weaviate_agents.classes

pydantic model weaviate_agents.classes.QueryAgentCollectionConfig

Bases: BaseModel

A collection configuration for the QueryAgent.

name

The name of the collection to query.

tenant

Tenant name for collections with multi-tenancy enabled.

view_properties

Optional list of property names the agent has the ability to view for this specific collection.

target_vector

Optional target vector name(s) for collections with named vectors. Can be a single vector name or a list of vector names.

additional_filters

Optional filters to apply when the query is executed, in addition to filters selected by the Query Agent (i.e., there are AND combined).

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.

field additional_filters: Annotated[_Filters, PlainSerializer(func=serialise_filter, return_type=PydanticUndefined, when_used=always)] | None = None

field name: str [Required]

field target_vector: str | list[str] | None = None

field tenant: str | None = None

field view_properties: list[str] | None = None

pydantic model weaviate_agents.classes.QueryAgentResponse

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.

field aggregations: list[list[AggregationResultWithCollection]] [Required]

field collection_names: list[str] [Required]

field final_answer: str [Required]

field is_partial_answer: bool [Required]

field missing_information: list[str] [Required]

field original_query: str [Required]

field output_type: Literal['final_state'] = 'final_state'

field searches: list[list[QueryResultