined default

• top_p (float | None) – The top P value to use. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static friendliai(*, base_url=None, model=None, temperature=None, max_tokens=None)

Create a _GenerativeFriendliai object for use when performing AI generation using the generative-friendliai module.

Parameters:

• base_url (str | None) – The base URL where the API request should go. Defaults to None, which uses the server-defined default

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• max_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static mistral(model=None, temperature=None, max_tokens=None, base_url=None)

Create a _GenerativeMistral object for use when performing AI generation using the generative-mistral module.

Parameters:

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• max_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

• base_url (str | None) – The base URL where the API request should go. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static nvidia(*, base_url=None, model=None, temperature=None, max_tokens=None)

Create a _GenerativeNvidia object for use when performing AI generation using the generative-nvidia module.

Parameters:

• base_url (str | None) – The base URL where the API request should go. Defaults to None, which uses the server-defined default

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• max_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static xai(*, base_url=None, model=None, temperature=None, max_tokens=None, top_p=None)

Create a _GenerativeXai object for use when performing AI generation using the generative-xai module.

Parameters:

• base_url (str | None) – The base URL where the API request should go. Defaults to None, which uses the server-defined default

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• max_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

• top_p (float | None) – The top P value to use. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static ollama(*, api_endpoint=None, model=None)

Create a _GenerativeOllama object for use when performing AI generation using the generative-ollama module.

Parameters:

• api_endpoint (str | None) – The API endpoint to use. Defaults to None, which uses the server-defined default Docker users may need to specify an alias, such as http://host.docker.internal:11434 so that the container can access the host machine.

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static openai(model=None, frequency_penalty=None, max_tokens=None, presence_penalty=None, temperature=None, top_p=None, base_url=None, *, verbosity=None, reasoning_effort=None)

Create a _GenerativeOpenAIConfig object for use when performing AI generation using the generative-openai module.

See the documentation for detailed usage.

Parameters:

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

• frequency_penalty (float | None) – The frequency penalty to use. Defaults to None, which uses the server-defined default

• max_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

• presence_penalty (float | None) – The presence penalty to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• top_p (float | None) – The top P to use. Defaults to None, which uses the server-defined default

• base_url (AnyHttpUrl | None) – The base URL where the API request should go. Defaults to None, which uses the server-defined default

• verbosity (Literal['low', 'medium', 'high'] | str | None) – The verbosity level to use. One of ‘low’, ‘medium’, ‘high’. Defaults to None, which uses the server-defined default

• reasoning_effort (Literal['minimal', 'low', 'medium', 'high'] | str | None) – The reasoning effort level to use. One of ‘minimal’, ‘low

Return type:

_GenerativeProvider

static azure_openai(resource_name, deployment_id, frequency_penalty=None, max_tokens=None, presence_penalty=None, temperature=None, top_p=None, base_url=None)

Create a _GenerativeAzureOpenAIConfig object for use when performing AI generation using the generative-openai module.

See the documentation for detailed usage.

Parameters:

• resource_name (str) – The name of the Azure OpenAI resource to use.

• deployment_id (str) – The Azure OpenAI deployment ID to use.

• frequency_penalty (float | None) – The frequency penalty to use. Defaults to None, which uses the server-defined default

• max_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

• presence_penalty (float | None) – The presence penalty to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• top_p (float | None) – The top P to use. Defaults to None, which uses the server-defined default

• base_url (AnyHttpUrl | None) – The base URL where the API request should go. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static cohere(model=None, k=None, max_tokens=None, return_likelihoods=None, stop_sequences=None, temperature=None, base_url=None)

Create a _GenerativeCohereConfig object for use when performing AI generation using the generative-cohere module.

See the documentation for detailed usage.

Parameters:

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

• k (int | None) – The number of sequences to generate. Defaults to None, which uses the server-defined default

• max_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

• return_likelihoods (str | None) – (Deprecated) The return likelihoods setting to use. No longer has any effect.

• stop_sequences (List[str] | None) – The stop sequences to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• base_url (AnyHttpUrl | None) – The base URL where the API request should go. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static contextualai(model=None, max_new_tokens=None, temperature=None, top_p=None, system_prompt=None, avoid_commentary=None, knowledge=None)

Create a _GenerativeContextualAIConfig object for use when performing AI generation using the generative-contextualai module.

See the documentation for detailed usage.

Parameters:

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

• max_new_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• top_p (float | None) – Nucleus sampling parameter (0 < x <= 1). Defaults to None, which uses the server-defined default

• system_prompt (str | None) – System instructions the model follows. Defaults to None, which uses the server-defined default

• avoid_commentary (bool | None) – If True, reduce conversational commentary in responses. Defaults to None, which uses the server-defined default

• knowledge (List[str] | None) – Additional detailed knowledge sources with varied information. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static palm(project_id, api_endpoint=None, max_output_tokens=None, model_id=None, temperature=None, top_k=None, top_p=None)

Deprecated since version 4.9.0.

This method is deprecated and will be removed in Q2 ‘25. Please use google() instead.

Create a _GenerativePaLMConfig object for use when performing AI generation using the generative-palm module.

See the documentation for detailed usage.

Args:

project_id: The PalM project ID to use. api_endpoint: The API endpoint to use without a leading scheme such as http://. Defaults to None, which uses the server-defined default max_output_tokens: The maximum number of tokens to generate. Defaults to None, which uses the server-defined default model_id: The model ID to use. Defaults to None, which uses the server-defined default temperature: The temperature to use. Defaults to None, which uses the server-defined default top_k: The top K to use. Defaults to None, which uses the server-defined default top_p: The top P to use. Defaults to None, which uses the server-defined default

Parameters:

• project_id (str)

• api_endpoint (str | None)

• max_output_tokens (int | None)

• model_id (str | None)

• temperature (float | None)

• top_k (int | None)

• top_p (float | None)

Return type:

_GenerativeProvider

static google(project_id, api_endpoint=None, max_output_tokens=None, model_id=None, temperature=None, top_k=None, top_p=None)

Create a _GenerativeGoogleConfig object for use when performing AI generation using the generative-google module.

See the documentation for detailed usage.

Parameters:

• project_id (str) – The PalM project ID to use.

• api_endpoint (str | None) – The API endpoint to use without a leading scheme such as http://. Defaults to None, which uses the server-defined default

• max_output_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

• model_id (str | None) – The model ID to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• top_k (int | None) – The top K to use. Defaults to None, which uses the server-defined default

• top_p (float | None) – The top P to use. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static google_vertex(project_id, api_endpoint=None, region=None, max_output_tokens=None, model_id=None, endpoint_id=None, temperature=None, top_k=None, top_p=None)

Create a _GenerativeGoogleConfig object for use when performing AI generation using the generative-google module.

See the documentation for detailed usage.

Parameters:

• project_id (str) – The Google Vertex project ID to use.

• api_endpoint (str | None) – The API endpoint to use without a leading scheme such as http://. Defaults to None, which uses the server-defined default

• region (str | None) – The region to use. Defaults to None, which uses the server-defined default

• max_output_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

• model_id (str | None) – The model ID to use. Defaults to None, which uses the server-defined default

• endpoint_id (str | None) – The endpoint ID to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• top_k (int | None) – The top K to use. Defaults to None, which uses the server-defined default

• top_p (float | None) – The top P to use. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static google_gemini(max_output_tokens=None, model=None, temperature=None, top_k=None, top_p=None)

Create a _GenerativeGoogleConfig object for use when performing AI generation using the generative-google module with the Gemini API.

See the documentation for detailed usage.

Parameters:

• max_output_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• top_k (int | None) – The top K to use. Defaults to None, which uses the server-defined default

• top_p (float | None) – The top P to use. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static aws(model=None, region='', endpoint=None, service='bedrock', max_tokens=None)

Create a _GenerativeAWSConfig object for use when performing AI generation using the generative-aws module.

See the documentation for detailed usage.

Parameters:

• model (str | None) – The model to use, REQUIRED for service “bedrock”.

• max_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default.

• region (str) – The AWS region to run the model from, REQUIRED.

• endpoint (str | None) – The model to use, REQUIRED for service “sagemaker”.

• service (Literal['bedrock', 'sagemaker'] | str) – The AWS service to use, options are “bedrock” and “sagemaker”.

Return type:

_GenerativeProvider

static aws_bedrock(model, region, temperature=None, max_tokens=None, top_k=None, top_p=None, stop_sequences=None)

Create a _GenerativeAWSConfig object for use when performing AI generation using the generative-aws module.

See the documentation for detailed usage.

Parameters:

• model (str) – The model to use, REQUIRED

• region (str) – The AWS region to run the model from, REQUIRED.

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• max_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default.

• top_k (int | None) – The top K to use. Defaults to None, which uses the server-defined default

• top_p (float | None) – The top P to use. Defaults to None, which uses the server-defined default

• stop_sequences (List[str] | None) – The stop sequences to use. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static aws_sagemaker(region, endpoint, max_tokens=None, target_model=None, target_variant=None, temperature=None, top_k=None, top_p=None, stop_sequences=None)

Create a _GenerativeAWSConfig object for use when performing AI generation using the generative-aws module.

See the documentation for detailed usage.

Parameters:

• region (str) – The AWS region to run the model from, REQUIRED.

• endpoint (str) – The model to use, REQUIRED.

• max_tokens (int | None) – The maximum token count to generate. Defaults to None, which uses the server-defined default.

• target_model (str | None) – The target model to use. Defaults to None, which uses the server-defined default

• target_variant (str | None) – The target variant to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• top_k (int | None) – The top K to use. Defaults to None, which uses the server-defined default

• top_p (float | None) – The top P to use. Defaults to None, which uses the server-defined default

• stop_sequences (List[str] | None) – The stop sequences to use. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

static anthropic(model=None, max_tokens=None, stop_sequences=None, temperature=None, top_k=None, top_p=None)

Create a _GenerativeAnthropicConfig object for use when performing AI generation using the generative-anthropic module.

Parameters:

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

• max_tokens (int | None) – The maximum number of tokens to generate. Defaults to None, which uses the server-defined default

• stop_sequences (List[str] | None) – The stop sequences to use. Defaults to None, which uses the server-defined default

• temperature (float | None) – The temperature to use. Defaults to None, which uses the server-defined default

• top_k (int | None) – The top K to use. Defaults to None, which uses the server-defined default

• top_p (float | None) – The top P to use. Defaults to None, which uses the server-defined default

Return type:

_GenerativeProvider

class weaviate.collections.classes.config._Reranker

Bases: object

Use this factory class to create the correct object for the reranker_config argument in the collections.create() method.

Each staticmethod provides options specific to the named reranker in the function’s name. Under-the-hood data validation steps will ensure that any mis-specifications will be caught before the request is sent to Weaviate.

static transformers()

Create a _RerankerTransformersConfig object for use when reranking using the reranker-transformers module.

See the documentation for detailed usage.

Return type:

_RerankerProvider

static custom(module_name, module_config=None)

Create a _RerankerCustomConfig object for use when reranking using a custom module.

Parameters:

• module_name (str) – The name of the module to use, REQUIRED.

• module_config (Dict[str, Any] | None) – The configuration to use for the module. Defaults to None, which uses the server-defined default.

Return type:

_RerankerProvider

static cohere(model=None, base_url=None)

Create a _RerankerCohereConfig object for use when reranking using the reranker-cohere module.

See the documentation for detailed usage.

Parameters:

• model (Literal['rerank-english-v2.0', 'rerank-multilingual-v2.0'] | str | None) – The model to use. Defaults to None, which uses the server-defined default

• base_url (str | None) – The base URL to send the reranker requests to. Defaults to None, which uses the server-defined default.

Return type:

_RerankerProvider

static jinaai(model=None)

Create a _RerankerJinaAIConfig object for use when reranking using the reranker-jinaai module.

See the documentation for detailed usage.

Parameters:

model (Literal['jina-reranker-v2-base-multilingual', 'jina-reranker-v1-base-en', 'jina-reranker-v1-turbo-en', 'jina-reranker-v1-tiny-en', 'jina-colbert-v1-en'] | str | None) – The model to use. Defaults to None, which uses the server-defined default

Return type:

_RerankerProvider

static voyageai(model=None)

Create a _RerankerVoyageAIConfig object for use when reranking using the reranker-voyageai module.

See the documentation for detailed usage.

Parameters:

model (Literal['rerank-2', 'rerank-2-lite', 'rerank-lite-1', 'rerank-1'] | str | None) – The model to use. Defaults to None, which uses the server-defined default

Return type:

_RerankerProvider

static nvidia(model=None, base_url=None)

Create a _RerankerNvidiaConfig object for use when reranking using the reranker-nvidia module.

See the documentation for detailed usage.

Parameters:

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

• base_url (AnyHttpUrl | None) – The base URL to send the reranker requests to. Defaults to None, which uses the server-defined default.

Return type:

_RerankerProvider

static contextualai(model=None, instruction=None, top_n=None)

Create a _RerankerContextualAIConfig object for use when reranking using the reranker-contextualai module.

See the documentation for detailed usage.

Parameters:

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default

• instruction (str | None) – Custom instructions for reranking. Defaults to None.

• top_n (int | None) – Number of top results to return. Defaults to None, which uses the server-defined default.

Return type:

_RerankerProvider

class weaviate.collections.classes.config._CollectionConfigUpdate(*, description=None, property_descriptions=None, inverted_index_config=None, object_ttl_config=None, replication_config=None, vector_index_config=None, vectorizer_config=None, vector_config=None, multi_tenancy_config=None, generative_config=None, reranker_config=None)

Bases: _ConfigUpdateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• description (str | None)

• property_descriptions (Dict[str, str] | None)

• inverted_index_config (_InvertedIndexConfigUpdate | None)

• object_ttl_config (_ObjectTTLConfigUpdate | None)

• replication_config (_ReplicationConfigUpdate | None)

• vector_index_config (_VectorIndexConfigUpdate | None)

• vectorizer_config (_VectorIndexConfigUpdate | List[_NamedVectorConfigUpdate] | None)

• vector_config (_VectorConfigUpdate | List[_VectorConfigUpdate] | None)

• multi_tenancy_config (_MultiTenancyConfigUpdate | None)

• generative_config (_GenerativeProvider | None)

• reranker_config (_RerankerProvider | None)

description: str | None

property_descriptions: Dict[str, str] | None

invertedIndexConfig: _InvertedIndexConfigUpdate | None

objectTTLConfig: _ObjectTTLConfigUpdate | None

replicationConfig: _ReplicationConfigUpdate | None

vectorIndexConfig: _VectorIndexConfigUpdate | None

vectorizerConfig: _VectorIndexConfigUpdate | List[_NamedVectorConfigUpdate] | None

vectorConfig: _VectorConfigUpdate | List[_VectorConfigUpdate] | None

multiTenancyConfig: _MultiTenancyConfigUpdate | None

generativeConfig: _GenerativeProvider | None

rerankerConfig: _RerankerProvider | None

classmethod mutual_exclusivity(v, info)

Parameters:

• v (_VectorConfigUpdate | List[_VectorConfigUpdate] | None)

• info (ValidationInfo)

merge_with_existing(schema)

Parameters:

schema (Dict[str, Any])

Return type:

Dict[str, Any]

static _CollectionConfigUpdate__add_to_module_config(return_dict, addition_key, addition_val)

Parameters:

• return_dict (Dict[str, Any])

• addition_key (str)

• addition_val (Dict[str, Any])

Return type:

None

_CollectionConfigUpdate__check_quantizers(quantizer, vector_index_config)

Parameters:

• quantizer (_QuantizerConfigUpdate | None)

• vector_index_config (dict)

Return type:

None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._BM25Config(b: float, k1: float)

Bases: _ConfigBase

Parameters:

• b (float)

• k1 (float)

b: float

k1: float

weaviate.collections.classes.config.BM25Config

alias of _BM25Config

class weaviate.collections.classes.config._StopwordsConfig(preset: weaviate.collections.classes.config.StopwordsPreset, additions: List[str] | None, removals: List[str] | None)

Bases: _ConfigBase

Parameters:

• preset (StopwordsPreset)

• additions (List[str] | None)

• removals (List[str] | None)

preset: StopwordsPreset

additions: List[str] | None

removals: List[str] | None

weaviate.collections.classes.config.StopwordsConfig

alias of _StopwordsConfig

weaviate.collections.classes.config.StopwordsCreate

alias of _StopwordsCreate

class weaviate.collections.classes.config._InvertedIndexConfig(bm25: weaviate.collections.classes.config._BM25Config, cleanup_interval_seconds: int, index_null_state: bool, index_property_length: bool, index_timestamps: bool, stopwords: weaviate.collections.classes.config._StopwordsConfig, stopword_presets: Dict[str, List[str]] | None = None)

Bases: _ConfigBase

Parameters:

• bm25 (_BM25Config)

• cleanup_interval_seconds (int)

• index_null_state (bool)

• index_property_length (bool)

• index_timestamps (bool)

• stopwords (_StopwordsConfig)

• stopword_presets (Dict[str, List[str]] | None)

bm25: _BM25Config

cleanup_interval_seconds: int

index_null_state: bool

index_property_length: bool

index_timestamps: bool

stopwords: _StopwordsConfig

stopword_presets: Dict[str, List[str]] | None = None

weaviate.collections.classes.config.InvertedIndexConfig

alias of _InvertedIndexConfig

class weaviate.collections.classes.config._MultiTenancyConfig(enabled: bool, auto_tenant_creation: bool, auto_tenant_activation: bool)

Bases: _ConfigBase

Parameters:

• enabled (bool)

• auto_tenant_creation (bool)

• auto_tenant_activation (bool)

enabled: bool

auto_tenant_creation: bool

auto_tenant_activation: bool

weaviate.collections.classes.config.MultiTenancyConfig

alias of _MultiTenancyConfig

class weaviate.collections.classes.config._PropertyVectorizerConfig(skip: bool, vectorize_property_name: bool)

Bases: object

Parameters:

• skip (bool)

• vectorize_property_name (bool)

skip: bool

vectorize_property_name: bool

weaviate.collections.classes.config.PropertyVectorizerConfig

alias of _PropertyVectorizerConfig

class weaviate.collections.classes.config._TextAnalyzerConfig(ascii_fold: bool, ascii_fold_ignore: List[str] | None, stopword_preset: str | None)

Bases: _ConfigBase

Parameters:

• ascii_fold (bool)

• ascii_fold_ignore (List[str] | None)

• stopword_preset (str | None)

ascii_fold: bool

ascii_fold_ignore: List[str] | None

stopword_preset: str | None

weaviate.collections.classes.config.TextAnalyzerConfig

alias of _TextAnalyzerConfig

class weaviate.collections.classes.config._NestedProperty(data_type: weaviate.collections.classes.config.DataType, description: str | None, index_filterable: bool, index_searchable: bool, name: str, nested_properties: List[ForwardRef('NestedProperty')] | None, text_analyzer: weaviate.collections.classes.config._TextAnalyzerConfig | None, tokenization: weaviate.collections.classes.config.Tokenization | None)

Bases: _ConfigBase

Parameters:

• data_type (DataType)

• description (str | None)

• index_filterable (bool)

• index_searchable (bool)

• name (str)

• nested_properties (List[_NestedProperty] | None)

• text_analyzer (_TextAnalyzerConfig | None)

• tokenization (Tokenization | None)

data_type: DataType

description: str | None

index_filterable: bool

index_searchable: bool

name: str

nested_properties: List[_NestedProperty] | None

text_analyzer: _TextAnalyzerConfig | None

tokenization: Tokenization | None

to_dict()

Return type:

Dict[str, Any]

weaviate.collections.classes.config.NestedProperty

alias of _NestedProperty

class weaviate.collections.classes.config._PropertyBase(name: str, description: str | None)

Bases: _ConfigBase

Parameters:

• name (str)

• description (str | None)

name: str

description: str | None

to_dict()

Return type:

Dict[str, Any]

class weaviate.collections.classes.config._Property(name: str, description: str | None, data_type: weaviate.collections.classes.config.DataType, index_filterable: bool, index_range_filters: bool, index_searchable: bool, nested_properties: List[weaviate.collections.classes.config._NestedProperty] | None, text_analyzer: weaviate.collections.classes.config._TextAnalyzerConfig | None, tokenization: weaviate.collections.classes.config.Tokenization | None, vectorizer_config: weaviate.collections.classes.config._PropertyVectorizerConfig | None, vectorizer: str | None, vectorizer_configs: Dict[str, weaviate.collections.classes.config._PropertyVectorizerConfig] | None)

Bases: _PropertyBase

Parameters:

• name (str)

• description (str | None)

• data_type (DataType)

• index_filterable (bool)

• index_range_filters (bool)

• index_searchable (bool)

• nested_properties (List[_NestedProperty] | None)

• text_analyzer (_TextAnalyzerConfig | None)

• tokenization (Tokenization | None)

• vectorizer_config (_PropertyVectorizerConfig | None)

• vectorizer (str | None)

• vectorizer_configs (Dict[str, _PropertyVectorizerConfig] | None)

data_type: DataType

index_filterable: bool

index_range_filters: bool

index_searchable: bool

nested_properties: List[_NestedProperty] | None

text_analyzer: _TextAnalyzerConfig | None

tokenization: Tokenization | None

vectorizer_config: _PropertyVectorizerConfig | None

vectorizer: str | None

vectorizer_configs: Dict[str, _PropertyVectorizerConfig] | None

to_dict()

Return type:

Dict[str, Any]

weaviate.collections.classes.config.PropertyConfig

alias of _Property

class weaviate.collections.classes.config._ReferenceProperty(name: str, description: str | None, target_collections: List[str])

Bases: _PropertyBase

Parameters:

• name (str)

• description (str | None)

• target_collections (List[str])

target_collections: List[str]

to_dict()

Return type:

Dict[str, Any]

weaviate.collections.classes.config.ReferencePropertyConfig

alias of _ReferenceProperty

class weaviate.collections.classes.config._AsyncReplicationConfig(max_workers: int | None, hashtree_height: int | None, frequency: int | None, frequency_while_propagating: int | None, alive_nodes_checking_frequency: int | None, logging_frequency: int | None, diff_batch_size: int | None, diff_per_node_timeout: int | None, pre_propagation_timeout: int | None, propagation_timeout: int | None, propagation_limit: int | None, propagation_delay: int | None, propagation_concurrency: int | None, propagation_batch_size: int | None)

Bases: _ConfigBase

Parameters:

• max_workers (int | None)

• hashtree_height (int | None)

• frequency (int | None)

• frequency_while_propagating (int | None)

• alive_nodes_checking_frequency (int | None)

• logging_frequency (int | None)

• diff_batch_size (int | None)

• diff_per_node_timeout (int | None)

• pre_propagation_timeout (int | None)

• propagation_timeout (int | None)

• propagation_limit (int | None)

• propagation_delay (int | None)

• propagation_concurrency (int | None)

• propagation_batch_size (int | None)

max_workers: int | None

hashtree_height: int | None

frequency: int | None

frequency_while_propagating: int | None

alive_nodes_checking_frequency: int | None

logging_frequency: int | None

diff_batch_size: int | None

diff_per_node_timeout: int | None

pre_propagation_timeout: int | None

propagation_timeout: int | None

propagation_limit: int | None

propagation_delay: int | None

propagation_concurrency: int | None

propagation_batch_size: int | None

weaviate.collections.classes.config.AsyncReplicationConfig

alias of _AsyncReplicationConfig

class weaviate.collections.classes.config._ReplicationConfig(factor: int, async_enabled: bool, deletion_strategy: weaviate.collections.classes.config.ReplicationDeletionStrategy, async_config: weaviate.collections.classes.config._AsyncReplicationConfig | None = None)

Bases: _ConfigBase

Parameters:

• factor (int)

• async_enabled (bool)

• deletion_strategy (ReplicationDeletionStrategy)

• async_config (_AsyncReplicationConfig | None)

factor: int

async_enabled: bool

deletion_strategy: ReplicationDeletionStrategy

async_config: _AsyncReplicationConfig | None = None

weaviate.collections.classes.config.ReplicationConfig

alias of _ReplicationConfig

class weaviate.collections.classes.config._ShardingConfig(virtual_per_physical: int, desired_count: int, actual_count: int, desired_virtual_count: int, actual_virtual_count: int, key: str, strategy: str, function: str)

Bases: _ConfigBase

Parameters:

• virtual_per_physical (int)

• desired_count (int)

• actual_count (int)

• desired_virtual_count (int)

• actual_virtual_count (int)

• key (str)

• strategy (str)

• function (str)

virtual_per_physical: int

desired_count: int

actual_count: int

desired_virtual_count: int

actual_virtual_count: int

key: str

strategy: str

function: str

weaviate.collections.classes.config.ShardingConfig

alias of _ShardingConfig

class weaviate.collections.classes.config._PQEncoderConfig(type_: weaviate.collections.classes.config_vector_index.PQEncoderType, distribution: weaviate.collections.classes.config_vector_index.PQEncoderDistribution)

Bases: _ConfigBase

Parameters:

• type_ (PQEncoderType)

• distribution (PQEncoderDistribution)

type_: PQEncoderType

distribution: PQEncoderDistribution

to_dict()

Return type:

Dict[str, Any]

weaviate.collections.classes.config.PQEncoderConfig

alias of _PQEncoderConfig

class weaviate.collections.classes.config._PQConfig(internal_bit_compression: bool, segments: int, centroids: int, training_limit: int, encoder: weaviate.collections.classes.config._PQEncoderConfig)

Bases: _ConfigBase

Parameters:

• internal_bit_compression (bool)

• segments (int)

• centroids (int)

• training_limit (int)

• encoder (_PQEncoderConfig)

internal_bit_compression: bool

segments: int

centroids: int

training_limit: int

encoder: _PQEncoderConfig

property bit_compression: bool

weaviate.collections.classes.config.PQConfig

alias of _PQConfig

class weaviate.collections.classes.config._BQConfig(cache: bool | None, rescore_limit: int)

Bases: _ConfigBase

Parameters:

• cache (bool | None)

• rescore_limit (int)

cache: bool | None

rescore_limit: int

class weaviate.collections.classes.config._SQConfig(rescore_limit: int, training_limit: int)

Bases: _ConfigBase

Parameters:

• rescore_limit (int)

• training_limit (int)

rescore_limit: int

training_limit: int

class weaviate.collections.classes.config._RQConfig(cache: bool | None, bits: int | None, rescore_limit: int)

Bases: _ConfigBase

Parameters:

• cache (bool | None)

• bits (int | None)

• rescore_limit (int)

cache: bool | None

bits: int | None

rescore_limit: int

weaviate.collections.classes.config.BQConfig

alias of _BQConfig

weaviate.collections.classes.config.SQConfig

alias of _SQConfig

weaviate.collections.classes.config.RQConfig

alias of _RQConfig

class weaviate.collections.classes.config._MuveraConfig(enabled: bool | None, ksim: int | None, dprojections: int | None, repetitions: int | None)

Bases: _ConfigBase

Parameters:

• enabled (bool | None)

• ksim (int | None)

• dprojections (int | None)

• repetitions (int | None)

enabled: bool | None

ksim: int | None

dprojections: int | None

repetitions: int | None

weaviate.collections.classes.config.MuveraConfig

alias of _MuveraConfig

class weaviate.collections.classes.config._MultiVectorConfig(encoding: weaviate.collections.classes.config._MuveraConfig | None, aggregation: str)

Bases: _ConfigBase

Parameters:

• encoding (_MuveraConfig | None)

• aggregation (str)

encoding: _MuveraConfig | None

aggregation: str

weaviate.collections.classes.config.MultiVector

alias of _MultiVectorConfig

class weaviate.collections.classes.config._VectorIndexConfig(multi_vector: weaviate.collections.classes.config._MultiVectorConfig | None, quantizer: weaviate.collections.classes.config._PQConfig | weaviate.collections.classes.config._BQConfig | weaviate.collections.classes.config._SQConfig | weaviate.collections.classes.config._RQConfig | NoneType)

Bases: _ConfigBase

Parameters:

• multi_vector (_MultiVectorConfig | None)

• quantizer (_PQConfig | _BQConfig | _SQConfig | _RQConfig | None)

multi_vector: _MultiVectorConfig | None

quantizer: _PQConfig | _BQConfig | _SQConfig | _RQConfig | None

to_dict()

Return type:

Dict[str, Any]

class weaviate.collections.classes.config._VectorIndexConfigHNSW(multi_vector: weaviate.collections.classes.config._MultiVectorConfig | None, quantizer: weaviate.collections.classes.config._PQConfig | weaviate.collections.classes.config._BQConfig | weaviate.collections.classes.config._SQConfig | weaviate.collections.classes.config._RQConfig | NoneType, cleanup_interval_seconds: int, distance_metric: weaviate.collections.classes.config_vectorizers.VectorDistances, dynamic_ef_min: int, dynamic_ef_max: int, dynamic_ef_factor: int, ef: int, ef_construction: int, filter_strategy: weaviate.collections.classes.config_vector_index.VectorFilterStrategy, flat_search_cutoff: int, max_connections: int, skip: bool, vector_cache_max_objects: int)

Bases: _VectorIndexConfig

Parameters:

• multi_vector (_MultiVectorConfig | None)

• quantizer (_PQConfig | _BQConfig | _SQConfig | _RQConfig | None)

• cleanup_interval_seconds (int)

• distance_metric (VectorDistances)

• dynamic_ef_min (int)

• dynamic_ef_max (int)

• dynamic_ef_factor (int)

• ef (int)

• ef_construction (int)

• filter_strategy (VectorFilterStrategy)

• flat_search_cutoff (int)

• max_connections (int)

• skip (bool)

• vector_cache_max_objects (int)

cleanup_interval_seconds: int

distance_metric: VectorDistances

dynamic_ef_min: int

dynamic_ef_max: int

dynamic_ef_factor: int

ef: int

ef_construction: int

filter_strategy: VectorFilterStrategy

flat_search_cutoff: int

max_connections: int

skip: bool

vector_cache_max_objects: int

static vector_index_type()

Return type:

str

weaviate.collections.classes.config.VectorIndexConfigHNSW

alias of _VectorIndexConfigHNSW

class weaviate.collections.classes.config._VectorIndexConfigHFresh(multi_vector: weaviate.collections.classes.config._MultiVectorConfig | None, quantizer: weaviate.collections.classes.config._PQConfig | weaviate.collections.classes.config._BQConfig | weaviate.collections.classes.config._SQConfig | weaviate.collections.classes.config._RQConfig | NoneType, distance_metric: weaviate.collections.classes.config_vectorizers.VectorDistances, max_posting_size_kb: int, replicas: int, search_probe: int)

Bases: _VectorIndexConfig

Parameters:

• multi_vector (_MultiVectorConfig | None)

• quantizer (_PQConfig | _BQConfig | _SQConfig | _RQConfig | None)

• distance_metric (VectorDistances)

• max_posting_size_kb (int)

• replicas (int)

• search_probe (int)

distance_metric: VectorDistances

max_posting_size_kb: int

replicas: int

search_probe: int

static vector_index_type()

Return type:

str

to_dict()

Return type:

Dict[str, Any]

weaviate.collections.classes.config.VectorIndexConfigHFresh

alias of _VectorIndexConfigHFresh

class weaviate.collections.classes.config._VectorIndexConfigFlat(multi_vector: weaviate.collections.classes.config._MultiVectorConfig | None, quantizer: weaviate.collections.classes.config._PQConfig | weaviate.collections.classes.config._BQConfig | weaviate.collections.classes.config._SQConfig | weaviate.collections.classes.config._RQConfig | NoneType, distance_metric: weaviate.collections.classes.config_vectorizers.VectorDistances, vector_cache_max_objects: int)

Bases: _VectorIndexConfig

Parameters:

• multi_vector (_MultiVectorConfig | None)

• quantizer (_PQConfig | _BQConfig | _SQConfig | _RQConfig | None)

• distance_metric (VectorDistances)

• vector_cache_max_objects (int)

distance_metric: VectorDistances

vector_cache_max_objects: int

static vector_index_type()

Return type:

str

weaviate.collections.classes.config.VectorIndexConfigFlat

alias of _VectorIndexConfigFlat

class weaviate.collections.classes.config._VectorIndexConfigDynamic(distance_metric: weaviate.collections.classes.config_vectorizers.VectorDistances, hnsw: weaviate.collections.classes.config._VectorIndexConfigHNSW | None, flat: weaviate.collections.classes.config._VectorIndexConfigFlat | None, threshold: int | None)

Bases: _ConfigBase

Parameters:

• distance_metric (VectorDistances)

• hnsw (_VectorIndexConfigHNSW | None)

• flat (_VectorIndexConfigFlat | None)

• threshold (int | None)

distance_metric: VectorDistances

hnsw: _VectorIndexConfigHNSW | None

flat: _VectorIndexConfigFlat | None

threshold: int | None

static vector_index_type()

Return type:

str

weaviate.collections.classes.config.VectorIndexConfigDynamic

alias of _VectorIndexConfigDynamic

class weaviate.collections.classes.config._GenerativeConfig(generative: weaviate.collections.classes.config.GenerativeSearches | str, model: Dict[str, Any])

Bases: _ConfigBase

Parameters:

• generative (GenerativeSearches | str)

• model (Dict[str, Any])

generative: GenerativeSearches | str

model: Dict[str, Any]

weaviate.collections.classes.config.GenerativeConfig

alias of _GenerativeConfig

class weaviate.collections.classes.config._VectorizerConfig(vectorizer: weaviate.collections.classes.config_vectorizers.Vectorizers | str, model: Dict[str, Any], vectorize_collection_name: bool)

Bases: _ConfigBase

Parameters:

• vectorizer (Vectorizers | str)

• model (Dict[str, Any])

• vectorize_collection_name (bool)

vectorizer: Vectorizers | str

model: Dict[str, Any]

vectorize_collection_name: bool

weaviate.collections.classes.config.VectorizerConfig

alias of _VectorizerConfig

class weaviate.collections.classes.config._RerankerConfig(model: Dict[str, Any], reranker: weaviate.collections.classes.config.Rerankers | str)

Bases: _ConfigBase

Parameters:

• model (Dict[str, Any])

• reranker (Rerankers | str)

model: Dict[str, Any]

reranker: Rerankers | str

weaviate.collections.classes.config.RerankerConfig

alias of _RerankerConfig

class weaviate.collections.classes.config._NamedVectorizerConfig(vectorizer: weaviate.collections.classes.config_vectorizers.Vectorizers | str, model: Dict[str, Any], source_properties: List[str] | None)

Bases: _ConfigBase

Parameters:

• vectorizer (Vectorizers | str)

• model (Dict[str, Any])

• source_properties (List[str] | None)

vectorizer: Vectorizers | str

model: Dict[str, Any]

source_properties: List[str] | None

to_dict()

Return type:

Dict[str, Any]

class weaviate.collections.classes.config._NamedVectorConfig(vectorizer: weaviate.collections.classes.config._NamedVectorizerConfig, vector_index_config: weaviate.collections.classes.config._VectorIndexConfigHNSW | weaviate.collections.classes.config._VectorIndexConfigFlat | weaviate.collections.classes.config._VectorIndexConfigDynamic | weaviate.collections.classes.config._VectorIndexConfigHFresh)

Bases: _ConfigBase

Parameters:

• vectorizer (_NamedVectorizerConfig)

• vector_index_config (_VectorIndexConfigHNSW | _VectorIndexConfigFlat | _VectorIndexConfigDynamic | _VectorIndexConfigHFresh)

vectorizer: _NamedVectorizerConfig

vector_index_config: _VectorIndexConfigHNSW | _VectorIndexConfigFlat | _VectorIndexConfigDynamic | _VectorIndexConfigHFresh

to_dict()

Return type:

Dict

weaviate.collections.classes.config.NamedVectorConfig

alias of _NamedVectorConfig

class weaviate.collections.classes.config._ObjectTTLConfig(enabled: bool, time_to_live: datetime.timedelta | None, filter_expired_objects: bool, delete_on: str | Literal['updateTime'] | Literal['creationTime'])

Bases: _ConfigBase

Parameters:

• enabled (bool)

• time_to_live (timedelta | None)

• filter_expired_objects (bool)

• delete_on (str | Literal['updateTime'] | ~typing.Literal['creationTime'])

enabled: bool

time_to_live: timedelta | None

filter_expired_objects: bool

delete_on: str | Literal['updateTime'] | Literal['creationTime']

to_dict()

Return type:

dict

weaviate.collections.classes.config.ObjectTTLConfig

alias of _ObjectTTLConfig

class weaviate.collections.classes.config._CollectionConfig(name: str, description: str | None, generative_config: weaviate.collections.classes.config._GenerativeConfig | None, inverted_index_config: weaviate.collections.classes.config._InvertedIndexConfig, multi_tenancy_config: weaviate.collections.classes.config._MultiTenancyConfig, object_ttl_config: weaviate.collections.classes.config._ObjectTTLConfig | None, properties: List[weaviate.collections.classes.config._Property], references: List[weaviate.collections.classes.config._ReferenceProperty], replication_config: weaviate.collections.classes.config._ReplicationConfig, reranker_config: weaviate.collections.classes.config._RerankerConfig | None, sharding_config: weaviate.collections.classes.config._ShardingConfig | None, vector_index_config: weaviate.collections.classes.config._VectorIndexConfigHNSW | weaviate.collections.classes.config._VectorIndexConfigFlat | weaviate.collections.classes.config._VectorIndexConfigDynamic | weaviate.collections.classes.config._VectorIndexConfigHFresh | NoneType, vector_index_type: weaviate.collections.classes.config_vector_index.VectorIndexType | None, vectorizer_config: weaviate.collections.classes.config._VectorizerConfig | None, vectorizer: weaviate.collections.classes.config_vectorizers.Vectorizers | str | NoneType, vector_config: Dict[str, weaviate.collections.classes.config._NamedVectorConfig] | None)

Bases: _ConfigBase

Parameters:

• name (str)

• description (str | None)

• generative_config (_GenerativeConfig | None)

• inverted_index_config (_InvertedIndexConfig)

• multi_tenancy_config (_MultiTenancyConfig)

• object_ttl_config (_ObjectTTLConfig | None)

• properties (List[_Property])

• references (List[_ReferenceProperty])

• replication_config (_ReplicationConfig)

• reranker_config (_RerankerConfig | None)

• sharding_config (_ShardingConfig | None)

• vector_index_config (_VectorIndexConfigHNSW | _VectorIndexConfigFlat | _VectorIndexConfigDynamic | _VectorIndexConfigHFresh | None)

• vector_index_type (VectorIndexType | None)

• vectorizer_config (_VectorizerConfig | None)

• vectorizer (Vectorizers | str | None)

• vector_config (Dict[str, _NamedVectorConfig] | None)

name: str

description: str | None

generative_config: _GenerativeConfig | None

inverted_index_config: _InvertedIndexConfig

multi_tenancy_config: _MultiTenancyConfig

object_ttl_config: _ObjectTTLConfig | None

properties: List[_Property]

references: List[_ReferenceProperty]

replication_config: _ReplicationConfig

reranker_config: _RerankerConfig | None

sharding_config: _ShardingConfig | None

vector_index_config: _VectorIndexConfigHNSW | _VectorIndexConfigFlat | _VectorIndexConfigDynamic | _VectorIndexConfigHFresh | None

vector_index_type: VectorIndexType | None

vectorizer_config: _VectorizerConfig | None

vectorizer: Vectorizers | str | None

vector_config: Dict[str, _NamedVectorConfig] | None

to_dict()

Return type:

dict

weaviate.collections.classes.config.CollectionConfig

alias of _CollectionConfig

class weaviate.collections.classes.config._CollectionConfigSimple(name: str, description: str | None, generative_config: weaviate.collections.classes.config._GenerativeConfig | None, properties: List[weaviate.collections.classes.config._Property], references: List[weaviate.collections.classes.config._ReferenceProperty], reranker_config: weaviate.collections.classes.config._RerankerConfig | None, vectorizer_config: weaviate.collections.classes.config._VectorizerConfig | None, vectorizer: weaviate.collections.classes.config_vectorizers.Vectorizers | str | NoneType, vector_config: Dict[str, weaviate.collections.classes.config._NamedVectorConfig] | None, object_ttl_config: weaviate.collections.classes.config._ObjectTTLConfig | None)

Bases: _ConfigBase

Parameters:

• name (str)

• description (str | None)

• generative_config (_GenerativeConfig | None)

• properties (List[_Property])

• references (List[_ReferenceProperty])

• reranker_config (_RerankerConfig | None)

• vectorizer_config (_VectorizerConfig | None)

• vectorizer (Vectorizers | str | None)

• vector_config (Dict[str, _NamedVectorConfig] | None)

• object_ttl_config (_ObjectTTLConfig | None)

name: str

description: str | None

generative_config: _GenerativeConfig | None

properties: List[_Property]

references: List[_ReferenceProperty]

reranker_config: _RerankerConfig | None

vectorizer_config: _VectorizerConfig | None

vectorizer: Vectorizers | str | None

vector_config: Dict[str, _NamedVectorConfig] | None

object_ttl_config: _ObjectTTLConfig | None

weaviate.collections.classes.config.CollectionConfigSimple

alias of _CollectionConfigSimple

class weaviate.collections.classes.config._ShardStatus(name: str, status: Literal['READONLY', 'READY', 'INDEXING'], vector_queue_size: int)

Bases: object

Parameters:

• name (str)

• status (Literal['READONLY', 'READY', 'INDEXING'])

• vector_queue_size (int)

name: str

status: Literal['READONLY', 'READY', 'INDEXING']

vector_queue_size: int

weaviate.collections.classes.config.ShardStatus

alias of _ShardStatus

class weaviate.collections.classes.config._TextAnalyzerConfigCreate(*, ascii_fold=None, ascii_fold_ignore=None, stopword_preset=None)

Bases: _ConfigCreateModel

Text analysis options for a property.

Configures per-property text analysis for text and text[] properties that use an inverted index (searchable or filterable). Supports ASCII folding (accent/diacritic handling) and selecting a stopword preset that overrides the collection-level invertedIndexConfig.stopwords setting for this property only.

Parameters:

• ascii_fold (bool | None)

• ascii_fold_ignore (List[str] | None)

• stopword_preset (StopwordsPreset | str | None)

ascii_fold

If True, accent/diacritic marks are folded to their base characters during indexing and search (e.g. ‘école’ matches ‘ecole’). If omitted, the field is not sent to the server and the server default (False) applies.

ascii_fold_ignore

Optional list of characters that should be excluded from ASCII folding (e.g. [‘é’] keeps ‘é’ from being folded to ‘e’). If omitted, the field is not sent to the server.

stopword_preset

Stopword preset name. Overrides the collection-level invertedIndexConfig.stopwords for this property. Only applies to properties using Tokenization.WORD. Accepts a built-in preset (StopwordsPreset.EN or StopwordsPreset.NONE) or the name of a user-defined preset declared in Configure.inverted_index(stopword_presets=…).

All settings are immutable after the property is created.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

asciiFold: bool | None

asciiFoldIgnore: List[str] | None

stopwordPreset: StopwordsPreset | str | None

_validate_ascii_fold_ignore()

Return type:

_TextAnalyzerConfigCreate

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

weaviate.collections.classes.config.TextAnalyzerConfigCreate

alias of _TextAnalyzerConfigCreate

class weaviate.collections.classes.config.Property(*, name, data_type, description=None, index_filterable=None, index_searchable=None, index_range_filters=None, nested_properties=None, skip_vectorization=False, text_analyzer=None, tokenization=None, vectorize_property_name=True)

Bases: _ConfigCreateModel

This class defines the structure of a data property that a collection can have within Weaviate.

Parameters:

• name (str)

• data_type (DataType)

• description (str | None)

• index_filterable (bool | None)

• index_searchable (bool | None)

• index_range_filters (bool | None)

• nested_properties (Property | List[Property] | None)

• skip_vectorization (bool)

• text_analyzer (_TextAnalyzerConfigCreate | None)

• tokenization (Tokenization | None)

• vectorize_property_name (bool)

name

The name of the property, REQUIRED.

Type:

str

data_type

The data type of the property, REQUIRED.

description

A description of the property.

Type:

str | None

index_filterable

Whether the property should be filterable in the inverted index.

index_range_filters

Whether the property should support range filters in the inverted index.

index_searchable

Whether the property should be searchable in the inverted index.

nested_properties

nested properties for data type OBJECT and OBJECT_ARRAY`.

skip_vectorization

Whether to skip vectorization of the property. Defaults to False.

Type:

bool

text_analyzer

Text analysis options for the property. Configures ASCII folding behavior for text and text[] properties using an inverted index. Immutable after the property is created.

tokenization

The tokenization method to use for the inverted index. Defaults to None.

Type:

weaviate.collections.classes.config.Tokenization | None

vectorize_property_name

Whether to vectorize the property name. Defaults to True.

Type:

bool

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

name: str

dataType: DataType

description: str | None

indexFilterable: bool | None

indexSearchable: bool | None

indexRangeFilters: bool | None

nestedProperties: Property | List[Property] | None

skip_vectorization: bool

textAnalyzer: _TextAnalyzerConfigCreate | None

tokenization: Tokenization | None

vectorize_property_name: bool

classmethod _check_name(v)

Parameters:

v (str)

Return type:

str

_to_dict(vectorizers=None)

Parameters:

vectorizers (Sequence[Vectorizers | _EnumLikeStr] | None)

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._ReferencePropertyBase(*, name)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

name (str)

name: str

classmethod check_name(v)

Parameters:

v (str)

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._ReferencePropertyMultiTarget(*, name, target_collections, description=None)

Bases: _ReferencePropertyBase

This class defines properties that are cross references to multiple target collections.

Use this class when you want to create a cross-reference in the collection’s config that is capable of having cross-references to multiple other collections at once.

Parameters:

• name (str)

• target_collections (List[str])

• description (str | None)

name

The name of the property, REQUIRED.

target_collections

The names of the target collections, REQUIRED.

Type:

List[str]

description

A description of the property.

Type:

str | None

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

target_collections: List[str]

description: str | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config.ReferenceProperty(*, name, target_collection, description=None)

Bases: _ReferencePropertyBase

This class defines properties that are cross references to a single target collection.

Use this class when you want to create a cross-reference in the collection’s config that is capable of having only cross-references to a single other collection.

Parameters:

• name (str)

• target_collection (str)

• description (str | None)

name

The name of the property, REQUIRED.

target_collection

The name of the target collection, REQUIRED.

Type:

str

description

A description of the property.

Type:

str | None

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

target_collection: str

description: str | None

MultiTarget

alias of _ReferencePropertyMultiTarget

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._CollectionConfigCreate(*, name, properties=None, references=None, description=None, inverted_index_config=None, multi_tenancy_config=None, object_ttl_config=None, replication_config=None, sharding_config=None, vector_index_config=None, vectorizer_config=None, vector_config=None, generative_config=None, reranker_config=None)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• name (str)

• properties (Sequence[Property] | None)

• references (List[_ReferencePropertyBase] | None)

• description (str | None)

• inverted_index_config (_InvertedIndexConfigCreate | None)

• multi_tenancy_config (_MultiTenancyConfigCreate | None)

• object_ttl_config (_ObjectTTLConfigCreate | None)

• replication_config (_ReplicationConfigCreate | None)

• sharding_config (_ShardingConfigCreate | None)

• vector_index_config (_VectorIndexConfigCreate | None)

• vectorizer_config (_VectorizerConfigCreate | List[_NamedVectorConfigCreate] | None)

• vector_config (_VectorConfigCreate | List[_VectorConfigCreate] | None)

• generative_config (_GenerativeProvider | None)

• reranker_config (_RerankerProvider | None)

name: str

properties: Sequence[Property] | None

references: List[_ReferencePropertyBase] | None

description: str | None

invertedIndexConfig: _InvertedIndexConfigCreate | None

multiTenancyConfig: _MultiTenancyConfigCreate | None

objectTtlConfig: _ObjectTTLConfigCreate | None

replicationConfig: _ReplicationConfigCreate | None

shardingConfig: _ShardingConfigCreate | None

vectorIndexConfig: _VectorIndexConfigCreate | None

vectorizerConfig: _VectorizerConfigCreate | List[_NamedVectorConfigCreate] | None

vectorConfig: _VectorConfigCreate | List[_VectorConfigCreate] | None

generativeSearch: _GenerativeProvider | None

rerankerConfig: _RerankerProvider | None

model_post_init(_CollectionConfigCreate__context)

Override this method to perform additional initialization after __init__ and model_construct. This is useful if you want to do some validation that requires the entire model to be initialized.

Parameters:

_CollectionConfigCreate__context (Any)

Return type:

None

classmethod _check_top_level_property_names(v)

Parameters:

v (Sequence[Property] | None)

Return type:

Sequence[Property] | None

classmethod validate_vector_names(v, info)

Parameters:

• v (_VectorizerConfigCreate | _NamedVectorConfigCreate | List[_NamedVectorConfigCreate])

• info (ValidationInfo)

Return type:

_VectorizerConfigCreate | _NamedVectorConfigCreate | List[_NamedVectorConfigCreate]

classmethod inject_vector_config_none(v, info)

Parameters:

• v (_VectorConfigCreate | List[_VectorConfigCreate] | None)

• info (ValidationInfo)

Return type:

_VectorConfigCreate | List[_VectorConfigCreate] | None

_to_dict()

Return type:

Dict[str, Any]

_CollectionConfigCreate__add_props(props, ret_dict)

Parameters:

• props (Sequence[Property | _ReferencePropertyBase] | List[_ReferencePropertyBase] | None)

• ret_dict (Dict[str, Any])

Return type:

None

static _CollectionConfigCreate__add_to_module_config(return_dict, addition_key, addition_val)

Parameters:

• return_dict (Dict[str, Any])

• addition_key (str)

• addition_val (Dict[str, Any])

Return type:

None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config._Replication

Bases: object

static async_config(*, max_workers=None, hashtree_height=None, frequency=None, frequency_while_propagating=None, alive_nodes_checking_frequency=None, logging_frequency=None, diff_batch_size=None, diff_per_node_timeout=None, pre_propagation_timeout=None, propagation_timeout=None, propagation_limit=None, propagation_delay=None, propagation_concurrency=None, propagation_batch_size=None)

Create a configuration object create for async replication settings when creating a collection.

This is only available with WeaviateDB >=v1.36.0.

Parameters:

• max_workers (int | None)

• hashtree_height (int | None)

• frequency (int | None)

• frequency_while_propagating (int | None)

• alive_nodes_checking_frequency (int | None)

• logging_frequency (int | None)

• diff_batch_size (int | None)

• diff_per_node_timeout (int | None)

• pre_propagation_timeout (int | None)

• propagation_timeout (int | None)

• propagation_limit (int | None)

• propagation_delay (int | None)

• propagation_concurrency (int | None)

• propagation_batch_size (int | None)

Return type:

_AsyncReplicationConfigCreate

class weaviate.collections.classes.config._ReplicationUpdate

Bases: object

static async_config(*, max_workers=None, hashtree_height=None, frequency=None, frequency_while_propagating=None, alive_nodes_checking_frequency=None, logging_frequency=None, diff_batch_size=None, diff_per_node_timeout=None, pre_propagation_timeout=None, propagation_timeout=None, propagation_limit=None, propagation_delay=None, propagation_concurrency=None, propagation_batch_size=None)

Create a configuration object for async replication settings when updating a collection.

This is only available with WeaviateDB >=v1.36.0.

Parameters:

• max_workers (int | None)

• hashtree_height (int | None)

• frequency (int | None)

• frequency_while_propagating (int | None)

• alive_nodes_checking_frequency (int | None)

• logging_frequency (int | None)

• diff_batch_size (int | None)

• diff_per_node_timeout (int | None)

• pre_propagation_timeout (int | None)

• propagation_timeout (int | None)

• propagation_limit (int | None)

• propagation_delay (int | None)

• propagation_concurrency (int | None)

• propagation_batch_size (int | None)

Return type:

_AsyncReplicationConfigUpdate

class weaviate.collections.classes.config.Configure

Bases: object

Use this factory class to generate the correct object for use when using the collections.create() method. E.g., .multi_tenancy() will return a MultiTenancyConfigCreate object to be used in the multi_tenancy_config argument.

Each class method provides options specific to the named configuration type in the function’s name. Under-the-hood data validation steps will ensure that any mis-specifications are caught before the request is sent to Weaviate.

Generative

alias of _Generative

Reranker

alias of _Reranker

Vectorizer

alias of _Vectorizer

VectorIndex

alias of _VectorIndex

NamedVectors

alias of _NamedVectors

Vectors

alias of _Vectors

MultiVectors

alias of _MultiVectors

ObjectTTL

alias of _ObjectTTL

Replication

alias of _Replication

static text_analyzer(ascii_fold=None, ascii_fold_ignore=None, stopword_preset=None)

Create a text analyzer config for a property.

Parameters:

• ascii_fold (bool | None) – If True, accent/diacritic marks are folded to their base characters during indexing and search (e.g. ‘école’ matches ‘ecole’).

• ascii_fold_ignore (List[str] | None) – Optional list of characters that should be excluded from ASCII folding (e.g. ['é'] keeps ‘é’ from being folded to ‘e’). Requires ascii_fold=True.

• stopword_preset (StopwordsPreset | str | None) – Stopword preset name to override the collection-level stopwords for this property. Accepts a StopwordsPreset or a user-defined preset name.

Return type:

_TextAnalyzerConfigCreate

static inverted_index(bm25_b=None, bm25_k1=None, cleanup_interval_seconds=None, index_timestamps=None, index_property_length=None, index_null_state=None, stopwords_preset=None, stopwords_additions=None, stopwords_removals=None, stopword_presets=None)

Create an InvertedIndexConfigCreate object to be used when defining the configuration of the keyword searching algorithm of Weaviate.

Parameters:

• stopword_presets (Dict[str, List[str]] | None) – User-defined named stopword lists keyed by preset name. Each value is a flat list of stopword strings. A preset can be referenced from a property’s text_analyzer.stopword_preset to override the collection-level stopwords for that property only. Requires Weaviate >= 1.37.0.

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/configuration/indexes#configure-the-inverted-index>`_ for details on the other parameters.

• bm25_b (float | None)

• bm25_k1 (float | None)

• cleanup_interval_seconds (int | None)

• index_timestamps (bool | None)

• index_property_length (bool | None)

• index_null_state (bool | None)

• stopwords_preset (StopwordsPreset | None)

• stopwords_additions (List[str] | None)

• stopwords_removals (List[str] | None)

Return type:

_InvertedIndexConfigCreate

static multi_tenancy(enabled=True, auto_tenant_creation=None, auto_tenant_activation=None)

Create a MultiTenancyConfigCreate object to be used when defining the multi-tenancy configuration of Weaviate.

Parameters:

• enabled (bool) – Whether multi-tenancy is enabled. Defaults to True.

• auto_tenant_creation (bool | None) – Automatically create nonexistent tenants during object creation. Defaults to None, which uses the server-defined default.

• auto_tenant_activation (bool | None) – Automatically turn tenants implicitly HOT when they are accessed. Defaults to None, which uses the server-defined default.

Return type:

_MultiTenancyConfigCreate

static replication(factor=None, async_enabled=None, deletion_strategy=None, async_config=None)

Create a ReplicationConfigCreate object to be used when defining the replication configuration of Weaviate.

NOTE: async_enabled is only available with WeaviateDB >=v1.26.0

Parameters:

• factor (int | None) – The replication factor.

• async_enabled (bool | None) – Enabled async replication.

• deletion_strategy (ReplicationDeletionStrategy | None) – How conflicts between different nodes about deleted objects are resolved.

• async_config (_AsyncReplicationConfigCreate | None) – The configuration for async replication. This is only relevant if async_enabled is True.

Return type:

_ReplicationConfigCreate

static sharding(virtual_per_physical=None, desired_count=None, actual_count=None, desired_virtual_count=None, actual_virtual_count=None)

Create a ShardingConfigCreate object to be used when defining the sharding configuration of Weaviate.

NOTE: You can only use one of Sharding or Replication, not both.

See the docs for more details.

Parameters:

• virtual_per_physical (int | None) – The number of virtual shards per physical shard.

• desired_count (int | None) – The desired number of physical shards.

• actual_count (int | None) – The actual number of physical shards. This is a read-only field so has no effect. It is kept for backwards compatibility but will be removed in a future release.

• desired_virtual_count (int | None) – The desired number of virtual shards.

• actual_virtual_count (int | None) – The actual number of virtual shards. This is a read-only field so has no effect. It is kept for backwards compatibility but will be removed in a future release.

Return type:

_ShardingConfigCreate

class weaviate.collections.classes.config._VectorIndexQuantizerUpdate

Bases: object

static pq(bit_compression=None, centroids=None, encoder_distribution=None, encoder_type=None, segments=None, training_limit=None, enabled=True)

Create a _PQConfigUpdate object to be used when updating the product quantization (PQ) configuration of Weaviate.

Use this method when defining the quantizer argument in the vector_index configuration in collection.update().

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/concepts/vector-index#hnsw-with-compression>`_ for a more detailed view!

• bit_compression (bool | None)

• centroids (int | None)

• encoder_distribution (PQEncoderDistribution | None)

• encoder_type (PQEncoderType | None)

• segments (int | None)

• training_limit (int | None)

• enabled (bool)

Return type:

_PQConfigUpdate

static bq(rescore_limit=None, enabled=True)

Create a _BQConfigUpdate object to be used when updating the binary quantization (BQ) configuration of Weaviate.

Use this method when defining the quantizer argument in the vector_index configuration in collection.update().

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/concepts/vector-index#hnsw-with-compression>`_ for a more detailed view!

• rescore_limit (int | None)

• enabled (bool)

Return type:

_BQConfigUpdate

static sq(rescore_limit=None, training_limit=None, enabled=True)

Create a _SQConfigUpdate object to be used when updating the scalar quantization (SQ) configuration of Weaviate.

Use this method when defining the quantizer argument in the vector_index configuration in collection.update().

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/concepts/vector-index#hnsw-with-compression>`_ for a more detailed view!

• rescore_limit (int | None)

• training_limit (int | None)

• enabled (bool)

Return type:

_SQConfigUpdate

static rq(rescore_limit=None, enabled=True, bits=None)

Create a _RQConfigUpdate object to be used when updating the Rotational quantization (RQ) configuration of Weaviate.

Use this method when defining the quantizer argument in the vector_index configuration in collection.update().

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/concepts/vector-index#hnsw-with-compression>`_ for a more detailed view!

• rescore_limit (int | None)

• enabled (bool)

• bits (int | None)

Return type:

_RQConfigUpdate

class weaviate.collections.classes.config._VectorIndexUpdate

Bases: object

Quantizer

alias of _VectorIndexQuantizerUpdate

static hnsw(dynamic_ef_factor=None, dynamic_ef_min=None, dynamic_ef_max=None, ef=None, flat_search_cutoff=None, filter_strategy=None, vector_cache_max_objects=None, quantizer=None)

Create an _VectorIndexConfigHNSWUpdate object to update the configuration of the HNSW vector index.

Use this method when defining the vectorizer_config argument in collection.update().

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/configuration/indexes#configure-the-inverted-index>`_ for a more detailed view!

• dynamic_ef_factor (int | None)

• dynamic_ef_min (int | None)

• dynamic_ef_max (int | None)

• ef (int | None)

• flat_search_cutoff (int | None)

• filter_strategy (VectorFilterStrategy | None)

• vector_cache_max_objects (int | None)

• quantizer (_PQConfigUpdate | _BQConfigUpdate | _SQConfigUpdate | _RQConfigUpdate | None)

Return type:

_VectorIndexConfigHNSWUpdate

static flat(vector_cache_max_objects=None, quantizer=None)

Create an _VectorIndexConfigFlatUpdate object to update the configuration of the FLAT vector index.

Use this method when defining the vectorizer_config argument in collection.update().

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/configuration/indexes#configure-the-inverted-index>`_ for a more detailed view!

• vector_cache_max_objects (int | None)

• quantizer (_BQConfigUpdate | _RQConfigUpdate | None)

Return type:

_VectorIndexConfigFlatUpdate

static dynamic(*, threshold=None, hnsw=None, flat=None, quantizer=None)

Create an _VectorIndexConfigDynamicUpdate object to update the configuration of the Dynamic vector index.

Use this method when defining the vectorizer_config argument in collection.update().

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/configuration/indexes#configure-the-inverted-index>`_ for a more detailed view!

• threshold (int | None)

• hnsw (_VectorIndexConfigHNSWUpdate | None)

• flat (_VectorIndexConfigFlatUpdate | None)

• quantizer (_BQConfigUpdate | None)

Return type:

_VectorIndexConfigDynamicUpdate

static hfresh(max_posting_size_kb=None, search_probe=None, quantizer=None)

Create an _VectorIndexConfigHFreshUpdate object to update the configuration of the HFresh vector index.

Use this method when defining the vectorizer_config argument in collection.update().

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/configuration/indexes#configure-the-inverted-index>`_ for a more detailed view!

• max_posting_size_kb (int | None)

• search_probe (int | None)

• quantizer (_RQConfigUpdate | None)

Return type:

_VectorIndexConfigHFreshUpdate

class weaviate.collections.classes.config.Reconfigure

Bases: object

Use this factory class to generate the correct xxxConfig object for use when using the collection.update() method.

Each staticmethod provides options specific to the named configuration type in the function’s name. Under-the-hood data validation steps will ensure that any mis-specifications are caught before the request is sent to Weaviate. Only those configurations that are mutable are available in this class. If you wish to update the configuration of an immutable aspect of your collection then you will have to delete the collection and re-create it with the new configuration.

NamedVectors

alias of _NamedVectorsUpdate

Vectors

alias of _VectorsUpdate

VectorIndex

alias of _VectorIndexUpdate

Generative

alias of _Generative

Reranker

alias of _Reranker

ObjectTTL

alias of _ObjectTTLUpdate

Replication

alias of _ReplicationUpdate

static inverted_index(bm25_b=None, bm25_k1=None, cleanup_interval_seconds=None, stopwords_additions=None, stopwords_preset=None, stopwords_removals=None, stopword_presets=None)

Create an InvertedIndexConfigUpdate object.

Use this method when defining the inverted_index_config argument in collection.update().

Parameters:

• stopword_presets (Dict[str, List[str]] | None) – User-defined named stopword lists keyed by preset name. Each value is a flat list of stopword strings. Passing this replaces the entire user-defined stopword preset map for the collection. Removing a preset still referenced by a property is rejected by the server. Requires Weaviate >= 1.37.0.

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/configuration/indexes#configure-the-inverted-index>`_ for details on the other parameters.

• bm25_b (float | None)

• bm25_k1 (float | None)

• cleanup_interval_seconds (int | None)

• stopwords_additions (List[str] | None)

• stopwords_preset (StopwordsPreset | None)

• stopwords_removals (List[str] | None)

Return type:

_InvertedIndexConfigUpdate

static replication(factor=None, async_enabled=None, deletion_strategy=None, async_config=None)

Create a ReplicationConfigUpdate object.

Use this method when defining the replication_config argument in collection.update().

Parameters:

• factor (int | None) – The replication factor.

• async_enabled (bool | None) – Enable async replication.

• deletion_strategy (ReplicationDeletionStrategy | None) – How conflicts between different nodes about deleted objects are resolved.

• async_config (_AsyncReplicationConfigUpdate | None) – The async replication configuration. This is only applicable if async_enabled is set to True.

Return type:

_ReplicationConfigUpdate

static multi_tenancy(auto_tenant_creation=None, auto_tenant_activation=None)

Create a MultiTenancyConfigUpdate object.

Use this method when defining the multi_tenancy argument in collection.update().

Parameters:

• auto_tenant_creation (bool | None) – When set, implicitly creates nonexistent tenants during object creation

• auto_tenant_activation (bool | None) – Automatically turn tenants implicitly HOT when they are accessed. Defaults to None, which uses the server-defined default.

Return type:

_MultiTenancyConfigUpdate

weaviate.collections.classes.config_base

class weaviate.collections.classes.config_base._ConfigCreateModel

Bases: BaseModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

class weaviate.collections.classes.config_base._ConfigUpdateModel

Bases: BaseModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

merge_with_existing(schema)

Parameters:

schema (Dict[str, Any])

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

class weaviate.collections.classes.config_base._ConfigBase

Bases: object

to_dict()

Return type:

dict

class weaviate.collections.classes.config_base._QuantizerConfigCreate(*, enabled=True)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

enabled (bool)

enabled: bool

abstractmethod static quantizer_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_base._QuantizerConfigUpdate

Bases: _ConfigUpdateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

abstractmethod static quantizer_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_base._EnumLikeStr(string: str)

Bases: object

Parameters:

string (str)

string: str

property value: str

weaviate.collections.classes.config_methods

weaviate.collections.classes.config_methods._is_primitive(d_type)

Parameters:

d_type (str)

Return type:

bool

weaviate.collections.classes.config_methods.__get_rerank_config(schema)

Parameters:

schema (Dict[str, Any])

Return type:

_RerankerConfig | None

weaviate.collections.classes.config_methods.__get_generative_config(schema)

Parameters:

schema (Dict[str, Any])

Return type:

_GenerativeConfig | None

weaviate.collections.classes.config_methods.__get_vectorizer_config(schema)

Parameters:

schema (Dict[str, Any])

Return type:

_VectorizerConfig | None

weaviate.collections.classes.config_methods.__is_vectorizer_present(schema)

Parameters:

schema (Dict[str, Any])

Return type:

bool

weaviate.collections.classes.config_methods.__get_vector_index_type(schema)

Parameters:

schema (Dict[str, Any])

Return type:

VectorIndexType | None

weaviate.collections.classes.config_methods.__get_quantizer_config(config)

Parameters:

config (Dict[str, Any])

Return type:

_PQConfig | _BQConfig | _SQConfig | _RQConfig | None

weaviate.collections.classes.config_methods.__get_multivector_encoding(config)

Parameters:

config (Dict[str, Any])

Return type:

_MuveraConfig | None

weaviate.collections.classes.config_methods.__get_multivector(config)

Parameters:

config (Dict[str, Any])

Return type:

_MultiVectorConfig | None

weaviate.collections.classes.config_methods.__get_hnsw_config(config)

Parameters:

config (Dict[str, Any])

Return type:

_VectorIndexConfigHNSW

weaviate.collections.classes.config_methods.__get_hfresh_config(config)

Parameters:

config (Dict[str, Any])

Return type:

_VectorIndexConfigHFresh

weaviate.collections.classes.config_methods.__get_flat_config(config)

Parameters:

config (Dict[str, Any])

Return type:

_VectorIndexConfigFlat

weaviate.collections.classes.config_methods.__get_vector_index_config(schema)

Parameters:

schema (Dict[str, Any])

Return type:

_VectorIndexConfigHNSW | _VectorIndexConfigFlat | _VectorIndexConfigDynamic | _VectorIndexConfigHFresh | None

weaviate.collections.classes.config_methods.__get_vector_config(schema, simple)

Parameters:

• schema (Dict[str, Any])

• simple (bool)

Return type:

Dict[str, _NamedVectorConfig] | None

weaviate.collections.classes.config_methods.__get_vectorizer(schema)

Parameters:

schema (Dict[str, Any])

Return type:

str | Vectorizers | None

weaviate.collections.classes.config_methods._collection_config_simple_from_json(schema)

Parameters:

schema (Dict[str, Any])

Return type:

_CollectionConfigSimple

weaviate.collections.classes.config_methods._collection_config_from_json(schema)

Parameters:

schema (Dict[str, Any])

Return type:

_CollectionConfig

weaviate.collections.classes.config_methods._get_object_ttl_config(schema)

Parameters:

schema (Dict[str, Any])

Return type:

_ObjectTTLConfig | None

weaviate.collections.classes.config_methods._collection_configs_from_json(schema)

Parameters:

schema (Dict[str, Any])

Return type:

Dict[str, _CollectionConfig]

weaviate.collections.classes.config_methods._collection_configs_simple_from_json(schema)

Parameters:

schema (Dict[str, Any])

Return type:

Dict[str, _CollectionConfigSimple]

weaviate.collections.classes.config_methods._text_analyzer_from_config(prop)

Parameters:

prop (Dict[str, Any])

Return type:

_TextAnalyzerConfig | None

weaviate.collections.classes.config_methods._nested_properties_from_config(props)

Parameters:

props (List[Dict[str, Any]])

Return type:

List[_NestedProperty]

weaviate.collections.classes.config_methods._properties_from_config(schema)

Parameters:

schema (Dict[str, Any])

Return type:

List[_Property]

weaviate.collections.classes.config_methods._references_from_config(schema)

Parameters:

schema (Dict[str, Any])

Return type:

List[_ReferenceProperty]

weaviate.collections.classes.config_named_vectors

class weaviate.collections.classes.config_named_vectors._NamedVectorConfigCreate(*, name, source_properties=None, vectorizer, vectorIndexType=VectorIndexType.HNSW, vector_index_config=None)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• name (str)

• source_properties (Annotated[List[str] | None, MinLen(min_length=1)])

• vectorizer (_VectorizerConfigCreate)

• vectorIndexType (VectorIndexType)

• vector_index_config (_VectorIndexConfigCreate | None)

name: str

properties: List[str] | None

vectorizer: _VectorizerConfigCreate

vectorIndexType: VectorIndexType

vectorIndexConfig: _VectorIndexConfigCreate | None

_to_dict()

Return type:

Dict[str, Any]

_NamedVectorConfigCreate__parse_vectorizer()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_named_vectors._NamedVectorConfigUpdate(*, name, vector_index_config)

Bases: _ConfigUpdateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• name (str)

• vector_index_config (_VectorIndexConfigUpdate)

name: str

vectorIndexConfig: _VectorIndexConfigUpdate

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_named_vectors._NamedVectors

Bases: object

static none(name, *, vector_index_config=None)

Create a named vector using no vectorizer. You will need to provide the vectors yourself.

Parameters:

• name (str) – The name of the named vector.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

Return type:

_NamedVectorConfigCreate

static custom(name, *, module_name, module_config=None, source_properties=None, vector_index_config=None)

Create a named vector using no vectorizer. You will need to provide the vectors yourself.

Parameters:

• name (str) – The name of the named vector.

• module_name (str) – The name of the custom module to use.

• module_config (Dict[str, Any] | None) – The configuration of the custom module to use.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

Return type:

_NamedVectorConfigCreate

static text2colbert_jinaai(name, *, dimensions=None, model=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2colbert_jinaai module.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• vectorize_collection_name – Whether to vectorize the collection name. Defaults to True.

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default.

• dimensions (int | None) – Number of dimensions. Applicable to v3 OpenAI models only. Defaults to None, which uses the server-defined default.

Return type:

_NamedVectorConfigCreate

static text2vec_cohere(name, *, base_url=None, model=None, truncate=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec_cohere model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• model (Literal['embed-v4.0', 'embed-multilingual-v2.0', 'embed-multilingual-v3.0', 'embed-multilingual-light-v3.0', 'small', 'medium', 'large', 'multilingual-22-12', 'embed-english-v2.0', 'embed-english-light-v2.0', 'embed-english-v3.0', 'embed-english-light-v3.0'] | str | None) – The model to use. Defaults to None, which uses the server-defined default.

• truncate (Literal['NONE', 'START', 'END', 'LEFT', 'RIGHT'] | None) – The truncation strategy to use. Defaults to None, which uses the server-defined default.

• vectorize_collection_name – Whether to vectorize the collection name. Defaults to True.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

Raises:

pydantic.ValidationError – If model is not a valid value from the CohereModel type or if truncate is not a valid value from the CohereTruncation type.

Return type:

_NamedVectorConfigCreate

static multi2vec_cohere(name, *, base_url=None, image_fields=None, model=None, text_fields=None, truncate=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the multi2vec_cohere model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• model (Literal['embed-v4.0', 'embed-multilingual-v3.0', 'embed-multilingual-light-v3.0', 'embed-english-v3.0', 'embed-english-light-v3.0'] | str | None) – The model to use. Defaults to None, which uses the server-defined default.

• truncate (Literal['NONE', 'START', 'END', 'LEFT', 'RIGHT'] | None) – The truncation strategy to use. Defaults to None, which uses the server-defined default.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

Raises:

pydantic.ValidationError – If model is not a valid value from the CohereMultimodalModel type or if truncate is not a valid value from the CohereTruncation type.

Return type:

_NamedVectorConfigCreate

static text2vec_contextionary(name, *, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec_contextionary model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Return type:

_NamedVectorConfigCreate

static text2vec_databricks(name, *, endpoint, instruction=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec-databricks model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• endpoint (str) – The endpoint to use.

• instruction (str | None) – The instruction strategy to use. Defaults to None, which uses the server-defined default.

Return type:

_NamedVectorConfigCreate

static text2vec_mistral(name, *, base_url=None, model=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec-mistral model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Return type:

_NamedVectorConfigCreate

static text2vec_ollama(name, *, api_endpoint=None, model=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec-ollama model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default.

• vectorize_collection_name – Whether to vectorize the collection name. Defaults to True.

• api_endpoint (str | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default. Docker users may need to specify an alias, such as http://host.docker.internal:11434 so that the container can access the host machine.

Return type:

_NamedVectorConfigCreate

static text2vec_openai(name, *, base_url=None, dimensions=None, model=None, model_version=None, type_=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec_openai model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• model (Literal['text-embedding-3-small', 'text-embedding-3-large', 'text-embedding-ada-002'] | str | None) – The model to use. Defaults to None, which uses the server-defined default.

• model_version (str | None) – The model version to use. Defaults to None, which uses the server-defined default.

• type – The type of model to use. Defaults to None, which uses the server-defined default.

• vectorize_collection_name – Whether to vectorize the collection name. Defaults to True.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• dimensions (int | None) – Number of dimensions. Applicable to v3 OpenAI models only. Defaults to None, which uses the server-defined default.

• type_ (Literal['text', 'code'] | None)

Raises:

pydantic.ValidationError – If type_ is not a valid value from the OpenAIType type.

Return type:

_NamedVectorConfigCreate

static text2vec_aws(name, region, *, endpoint=None, model=None, service='bedrock', source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec_aws model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• region (str) – The AWS region to run the model from, REQUIRED.

• endpoint (str | None) – The endpoint to use. Defaults to None, which uses the server-defined default.

• model (Literal['amazon.titan-embed-text-v1', 'cohere.embed-english-v3', 'cohere.embed-multilingual-v3'] | str | None) – The model to use.

• service (Literal['bedrock', 'sagemaker'] | str) – The AWS service to use. Defaults to bedrock.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Return type:

_NamedVectorConfigCreate

static img2vec_neural(name, image_fields, *, vector_index_config=None)

Create a Img2VecNeuralConfig object for use when vectorizing using the img2vec-neural model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• image_fields (List[str]) – The image fields to use. This is a required field and must match the property fields of the collection that are defined as DataType.BLOB.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

Raises:

pydantic.ValidationError – If image_fields is not a list.

Return type:

_NamedVectorConfigCreate

static multi2vec_clip(name, *, inference_url=None, image_fields=None, text_fields=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the multi2vec_clip model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

• inference_url (str | None) – The inference url to use where API requests should go. Defaults to None, which uses the server-defined default.

Return type:

_NamedVectorConfigCreate

static multi2vec_palm(name, *, vector_index_config=None, vectorize_collection_name=True, location, project_id, image_fields=None, text_fields=None, video_fields=None, dimensions=None, video_interval_seconds=None, model_id=None)

Deprecated since version 4.9.0.

This method is deprecated and will be removed in Q2 ‘25. Please use multi2vec_google() instead.

Create a named vector using the multi2vec_palm model.

See the documentation for detailed usage.

Args:

name: The name of the named vector. vector_index_config: The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default vectorize_collection_name: Whether to vectorize the collection name. Defaults to True. location: Where the model runs. REQUIRED. project_id: The project ID to use, REQUIRED. image_fields: The image fields to use in vectorization. text_fields: The text fields to use in vectorization. video_fields: The video fields to use in vectorization. dimensions: The number of dimensions to use. Defaults to None, which uses the server-defined default. video_interval_seconds: Length of a video interval. Defaults to None, which uses the server-defined default. model_id: The model ID to use. Defaults to None, which uses the server-defined default.

Parameters:

• name (str)

• vector_index_config (_VectorIndexConfigCreate | None)

• vectorize_collection_name (bool)

• location (str)

• project_id (str)

• image_fields (List[str] | List[Multi2VecField] | None)

• text_fields (List[str] | List[Multi2VecField] | None)

• video_fields (List[str] | List[Multi2VecField] | None)

• dimensions (int | None)

• video_interval_seconds (int | None)

• model_id (str | None)

Return type:

_NamedVectorConfigCreate

static multi2vec_google(name, *, location, project_id, audio_fields=None, image_fields=None, text_fields=None, video_fields=None, dimensions=None, video_interval_seconds=None, model_id=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the multi2vec_google model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• location (str) – Where the model runs. REQUIRED.

• project_id (str) – The project ID to use, REQUIRED.

• audio_fields (List[str] | List[Multi2VecField] | None) – The audio fields to use in vectorization.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

• video_fields (List[str] | List[Multi2VecField] | None) – The video fields to use in vectorization.

• dimensions (int | None) – The number of dimensions to use. Defaults to None, which uses the server-defined default.

• video_interval_seconds (int | None) – Length of a video interval. Defaults to None, which uses the server-defined default.

• model_id (str | None) – The model ID to use. Defaults to None, which uses the server-defined default.

Return type:

_NamedVectorConfigCreate

static multi2vec_bind(name, *, audio_fields=None, depth_fields=None, image_fields=None, imu_fields=None, text_fields=None, thermal_fields=None, video_fields=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the multi2vec_bind model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• audio_fields (List[str] | List[Multi2VecField] | None) – The audio fields to use in vectorization.

• depth_fields (List[str] | List[Multi2VecField] | None) – The depth fields to use in vectorization.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• imu_fields (List[str] | List[Multi2VecField] | None) – The IMU fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

• thermal_fields (List[str] | List[Multi2VecField] | None) – The thermal fields to use in vectorization.

• video_fields (List[str] | List[Multi2VecField] | None) – The video fields to use in vectorization.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Return type:

_NamedVectorConfigCreate

static multi2vec_voyageai(name, *, base_url=None, model=None, truncation=None, output_encoding=None, image_fields=None, text_fields=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the multi2vec_voyageai model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• model (Literal['voyage-multimodal-3', 'voyage-multimodal-3.5'] | str | None) – The model to use. Defaults to None, which uses the server-defined default.

• truncation (bool | None) – The truncation strategy to use. Defaults to None, which uses the server-defined default.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

• output_encoding (str | None)

Raises:

pydantic.ValidationError – If model is not a valid value from the VoyageaiMultimodalModel type.

Return type:

_NamedVectorConfigCreate

static multi2vec_nvidia(name, *, base_url=None, model=None, truncation=None, output_encoding=None, image_fields=None, text_fields=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the multi2vec_nvidia model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default.

• truncation (bool | None) – The truncation strategy to use. Defaults to None, which uses the server-defined default.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

• output_encoding (str | None)

Raises:

pydantic.ValidationError – If model is not a valid value from the NvidiaMultimodalModel type.

Return type:

_NamedVectorConfigCreate

static ref2vec_centroid(name, reference_properties, *, method='mean', vector_index_config=None)

Create a named vector using the ref2vec_centroid model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• reference_properties (List[str]) – The reference properties to use in vectorization, REQUIRED.

• method (Literal['mean']) – The method to use. Defaults to mean.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

Return type:

_NamedVectorConfigCreate

static text2vec_azure_openai(name, resource_name, deployment_id, *, base_url=None, dimensions=None, model=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec_azure_openai model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• resource_name (str) – The resource name to use, REQUIRED.

• deployment_id (str) – The deployment ID to use, REQUIRED.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• dimensions (int | None) – The dimensionality of the vectors. Defaults to None, which uses the server-defined default.

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Return type:

_NamedVectorConfigCreate

static text2vec_gpt4all(name, *, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec_gpt4all model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Return type:

_NamedVectorConfigCreate

static text2vec_huggingface(name, *, model=None, passage_model=None, query_model=None, endpoint_url=None, wait_for_model=None, use_gpu=None, use_cache=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec_huggingface model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default.

• passage_model (str | None) – The passage model to use. Defaults to None, which uses the server-defined default.

• query_model (str | None) – The query model to use. Defaults to None, which uses the server-defined default.

• endpoint_url (AnyHttpUrl | None) – The endpoint URL to use. Defaults to None, which uses the server-defined default.

• wait_for_model (bool | None) – Whether to wait for the model to be loaded. Defaults to None, which uses the server-defined default.

• use_gpu (bool | None) – Whether to use the GPU. Defaults to None, which uses the server-defined default.

• use_cache (bool | None) – Whether to use the cache. Defaults to None, which uses the server-defined default.

Raises:

pydantic.ValidationError –

If the arguments passed to the function are invalid. It is important to note that some of these variables are mutually exclusive. See the documentation for more details.

Return type:

_NamedVectorConfigCreate

static text2vec_palm(name, project_id, *, source_properties=None, vector_index_config=None, vectorize_collection_name=True, api_endpoint=None, model_id=None, title_property=None)

Deprecated since version 4.9.0.

This method is deprecated and will be removed in Q2 ‘25. Please use text2vec_google() instead.

Create a named vector using the text2vec_palm model.

See the documentation for detailed usage.

Args:

name: The name of the named vector. source_properties: Which properties should be included when vectorizing. By default all text properties are included. project_id: The project ID to use, REQUIRED. source_properties: Which properties should be included when vectorizing. By default all text properties are included. vector_index_config: The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default vectorize_collection_name: Whether to vectorize the collection name. Defaults to True. api_endpoint: The API endpoint to use without a leading scheme such as http://. Defaults to None, which uses the server-defined default model_id: The model ID to use. Defaults to None, which uses the server-defined default. title_property: The Weaviate property name for the gecko-002 or gecko-003 model to use as the title.

Raises:

pydantic.ValidationError: If api_endpoint is not a valid URL.

Parameters:

• name (str)

• project_id (str)

• source_properties (List[str] | None)

• vector_index_config (_VectorIndexConfigCreate | None)

• vectorize_collection_name (bool)

• api_endpoint (str | None)

• model_id (str | None)

• title_property (str | None)

Return type:

_NamedVectorConfigCreate

static text2vec_google(name, project_id, *, api_endpoint=None, model_id=None, title_property=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec_palm model.

See the [documentation]https://weaviate.io/developers/weaviate/model-providers/google/embeddings) for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• project_id (str) – The project ID to use, REQUIRED.

• source_properties – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• api_endpoint (str | None) – The API endpoint to use without a leading scheme such as http://. Defaults to None, which uses the server-defined default

• model_id (str | None) – The model ID to use. Defaults to None, which uses the server-defined default.

• title_property (str | None) – The Weaviate property name for the gecko-002 or gecko-003 model to use as the title.

Raises:

pydantic.ValidationError – If api_endpoint is not a valid URL.

Return type:

_NamedVectorConfigCreate

static text2vec_google_aistudio(name, *, model_id=None, title_property=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec_palm model.

See the [documentation]https://weaviate.io/developers/weaviate/model-providers/google/embeddings) for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• source_properties – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• model_id (str | None) – The model ID to use. Defaults to None, which uses the server-defined default.

• title_property (str | None) – The Weaviate property name for the gecko-002 or gecko-003 model to use as the title.

Raises:

pydantic.ValidationError – If api_endpoint is not a valid URL.

Return type:

_NamedVectorConfigCreate

static text2vec_transformers(name, *, dimensions=None, pooling_strategy='masked_mean', inference_url=None, passage_inference_url=None, query_inference_url=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec_transformers model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• dimensions (int | None) – The number of dimensions for the generated embeddings. Defaults to None, which uses the server-defined default.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• pooling_strategy (Literal['masked_mean', 'cls']) – The pooling strategy to use. Defaults to masked_mean.

• inference_url (str | None) – The inferenceUrl to use where API requests should go. You can use either this OR passage/query_inference_url. Defaults to None, which uses the server-defined default.

• passage_inference_url (str | None) – The inferenceUrl to use where passage API requests should go. You can use either this and query_inference_url OR inference_url. Defaults to None, which uses the server-defined default.

• query_inference_url (str | None) – The inferenceUrl to use where query API requests should go. You can use either this and passage_inference_url OR inference_url. Defaults to None, which uses the server-defined default.

Return type:

_NamedVectorConfigCreate

static text2vec_jinaai(name, *, base_url=None, dimensions=None, model=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec-jinaai model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• base_url (str | None) – The base URL to send the vectorization requests to. Defaults to None, which uses the server-defined default.

• dimensions (int | None) – The number of dimensions for the generated embeddings. Defaults to None, which uses the server-defined default.

• model (Literal['jina-embeddings-v2-base-en', 'jina-embeddings-v2-small-en', 'jina-embeddings-v2-base-zh', 'jina-embeddings-v2-base-es', 'jina-embeddings-v2-base-code', 'jina-embeddings-v3', 'jina-embeddings-v4'] | str | None) – The model to use. Defaults to None, which uses the server-defined default.

Return type:

_NamedVectorConfigCreate

static multi2vec_jinaai(name, *, base_url=None, model=None, dimensions=None, image_fields=None, text_fields=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the multi2vec_jinaai model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• model (Literal['jina-clip-v1', 'jina-clip-v2', 'jina-embeddings-v4'] | str | None) – The model to use. Defaults to None, which uses the server-defined default.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• dimensions (int | None) – The number of dimensions for the generated embeddings (only available for some models). Defaults to None, which uses the server-defined default.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

Raises:

pydantic.ValidationError – If model is not a valid value from the JinaMultimodalModel type.

Return type:

_NamedVectorConfigCreate

static text2vec_voyageai(name, *, model=None, base_url=None, truncate=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec-jinaai model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• model (Literal['voyage-4', 'voyage-4-lite', 'voyage-4-large', 'voyage-3.5', 'voyage-3.5-lite', 'voyage-3-large', 'voyage-3', 'voyage-3-lite', 'voyage-context-3', 'voyage-large-2', 'voyage-code-2', 'voyage-2', 'voyage-law-2', 'voyage-large-2-instruct', 'voyage-finance-2', 'voyage-multilingual-2'] | str | None) –

  The model to use. Defaults to None, which uses the server-defined default. See the documentation for more details.

• base_url (str | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• truncate (bool | None) – Whether to truncate the input texts to fit within the context length. Defaults to None, which uses the server-defined default.

Return type:

_NamedVectorConfigCreate

static text2vec_weaviate(name, *, model=None, base_url=None, dimensions=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Parameters:

• name (str)

• model (Literal['Snowflake/snowflake-arctic-embed-l-v2.0', 'Snowflake/snowflake-arctic-embed-m-v1.5'] | str | None)

• base_url (str | None)

• dimensions (int | None)

• source_properties (List[str] | None)

• vector_index_config (_VectorIndexConfigCreate | None)

• vectorize_collection_name (bool)

Return type:

_NamedVectorConfigCreate

static text2vec_nvidia(name, *, model=None, base_url=None, truncate=None, source_properties=None, vector_index_config=None, vectorize_collection_name=True)

Create a named vector using the text2vec-nvidia model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• model (str | None) –

  The model to use. Defaults to None, which uses the server-defined default. See the documentation for more details.

• base_url (str | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• truncate (bool | None) – Whether to truncate the input texts to fit within the context length. Defaults to None, which uses the server-defined default.

Return type:

_NamedVectorConfigCreate

static text2vec_model2vec(name, *, source_properties=None, vector_index_config=None, vectorize_collection_name=True, inference_url=None)

Create a named vector using the text2vec-model2vec model.

See the documentation for detailed usage.

Parameters:

• name (str) – The name of the named vector.

• source_properties (List[str] | None) – Which properties should be included when vectorizing. By default all text properties are included.

• vector_index_config (_VectorIndexConfigCreate | None) – The configuration for Weaviate’s vector index. Use wvc.config.Configure.VectorIndex to create a vector index configuration. None by default

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• inference_url (str | None) – The inference url to use where API requests should go. Defaults to None, which uses the server-defined default.

Return type:

_NamedVectorConfigCreate

class weaviate.collections.classes.config_named_vectors._NamedVectorsUpdate

Bases: object

static update(name, *, vector_index_config)

Update the vector index configuration of a named vector.

This is the only update operation allowed currently. If you wish to change the vectorization configuration itself, you will have to recreate the collection with the new configuration.

Parameters:

• name (str) – The name of the named vector.

• vector_index_config (_VectorIndexConfigHNSWUpdate | _VectorIndexConfigHFreshUpdate | _VectorIndexConfigFlatUpdate | _VectorIndexConfigDynamicUpdate) – The configuration for Weaviate’s vector index. Use wvc.config.Reconfigure.VectorIndex to create a vector index configuration. None by default

Return type:

_NamedVectorConfigUpdate

weaviate.collections.classes.config_vector_index

class weaviate.collections.classes.config_vector_index.VectorFilterStrategy(*values)

Bases: str, Enum

Set the strategy when doing a filtered HNSW search.

SWEEPING

Do normal ANN search and skip nodes.

ACORN

Multi-hop search to find new candidates matching the filter.

SWEEPING = 'sweeping'

ACORN = 'acorn'

class weaviate.collections.classes.config_vector_index.VectorIndexType(*values)

Bases: str, Enum

The available vector index types in Weaviate.

HNSW

Hierarchical Navigable Small World (HNSW) index.

FLAT

Flat index.

DYNAMIC

Dynamic index.

HFRESH

HFRESH index.

HNSW = 'hnsw'

FLAT = 'flat'

DYNAMIC = 'dynamic'

HFRESH = 'hfresh'

class weaviate.collections.classes.config_vector_index._MultiVectorConfigCreateBase(*, enabled=True)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

enabled (bool)

enabled: bool

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._MultiVectorEncodingConfigCreate(*, enabled=True)

Bases: _MultiVectorConfigCreateBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

enabled (bool)

enabled: bool

abstractmethod static encoding_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._MuveraConfigCreate(*, enabled=True, ksim, dprojections, repetitions)

Bases: _MultiVectorEncodingConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• enabled (bool)

• ksim (int | None)

• dprojections (int | None)

• repetitions (int | None)

ksim: int | None

dprojections: int | None

repetitions: int | None

static encoding_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._MultiVectorConfigCreate(*, enabled=True, encoding, aggregation)

Bases: _MultiVectorConfigCreateBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• enabled (bool)

• encoding (_MultiVectorEncodingConfigCreate | None)

• aggregation (str | None)

encoding: _MultiVectorEncodingConfigCreate | None

aggregation: str | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._VectorIndexConfigCreate(*, distance, multivector, quantizer)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• distance (VectorDistances | None)

• multivector (_MultiVectorConfigCreate | None)

• quantizer (_QuantizerConfigCreate | None)

distance: VectorDistances | None

multivector: _MultiVectorConfigCreate | None

quantizer: _QuantizerConfigCreate | None

abstractmethod static vector_index_type()

Return type:

VectorIndexType

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._VectorIndexConfigUpdate(*, quantizer)

Bases: _ConfigUpdateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

quantizer (_QuantizerConfigUpdate | None)

quantizer: _QuantizerConfigUpdate | None

abstractmethod static vector_index_type()

Return type:

VectorIndexType

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._VectorIndexConfigSkipCreate(*, distance, multivector, quantizer, skip=True)

Bases: _VectorIndexConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• distance (VectorDistances | None)

• multivector (_MultiVectorConfigCreate | None)

• quantizer (_QuantizerConfigCreate | None)

• skip (bool)

skip: bool

static vector_index_type()

Return type:

VectorIndexType

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._VectorIndexConfigHNSWCreate(*, distance, multivector, quantizer, cleanupIntervalSeconds, dynamicEfMin, dynamicEfMax, dynamicEfFactor, efConstruction, ef, filterStrategy, flatSearchCutoff, maxConnections, vectorCacheMaxObjects)

Bases: _VectorIndexConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• distance (VectorDistances | None)

• multivector (_MultiVectorConfigCreate | None)

• quantizer (_QuantizerConfigCreate | None)

• cleanupIntervalSeconds (int | None)

• dynamicEfMin (int | None)

• dynamicEfMax (int | None)

• dynamicEfFactor (int | None)

• efConstruction (int | None)

• ef (int | None)

• filterStrategy (VectorFilterStrategy | None)

• flatSearchCutoff (int | None)

• maxConnections (int | None)

• vectorCacheMaxObjects (int | None)

cleanupIntervalSeconds: int | None

dynamicEfMin: int | None

dynamicEfMax: int | None

dynamicEfFactor: int | None

efConstruction: int | None

ef: int | None

filterStrategy: VectorFilterStrategy | None

flatSearchCutoff: int | None

maxConnections: int | None

vectorCacheMaxObjects: int | None

static vector_index_type()

Return type:

VectorIndexType

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._VectorIndexConfigHFreshCreate(*, distance, multivector, quantizer, maxPostingSizeKB, replicas, searchProbe)

Bases: _VectorIndexConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• distance (VectorDistances | None)

• multivector (_MultiVectorConfigCreate | None)

• quantizer (_QuantizerConfigCreate | None)

• maxPostingSizeKB (int | None)

• replicas (int | None)

• searchProbe (int | None)

maxPostingSizeKB: int | None

replicas: int | None

searchProbe: int | None

static vector_index_type()

Return type:

VectorIndexType

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._VectorIndexConfigFlatCreate(*, distance, multivector, quantizer, vectorCacheMaxObjects)

Bases: _VectorIndexConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• distance (VectorDistances | None)

• multivector (_MultiVectorConfigCreate | None)

• quantizer (_QuantizerConfigCreate | None)

• vectorCacheMaxObjects (int | None)

vectorCacheMaxObjects: int | None

static vector_index_type()

Return type:

VectorIndexType

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._VectorIndexConfigHNSWUpdate(*, quantizer, dynamicEfMin, dynamicEfMax, dynamicEfFactor, ef, filterStrategy, flatSearchCutoff, vectorCacheMaxObjects)

Bases: _VectorIndexConfigUpdate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• quantizer (_QuantizerConfigUpdate | None)

• dynamicEfMin (int | None)

• dynamicEfMax (int | None)

• dynamicEfFactor (int | None)

• ef (int | None)

• filterStrategy (VectorFilterStrategy | None)

• flatSearchCutoff (int | None)

• vectorCacheMaxObjects (int | None)

dynamicEfMin: int | None

dynamicEfMax: int | None

dynamicEfFactor: int | None

ef: int | None

filterStrategy: VectorFilterStrategy | None

flatSearchCutoff: int | None

vectorCacheMaxObjects: int | None

static vector_index_type()

Return type:

VectorIndexType

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._VectorIndexConfigHFreshUpdate(*, quantizer, maxPostingSizeKB, searchProbe)

Bases: _VectorIndexConfigUpdate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• quantizer (_QuantizerConfigUpdate | None)

• maxPostingSizeKB (int | None)

• searchProbe (int | None)

maxPostingSizeKB: int | None

searchProbe: int | None

static vector_index_type()

Return type:

VectorIndexType

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._VectorIndexConfigFlatUpdate(*, quantizer, vectorCacheMaxObjects)

Bases: _VectorIndexConfigUpdate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• quantizer (_QuantizerConfigUpdate | None)

• vectorCacheMaxObjects (int | None)

vectorCacheMaxObjects: int | None

static vector_index_type()

Return type:

VectorIndexType

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._VectorIndexConfigDynamicCreate(*, distance, multivector, quantizer, threshold, hnsw, flat)

Bases: _VectorIndexConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• distance (VectorDistances | None)

• multivector (_MultiVectorConfigCreate | None)

• quantizer (_QuantizerConfigCreate | None)

• threshold (int | None)

• hnsw (_VectorIndexConfigHNSWCreate | None)

• flat (_VectorIndexConfigFlatCreate | None)

threshold: int | None

hnsw: _VectorIndexConfigHNSWCreate | None

flat: _VectorIndexConfigFlatCreate | None

static vector_index_type()

Return type:

VectorIndexType

_to_dict()

Return type:

dict

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._VectorIndexConfigDynamicUpdate(*, quantizer, threshold, hnsw, flat)

Bases: _VectorIndexConfigUpdate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• quantizer (_QuantizerConfigUpdate | None)

• threshold (int | None)

• hnsw (_VectorIndexConfigHNSWUpdate | None)

• flat (_VectorIndexConfigFlatUpdate | None)

threshold: int | None

hnsw: _VectorIndexConfigHNSWUpdate | None

flat: _VectorIndexConfigFlatUpdate | None

static vector_index_type()

Return type:

VectorIndexType

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index.PQEncoderType(*values)

Bases: str, BaseEnum

Type of the PQ encoder.

KMEANS

K-means encoder.

TILE

Tile encoder.

KMEANS = 'kmeans'

TILE = 'tile'

class weaviate.collections.classes.config_vector_index.PQEncoderDistribution(*values)

Bases: str, BaseEnum

Distribution of the PQ encoder.

LOG_NORMAL

Log-normal distribution.

NORMAL

Normal distribution.

LOG_NORMAL = 'log-normal'

NORMAL = 'normal'

class weaviate.collections.classes.config_vector_index.MultiVectorAggregation(*values)

Bases: str, BaseEnum

Aggregation type to use for multivector indices.

MAX_SIM

Maximum similarity.

MAX_SIM = 'maxSim'

class weaviate.collections.classes.config_vector_index._PQEncoderConfigCreate(*, type_, distribution)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• type_ (PQEncoderType | None)

• distribution (PQEncoderDistribution | None)

type_: PQEncoderType | None

distribution: PQEncoderDistribution | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._PQEncoderConfigUpdate(*, type_, distribution)

Bases: _ConfigUpdateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• type_ (PQEncoderType | None)

• distribution (PQEncoderDistribution | None)

type_: PQEncoderType | None

distribution: PQEncoderDistribution | None

merge_with_existing(schema)

Must be done manually since Pydantic does not work well with type and type_.

Errors shadowing type occur if we want to use type as a field name.

Parameters:

schema (Dict[str, Any])

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._PQConfigCreate(*, enabled=True, bitCompression=None, centroids, encoder, segments, trainingLimit)

Bases: _QuantizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• enabled (bool)

• bitCompression (bool | None)

• centroids (int | None)

• encoder (_PQEncoderConfigCreate)

• segments (int | None)

• trainingLimit (int | None)

bitCompression: bool | None

centroids: int | None

encoder: _PQEncoderConfigCreate

segments: int | None

trainingLimit: int | None

static quantizer_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._BQConfigCreate(*, enabled=True, cache, rescoreLimit)

Bases: _QuantizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• enabled (bool)

• cache (bool | None)

• rescoreLimit (int | None)

cache: bool | None

rescoreLimit: int | None

static quantizer_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._SQConfigCreate(*, enabled=True, rescoreLimit, trainingLimit)

Bases: _QuantizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• enabled (bool)

• rescoreLimit (int | None)

• trainingLimit (int | None)

rescoreLimit: int | None

trainingLimit: int | None

static quantizer_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._RQConfigCreate(*, enabled=True, cache, bits, rescoreLimit)

Bases: _QuantizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• enabled (bool)

• cache (bool | None)

• bits (int | None)

• rescoreLimit (int | None)

cache: bool | None

bits: int | None

rescoreLimit: int | None

static quantizer_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._UncompressedConfigCreate(*, enabled=True)

Bases: _QuantizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

enabled (bool)

static quantizer_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._PQConfigUpdate(*, bitCompression=None, centroids, enabled, segments, trainingLimit, encoder)

Bases: _QuantizerConfigUpdate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• bitCompression (bool | None)

• centroids (int | None)

• enabled (bool | None)

• segments (int | None)

• trainingLimit (int | None)

• encoder (_PQEncoderConfigUpdate | None)

bitCompression: bool | None

centroids: int | None

enabled: bool | None

segments: int | None

trainingLimit: int | None

encoder: _PQEncoderConfigUpdate | None

static quantizer_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._BQConfigUpdate(*, enabled, rescoreLimit)

Bases: _QuantizerConfigUpdate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• enabled (bool | None)

• rescoreLimit (int | None)

enabled: bool | None

rescoreLimit: int | None

static quantizer_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._RQConfigUpdate(*, enabled, rescoreLimit, bits)

Bases: _QuantizerConfigUpdate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• enabled (bool | None)

• rescoreLimit (int | None)

• bits (int | None)

enabled: bool | None

rescoreLimit: int | None

bits: int | None

static quantizer_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._SQConfigUpdate(*, enabled, rescoreLimit, trainingLimit)

Bases: _QuantizerConfigUpdate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• enabled (bool | None)

• rescoreLimit (int | None)

• trainingLimit (int | None)

enabled: bool | None

rescoreLimit: int | None

trainingLimit: int | None

static quantizer_name()

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vector_index._VectorIndexMultivectorEncoding

Bases: object

static muvera(ksim=None, dprojections=None, repetitions=None)

Parameters:

• ksim (int | None)

• dprojections (int | None)

• repetitions (int | None)

Return type:

_MultiVectorEncodingConfigCreate

class weaviate.collections.classes.config_vector_index._VectorIndexMultiVector

Bases: object

Encoding

alias of _VectorIndexMultivectorEncoding

static multi_vector(encoding: _MultiVectorEncodingConfigCreate, aggregation: MultiVectorAggregation | None = None) → _MultiVectorConfigCreate

static multi_vector(encoding: _MultiVectorEncodingConfigCreate | None = None, aggregation: MultiVectorAggregation | None = None) → _MultiVectorConfigCreate

Parameters:

• encoding (_MultiVectorEncodingConfigCreate | None)

• aggregation (MultiVectorAggregation | None)

Return type:

_MultiVectorConfigCreate

class weaviate.collections.classes.config_vector_index._VectorIndexQuantizer

Bases: object

static pq(bit_compression=None, centroids=None, encoder_distribution=None, encoder_type=None, segments=None, training_limit=None)

Create a _PQConfigCreate object to be used when defining the product quantization (PQ) configuration of Weaviate.

Use this method when defining the quantizer argument in the vector_index configuration.

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/concepts/vector-index#hnsw-with-compression>`_ for a more detailed view!

• bit_compression (bool | None)

• centroids (int | None)

• encoder_distribution (PQEncoderDistribution | None)

• encoder_type (PQEncoderType | None)

• segments (int | None)

• training_limit (int | None)

Return type:

_PQConfigCreate

static bq(cache=None, rescore_limit=None)

Create a _BQConfigCreate object to be used when defining the binary quantization (BQ) configuration of Weaviate.

Use this method when defining the quantizer argument in the vector_index configuration. Note that the arguments have no effect for HNSW.

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/concepts/vector-index#binary-quantization>`_ for a more detailed view!

• cache (bool | None)

• rescore_limit (int | None)

Return type:

_BQConfigCreate

static sq(cache: bool, rescore_limit: int | None = None, training_limit: int | None = None) → _SQConfigCreate

static sq(cache: Literal[None] = None, rescore_limit: int | None = None, training_limit: int | None = None) → _SQConfigCreate

Create a _SQConfigCreate object to be used when defining the scalar quantization (SQ) configuration of Weaviate.

Use this method when defining the quantizer argument in the vector_index configuration. Note that the arguments have no effect for HNSW.

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/concepts/vector-index#binary-quantization>`_ for a more detailed view!

• cache (bool | None)

• rescore_limit (int | None)

• training_limit (int | None)

Return type:

_SQConfigCreate

static rq(cache=None, bits=None, rescore_limit=None)

Create a _RQConfigCreate object to be used when defining the Rotational quantization (RQ) configuration of Weaviate.

Use this method when defining the quantizer argument in the vector_index configuration. Note that the arguments have no effect for HNSW.

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/concepts/vector-index>`_ for a more detailed view!

• cache (bool | None)

• bits (int | None)

• rescore_limit (int | None)

Return type:

_RQConfigCreate

static none()

Create a a vector index without compression.

Return type:

_UncompressedConfigCreate

class weaviate.collections.classes.config_vector_index._VectorIndex

Bases: object

MultiVector

alias of _VectorIndexMultiVector

Quantizer

alias of _VectorIndexQuantizer

static none()

Create a _VectorIndexConfigSkipCreate object to be used when configuring Weaviate to not index your vectors.

Use this method when defining the vector_index_config argument in collections.create().

Return type:

_VectorIndexConfigSkipCreate

static hnsw(cleanup_interval_seconds: int | None = None, distance_metric: VectorDistances | None = None, dynamic_ef_factor: int | None = None, dynamic_ef_max: int | None = None, dynamic_ef_min: int | None = None, ef: int | None = None, ef_construction: int | None = None, filter_strategy: VectorFilterStrategy | None = None, flat_search_cutoff: int | None = None, max_connections: int | None = None, vector_cache_max_objects: int | None = None, *, quantizer: _QuantizerConfigCreate | None = None, multi_vector: _MultiVectorConfigCreate) → _VectorIndexConfigHNSWCreate

static hnsw(cleanup_interval_seconds: int | None = None, distance_metric: VectorDistances | None = None, dynamic_ef_factor: int | None = None, dynamic_ef_max: int | None = None, dynamic_ef_min: int | None = None, ef: int | None = None, ef_construction: int | None = None, filter_strategy: VectorFilterStrategy | None = None, flat_search_cutoff: int | None = None, max_connections: int | None = None, vector_cache_max_objects: int | None = None, quantizer: _QuantizerConfigCreate | None = None, multi_vector: _MultiVectorConfigCreate | None = None) → _VectorIndexConfigHNSWCreate

Create a _VectorIndexConfigHNSWCreate object to be used when defining the HNSW vector index configuration of Weaviate.

Use this method when defining the vector_index_config argument in collections.create().

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/configuration/indexes#how-to-configure-hnsw>`_ for a more detailed view!

• cleanup_interval_seconds (int | None)

• distance_metric (VectorDistances | None)

• dynamic_ef_factor (int | None)

• dynamic_ef_max (int | None)

• dynamic_ef_min (int | None)

• ef (int | None)

• ef_construction (int | None)

• filter_strategy (VectorFilterStrategy | None)

• flat_search_cutoff (int | None)

• max_connections (int | None)

• vector_cache_max_objects (int | None)

• quantizer (_QuantizerConfigCreate | None)

• multi_vector (_MultiVectorConfigCreate | None)

Return type:

_VectorIndexConfigHNSWCreate

static hfresh(distance_metric=None, max_posting_size_kb=None, replicas=None, search_probe=None, quantizer=None, multi_vector=None)

Create a _VectorIndexConfigHFreshCreate object to be used when defining the HFresh vector index configuration of Weaviate.

Use this method when defining the vector_index_config argument in collections.create().

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/configuration/indexes#how-to-configure-hfresh>`_ for a more detailed view!

• distance_metric (VectorDistances | None)

• max_posting_size_kb (int | None)

• replicas (int | None)

• search_probe (int | None)

• quantizer (_QuantizerConfigCreate | None)

• multi_vector (_MultiVectorConfigCreate | None)

Return type:

_VectorIndexConfigHFreshCreate

static flat(distance_metric=None, vector_cache_max_objects=None, quantizer=None)

Create a _VectorIndexConfigFlatCreate object to be used when defining the FLAT vector index configuration of Weaviate.

Use this method when defining the vector_index_config argument in collections.create().

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/configuration/indexes#how-to-configure-hnsw>`_ for a more detailed view!

• distance_metric (VectorDistances | None)

• vector_cache_max_objects (int | None)

• quantizer (_QuantizerConfigCreate | None)

Return type:

_VectorIndexConfigFlatCreate

static dynamic(distance_metric=None, threshold=None, hnsw=None, flat=None)

Create a _VectorIndexConfigDynamicCreate object to be used when defining the DYNAMIC vector index configuration of Weaviate.

Use this method when defining the vector_index_config argument in collections.create().

Parameters:

• <https (See `the docs) –

  //weaviate.io/developers/weaviate/configuration/indexes#how-to-configure-hnsw>`_ for a more detailed view!

• distance_metric (VectorDistances | None)

• threshold (int | None)

• hnsw (_VectorIndexConfigHNSWCreate | None)

• flat (_VectorIndexConfigFlatCreate | None)

Return type:

_VectorIndexConfigDynamicCreate

weaviate.collections.classes.config_vectorizers

class weaviate.collections.classes.config_vectorizers.Vectorizers(*values)

Bases: str, Enum

The available vectorization modules in Weaviate.

These modules encode binary data into lists of floats called vectors. See the docs for more details.

NONE

No vectorizer.

TEXT2VEC_AWS

Weaviate module backed by AWS text-based embedding models.

TEXT2VEC_COHERE

Weaviate module backed by Cohere text-based embedding models.

TEXT2VEC_CONTEXTIONARY

Weaviate module backed by Contextionary text-based embedding models.

TEXT2VEC_GPT4ALL

Weaviate module backed by GPT-4-All text-based embedding models.

TEXT2VEC_HUGGINGFACE

Weaviate module backed by HuggingFace text-based embedding models.

TEXT2VEC_OPENAI

Weaviate module backed by OpenAI and Azure-OpenAI text-based embedding models.

TEXT2VEC_PALM

Weaviate module backed by PaLM text-based embedding models.

TEXT2VEC_TRANSFORMERS

Weaviate module backed by Transformers text-based embedding models.

TEXT2VEC_JINAAI

Weaviate module backed by Jina AI text-based embedding models.

TEXT2VEC_VOYAGEAI

Weaviate module backed by Voyage AI text-based embedding models.

TEXT2VEC_NVIDIA

Weaviate module backed by NVIDIA text-based embedding models.

TEXT2VEC_WEAVIATE

Weaviate module backed by Weaviate’s self-hosted text-based embedding models.

IMG2VEC_NEURAL

Weaviate module backed by a ResNet-50 neural network for images.

MULTI2VEC_CLIP

Weaviate module backed by a Sentence-BERT CLIP model for images and text.

MULTI2VEC_PALM

Weaviate module backed by a palm model for images and text.

MULTI2VEC_BIND

Weaviate module backed by the ImageBind model for images, text, audio, depth, IMU, thermal, and video.

MULTI2VEC_VOYAGEAI

Weaviate module backed by a Voyage AI multimodal embedding models.

MULTI2VEC_NVIDIA

Weaviate module backed by NVIDIA multimodal embedding models.

REF2VEC_CENTROID

Weaviate module backed by a centroid-based model that calculates an object’s vectors from its referenced vectors.

NONE = 'none'

TEXT2COLBERT_JINAAI = 'text2colbert-jinaai'

TEXT2VEC_AWS = 'text2vec-aws'

TEXT2VEC_COHERE = 'text2vec-cohere'

TEXT2VEC_CONTEXTIONARY = 'text2vec-contextionary'

TEXT2VEC_DATABRICKS = 'text2vec-databricks'

TEXT2VEC_GPT4ALL = 'text2vec-gpt4all'

TEXT2VEC_HUGGINGFACE = 'text2vec-huggingface'

TEXT2VEC_MISTRAL = 'text2vec-mistral'

TEXT2VEC_MORPH = 'text2vec-morph'

TEXT2VEC_MODEL2VEC = 'text2vec-model2vec'

TEXT2VEC_NVIDIA = 'text2vec-nvidia'

TEXT2VEC_OLLAMA = 'text2vec-ollama'

TEXT2VEC_OPENAI = 'text2vec-openai'

TEXT2VEC_PALM = 'text2vec-palm'

TEXT2VEC_TRANSFORMERS = 'text2vec-transformers'

TEXT2VEC_JINAAI = 'text2vec-jinaai'

TEXT2VEC_VOYAGEAI = 'text2vec-voyageai'

TEXT2VEC_WEAVIATE = 'text2vec-weaviate'

IMG2VEC_NEURAL = 'img2vec-neural'

MULTI2VEC_AWS = 'multi2vec-aws'

MULTI2VEC_CLIP = 'multi2vec-clip'

MULTI2VEC_COHERE = 'multi2vec-cohere'

MULTI2VEC_JINAAI = 'multi2vec-jinaai'

MULTI2MULTI_JINAAI = 'multi2multivec-jinaai'

MULTI2MULTI_WEAVIATE = 'multi2multivec-weaviate'

MULTI2VEC_BIND = 'multi2vec-bind'

MULTI2VEC_PALM = 'multi2vec-palm'

MULTI2VEC_VOYAGEAI = 'multi2vec-voyageai'

MULTI2VEC_NVIDIA = 'multi2vec-nvidia'

REF2VEC_CENTROID = 'ref2vec-centroid'

class weaviate.collections.classes.config_vectorizers.VectorDistances(*values)

Bases: str, Enum

Vector similarity distance metric to be used in the VectorIndexConfig class.

To ensure optimal search results, we recommend reviewing whether your model provider advises a specific distance metric and following their advice.

COSINE

Cosine distance: reference

DOT

Dot distance: reference

L2_SQUARED

L2 squared distance: reference

HAMMING

Hamming distance: reference

MANHATTAN

Manhattan distance: reference

COSINE = 'cosine'

DOT = 'dot'

L2_SQUARED = 'l2-squared'

HAMMING = 'hamming'

MANHATTAN = 'manhattan'

class weaviate.collections.classes.config_vectorizers._VectorizerConfigCreate(*, vectorizer)

Bases: _ConfigCreateModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

vectorizer (Vectorizers | _EnumLikeStr)

vectorizer: Vectorizers | _EnumLikeStr

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2ColbertJinaAIConfig(*, vectorizer=Vectorizers.TEXT2COLBERT_JINAAI, vectorizeClassName, model, dimensions)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• vectorizeClassName (bool)

• model (str | None)

• dimensions (int | None)

vectorizer: Vectorizers | _EnumLikeStr

vectorizeClassName: bool

model: str | None

dimensions: int | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecContextionaryConfig(*, vectorizer=Vectorizers.TEXT2VEC_CONTEXTIONARY, vectorizeClassName)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• vectorizeClassName (bool)

vectorizer: Vectorizers | _EnumLikeStr

vectorizeClassName: bool

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecModel2VecConfig(*, vectorizer=Vectorizers.TEXT2VEC_MODEL2VEC, vectorizeClassName, inferenceUrl)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• vectorizeClassName (bool)

• inferenceUrl (str | None)

vectorizer: Vectorizers | _EnumLikeStr

vectorizeClassName: bool

inferenceUrl: str | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._VectorizerCustomConfig(*, vectorizer, module_config)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• module_config (Dict[str, Any] | None)

module_config: Dict[str, Any] | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecAWSConfig(*, vectorizer=Vectorizers.TEXT2VEC_AWS, model, endpoint, region, service, targetModel, targetVariant, vectorizeClassName)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• model (str | None)

• endpoint (str | None)

• region (str)

• service (str)

• targetModel (str | None)

• targetVariant (str | None)

• vectorizeClassName (bool)

vectorizer: Vectorizers | _EnumLikeStr

model: str | None

endpoint: str | None

region: str

service: str

targetModel: str | None

targetVariant: str | None

vectorizeClassName: bool

classmethod _check_name(r)

Parameters:

r (str)

Return type:

str

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecAzureOpenAIConfig(*, vectorizer=Vectorizers.TEXT2VEC_OPENAI, baseURL, resourceName, deploymentId, vectorizeClassName, dimensions, model)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• baseURL (AnyHttpUrl | None)

• resourceName (str)

• deploymentId (str)

• vectorizeClassName (bool)

• dimensions (int | None)

• model (str | None)

vectorizer: Vectorizers | _EnumLikeStr

baseURL: AnyHttpUrl | None

resourceName: str

deploymentId: str

vectorizeClassName: bool

dimensions: int | None

model: str | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecHuggingFaceConfig(*, vectorizer=Vectorizers.TEXT2VEC_HUGGINGFACE, model, passageModel, queryModel, endpointURL, waitForModel, useGPU, useCache, vectorizeClassName)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• model (str | None)

• passageModel (str | None)

• queryModel (str | None)

• endpointURL (AnyHttpUrl | None)

• waitForModel (bool | None)

• useGPU (bool | None)

• useCache (bool | None)

• vectorizeClassName (bool)

vectorizer: Vectorizers | _EnumLikeStr

model: str | None

passageModel: str | None

queryModel: str | None

endpointURL: AnyHttpUrl | None

waitForModel: bool | None

useGPU: bool | None

useCache: bool | None

vectorizeClassName: bool

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecMistralConfig(*, vectorizer=Vectorizers.TEXT2VEC_MISTRAL, model, vectorizeClassName, baseURL)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• model (str | None)

• vectorizeClassName (bool)

• baseURL (AnyHttpUrl | None)

vectorizer: Vectorizers | _EnumLikeStr

model: str | None

vectorizeClassName: bool

baseURL: AnyHttpUrl | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecMorphConfig(*, vectorizer=Vectorizers.TEXT2VEC_MORPH, model, vectorizeClassName, baseURL)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• model (str | None)

• vectorizeClassName (bool)

• baseURL (AnyHttpUrl | None)

vectorizer: Vectorizers | _EnumLikeStr

model: str | None

vectorizeClassName: bool

baseURL: AnyHttpUrl | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecDatabricksConfig(*, vectorizer=Vectorizers.TEXT2VEC_DATABRICKS, endpoint, instruction, vectorizeClassName)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• endpoint (str)

• instruction (str | None)

• vectorizeClassName (bool)

vectorizer: Vectorizers | _EnumLikeStr

endpoint: str

instruction: str | None

vectorizeClassName: bool

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecOpenAIConfig(*, vectorizer=Vectorizers.TEXT2VEC_OPENAI, baseURL, dimensions, model, modelVersion, type_, vectorizeClassName)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• baseURL (AnyHttpUrl | None)

• dimensions (int | None)

• model (str | None)

• modelVersion (str | None)

• type_ (Literal['text', 'code'] | None)

• vectorizeClassName (bool)

vectorizer: Vectorizers | _EnumLikeStr

baseURL: AnyHttpUrl | None

dimensions: int | None

model: str | None

modelVersion: str | None

type_: Literal['text', 'code'] | None

vectorizeClassName: bool

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecCohereConfig(*, vectorizer=Vectorizers.TEXT2VEC_COHERE, baseURL, model, dimensions, truncate, vectorizeClassName)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• baseURL (AnyHttpUrl | None)

• model (str | None)

• dimensions (int | None)

• truncate (Literal['NONE', 'START', 'END', 'LEFT', 'RIGHT'] | None)

• vectorizeClassName (bool)

vectorizer: Vectorizers | _EnumLikeStr

baseURL: AnyHttpUrl | None

model: str | None

dimensions: int | None

truncate: Literal['NONE', 'START', 'END', 'LEFT', 'RIGHT'] | None

vectorizeClassName: bool

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecGoogleConfig(*, vectorizer=Vectorizers.TEXT2VEC_PALM, projectId, apiEndpoint, dimensions, modelId, vectorizeClassName, titleProperty, taskType)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• projectId (str | None)

• apiEndpoint (str | None)

• dimensions (int | None)

• modelId (str | None)

• vectorizeClassName (bool)

• titleProperty (str | None)

• taskType (str | None)

vectorizer: Vectorizers | _EnumLikeStr

projectId: str | None

apiEndpoint: str | None

dimensions: int | None

modelId: str | None

vectorizeClassName: bool

titleProperty: str | None

taskType: str | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecTransformersConfig(*, vectorizer=Vectorizers.TEXT2VEC_TRANSFORMERS, poolingStrategy, vectorizeClassName, inferenceUrl, passageInferenceUrl, queryInferenceUrl, dimensions=None)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• poolingStrategy (Literal['masked_mean', 'cls'])

• vectorizeClassName (bool)

• inferenceUrl (str | None)

• passageInferenceUrl (str | None)

• queryInferenceUrl (str | None)

• dimensions (int | None)

vectorizer: Vectorizers | _EnumLikeStr

poolingStrategy: Literal['masked_mean', 'cls']

vectorizeClassName: bool

inferenceUrl: str | None

passageInferenceUrl: str | None

queryInferenceUrl: str | None

dimensions: int | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecGPT4AllConfig(*, vectorizer=Vectorizers.TEXT2VEC_GPT4ALL, vectorizeClassName)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• vectorizeClassName (bool)

vectorizer: Vectorizers | _EnumLikeStr

vectorizeClassName: bool

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecJinaConfig(*, vectorizer=Vectorizers.TEXT2VEC_JINAAI, baseURL, dimensions, model, vectorizeClassName)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• baseURL (str | None)

• dimensions (int | None)

• model (str | None)

• vectorizeClassName (bool)

vectorizer: Vectorizers | _EnumLikeStr

baseURL: str | None

dimensions: int | None

model: str | None

vectorizeClassName: bool

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecVoyageConfig(*, vectorizer=Vectorizers.TEXT2VEC_VOYAGEAI, dimensions, model, baseURL, truncate, vectorizeClassName)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• dimensions (int | None)

• model (str | None)

• baseURL (str | None)

• truncate (bool | None)

• vectorizeClassName (bool)

vectorizer: Vectorizers | _EnumLikeStr

dimensions: int | None

model: str | None

baseURL: str | None

truncate: bool | None

vectorizeClassName: bool

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecNvidiaConfig(*, vectorizer=Vectorizers.TEXT2VEC_NVIDIA, model, baseURL, truncate, vectorizeClassName)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• model (str | None)

• baseURL (str | None)

• truncate (bool | None)

• vectorizeClassName (bool)

vectorizer: Vectorizers | _EnumLikeStr

model: str | None

baseURL: str | None

truncate: bool | None

vectorizeClassName: bool

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecWeaviateConfig(*, vectorizer=Vectorizers.TEXT2VEC_WEAVIATE, model, baseURL, vectorizeClassName, dimensions)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• model (str | None)

• baseURL (str | None)

• vectorizeClassName (bool)

• dimensions (int | None)

vectorizer: Vectorizers | _EnumLikeStr

model: str | None

baseURL: str | None

vectorizeClassName: bool

dimensions: int | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Text2VecOllamaConfig(*, vectorizer=Vectorizers.TEXT2VEC_OLLAMA, model, apiEndpoint, vectorizeClassName)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• model (str | None)

• apiEndpoint (str | None)

• vectorizeClassName (bool)

vectorizer: Vectorizers | _EnumLikeStr

model: str | None

apiEndpoint: str | None

vectorizeClassName: bool

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Img2VecNeuralConfig(*, vectorizer=Vectorizers.IMG2VEC_NEURAL, imageFields)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• imageFields (List[str])

vectorizer: Vectorizers | _EnumLikeStr

imageFields: List[str]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers.Multi2VecField(*, name, weight=None)

Bases: BaseModel

Use this class when defining the fields to use in the Multi2VecClip and Multi2VecBind vectorizers.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• name (str)

• weight (float | None)

name: str

weight: float | None

_abc_impl = <_abc._abc_data object>

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Multi2VecBase(*, vectorizer, imageFields, textFields)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• imageFields (List[Multi2VecField] | None)

• textFields (List[Multi2VecField] | None)

imageFields: List[Multi2VecField] | None

textFields: List[Multi2VecField] | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Multi2VecCohereConfig(*, vectorizer=Vectorizers.MULTI2VEC_COHERE, imageFields, textFields, baseURL, model, dimensions, truncate)

Bases: _Multi2VecBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• imageFields (List[Multi2VecField] | None)

• textFields (List[Multi2VecField] | None)

• baseURL (AnyHttpUrl | None)

• model (str | None)

• dimensions (int | None)

• truncate (Literal['NONE', 'START', 'END', 'LEFT', 'RIGHT'] | None)

vectorizer: Vectorizers | _EnumLikeStr

baseURL: AnyHttpUrl | None

model: str | None

dimensions: int | None

truncate: Literal['NONE', 'START', 'END', 'LEFT', 'RIGHT'] | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Multi2VecJinaConfig(*, vectorizer=Vectorizers.MULTI2VEC_JINAAI, imageFields, textFields, baseURL, model, dimensions)

Bases: _Multi2VecBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• imageFields (List[Multi2VecField] | None)

• textFields (List[Multi2VecField] | None)

• baseURL (AnyHttpUrl | None)

• model (str | None)

• dimensions (int | None)

vectorizer: Vectorizers | _EnumLikeStr

baseURL: AnyHttpUrl | None

model: str | None

dimensions: int | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Multi2VecAWSConfig(*, vectorizer=Vectorizers.MULTI2VEC_AWS, imageFields, textFields, region, model, dimensions)

Bases: _Multi2VecBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• imageFields (List[Multi2VecField] | None)

• textFields (List[Multi2VecField] | None)

• region (str | None)

• model (str | None)

• dimensions (int | None)

vectorizer: Vectorizers | _EnumLikeStr

region: str | None

model: str | None

dimensions: int | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Multi2MultiVecJinaConfig(*, vectorizer=Vectorizers.MULTI2MULTI_JINAAI, imageFields, textFields, baseURL, model)

Bases: _Multi2VecBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• imageFields (List[Multi2VecField] | None)

• textFields (List[Multi2VecField] | None)

• baseURL (AnyHttpUrl | None)

• model (str | None)

vectorizer: Vectorizers | _EnumLikeStr

baseURL: AnyHttpUrl | None

model: str | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Multi2MultiVecWeaviateConfig(*, vectorizer=Vectorizers.MULTI2MULTI_WEAVIATE, imageFields, textFields, baseURL, model)

Bases: _Multi2VecBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• imageFields (List[Multi2VecField] | None)

• textFields (List[Multi2VecField] | None)

• baseURL (AnyHttpUrl | None)

• model (str | None)

vectorizer: Vectorizers | _EnumLikeStr

baseURL: AnyHttpUrl | None

model: str | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Multi2VecClipConfig(*, vectorizer=Vectorizers.MULTI2VEC_CLIP, imageFields, textFields, inferenceUrl)

Bases: _Multi2VecBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• imageFields (List[Multi2VecField] | None)

• textFields (List[Multi2VecField] | None)

• inferenceUrl (str | None)

vectorizer: Vectorizers | _EnumLikeStr

inferenceUrl: str | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Multi2VecGoogleConfig(*, vectorizer=Vectorizers.MULTI2VEC_PALM, imageFields, textFields, audioFields, videoFields, projectId, location, apiEndpoint=None, modelId, dimensions, videoIntervalSeconds)

Bases: _Multi2VecBase, _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• imageFields (List[Multi2VecField] | None)

• textFields (List[Multi2VecField] | None)

• audioFields (List[Multi2VecField] | None)

• videoFields (List[Multi2VecField] | None)

• projectId (str | None)

• location (str | None)

• apiEndpoint (str | None)

• modelId (str | None)

• dimensions (int | None)

• videoIntervalSeconds (int | None)

vectorizer: Vectorizers | _EnumLikeStr

audioFields: List[Multi2VecField] | None

videoFields: List[Multi2VecField] | None

projectId: str | None

location: str | None

apiEndpoint: str | None

modelId: str | None

dimensions: int | None

videoIntervalSeconds: int | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Multi2VecBindConfig(*, vectorizer=Vectorizers.MULTI2VEC_BIND, imageFields, textFields, audioFields, depthFields, IMUFields, thermalFields, videoFields)

Bases: _Multi2VecBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• imageFields (List[Multi2VecField] | None)

• textFields (List[Multi2VecField] | None)

• audioFields (List[Multi2VecField] | None)

• depthFields (List[Multi2VecField] | None)

• IMUFields (List[Multi2VecField] | None)

• thermalFields (List[Multi2VecField] | None)

• videoFields (List[Multi2VecField] | None)

vectorizer: Vectorizers | _EnumLikeStr

audioFields: List[Multi2VecField] | None

depthFields: List[Multi2VecField] | None

IMUFields: List[Multi2VecField] | None

thermalFields: List[Multi2VecField] | None

videoFields: List[Multi2VecField] | None

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Multi2VecVoyageaiConfig(*, vectorizer=Vectorizers.MULTI2VEC_VOYAGEAI, imageFields, textFields, baseURL, model, truncation, dimensions, videoFields)

Bases: _Multi2VecBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• imageFields (List[Multi2VecField] | None)

• textFields (List[Multi2VecField] | None)

• baseURL (AnyHttpUrl | None)

• model (str | None)

• truncation (bool | None)

• dimensions (int | None)

• videoFields (List[Multi2VecField] | None)

vectorizer: Vectorizers | _EnumLikeStr

baseURL: AnyHttpUrl | None

model: str | None

truncation: bool | None

dimensions: int | None

videoFields: List[Multi2VecField] | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Multi2VecNvidiaConfig(*, vectorizer=Vectorizers.MULTI2VEC_NVIDIA, imageFields, textFields, baseURL, model, truncation)

Bases: _Multi2VecBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• imageFields (List[Multi2VecField] | None)

• textFields (List[Multi2VecField] | None)

• baseURL (AnyHttpUrl | None)

• model (str | None)

• truncation (bool | None)

vectorizer: Vectorizers | _EnumLikeStr

baseURL: AnyHttpUrl | None

model: str | None

truncation: bool | None

_to_dict()

Return type:

Dict[str, Any]

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.config_vectorizers._Ref2VecCentroidConfig(*, vectorizer=Vectorizers.REF2VEC_CENTROID, referenceProperties, method)

Bases: _VectorizerConfigCreate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• vectorizer (Vectorizers | _EnumLikeStr)

• referenceProperties (List[str])

• method (Literal['mean'])

vectorizer: Vectorizers | _EnumLikeStr

referenceProperties: List[str]

method: Literal['mean']

_abc_impl = <_abc._abc_data object>

model_config = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

weaviate.collections.classes.config_vectorizers._map_multi2vec_fields(fields)

Parameters:

fields (List[str] | List[Multi2VecField] | None)

Return type:

List[Multi2VecField] | None

class weaviate.collections.classes.config_vectorizers._Vectorizer

Bases: object

Use this factory class to create the correct object for the vectorizer_config argument in the collections.create() method.

Each staticmethod provides options specific to the named vectorizer in the function’s name. Under-the-hood data validation steps will ensure that any mis-specifications will be caught before the request is sent to Weaviate.

static none()

Create a _VectorizerConfigCreate object with the vectorizer set to Vectorizer.NONE.

Return type:

_VectorizerConfigCreate

static img2vec_neural(image_fields)

Create a _Img2VecNeuralConfigCreate object for use when vectorizing using the img2vec-neural model.

See the documentation for detailed usage.

Parameters:

image_fields (List[str]) – The image fields to use. This is a required field and must match the property fields of the collection that are defined as DataType.BLOB.

Raises:

pydantic.ValidationError – If image_fields is not a list.

Return type:

_VectorizerConfigCreate

static multi2vec_clip(image_fields=None, text_fields=None, interference_url=None, inference_url=None, vectorize_collection_name=True)

Create a _Multi2VecClipConfigCreate object for use when vectorizing using the multi2vec-clip model.

See the documentation for detailed usage.

Parameters:

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

• inference_url (str | None) – The inference url to use where API requests should go. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• interference_url (str | None)

Raises:

pydantic.ValidationError – If image_fields or text_fields are not None or a list.

Return type:

_VectorizerConfigCreate

static multi2vec_bind(audio_fields=None, depth_fields=None, image_fields=None, imu_fields=None, text_fields=None, thermal_fields=None, video_fields=None, vectorize_collection_name=True)

Create a _Multi2VecBindConfigCreate object for use when vectorizing using the multi2vec-clip model.

See the documentation for detailed usage.

Parameters:

• audio_fields (List[str] | List[Multi2VecField] | None) – The audio fields to use in vectorization.

• depth_fields (List[str] | List[Multi2VecField] | None) – The depth fields to use in vectorization.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• imu_fields (List[str] | List[Multi2VecField] | None) – The IMU fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

• thermal_fields (List[str] | List[Multi2VecField] | None) – The thermal fields to use in vectorization.

• video_fields (List[str] | List[Multi2VecField] | None) – The video fields to use in vectorization.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Raises:

pydantic.ValidationError – If any of the *_fields are not None or a list.

Return type:

_VectorizerConfigCreate

static ref2vec_centroid(reference_properties, method='mean')

Create a _Ref2VecCentroidConfigCreate object for use when vectorizing using the ref2vec-centroid model.

See the documentation for detailed usage.

Parameters:

• reference_properties (List[str]) – The reference properties to use in vectorization, REQUIRED.

• method (Literal['mean']) – The method to use in vectorization. Defaults to mean.

Raises:

pydantic.ValidationError – If reference_properties is not a list.

Return type:

_VectorizerConfigCreate

static text2vec_aws(model=None, region='', endpoint=None, service='bedrock', vectorize_collection_name=True)

Create a _Text2VecAWSConfigCreate object for use when vectorizing using the text2vec-aws model.

See the documentation for detailed usage.

Parameters:

• model (Literal['amazon.titan-embed-text-v1', 'cohere.embed-english-v3', 'cohere.embed-multilingual-v3'] | str | None) – The model to use, REQUIRED for service “bedrock”.

• region (str) – The AWS region to run the model from, REQUIRED.

• endpoint (str | None) – The model to use, REQUIRED for service “sagemaker”.

• service (Literal['bedrock', 'sagemaker'] | str) – The AWS service to use, options are “bedrock” and “sagemaker”.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Return type:

_VectorizerConfigCreate

static text2vec_azure_openai(resource_name, deployment_id, vectorize_collection_name=True, base_url=None, dimensions=None, model=None)

Create a _Text2VecAzureOpenAIConfigCreate object for use when vectorizing using the text2vec-azure-openai model.

See the documentation for detailed usage.

Parameters:

• resource_name (str) – The resource name to use, REQUIRED.

• deployment_id (str) – The deployment ID to use, REQUIRED.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• dimensions (int | None) – The dimensionality of the vectors. Defaults to None, which uses the server-defined default.

• model (str | None)

Raises:

pydantic.ValidationError – If resource_name or deployment_id are not str.

Return type:

_VectorizerConfigCreate

static text2vec_contextionary(vectorize_collection_name=True)

Create a _Text2VecContextionaryConfigCreate object for use when vectorizing using the text2vec-contextionary model.

See the documentation for detailed usage.

Parameters:

vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Raises:

pydantic.ValidationError – If vectorize_collection_name is not a bool.

Return type:

_VectorizerConfigCreate

static custom(module_name, module_config=None)

Create a _VectorizerCustomConfig object for use when vectorizing using a custom specification.

Parameters:

• module_name (str) – The name of the module to use, REQUIRED.

• module_config (Dict[str, Any] | None) – The configuration to use for the module. Defaults to None, which uses the server-defined default.

Return type:

_VectorizerConfigCreate

static text2vec_cohere(model=None, truncate=None, vectorize_collection_name=True, base_url=None)

Create a _Text2VecCohereConfigCreate object for use when vectorizing using the text2vec-cohere model.

See the documentation for detailed usage.

Parameters:

• model (Literal['embed-v4.0', 'embed-multilingual-v2.0', 'embed-multilingual-v3.0', 'embed-multilingual-light-v3.0', 'small', 'medium', 'large', 'multilingual-22-12', 'embed-english-v2.0', 'embed-english-light-v2.0', 'embed-english-v3.0', 'embed-english-light-v3.0'] | str | None) – The model to use. Defaults to None, which uses the server-defined default.

• truncate (Literal['NONE', 'START', 'END', 'LEFT', 'RIGHT'] | None) – The truncation strategy to use. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

Raises:

pydantic.ValidationError – If model is not a valid value from the CohereModel type or if truncate is not a valid value from the CohereTruncation type.

Return type:

_VectorizerConfigCreate

static multi2vec_cohere(*, model=None, truncate=None, vectorize_collection_name=True, base_url=None, image_fields=None, text_fields=None)

Create a _Multi2VecCohereConfig object for use when vectorizing using the multi2vec-cohere model.

See the documentation for detailed usage.

Parameters:

• model (Literal['embed-v4.0', 'embed-multilingual-v3.0', 'embed-multilingual-light-v3.0', 'embed-english-v3.0', 'embed-english-light-v3.0'] | str | None) – The model to use. Defaults to None, which uses the server-defined default.

• truncate (Literal['NONE', 'START', 'END', 'LEFT', 'RIGHT'] | None) – The truncation strategy to use. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

Raises:

pydantic.ValidationError – If model is not a valid value from the CohereMultimodalModel type or if truncate is not a valid value from the CohereTruncation type.

Return type:

_VectorizerConfigCreate

static multi2vec_voyageai(*, model=None, truncation=None, output_encoding, vectorize_collection_name=True, base_url=None, image_fields=None, text_fields=None)

Create a _Multi2VecVoyageaiConfig object for use when vectorizing using the multi2vec-voyageai model.

See the documentation for detailed usage.

Parameters:

• model (Literal['voyage-multimodal-3', 'voyage-multimodal-3.5'] | str | None) – The model to use. Defaults to None, which uses the server-defined default.

• truncation (bool | None) – The truncation strategy to use. Defaults to None, which uses the server-defined default.

• output_encoding (str | None) – Deprecated, has no effect.

• vectorize_collection_name (bool) – Deprecated, has no effect.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

Raises:

pydantic.ValidationError – If model is not a valid value from the VoyageMultimodalModel type.

Return type:

_VectorizerConfigCreate

static multi2vec_nvidia(*, model=None, truncation=None, output_encoding=None, vectorize_collection_name=True, base_url=None, image_fields=None, text_fields=None)

Create a _Multi2VecNvidiaConfig object for use when vectorizing using the multi2vec-nvidia model.

See the documentation for detailed usage.

Parameters:

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default.

• truncate – The truncation strategy to use. Defaults to None, which uses the server-defined default.

• output_encoding (str | None) – Deprecated, has no effect.

• vectorize_collection_name (bool) – Deprecated, has no effect.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

• truncation (bool | None)

Raises:

pydantic.ValidationError – If model is not a valid value from the NvidiaMultimodalModel type or if truncate is not a valid value from the NvidiaTruncation type.

Return type:

_VectorizerConfigCreate

static text2vec_databricks(*, endpoint, instruction=None, vectorize_collection_name=True)

Create a _Text2VecDatabricksConfig object for use when vectorizing using the text2vec-databricks model.

See the documentation for detailed usage.

Parameters:

• endpoint (str) – The endpoint to use.

• instruction (str | None) – The instruction strategy to use. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Raises:

pydantic.ValidationError – If truncate is not a valid value from the CohereModel type.

Return type:

_VectorizerConfigCreate

static text2vec_gpt4all(vectorize_collection_name=True)

Create a _Text2VecGPT4AllConfigCreate object for use when vectorizing using the text2vec-gpt4all model.

See the documentation for detailed usage.

Parameters:

vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Raises:

pydantic.ValidationError – If vectorize_collection_name is not a bool.

Return type:

_VectorizerConfigCreate

static text2vec_huggingface(model=None, passage_model=None, query_model=None, endpoint_url=None, wait_for_model=None, use_gpu=None, use_cache=None, vectorize_collection_name=True)

Create a _Text2VecHuggingFaceConfigCreate object for use when vectorizing using the text2vec-huggingface model.

See the documentation for detailed usage.

Parameters:

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default.

• passage_model (str | None) – The passage model to use. Defaults to None, which uses the server-defined default.

• query_model (str | None) – The query model to use. Defaults to None, which uses the server-defined default.

• endpoint_url (AnyHttpUrl | None) – The endpoint URL to use. Defaults to None, which uses the server-defined default.

• wait_for_model (bool | None) – Whether to wait for the model to be loaded. Defaults to None, which uses the server-defined default.

• use_gpu (bool | None) – Whether to use the GPU. Defaults to None, which uses the server-defined default.

• use_cache (bool | None) – Whether to use the cache. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Raises:

pydantic.ValidationError –

If the arguments passed to the function are invalid. It is important to note that some of these variables are mutually exclusive. See the documentation for more details.

Return type:

_VectorizerConfigCreate

static text2vec_mistral(*, base_url=None, model=None, vectorize_collection_name=True)

Create a _Text2VecMistralConfig object for use when vectorizing using the text2vec-mistral model.

See the documentation for detailed usage.

Parameters:

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Return type:

_VectorizerConfigCreate

static text2vec_ollama(*, api_endpoint=None, model=None, vectorize_collection_name=True)

Create a _Text2VecOllamaConfig object for use when vectorizing using the text2vec-ollama model.

See the documentation for detailed usage.

Parameters:

• api_endpoint (str | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default. Docker users may need to specify an alias, such as http://host.docker.internal:11434 so that the container can access the host machine.

• model (str | None) – The model to use. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Return type:

_VectorizerConfigCreate

static text2vec_openai(model=None, model_version=None, type_=None, vectorize_collection_name=True, base_url=None, dimensions=None)

Create a _Text2VecOpenAIConfigCreate object for use when vectorizing using the text2vec-openai model.

See the documentation for detailed usage.

Parameters:

• model (Literal['text-embedding-3-small', 'text-embedding-3-large', 'text-embedding-ada-002'] | str | None) – The model to use. Defaults to None, which uses the server-defined default.

• model_version (str | None) – The model version to use. Defaults to None, which uses the server-defined default.

• type – The type of model to use. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• dimensions (int | None) – Number of dimensions. Applicable to v3 OpenAI models only. Defaults to None, which uses the server-defined default.

• type_ (Literal['text', 'code'] | None)

Raises:

pydantic.ValidationError – If type_ is not a valid value from the OpenAIType type.

Return type:

_VectorizerConfigCreate

static text2vec_palm(project_id, api_endpoint=None, model_id=None, title_property=None, vectorize_collection_name=True)

Deprecated since version 4.9.0.

This method is deprecated and will be removed in Q2 ‘25. Please use text2vec_google() instead.

Create a _Text2VecGoogleConfig object for use when vectorizing using the text2vec-palm model.

See the documentation for detailed usage.

Args:

project_id: The project ID to use, REQUIRED. api_endpoint: The API endpoint to use without a leading scheme such as http://. Defaults to None, which uses the server-defined default model_id: The model ID to use. Defaults to None, which uses the server-defined default. title_property: The Weaviate property name for the gecko-002 or gecko-003 model to use as the title. vectorize_collection_name: Whether to vectorize the collection name. Defaults to True.

Raises:

pydantic.ValidationError: If api_endpoint is not a valid URL.

Parameters:

• project_id (str)

• api_endpoint (str | None)

• model_id (str | None)

• title_property (str | None)

• vectorize_collection_name (bool)

Return type:

_VectorizerConfigCreate

static text2vec_google_aistudio(model_id=None, title_property=None, vectorize_collection_name=True)

Create a _Text2VecGoogleConfig object for use when vectorizing using the text2vec-google model.

See the documentation for detailed usage.

Parameters:

• model_id (str | None) – The model ID to use. Defaults to None, which uses the server-defined default.

• title_property (str | None) – The Weaviate property name for the gecko-002 or gecko-003 model to use as the title.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Raises:

pydantic.ValidationError – If api_endpoint is not a valid URL.

Return type:

_VectorizerConfigCreate

static text2vec_google(project_id, api_endpoint=None, model_id=None, title_property=None, vectorize_collection_name=True)

Create a _Text2VecGoogleConfig object for use when vectorizing using the text2vec-google model.

See the documentation for detailed usage.

Parameters:

• project_id (str) – The project ID to use, REQUIRED.

• api_endpoint (str | None) – The API endpoint to use without a leading scheme such as http://. Defaults to None, which uses the server-defined default

• model_id (str | None) – The model ID to use. Defaults to None, which uses the server-defined default.

• title_property (str | None) – The Weaviate property name for the gecko-002 or gecko-003 model to use as the title.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• dimensions – The dimensionality of the vectors. Defaults to None, which uses the server-defined default.

Raises:

pydantic.ValidationError – If api_endpoint is not a valid URL.

Return type:

_VectorizerConfigCreate

static multi2vec_palm(*, location, project_id, image_fields=None, text_fields=None, video_fields=None, dimensions=None, model_id=None, video_interval_seconds=None, vectorize_collection_name=True)

Deprecated since version 4.9.0.

This method is deprecated and will be removed in Q2 ‘25. Please use multi2vec_google() instead.

Create a _Multi2VecPalmConfig object for use when vectorizing using the text2vec-palm model.

See the documentation for detailed usage.

Args:

location: Where the model runs. REQUIRED. project_id: The project ID to use, REQUIRED. image_fields: The image fields to use in vectorization. text_fields: The text fields to use in vectorization. video_fields: The video fields to use in vectorization. dimensions: The number of dimensions to use. Defaults to None, which uses the server-defined default. model_id: The model ID to use. Defaults to None, which uses the server-defined default. video_interval_seconds: Length of a video interval. Defaults to None, which uses the server-defined default. vectorize_collection_name: Whether to vectorize the collection name. Defaults to True.

Raises:

pydantic.ValidationError: If api_endpoint is not a valid URL.

Parameters:

• location (str)

• project_id (str)

• image_fields (List[str] | List[Multi2VecField] | None)

• text_fields (List[str] | List[Multi2VecField] | None)

• video_fields (List[str] | List[Multi2VecField] | None)

• dimensions (int | None)

• model_id (str | None)

• video_interval_seconds (int | None)

• vectorize_collection_name (bool)

Return type:

_VectorizerConfigCreate

static multi2vec_google(*, location, project_id, image_fields=None, text_fields=None, video_fields=None, model_id=None, video_interval_seconds=None, vectorize_collection_name=True)

Create a _Multi2VecGoogleConfig object for use when vectorizing using the text2vec-google model.

See the documentation for detailed usage.

Parameters:

• location (str) – Where the model runs. REQUIRED.

• project_id (str) – The project ID to use, REQUIRED.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

• video_fields (List[str] | List[Multi2VecField] | None) – The video fields to use in vectorization.

• model_id (str | None) – The model ID to use. Defaults to None, which uses the server-defined default.

• video_interval_seconds (int | None) – Length of a video interval. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Raises:

pydantic.ValidationError – If api_endpoint is not a valid URL.

Return type:

_VectorizerConfigCreate

static text2vec_transformers(pooling_strategy='masked_mean', dimensions=None, vectorize_collection_name=True, inference_url=None, passage_inference_url=None, query_inference_url=None)

Create a _Text2VecTransformersConfigCreate object for use when vectorizing using the text2vec-transformers model.

See the documentation for detailed usage.

Parameters:

• pooling_strategy (Literal['masked_mean', 'cls']) – The pooling strategy to use. Defaults to masked_mean.

• dimensions (int | None) – The number of dimensions for the generated embeddings. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• inference_url (str | None) – The inference url to use where API requests should go. You can use either this OR passage/query_inference_url. Defaults to None, which uses the server-defined default.

• passage_inference_url (str | None) – The inference url to use where passage API requests should go. You can use either this and query_inference_url OR inference_url. Defaults to None, which uses the server-defined default.

• query_inference_url (str | None) – The inference url to use where query API requests should go. You can use either this and passage_inference_url OR inference_url. Defaults to None, which uses the server-defined default.

Raises:

pydantic.ValidationError – If pooling_strategy is not a valid value from the PoolingStrategy type.

Return type:

_VectorizerConfigCreate

static text2vec_jinaai(model=None, vectorize_collection_name=True, base_url=None, dimensions=None)

Create a _Text2VecJinaConfigCreate object for use when vectorizing using the text2vec-jinaai model.

See the documentation for detailed usage.

Parameters:

• model (Literal['jina-embeddings-v2-base-en', 'jina-embeddings-v2-small-en', 'jina-embeddings-v2-base-zh', 'jina-embeddings-v2-base-es', 'jina-embeddings-v2-base-code', 'jina-embeddings-v3', 'jina-embeddings-v4'] | str | None) –

  The model to use. Defaults to None, which uses the server-defined default. See the documentation for more details.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• base_url (str | None) – The base URL to send the vectorization requests to. Defaults to None, which uses the server-defined default.

• dimensions (int | None) – The number of dimensions for the generated embeddings. Defaults to None, which uses the server-defined default.

Return type:

_VectorizerConfigCreate

static multi2vec_jinaai(*, model=None, vectorize_collection_name=True, base_url=None, dimensions=None, image_fields=None, text_fields=None)

Create a _Multi2VecJinaConfig object for use when vectorizing using the multi2vec-jinaai model.

See the documentation for detailed usage.

Parameters:

• model (Literal['jina-clip-v1', 'jina-clip-v2', 'jina-embeddings-v4'] | str | None) – The model to use. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• base_url (AnyHttpUrl | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• dimensions (int | None) – The number of dimensions for the generated embeddings (only available for some models). Defaults to None, which uses the server-defined default.

• image_fields (List[str] | List[Multi2VecField] | None) – The image fields to use in vectorization.

• text_fields (List[str] | List[Multi2VecField] | None) – The text fields to use in vectorization.

Raises:

pydantic.ValidationError – If model is not a valid value from the JinaMultimodalModel type.

Return type:

_VectorizerConfigCreate

static text2vec_voyageai(*, model=None, base_url=None, truncate=None, vectorize_collection_name=True)

Create a _Text2VecVoyageConfigCreate object for use when vectorizing using the text2vec-voyageai model.

See the documentation for detailed usage.

Parameters:

• model (Literal['voyage-4', 'voyage-4-lite', 'voyage-4-large', 'voyage-3.5', 'voyage-3.5-lite', 'voyage-3-large', 'voyage-3', 'voyage-3-lite', 'voyage-context-3', 'voyage-large-2', 'voyage-code-2', 'voyage-2', 'voyage-law-2', 'voyage-large-2-instruct', 'voyage-finance-2', 'voyage-multilingual-2'] | str | None) –

  The model to use. Defaults to None, which uses the server-defined default. See the documentation for more details.

• base_url (str | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• truncate (bool | None) – Whether to truncate the input texts to fit within the context length. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Return type:

_VectorizerConfigCreate

static text2vec_weaviate(*, model=None, base_url=None, vectorize_collection_name=True, dimensions=None)

TODO: add docstrings when the documentation is available.

Parameters:

• model (Literal['Snowflake/snowflake-arctic-embed-l-v2.0', 'Snowflake/snowflake-arctic-embed-m-v1.5'] | str | None)

• base_url (str | None)

• vectorize_collection_name (bool)

• dimensions (int | None)

Return type:

_VectorizerConfigCreate

static text2vec_nvidia(*, model=None, base_url=None, truncate=None, vectorize_collection_name=True)

Create a _Text2VecNvidiaConfigCreate object for use when vectorizing using the text2vec-nvidia model.

See the documentation for detailed usage.

Parameters:

• model (str | None) –

  The model to use. Defaults to None, which uses the server-defined default. See the documentation for more details.

• base_url (str | None) – The base URL to use where API requests should go. Defaults to None, which uses the server-defined default.

• truncate (bool | None) – Whether to truncate the input texts to fit within the context length. Defaults to None, which uses the server-defined default.

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

Return type:

_VectorizerConfigCreate

static text2vec_model2vec(*, inference_url=None, vectorize_collection_name=True)

Create a _Text2VecModel2VecConfigCreate object for use when vectorizing using the text2vec-model2vec model.

See the documentation for detailed usage.

Parameters:

• vectorize_collection_name (bool) – Whether to vectorize the collection name. Defaults to True.

• inference_url (str | None) – The inference url to use where API requests should go. Defaults to None, which uses the server-defined default.

Return type:

_VectorizerConfigCreate

weaviate.collections.classes.data

class weaviate.collections.classes.data.Error(message, code=None, original_uuid=None)

Bases: object

This class represents an error that occurred when attempting to insert an object within a batch.

Parameters:

• message (str)

• code (int | None)

• original_uuid (str | UUID | None)

message: str

code: int | None = None

original_uuid: str | UUID | None = None

class weaviate.collections.classes.data.RefError(message)

Bases: object

This class represents an error that occurred when attempting to insert a reference between objects within a batch.

Parameters:

message (str)

message: str

class weaviate.collections.classes.data.DataObject(properties=None, uuid=None, vector=None, references=None)

Bases: Generic[P, R]

This class represents an entire object within a collection to be used when batching.

Parameters:

• properties (P)

• uuid (str | UUID | None)

• vector (Mapping[str, Sequence[int | float] | Sequence[Sequence[int | float]]] | Sequence[int | float] | None)

• references (R)

properties: P = None

uuid: str | UUID | None = None

vector: Mapping[str, Sequence[int | float] | Sequence[Sequence[int | float]]] | Sequence[int | float] | None = None

references: R = None

class weaviate.collections.classes.data._DataReference(from_property: str, from_uuid: str | uuid.UUID, to_uuid: str | uuid.UUID | List[str | uuid.UUID])

Bases: object

Parameters:

• from_property (str)

• from_uuid (str | UUID)

• to_uuid (str | UUID | List[str | UUID])

from_property: str

from_uuid: str | UUID

to_uuid: str | UUID | List[str | UUID]

_to_uuids()

Return type:

List[str | UUID]

class weaviate.collections.classes.data.DataReferenceMulti(from_property, from_uuid, to_uuid, target_collection)

Bases: _DataReference

This class represents a reference between objects within a collection to be used when batching.

Parameters:

• from_property (str)

• from_uuid (str | UUID)

• to_uuid (str | UUID | List[str | UUID])

• target_collection (str)

target_collection: str

_to_beacons()

Return type:

List[str]

class weaviate.collections.classes.data.DataReference(from_property, from_uuid, to_uuid)

Bases: _DataReference

This class represents a reference between objects within a collection to be used when batching.

Parameters:

• from_property (str)

• from_uuid (str | UUID)

• to_uuid (str | UUID | List[str | UUID])

MultiTarget

alias of DataReferenceMulti

_to_beacons()

Return type:

List[str]

weaviate.collections.classes.filters

class weaviate.collections.classes.filters._Operator(*values)

Bases: str, Enum

EQUAL = 'Equal'

NOT_EQUAL = 'NotEqual'

LESS_THAN = 'LessThan'

LESS_THAN_EQUAL = 'LessThanEqual'

GREATER_THAN = 'GreaterThan'

GREATER_THAN_EQUAL = 'GreaterThanEqual'

LIKE = 'Like'

IS_NULL = 'IsNull'

CONTAINS_ANY = 'ContainsAny'

CONTAINS_ALL = 'ContainsAll'

CONTAINS_NONE = 'ContainsNone'

WITHIN_GEO_RANGE = 'WithinGeoRange'

AND = 'And'

OR = 'Or'

NOT = 'Not'

_to_grpc()

Return type:

<google.protobuf.internal.enum_type_wrapper.EnumTypeWrapper object at 0x74e9b52f55e0>

class weaviate.collections.classes.filters._Filters

Bases: object

class weaviate.collections.classes.filters._FilterAnd(filters)

Bases: _Filters

Parameters:

filters (List[_Filters])

filters: List[_Filters]

property operator: _Operator

class weaviate.collections.classes.filters._FilterOr(filters)

Bases: _Filters

Parameters:

filters (List[_Filters])

filters: List[_Filters]

property operator: _Operator

class weaviate.collections.classes.filters._FilterNot(filter_)

Bases: _Filters

Parameters:

filter_ (_Filters)

filters: List[_Filters]

property operator: _Operator

class weaviate.collections.classes.filters._GeoCoordinateFilter(*, latitude, longitude, distance)

Bases: GeoCoordinate

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• latitude (Annotated[float, Ge(ge=-90), Le(le=90)])

• longitude (Annotated[float, Ge(ge=-180), Le(le=180)])

• distance (float)

distance: float

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.filters._SingleTargetRef

Bases: _WeaviateInput

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

link_on: str

target: _FilterTargets | None

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.filters._MultiTargetRef

Bases: _WeaviateInput

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

target_collection: str

link_on: str

target: _FilterTargets | None

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.filters._CountRef(*, link_on)

Bases: _WeaviateInput

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

link_on (str)

link_on: str

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.filters._FilterValue(*, value, operator, target)

Bases: _Filters, _WeaviateInput

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• value (int | float | str | bool | datetime | UUID | _GeoCoordinateFilter | None | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[str | UUID])

• operator (_Operator)

• target (_SingleTargetRef | _MultiTargetRef | _CountRef | str)

value: int | float | str | bool | datetime | UUID | _GeoCoordinateFilter | None | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[str | UUID]

operator: _Operator

target: _SingleTargetRef | _MultiTargetRef | _CountRef | str

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.filters._FilterBase

Bases: object

_target: _SingleTargetRef | _MultiTargetRef | None = None

_property: str | _CountRef

_target_path()

Return type:

_SingleTargetRef | _MultiTargetRef | _CountRef | str

class weaviate.collections.classes.filters._FilterByProperty(prop, length, target=None)

Bases: _FilterBase

Parameters:

• prop (str)

• length (bool)

• target (_SingleTargetRef | _MultiTargetRef | None)

is_none(val)

Filter on whether the property is None.

Parameters:

val (bool)

Return type:

_Filters

contains_any(val)

Filter on whether the property contains any of the given values.

Parameters:

val (Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[str | UUID])

Return type:

_Filters

contains_all(val)

Filter on whether the property contains all of the given values.

Parameters:

val (Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[str | UUID])

Return type:

_Filters

contains_none(val)

Filter on whether the property contains none of the given values.

Parameters:

val (Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[str | UUID])

Return type:

_Filters

equal(val)

Filter on whether the property is equal to the given value.

Parameters:

val (int | float | str | bool | datetime | UUID | _GeoCoordinateFilter | None | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[str | UUID])

Return type:

_Filters

not_equal(val)

Filter on whether the property is not equal to the given value.

Parameters:

val (int | float | str | bool | datetime | UUID | _GeoCoordinateFilter | None | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[str | UUID])

Return type:

_Filters

less_than(val)

Filter on whether the property is less than the given value.

Parameters:

val (int | float | str | bool | datetime | UUID | _GeoCoordinateFilter | None | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[str | UUID])

Return type:

_Filters

less_or_equal(val)

Filter on whether the property is less than or equal to the given value.

Parameters:

val (int | float | str | bool | datetime | UUID | _GeoCoordinateFilter | None | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[str | UUID])

Return type:

_Filters

greater_than(val)

Filter on whether the property is greater than the given value.

Parameters:

val (int | float | str | bool | datetime | UUID | _GeoCoordinateFilter | None | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[str | UUID])

Return type:

_Filters

greater_or_equal(val)

Filter on whether the property is greater than or equal to the given value.

Parameters:

val (int | float | str | bool | datetime | UUID | _GeoCoordinateFilter | None | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[str | UUID])

Return type:

_Filters

like(val)

Filter on whether the property is like the given value.

This filter can make use of * and ? as wildcards. See the docs for more details.

Parameters:

val (str)

Return type:

_Filters

within_geo_range(coordinate, distance)

Filter on whether the property is within a given range of a geo-coordinate.

See the docs for more details.

Parameters:

• coordinate (GeoCoordinate)

• distance (float)

Return type:

_Filters

class weaviate.collections.classes.filters._FilterByTime

Bases: _FilterBase

contains_any(dates)

Filter for objects with the given time.

Parameters:

dates (List[datetime]) – List of dates to filter on.

Return type:

_Filters

contains_none(dates)

Filter for objects that contain none of the dates.

Parameters:

dates (List[datetime]) – List of dates to filter on.

Return type:

_Filters

equal(date)

Filter on whether the creation time is equal to the given time.

Parameters:

• date (datetime) – date to filter on.

• on_reference_path – If the filter is on a cross-ref property, the path to the property to be filtered on, example: on_reference_path=[“ref_property”, “target_collection”].

Return type:

_Filters

not_equal(date)

Filter on whether the creation time is not equal to the given time.

Parameters:

• date (datetime) – date to filter on.

• on_reference_path – If the filter is on a cross-ref property, the path to the property to be filtered on, example: on_reference_path=[“ref_property”, “target_collection”].

Return type:

_Filters

less_than(date)

Filter on whether the creation time is less than the given time.

Parameters:

• date (datetime) – date to filter on.

• on_reference_path – If the filter is on a cross-ref property, the path to the property to be filtered on, example: on_reference_path=[“ref_property”, “target_collection”].

Return type:

_Filters

less_or_equal(date)

Filter on whether the creation time is less than or equal to the given time.

Parameters:

• date (datetime) – date to filter on.

• on_reference_path – If the filter is on a cross-ref property, the path to the property to be filtered on, example: on_reference_path=[“ref_property”, “target_collection”].

Return type:

_Filters

greater_than(date)

Filter on whether the creation time is greater than the given time.

Parameters:

• date (datetime) – date to filter on.

• on_reference_path – If the filter is on a cross-ref property, the path to the property to be filtered on, example: on_reference_path=[“ref_property”, “target_collection”].

Return type:

_Filters

greater_or_equal(date)

Filter on whether the creation time is greater than or equal to the given time.

Parameters:

• date (datetime) – date to filter on.

• on_reference_path – If the filter is on a cross-ref property, the path to the property to be filtered on, example: on_reference_path=[“ref_property”, “target_collection”].

Return type:

_Filters

class weaviate.collections.classes.filters._FilterByUpdateTime(target=None)

Bases: _FilterByTime

Parameters:

target (_SingleTargetRef | _MultiTargetRef | None)

class weaviate.collections.classes.filters._FilterByCreationTime(target=None)

Bases: _FilterByTime

Parameters:

target (_SingleTargetRef | _MultiTargetRef | None)

class weaviate.collections.classes.filters._FilterById(target=None)

Bases: _FilterBase

Parameters:

target (_SingleTargetRef | _MultiTargetRef | None)

contains_any(uuids)

Filter for objects that has one of the given IDs.

Parameters:

uuids (Sequence[str | UUID])

Return type:

_Filters

contains_none(uuids)

Filter for objects that has none of the given IDs.

Parameters:

uuids (Sequence[str | UUID])

Return type:

_Filters

equal(uuid)

Filter for object that has the given ID.

Parameters:

uuid (str | UUID)

Return type:

_Filters

not_equal(uuid)

Filter our object that has the given ID.

Parameters:

uuid (str | UUID)

Return type:

_Filters

class weaviate.collections.classes.filters._FilterByCount(link_on, target=None)

Bases: _FilterBase

Parameters:

• link_on (str)

• target (_SingleTargetRef | _MultiTargetRef | None)

equal(count)

Filter on whether the number of references is equal to the given integer.

Parameters:

count (int) – count to filter on.

Return type:

_Filters

not_equal(count)

Filter on whether the number of references is equal to the given integer.

Parameters:

count (int) – count to filter on.

Return type:

_Filters

less_than(count)

Filter on whether the number of references is equal to the given integer.

Parameters:

count (int) – count to filter on.

Return type:

_Filters

less_or_equal(count)

Filter on whether the number of references is equal to the given integer.

Parameters:

count (int) – count to filter on.

Return type:

_Filters

greater_than(count)

Filter on whether the number of references is equal to the given integer.

Parameters:

count (int) – count to filter on.

Return type:

_Filters

greater_or_equal(count)

Filter on whether the number of references is equal to the given integer.

Parameters:

count (int) – count to filter on.

Return type:

_Filters

class weaviate.collections.classes.filters._FilterByRef(target)

Bases: object

Parameters:

target (_SingleTargetRef | _MultiTargetRef)

by_ref(link_on)

Filter on the given reference.

Parameters:

link_on (str)

Return type:

_FilterByRef

by_ref_multi_target(reference, target_collection)

Filter on the given multi-target reference.

Parameters:

• reference (str)

• target_collection (str)

Return type:

_FilterByRef

by_ref_count(link_on)

Filter on the given reference.

Parameters:

link_on (str)

Return type:

_FilterByCount

by_id()

Define a filter based on the uuid to be used when querying and deleting from a collection.

Return type:

_FilterById

by_creation_time()

Define a filter based on the creation time to be used when querying and deleting from a collection.

Return type:

_FilterByCreationTime

by_update_time()

Define a filter based on the update time to be used when querying and deleting from a collection.

Return type:

_FilterByUpdateTime

by_property(name, length=False)

Define a filter based on a property to be used when querying and deleting from a collection.

Parameters:

• name (str)

• length (bool)

Return type:

_FilterByProperty

class weaviate.collections.classes.filters.Filter

Bases: object

This class is used to define filters to be used when querying and deleting from a collection.

It forms the root of a method chaining hierarchy that allows you to iteratively define filters that can hop between objects through references in a formulaic way.

See the docs for more information.

static by_ref(link_on)

Define a filter based on a reference to be used when querying and deleting from a collection.

Parameters:

link_on (str)

Return type:

_FilterByRef

static by_ref_multi_target(link_on, target_collection)

Define a filter based on a reference to be used when querying and deleting from a collection.

Parameters:

• link_on (str)

• target_collection (str)

Return type:

_FilterByRef

static by_ref_count(link_on)

Define a filter based on the number of references to be used when querying and deleting from a collection.

Parameters:

link_on (str)

Return type:

_FilterByCount

static by_id()

Define a filter based on the uuid to be used when querying and deleting from a collection.

Return type:

_FilterById

static by_creation_time()

Define a filter based on the creation time to be used when querying and deleting from a collection.

Return type:

_FilterByCreationTime

static by_update_time()

Define a filter based on the update time to be used when querying and deleting from a collection.

Return type:

_FilterByUpdateTime

static by_property(name, length=False)

Define a filter based on a property to be used when querying and deleting from a collection.

Parameters:

• name (str)

• length (bool)

Return type:

_FilterByProperty

static all_of(filters)

Combine all filters in the input list with an AND operator.

Parameters:

filters (List[_Filters])

Return type:

_Filters

static any_of(filters)

Combine all filters in the input list with an OR operator.

Parameters:

filters (List[_Filters])

Return type:

_Filters

static not_(filter_)

Negate the filter with a NOT operator.

Parameters:

filter_ (_Filters)

Return type:

_Filters

weaviate.collections.classes.filters.FilterByProperty

alias of _FilterByProperty

weaviate.collections.classes.filters.FilterById

alias of _FilterById

weaviate.collections.classes.filters.FilterByCreationTime

alias of _FilterByCreationTime

weaviate.collections.classes.filters.FilterByUpdateTime

alias of _FilterByUpdateTime

weaviate.collections.classes.filters.FilterByRef

alias of _FilterByRef

weaviate.collections.classes.filters.FilterReturn

alias of _Filters

weaviate.collections.classes.grpc

class weaviate.collections.classes.grpc.HybridFusion(*values)

Bases: str, BaseEnum

Define how the query’s hybrid fusion operation should be performed.

RANKED = 'FUSION_TYPE_RANKED'

RELATIVE_SCORE = 'FUSION_TYPE_RELATIVE_SCORE'

class weaviate.collections.classes.grpc.Move(force, objects=None, concepts=None)

Bases: object

Define how the query’s move operation should be performed.

Parameters:

• force (float)

• objects (List[str | UUID] | str | UUID | None)

• concepts (List[str] | str | None)

property _objects_list: List[str] | None

property _concepts_list: List[str] | None

_to_gql_payload()

Return type:

dict

class weaviate.collections.classes.grpc.MetadataQuery(*, creation_time=False, last_update_time=False, distance=False, certainty=False, score=False, explain_score=False, is_consistent=False, query_profile=False)

Bases: _WeaviateInput

Define which metadata should be returned in the query’s results.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• creation_time (bool)

• last_update_time (bool)

• distance (bool)

• certainty (bool)

• score (bool)

• explain_score (bool)

• is_consistent (bool)

• query_profile (bool)

creation_time: bool

last_update_time: bool

distance: bool

certainty: bool

score: bool

explain_score: bool

is_consistent: bool

query_profile: bool

classmethod full()

Return a MetadataQuery with all fields set to True.

NOTE: query_profile is excluded because it adds performance overhead. Use full_with_profile() to include it.

Return type:

MetadataQuery

classmethod full_with_profile()

Return a MetadataQuery with all fields set to True, including query profiling.

Query profiling adds per-shard execution timing breakdowns to the response but has performance overhead. Requires Weaviate >= 1.36.9.

Return type:

MetadataQuery

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.grpc._MetadataQuery(vector: bool, uuid: bool = True, creation_time_unix: bool = False, last_update_time_unix: bool = False, distance: bool = False, certainty: bool = False, score: bool = False, explain_score: bool = False, is_consistent: bool = False, vectors: List[str] | None = None, query_profile: bool = False)

Bases: object

Parameters:

• vector (bool)

• uuid (bool)

• creation_time_unix (bool)

• last_update_time_unix (bool)

• distance (bool)

• certainty (bool)

• score (bool)

• explain_score (bool)

• is_consistent (bool)

• vectors (List[str] | None)

• query_profile (bool)

vector: bool

uuid: bool = True

creation_time_unix: bool = False

last_update_time_unix: bool = False

distance: bool = False

certainty: bool = False

score: bool = False

explain_score: bool = False

is_consistent: bool = False

vectors: List[str] | None = None

query_profile: bool = False

classmethod from_public(public, include_vector)

Parameters:

• public (MetadataQuery | None)

• include_vector (bool | str | List[str])

Return type:

_MetadataQuery

class weaviate.collections.classes.grpc.Generate(*, single_prompt=None, grouped_task=None, grouped_properties=None)

Bases: _WeaviateInput

Define how the query’s RAG capabilities should be performed.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• single_prompt (str | None)

• grouped_task (str | None)

• grouped_properties (List[str] | None)

single_prompt: str | None

grouped_task: str | None

grouped_properties: List[str] | None

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.grpc.GroupBy(*, prop, objects_per_group, number_of_groups)

Bases: _WeaviateInput

Define how the query’s group-by operation should be performed.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• prop (str)

• objects_per_group (int)

• number_of_groups (int)

prop: str

objects_per_group: int

number_of_groups: int

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.grpc._Sort(*, prop, ascending=True)

Bases: _WeaviateInput

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• prop (str)

• ascending (bool)

prop: str

ascending: bool

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.grpc._Sorting

Bases: object

sorts: List[_Sort]

by_property(name, ascending=True)

Sort by an object property in the collection.

Parameters:

• name (str)

• ascending (bool)

Return type:

_Sorting

by_id(ascending=True)

Sort by an object’s ID in the collection.

Parameters:

ascending (bool)

Return type:

_Sorting

by_creation_time(ascending=True)

Sort by an object’s creation time.

Parameters:

ascending (bool)

Return type:

_Sorting

by_update_time(ascending=True)

Sort by an object’s last update time.

Parameters:

ascending (bool)

Return type:

_Sorting

weaviate.collections.classes.grpc.Sorting

The type returned by the Sort class to be used when defining programmatic sort chains.

class weaviate.collections.classes.grpc.Sort

Bases: object

Define how the query’s sort operation should be performed using the available static methods.

static by_property(name, ascending=True)

Sort by an object property in the collection.

Parameters:

• name (str)

• ascending (bool)

Return type:

_Sorting

static by_id(ascending=True)

Sort by an object’s ID in the collection.

Parameters:

ascending (bool)

Return type:

_Sorting

static by_creation_time(ascending=True)

Sort by an object’s creation time.

Parameters:

ascending (bool)

Return type:

_Sorting

static by_update_time(ascending=True)

Sort by an object’s last update time.

Parameters:

ascending (bool)

Return type:

_Sorting

class weaviate.collections.classes.grpc.Rerank(*, prop, query=None)

Bases: _WeaviateInput

Define how the query’s rerank operation should be performed.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• prop (str)

• query (str | None)

prop: str

query: str | None

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.grpc.MMR(limit=None, balance=None)

Bases: object

Define MMR (Maximal Marginal Relevance) diversity selection.

Parameters:

• limit (int | None) – Optional number of candidates to consider for diversification.

• balance (float | None) – Optional MMR lambda in [0.0, 1.0] — 1.0 is pure relevance, 0.0 is pure diversity.

limit: int | None = None

balance: float | None = None

class weaviate.collections.classes.grpc.Diversity

Bases: object

Use this factory class to apply diversity selection to search results via MMR.

static mmr(limit=None, balance=None)

Maximal Marginal Relevance diversity selection.

Parameters:

• limit (int | None) – Number of candidates to consider for diversification.

• balance (float | None) – MMR lambda in [0.0, 1.0] — 1.0 pure relevance, 0.0 pure diversity.

Return type:

MMR

class weaviate.collections.classes.grpc.BM25OperatorOptions

Bases: object

operator: ClassVar[Any]

class weaviate.collections.classes.grpc.BM25OperatorOr(minimum_should_match)

Bases: BM25OperatorOptions

Define the ‘Or’ operator for keyword queries.

Parameters:

minimum_should_match (int)

operator: ClassVar[Any] = 1

minimum_should_match: int

class weaviate.collections.classes.grpc.BM25OperatorAnd

Bases: BM25OperatorOptions

Define the ‘And’ operator for keyword queries.

operator: ClassVar[Any] = 2

class weaviate.collections.classes.grpc.BM25OperatorFactory

Bases: object

Define how the BM25 query’s token matching should be performed.

static or_(minimum_match)

Use the ‘Or’ operator for keyword queries, where at least a minimum number of tokens must match.

Note that the query is tokenized using the respective tokenization method of each property.

Parameters:

minimum_match (int) – The minimum number of keyword tokens (excluding stopwords) that must match for an object to be considered a match.

Return type:

BM25OperatorOptions

static and_()

Use the ‘And’ operator for keyword queries, where all query tokens must match.

Note that the query is tokenized using the respective tokenization method of each property.

Return type:

BM25OperatorOptions

weaviate.collections.classes.grpc.OneDimensionalVectorType

Represents a one-dimensional vector, e.g. one produced by the Configure.Vectors.text2vec_jinaai() module

alias of Sequence[int | float]

weaviate.collections.classes.grpc.TwoDimensionalVectorType

Represents a two-dimensional vector, e.g. one produced by the Configure.MultiVectors.text2vec_jinaai() module

alias of Sequence[Sequence[int | float]]

class weaviate.collections.classes.grpc._ListOfVectorsQuery(*, dimensionality, vectors)

Bases: _WeaviateInput, Generic[V]

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• dimensionality (Literal['1D', '2D'])

• vectors (Sequence[V])

dimensionality: Literal['1D', '2D']

vectors: Sequence[V]

static is_one_dimensional(self_)

Parameters:

self_ (_ListOfVectorsQuery)

Return type:

TypeGuard[_ListOfVectorsQuery[Sequence[Union[int, float]]]]

static is_two_dimensional(self_)

Parameters:

self_ (_ListOfVectorsQuery)

Return type:

TypeGuard[_ListOfVectorsQuery[Sequence[Sequence[Union[int, float]]]]]

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.grpc._ListOfVectorsQuery(*, dimensionality, vectors)

Bases: _WeaviateInput, Generic[V]

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• dimensionality (Literal['1D', '2D'])

• vectors (Sequence[V])

dimensionality: Literal['1D', '2D']

vectors: Sequence[V]

static is_one_dimensional(self_)

Parameters:

self_ (_ListOfVectorsQuery)

Return type:

TypeGuard[_ListOfVectorsQuery[Sequence[Union[int, float]]]]

static is_two_dimensional(self_)

Parameters:

self_ (_ListOfVectorsQuery)

Return type:

TypeGuard[_ListOfVectorsQuery[Sequence[Sequence[Union[int, float]]]]]

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.grpc._ListOfVectorsQuery(*, dimensionality, vectors)

Bases: _WeaviateInput, Generic[V]

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• dimensionality (Literal['1D', '2D'])

• vectors (Sequence[V])

dimensionality: Literal['1D', '2D']

vectors: Sequence[V]

static is_one_dimensional(self_)

Parameters:

self_ (_ListOfVectorsQuery)

Return type:

TypeGuard[_ListOfVectorsQuery[Sequence[Union[int, float]]]]

static is_two_dimensional(self_)

Parameters:

self_ (_ListOfVectorsQuery)

Return type:

TypeGuard[_ListOfVectorsQuery[Sequence[Sequence[Union[int, float]]]]]

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

weaviate.collections.classes.grpc.ListOfVectorsQuery

Define a many-vectors query to be used within a near vector search, i.e. multiple vectors over a single-vector space.

weaviate.collections.classes.grpc.NearVectorInputType

Define the input types that can be used in a near vector search

alias of Sequence[int | float] | Sequence[Sequence[int | float]] | Mapping[str, Sequence[int | float] | Sequence[Sequence[int | float]] | _ListOfVectorsQuery[Sequence[Union[int, float]]] | _ListOfVectorsQuery[Sequence[Sequence[Union[int, float]]]]]

class weaviate.collections.classes.grpc.NearVector

Bases: object

Factory class to use when defining near vector queries with multiple vectors in near_vector() and hybrid() methods.

static list_of_vectors(*vectors)

Define a many-vectors query to be used within a near vector search, i.e. multiple vectors over a single-vector space.

Parameters:

vectors (V)

Return type:

_ListOfVectorsQuery

class weaviate.collections.classes.grpc._HybridNearBase(*, distance=None, certainty=None)

Bases: _WeaviateInput

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• distance (float | None)

• certainty (float | None)

model_config = {'arbitrary_types_allowed': True, 'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

distance: float | None

certainty: float | None

_abc_impl = <_abc._abc_data object>

class weaviate.collections.classes.grpc._HybridNearText(*, distance=None, certainty=None, text, move_to=None, move_away=None)

Bases: _HybridNearBase

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• distance (float | None)

• certainty (float | None)

• text (str | List[str])

• move_to (Move | None)

• move_away (Move | None)

text: str | List[str]

move_to: Move | None

move_away: Move | None

_abc_impl = <_abc._abc_data object>

model_config = {'arbitrary_types_allowed': True, 'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.grpc._HybridNearVector(*, vector, distance=None, certainty=None)

Bases: object

Parameters:

• vector (Sequence[int | float] | Sequence[Sequence[int | float]] | Mapping[str, Sequence[int | float] | Sequence[Sequence[int | float]] | _ListOfVectorsQuery[Sequence[Union[int, float]]] | _ListOfVectorsQuery[Sequence[Sequence[Union[int, float]]]]])

• distance (float | None)

• certainty (float | None)

vector: Sequence[int | float] | Sequence[Sequence[int | float]] | Mapping[str, Sequence[int | float] | Sequence[Sequence[int | float]] | _ListOfVectorsQuery[Sequence[int | float]] | _ListOfVectorsQuery[Sequence[Sequence[int | float]]]]

distance: float | None

certainty: float | None

class weaviate.collections.classes.grpc._MultiTargetVectorJoinEnum(*values)

Bases: BaseEnum

Define how multi target vector searches should be combined.

SUM = 1

AVERAGE = 2

MINIMUM = 3

RELATIVE_SCORE = 4

MANUAL_WEIGHTS = 5

class weaviate.collections.classes.grpc._MultiTargetVectorJoin(combination: weaviate.collections.classes.grpc._MultiTargetVectorJoinEnum, target_vectors: List[str], weights: Dict[str, float | List[float]] | None = None)

Bases: object

Parameters:

• combination (_MultiTargetVectorJoinEnum)

• target_vectors (List[str])

• weights (Dict[str, float | List[float]] | None)

combination: _MultiTargetVectorJoinEnum

target_vectors: List[str]

weights: Dict[str, float | List[float]] | None = None

to_grpc_target_vector(version)

Parameters:

version (_ServerVersion)

Return type:

Targets

class weaviate.collections.classes.grpc.TargetVectors

Bases: object

Define how the distances from different target vectors should be combined using the available methods.

static sum(target_vectors)

Combine the distance from different target vectors by summing them.

Parameters:

target_vectors (List[str])

Return type:

_MultiTargetVectorJoin

static average(target_vectors)

Combine the distance from different target vectors by averaging them.

Parameters:

target_vectors (List[str])

Return type:

_MultiTargetVectorJoin

static minimum(target_vectors)

Combine the distance from different target vectors by using the minimum distance.

Parameters:

target_vectors (List[str])

Return type:

_MultiTargetVectorJoin

static manual_weights(weights)

Combine the distance from different target vectors by summing them using manual weights.

Parameters:

weights (Dict[str, float | List[float]])

Return type:

_MultiTargetVectorJoin

static relative_score(weights)

Combine the distance from different target vectors using score fusion.

Parameters:

weights (Dict[str, float | List[float]])

Return type:

_MultiTargetVectorJoin

class weaviate.collections.classes.grpc.HybridVector

Bases: object

Use this factory class to define the appropriate classes needed when defining near text and near vector sub-searches in hybrid queries.

static near_text(query, *, certainty=None, distance=None, move_to=None, move_away=None)

Define a near text search to be used within a hybrid query.

Parameters:

• query (str | List[str]) – The text to search for as a string or a list of strings.

• certainty (float | None) – The minimum similarity score to return. If not specified, the default certainty specified by the server is used.

• distance (float | None) – The maximum distance to search. If not specified, the default distance specified by the server is used.

• move_to (Move | None) – Define the concepts that should be moved towards in the vector space during the search.

• move_away (Move | None) – Define the concepts that should be moved away from in the vector space during the search.

Returns:

A _HybridNearText object to be used in the vector parameter of the query.hybrid and generate.hybrid search methods.

Return type:

_HybridNearText

static near_vector(vector, *, certainty=None, distance=None)

Define a near vector search to be used within a hybrid query.

Parameters:

• certainty (float | None) – The minimum similarity score to return. If not specified, the default certainty specified by the server is used.

• distance (float | None) – The maximum distance to search. If not specified, the default distance specified by the server is used.

• vector (Sequence[int | float] | Sequence[Sequence[int | float]] | Mapping[str, Sequence[int | float] | Sequence[Sequence[int | float]] | _ListOfVectorsQuery[Sequence[Union[int, float]]] | _ListOfVectorsQuery[Sequence[Sequence[Union[int, float]]]]])

Returns:

A _HybridNearVector object to be used in the vector parameter of the query.hybrid and generate.hybrid search methods.

Return type:

_HybridNearVector

class weaviate.collections.classes.grpc._QueryReference

Bases: _WeaviateInput

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

link_on: str

include_vector: bool | str | List[str]

return_metadata: MetadataQuery | None

return_properties: PROPERTIES | bool | None

return_references: REFERENCES | None

property _return_metadata: _MetadataQuery

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.grpc._QueryReferenceMultiTarget

Bases: _QueryReference

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

target_collection: str

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.grpc.QueryReference(*, link_on, include_vector=False, return_metadata=None, return_properties=None, return_references=None)

Bases: _QueryReference

Define a query-time reference to a single-target property when querying through cross-references.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• link_on (str)

• include_vector (bool | str | List[str])

• return_metadata (MetadataQuery | None)

• return_properties (Sequence[str | QueryNested] | str | QueryNested | bool | None)

• return_references (Sequence[_QueryReference | _QueryReferenceMultiTarget] | _QueryReference | _QueryReferenceMultiTarget | None)

MultiTarget

Define a query-time reference to a multi-target property when querying through cross-references.

alias of _QueryReferenceMultiTarget

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.grpc.QueryNested(*, name, properties)

Bases: _WeaviateInput

Define the query-time return properties of a nested property.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• name (str)

• properties (Sequence[str | QueryNested] | str | QueryNested)

name: str

properties: PROPERTIES

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.grpc.NearMediaType(*values)

Bases: str, Enum

The different types of media that can be used in a near_media query to leverage the multi2vec-* modules.

All are available when using multi2vec-bind but only IMAGE is available when using multi2vec-clip.

AUDIO = 'audio'

DEPTH = 'depth'

IMAGE = 'image'

IMU = 'imu'

THERMAL = 'thermal'

VIDEO = 'video'

weaviate.collections.classes.internal

class weaviate.collections.classes.internal.MetadataReturn(creation_time=None, last_update_time=None, distance=None, certainty=None, score=None, explain_score=None, is_consistent=None, rerank_score=None)

Bases: object

Metadata of an object returned by a query.

Parameters:

• creation_time (datetime | None)

• last_update_time (datetime | None)

• distance (float | None)

• certainty (float | None)

• score (float | None)

• explain_score (str | None)

• is_consistent (bool | None)

• rerank_score (float | None)

creation_time: datetime | None = None

last_update_time: datetime | None = None

distance: float | None = None

certainty: float | None = None

score: float | None = None

explain_score: str | None = None

is_consistent: bool | None = None

rerank_score: float | None = None

_is_empty()

Return type:

bool

class weaviate.collections.classes.internal.SearchProfileReturn(details)

Bases: object

Profiling details for a single search type within a shard.

Parameters:

details (Dict[str, str])

details: Dict[str, str]

class weaviate.collections.classes.internal.ShardProfileReturn(name, node, searches)

Bases: object

Profiling data for a single shard.

Parameters:

• name (str)

• node (str)

• searches (Dict[str, SearchProfileReturn])

name: str

node: str

searches: Dict[str, SearchProfileReturn]

class weaviate.collections.classes.internal.QueryProfileReturn(shards)

Bases: object

Per-shard query profiling data returned when query_profile=True is set in metadata.

Parameters:

shards (List[ShardProfileReturn])

shards: List[ShardProfileReturn]

class weaviate.collections.classes.internal.GroupByMetadataReturn(distance=None)

Bases: object

Metadata of an object returned by a group by query.

Parameters:

distance (float | None)

distance: float | None = None

class weaviate.collections.classes.internal._Object(uuid: uuid.UUID, metadata: M, properties: P, references: R, vector: Dict[str, List[float] | List[List[float]]], collection: str)

Bases: Generic[P, R, M]

Parameters:

• uuid (UUID)

• metadata (M)

• properties (P)

• references (R)

• vector (Dict[str, List[float] | List[List[float]]])

• collection (str)

uuid: UUID

metadata: M

properties: P

references: R

vector: Dict[str, List[float] | List[List[float]]]

collection: str

class weaviate.collections.classes.internal.Object(uuid, metadata, properties, references, vector, collection)

Bases: Generic[P, R], _Object[P, R, MetadataReturn]

A single Weaviate object returned by a query within the .query namespace of a collection.

Parameters:

• uuid (UUID)

• metadata (M)

• properties (P)

• references (R)

• vector (Dict[str, List[float] | List[List[float]]])

• collection (str)

class weaviate.collections.classes.internal.MetadataSingleObjectReturn(creation_time, last_update_time, is_consistent)

Bases: object

Metadata of an object returned by the fetch_object_by_id query.

Parameters:

• creation_time (datetime)

• last_update_time (datetime)

• is_consistent (bool | None)

creation_time: datetime

last_update_time: datetime

is_consistent: bool | None

class weaviate.collections.classes.internal.ObjectSingleReturn(uuid, metadata, properties, references, vector, collection)

Bases: Generic[P, R], _Object[P, R, MetadataSingleObjectReturn]

A single Weaviate object returned by the fetch_object_by_id query.

Parameters:

• uuid (UUID)

• metadata (M)

• properties (P)

• references (R)

• vector (Dict[str, List[float] | List[List[float]]])

• collection (str)

class weaviate.collections.classes.internal.GroupByObject(uuid, metadata, properties, references, vector, collection, belongs_to_group)

Bases: Generic[P, R], _Object[P, R, GroupByMetadataReturn]

A single Weaviate object returned by a query with the group_by argument specified.

Parameters:

• uuid (UUID)

• metadata (M)

• properties (P)

• references (R)

• vector (Dict[str, List[float] | List[List[float]]])

• collection (str)

• belongs_to_group (str)

belongs_to_group: str

class weaviate.collections.classes.internal.GenerativeSingle(debug, metadata, text)

Bases: object

The generative data returned relevant to a single prompt generative query.

Parameters:

• debug (GenerativeDebug | None)

• metadata (GenerativeAnthropicMetadata | GenerativeAnyscaleMetadata | GenerativeAWSMetadata | GenerativeCohereMetadata | GenerativeDatabricksMetadata | GenerativeDummyMetadata | GenerativeFriendliAIMetadata | GenerativeGoogleMetadata | GenerativeMistralMetadata | GenerativeNvidiaMetadata | GenerativeOllamaMetadata | GenerativeOpenAIMetadata | None)

• text (str | None)

debug: GenerativeDebug | None

metadata: GenerativeAnthropicMetadata | GenerativeAnyscaleMetadata | GenerativeAWSMetadata | GenerativeCohereMetadata | GenerativeDatabricksMetadata | GenerativeDummyMetadata | GenerativeFriendliAIMetadata | GenerativeGoogleMetadata | GenerativeMistralMetadata | GenerativeNvidiaMetadata | GenerativeOllamaMetadata | GenerativeOpenAIMetadata | None

text: str | None

class weaviate.collections.classes.internal.GenerativeGrouped(metadata, text)

Bases: object

The generative data returned relevant to a grouped prompt generative query.

Parameters:

• metadata (GenerativeAnthropicMetadata | GenerativeAnyscaleMetadata | GenerativeAWSMetadata | GenerativeCohereMetadata | GenerativeDatabricksMetadata | GenerativeDummyMetadata | GenerativeFriendliAIMetadata | GenerativeGoogleMetadata | GenerativeMistralMetadata | GenerativeNvidiaMetadata | GenerativeOllamaMetadata | GenerativeOpenAIMetadata | None)

• text (str | None)

metadata: GenerativeAnthropicMetadata | GenerativeAnyscaleMetadata | GenerativeAWSMetadata | GenerativeCohereMetadata | GenerativeDatabricksMetadata | GenerativeDummyMetadata | GenerativeFriendliAIMetadata | GenerativeGoogleMetadata | GenerativeMistralMetadata | GenerativeNvidiaMetadata | GenerativeOllamaMetadata | GenerativeOpenAIMetadata | None

text: str | None

class weaviate.collections.classes.internal.GenerativeObject(generated, generative, uuid, metadata, properties, references, vector, collection)

Bases: Generic[P, R], Object[P, R]

A single Weaviate object returned by a query within the generate namespace of a collection.

Parameters:

• generated (str | None)

• generative (GenerativeSingle | None)

• uuid (UUID)

• metadata (M)

• properties (P)

• references (R)

• vector (Dict[str, List[float] | List[List[float]]])

• collection (str)

__generated: str | None

generative: GenerativeSingle | None

property generated: str | None

The single generated text of the object.

class weaviate.collections.classes.internal.GenerativeReturn(generated, objects, generative, query_profile=None)

Bases: Generic[P, R]

The return type of a query within the generate namespace of a collection.

Parameters:

• generated (str | None)

• objects (List[GenerativeObject[P, R]])

• generative (GenerativeGrouped | None)

• query_profile (QueryProfileReturn | None)

__generated: str | None

objects: List[GenerativeObject[P, R]]

generative: GenerativeGrouped | None

query_profile: QueryProfileReturn | None

property generated: str | None

The grouped generated text of the objects.

class weaviate.collections.classes.internal.Group(name, min_distance, max_distance, number_of_objects, objects, rerank_score)

Bases: Generic[P, R]

A group of objects returned in a group by query.

Parameters:

• name (str)

• min_distance (float)

• max_distance (float)

• number_of_objects (int)

• objects (List[GroupByObject[P, R]])

• rerank_score (float | None)

name: str

min_distance: float

max_distance: float

number_of_objects: int

objects: List[GroupByObject[P, R]]

rerank_score: float | None

class weaviate.collections.classes.internal.GenerativeGroup(name, min_distance, max_distance, number_of_objects, objects, rerank_score, generated)

Bases: Generic[P, R], Group[P, R]

A group of objects returned in a generative group by query.

Parameters:

• name (str)

• min_distance (float)

• max_distance (float)

• number_of_objects (int)

• objects (List[GroupByObject[P, R]])

• rerank_score (float | None)

• generated (str | None)

generated: str | None

class weaviate.collections.classes.internal.GenerativeGroupByReturn(objects, groups, generated, query_profile=None)

Bases: Generic[P, R]

The return type of a query within the .generate namespace of a collection with the group_by argument specified.

Parameters:

• objects (List[GroupByObject[P, R]])

• groups (Dict[str, GenerativeGroup[P, R]])

• generated (str | None)

• query_profile (QueryProfileReturn | None)

objects: List[GroupByObject[P, R]]

groups: Dict[str, GenerativeGroup[P, R]]

generated: str | None

query_profile: QueryProfileReturn | None = None

class weaviate.collections.classes.internal.GroupByReturn(objects, groups, query_profile=None)

Bases: Generic[P, R]

The return type of a query within the .query namespace of a collection with the group_by argument specified.

Parameters:

• objects (List[GroupByObject[P, R]])

• groups (Dict[str, Group[P, R]])

• query_profile (QueryProfileReturn | None)

objects: List[GroupByObject[P, R]]

groups: Dict[str, Group[P, R]]

query_profile: QueryProfileReturn | None = None

class weaviate.collections.classes.internal.QueryReturn(objects, query_profile=None)

Bases: Generic[P, R]

The return type of a query within the .query namespace of a collection.

Parameters:

• objects (List[Object[P, R]])

• query_profile (QueryProfileReturn | None)

objects: List[Object[P, R]]

query_profile: QueryProfileReturn | None = None

class weaviate.collections.classes.internal._RawGQLReturn(aggregate: Dict[str, List[Dict[str, Any]]], explore: Dict[str, List[Dict[str, Any]]], get: Dict[str, List[Dict[str, Any]]], errors: Dict[str, Any] | None)

Bases: object

Parameters:

• aggregate (Dict[str, List[Dict[str, Any]]])

• explore (Dict[str, List[Dict[str, Any]]])

• get (Dict[str, List[Dict[str, Any]]])

• errors (Dict[str, Any] | None)

aggregate: Dict[str, List[Dict[str, Any]]]

explore: Dict[str, List[Dict[str, Any]]]

get: Dict[str, List[Dict[str, Any]]]

errors: Dict[str, Any] | None

class weaviate.collections.classes.internal._Generative(single, grouped, grouped_properties, generative_provider=None)

Bases: object

Parameters:

• single (str | _SinglePrompt | None)

• grouped (str | _GroupedTask | None)

• grouped_properties (List[str] | None)

• generative_provider (_GenerativeConfigRuntime | None)

single: str | _SinglePrompt | None

grouped: str | _GroupedTask | None

grouped_properties: List[str] | None

generative_provider: _GenerativeConfigRuntime | None

to_grpc(server_version)

Parameters:

server_version (_ServerVersion)

Return type:

GenerativeSearch

class weaviate.collections.classes.internal._GroupBy(prop, number_of_groups, objects_per_group)

Bases: object

Parameters:

• prop (str)

• number_of_groups (int)

• objects_per_group (int)

prop: str

number_of_groups: int

objects_per_group: int

to_grpc()

Return type:

GroupBy

classmethod from_input(group_by)

Parameters:

group_by (GroupBy | None)

Return type:

_GroupBy | None

weaviate.collections.classes.internal.__is_nested(value)

Parameters:

value (Any)

Return type:

bool

weaviate.collections.classes.internal.__create_nested_property_from_nested(name, value)

Parameters:

• name (str)

• value (Any)

Return type:

QueryNested

class weaviate.collections.classes.internal._Reference(target_collection, uuids)

Bases: object

You should not initialise this class directly. Use the .to_multi() class methods instead.

Parameters:

• target_collection (str | None)

• uuids (Sequence[str | UUID] | str | UUID)

_to_beacons()

Return type:

List[Dict[str, str]]

property is_one_to_many: bool

Returns True if the reference is to a one-to-many references, i.e. points to more than one object.

class weaviate.collections.classes.internal.ReferenceToMulti(*, target_collection, uuids)

Bases: _WeaviateInput

Use this class when you want to insert a multi-target reference property.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• target_collection (str)

• uuids (Sequence[str | UUID] | str | UUID)

target_collection: str

uuids: Sequence[str | UUID] | str | UUID

_to_beacons()

Return type:

List[Dict[str, str]]

property uuids_str: List[str]

Returns the UUIDs as strings.

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.internal._CrossReference(objects)

Bases: Generic[Properties, IReferences]

Parameters:

objects (List[Object[Properties, IReferences]] | None)

classmethod _from(objects)

Parameters:

objects (List[Object[Properties, IReferences]])

Return type:

_CrossReference[Properties, IReferences]

property objects: List[Object[Properties, IReferences]]

Returns the objects of the cross reference.

weaviate.collections.classes.internal.CrossReference

Use this TypeAlias when you want to type hint a cross reference within a generic data model.

If you want to define a reference property when creating your collection, use ReferenceProperty or ReferencePropertyMultiTarget instead.

If you want to create a reference when inserting an object, supply the UUIDs directly or use Reference.to_multi() instead.

Example

>>> import typing
>>> import weaviate.classes as wvc
>>>
>>> class One(typing.TypedDict):
...     prop: str
>>>
>>> class Two(typing.TypedDict):
...     one: wvc.CrossReference[One]

alias of _CrossReference[Properties, IReferences]

weaviate.collections.classes.internal.ReferenceInput

This type alias is used when providing references as inputs within the .data namespace of a collection.

alias of str | UUID | Sequence[str | UUID] | ReferenceToMulti

weaviate.collections.classes.internal.ReferenceInputs

This type alias is used when providing references as inputs within the .data namespace of a collection.

alias of Mapping[str, str | UUID | Sequence[str | UUID] | ReferenceToMulti]

class weaviate.collections.classes.internal.CrossReferenceAnnotation(include_vector=False, metadata=None, target_collection=None)

Bases: object

Dataclass to be used when annotating a generic cross reference property with options for retrieving data from the cross referenced object when querying.

Example

>>> import typing
>>> import weaviate.classes as wvc
>>>
>>> class One(typing.TypedDict):
...     prop: str
>>>
>>> class Two(typing.TypedDict):
...     one: typing.Annotated[
...         wvc.CrossReference[One],
...         wvc.CrossReferenceAnnotation(include_vector=True)
...     ]

Parameters:

• include_vector (bool)

• metadata (MetadataQuery | None)

• target_collection (str | None)

include_vector: bool = False

metadata: MetadataQuery | None = None

target_collection: str | None = None

weaviate.collections.classes.internal._extract_types_from_reference(type_, field)

Extract first inner type from CrossReference[Properties, References].

Parameters:

• type_ (_CrossReference[Properties, References])

• field (str)

Return type:

Tuple[Type[Properties], Type[References]]

weaviate.collections.classes.internal._extract_types_from_annotated_reference(type_, field)

Extract inner type from Annotated[CrossReference[Properties, References]].

Parameters:

• type_ (Annotated[_CrossReference[Properties, References], CrossReferenceAnnotation])

• field (str)

Return type:

Tuple[Type[Properties], Type[References]]

weaviate.collections.classes.internal.__is_annotated_reference(value)

Parameters:

value (Any)

Return type:

bool

weaviate.collections.classes.internal.__create_link_to_from_annotated_reference(link_on, value)

Create FromReference or FromReferenceMultiTarget from Annotated[CrossReference[Properties], ReferenceAnnotation].

Parameters:

• link_on (str)

• value (Annotated[_CrossReference[Properties, References], CrossReferenceAnnotation])

Return type:

_QueryReference | _QueryReferenceMultiTarget

weaviate.collections.classes.internal.__create_link_to_from_reference(link_on, value)

Create FromReference from CrossReference[Properties].

Parameters:

• link_on (str)

• value (_CrossReference[Properties, References])

Return type:

_QueryReference

weaviate.collections.classes.internal._extract_properties_from_data_model(type_)

Extract properties of Properties recursively from Properties.

Checks to see if there is a _Reference[Properties], Annotated[_Reference[Properties]], or _Nested[Properties] in the data model and lists out the properties as classes readily consumable by the underlying API.

Parameters:

type_ (Type[Properties])

Return type:

Sequence[str | QueryNested] | str | QueryNested

weaviate.collections.classes.internal._extract_references_from_data_model(type_)

Extract references of References recursively from References.

Checks to see if there is a _Reference[References], Annotated[_Reference[References]], or _Nested[References] in the data model and lists out the references as classes readily consumable by the underlying API.

Parameters:

type_ (Type[References])

Return type:

Sequence[_QueryReference | _QueryReferenceMultiTarget] | _QueryReference | _QueryReferenceMultiTarget | None

class weaviate.collections.classes.internal._QueryOptions(include_metadata: bool, include_properties: bool, include_references: bool, include_vector: bool, is_group_by: bool)

Bases: object

Parameters:

• include_metadata (bool)

• include_properties (bool)

• include_references (bool)

• include_vector (bool)

• is_group_by (bool)

include_metadata: bool

include_properties: bool

include_references: bool

include_vector: bool

is_group_by: bool

classmethod from_input(return_metadata, return_properties, include_vector, collection_references, query_references, rerank=None, group_by=None)

Parameters:

• return_metadata (List[Literal['creation_time', 'last_update_time', 'distance', 'certainty', 'score', 'explain_score', 'is_consistent', 'query_profile']] | ~weaviate.collections.classes.grpc.MetadataQuery | None)

• return_properties (Sequence[str | QueryNested] | str | QueryNested | bool | Type[Any] | None)

• include_vector (bool | str | List[str])

• collection_references (Type[Any] | None)

• query_references (_QueryReference | Sequence[_QueryReference] | Type[Any] | None)

• rerank (Rerank | None)

• group_by (GroupBy | None)

Return type:

_QueryOptions

weaviate.collections.classes.internal.GenerativeNearMediaReturnType

Use GenerativeSearchReturnType instead.

Type:

@Deprecated

alias of GenerativeReturn[Properties, References] | GenerativeReturn[TProperties, TReferences] | GenerativeReturn[Properties, Mapping[str, _CrossReference[Mapping[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, WeaviateField] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, WeaviateField]]], CrossReferences]]] | GenerativeReturn[Properties, TReferences] | GenerativeReturn[TProperties, References] | GenerativeReturn[TProperties, Mapping[str, _CrossReference[Mapping[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, WeaviateField] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, WeaviateField]]], CrossReferences]]] | GenerativeGroupByReturn[Properties, References] | GenerativeGroupByReturn[TProperties, TReferences] | GenerativeGroupByReturn[Properties, Mapping[str, _CrossReference[Mapping[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, WeaviateField] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, WeaviateField]]], CrossReferences]]] | GenerativeGroupByReturn[Properties, TReferences] | GenerativeGroupByReturn[TProperties, References] | GenerativeGroupByReturn[TProperties, Mapping[str, _CrossReference[Mapping[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, WeaviateField] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, WeaviateField]]], CrossReferences]]]

weaviate.collections.classes.internal.QueryNearMediaReturnType

Use QuerySearchReturnType instead.

Type:

@Deprecated

alias of QueryReturn[Properties, References] | QueryReturn[TProperties, TReferences] | QueryReturn[Properties, Mapping[str, _CrossReference[Mapping[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, WeaviateField] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, WeaviateField]]], CrossReferences]]] | QueryReturn[Properties, TReferences] | QueryReturn[TProperties, References] | QueryReturn[TProperties, Mapping[str, _CrossReference[Mapping[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, WeaviateField] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, WeaviateField]]], CrossReferences]]] | GroupByReturn[Properties, References] | GroupByReturn[TProperties, TReferences] | GroupByReturn[Properties, Mapping[str, _CrossReference[Mapping[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, WeaviateField] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, WeaviateField]]], CrossReferences]]] | GroupByReturn[Properties, TReferences] | GroupByReturn[TProperties, References] | GroupByReturn[TProperties, Mapping[str, _CrossReference[Mapping[str, None | str | bool | int | float | datetime | UUID | GeoCoordinate | PhoneNumber | _PhoneNumber | Mapping[str, WeaviateField] | Sequence[str] | Sequence[bool] | Sequence[int] | Sequence[float] | Sequence[datetime] | Sequence[UUID] | Sequence[Mapping[str, WeaviateField]]], CrossReferences]]]

weaviate.collections.classes.orm

weaviate.collections.classes.tenants

class weaviate.collections.classes.tenants._TenantActivistatusServerValues(*values)

Bases: str, Enum

Values to be used when sending tenants to weaviate. Needed for BC.

HOT = 'HOT'

COLD = 'COLD'

FROZEN = 'FROZEN'

OTHER = 'OTHER'

static from_string(value)

Parameters:

value (str)

Return type:

_TenantActivistatusServerValues

class weaviate.collections.classes.tenants.TenantActivityStatus(*values)

Bases: str, Enum

TenantActivityStatus class used to describe the activity status of a tenant in Weaviate.

ACTIVE

The tenant is fully active and can be used.

INACTIVE

The tenant is not active, files stored locally.

OFFLOADED

The tenant is not active, files stored on the cloud.

OFFLOADING

The tenant is in the process of being offloaded.

ONLOADING

The tenant is in the process of being activated.

HOT

DEPRECATED, please use ACTIVE. The tenant is fully active and can be used.

COLD

DEPRECATED, please use INACTIVE. The tenant is not active, files stored locally.

FROZEN

DEPRECATED, please use OFFLOADED. The tenant is not active, files stored on the cloud.

ACTIVE = 'ACTIVE'

INACTIVE = 'INACTIVE'

OFFLOADED = 'OFFLOADED'

OFFLOADING = 'OFFLOADING'

ONLOADING = 'ONLOADING'

HOT = 'HOT'

COLD = 'COLD'

FROZEN = 'FROZEN'

class weaviate.collections.classes.tenants.Tenant(*, name, activity_status=TenantActivityStatus.ACTIVE, activityStatus=_TenantActivistatusServerValues.HOT)

Bases: BaseModel

Tenant class used to describe a tenant in Weaviate.

Parameters:

• name (str)

• activity_status (TenantActivityStatus)

• activityStatus (_TenantActivistatusServerValues)

name

The name of the tenant.

Type:

str

activity_status

TenantActivityStatus, default: “HOT”

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

model_config = {'populate_by_name': True, 'validate_by_alias': True, 'validate_by_name': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

name: str

activityStatusInternal: TenantActivityStatus

activityStatus: _TenantActivistatusServerValues

property activity_status: TenantActivityStatus

Getter for the activity status of the tenant.

model_post_init(_Tenant__context)

Override this method to perform additional initialization after __init__ and model_construct. This is useful if you want to do some validation that requires the entire model to be initialized.

Parameters:

_Tenant__context (Any)

Return type:

None

_model_post_init(user_input)

Parameters:

user_input (bool)

Return type:

None

_abc_impl = <_abc._abc_data object>

class weaviate.collections.classes.tenants.TenantOutput(*, name, activity_status=TenantActivityStatus.ACTIVE, activityStatus=_TenantActivistatusServerValues.HOT)

Bases: Tenant

Wrapper around Tenant for output purposes.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• name (str)

• activity_status (TenantActivityStatus)

• activityStatus (_TenantActivistatusServerValues)

model_post_init(_TenantOutput__context)

Override this method to perform additional initialization after __init__ and model_construct. This is useful if you want to do some validation that requires the entire model to be initialized.

Parameters:

_TenantOutput__context (Any)

Return type:

None

_abc_impl = <_abc._abc_data object>

model_config = {'populate_by_name': True, 'validate_by_alias': True, 'validate_by_name': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.tenants.TenantCreateActivityStatus(*values)

Bases: str, Enum

TenantActivityStatus class used to describe the activity status of a tenant to create in Weaviate.

ACTIVE

The tenant is fully active and can be used.

INACTIVE

The tenant is not active, files stored locally.

HOT

DEPRECATED, please use ACTIVE. The tenant is fully active and can be used.

COLD

DEPRECATED, please use INACTIVE. The tenant is not active, files stored locally.

ACTIVE = 'ACTIVE'

INACTIVE = 'INACTIVE'

HOT = 'HOT'

COLD = 'COLD'

class weaviate.collections.classes.tenants.TenantUpdateActivityStatus(*values)

Bases: str, Enum

TenantActivityStatus class used to describe the activity status of a tenant to update in Weaviate.

ACTIVE

The tenant is fully active and can be used.

INACTIVE

The tenant is not active, files stored locally.

OFFLOADED

The tenant is not active, files stored on the cloud.

HOT

DEPRECATED, please use ACTIVE. The tenant is fully active and can be used.

COLD

DEPRECATED, please use INACTIVE. The tenant is not active, files stored locally.

FROZEN

DEPRECATED, please use OFFLOADED. The tenant is not active, files stored on the cloud.

ACTIVE = 'ACTIVE'

INACTIVE = 'INACTIVE'

OFFLOADED = 'OFFLOADED'

HOT = 'HOT'

COLD = 'COLD'

FROZEN = 'FROZEN'

class weaviate.collections.classes.tenants.TenantCreate(*, name, activity_status=TenantCreateActivityStatus.ACTIVE, activityStatus=_TenantActivistatusServerValues.HOT)

Bases: BaseModel

Tenant class used to describe a tenant to create in Weaviate.

Parameters:

• name (str)

• activity_status (TenantCreateActivityStatus)

• activityStatus (_TenantActivistatusServerValues)

name

the name of the tenant.

Type:

str

activity_status

TenantCreateActivityStatus, default: “HOT”

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

model_config = {'populate_by_name': True, 'validate_by_alias': True, 'validate_by_name': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

name: str

activityStatusInternal: TenantCreateActivityStatus

activityStatus: _TenantActivistatusServerValues

property activity_status: TenantCreateActivityStatus

Getter for the activity status of the tenant.

model_post_init(_TenantCreate__context)

Override this method to perform additional initialization after __init__ and model_construct. This is useful if you want to do some validation that requires the entire model to be initialized.

Parameters:

_TenantCreate__context (Any)

Return type:

None

_abc_impl = <_abc._abc_data object>

class weaviate.collections.classes.tenants.TenantUpdate(*, name, activity_status=TenantUpdateActivityStatus.ACTIVE, activityStatus=_TenantActivistatusServerValues.HOT)

Bases: BaseModel

Tenant class used to describe a tenant to create in Weaviate.

Parameters:

• name (str)

• activity_status (TenantUpdateActivityStatus)

• activityStatus (_TenantActivistatusServerValues)

name

The name of the tenant.

Type:

str

activity_status

TenantUpdateActivityStatus, default: “HOT”

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

model_config = {'populate_by_name': True, 'validate_by_alias': True, 'validate_by_name': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

name: str

activityStatusInternal: TenantUpdateActivityStatus

activityStatus: _TenantActivistatusServerValues

property activity_status: TenantUpdateActivityStatus

Getter for the activity status of the tenant.

model_post_init(_TenantUpdate__context)

Override this method to perform additional initialization after __init__ and model_construct. This is useful if you want to do some validation that requires the entire model to be initialized.

Parameters:

_TenantUpdate__context (Any)

Return type:

None

_abc_impl = <_abc._abc_data object>

weaviate.collections.classes.types

class weaviate.collections.classes.types._WeaviateInput

Bases: BaseModel

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

_abc_impl = <_abc._abc_data object>

class weaviate.collections.classes.types.GeoCoordinate(*, latitude, longitude)

Bases: _WeaviateInput

Input for the geo-coordinate datatype.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• latitude (Annotated[float, Ge(ge=-90), Le(le=90)])

• longitude (Annotated[float, Ge(ge=-180), Le(le=180)])

latitude: float

longitude: float

_to_dict()

Return type:

Dict[str, float]

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.types._PhoneNumberBase(*, number)

Bases: _WeaviateInput

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

number (str)

number: str

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.types.PhoneNumber(*, number, default_country=None)

Bases: _PhoneNumberBase

Input for the phone number datatype.

default_country should correspond to the ISO 3166-1 alpha-2 country code. This is used to figure out the correct countryCode and international format if only a national number (e.g. 0123 4567) is provided.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• number (str)

• default_country (str | None)

default_country: str | None

_to_dict()

Return type:

Mapping[str, str]

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class weaviate.collections.classes.types._PhoneNumber(*, number, country_code, default_country, international_formatted, national, national_formatted, valid)

Bases: _PhoneNumberBase

Output for the phone number datatype.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

• number (str)

• country_code (int)

• default_country (str)

• international_formatted (str)

• national (int)

• national_formatted (str)

• valid (bool)

country_code: int

default_country: str

international_formatted: str

national: int

national_formatted: str

valid: bool

_abc_impl = <_abc._abc_data object>

model_config = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

weaviate.collections.classes.types.PhoneNumberType

alias of _PhoneNumber

class weaviate.collections.classes.types.Properties

Properties is used wherever a single generic type is needed for properties

alias of TypeVar(‘Properties’, bound=Mapping[str, Any], contravariant=True)

class weaviate.collections.classes.types.TProperties

TProperties is used alongside Properties wherever there are two generic types needed

E.g., in _DataCollection, Properties is used when defining the generic of the class while TProperties is used when defining the generic to be supplied in .with_data_model to create a new instance of _DataCollection with a different Properties type.

To be clear: _DataCollection[Properties]().with_data_model(TProperties) -> _DataCollection[TProperties]()

alias of TypeVar(‘TProperties’, bound=Mapping[str, Any])

class weaviate.collections.classes.types.M

M is a completely general type that is used wherever generic metadata objects are defined that can be used

alias of TypeVar(‘M’)

class weaviate.collections.classes.types.P

P is a completely general type that is used wherever generic properties objects are defined that can be used within the non-ORM and ORM APIs interchangeably

alias of TypeVar(‘P’)

class weaviate.collections.classes.types.QP

QP is a completely general type that is used wherever generic properties objects are defined that can be used within the non-ORM and ORM APIs interchangeably

alias of TypeVar(‘QP’)

class weaviate.collections.classes.types.R

R is a completely general type that is used wherever generic reference objects are defined that can be used within the non-ORM and ORM APIs interchangeably

alias of TypeVar(‘R’)

class weaviate.collections.classes.types.QR

QR is a completely general type that is used wherever generic reference objects are defined that can be used within the non-ORM and ORM APIs interchangeably

alias of TypeVar(‘QR’)

class weaviate.collections.classes.types.T

T is a completely general type that is used in any kind of generic

alias of TypeVar(‘T’)

class weaviate.collections.classes.types.References

References is used wherever a single generic type is needed for references

alias of TypeVar(‘References’, bound=Mapping[str, Any] | None)

class weaviate.collections.classes.types.TReferences

TReferences is used alongside References wherever there are two generic types needed

alias of TypeVar(‘TReferences’, bound=Mapping[str, Any] | None)

weaviate.collections.classes.types._check_properties_generic(properties)

Parameters:

properties (Type[Properties] | None)

Return type:

None

weaviate.collections.classes.types._check_references_generic(references)

Parameters:

references (Type[References] | None)

Return type:

None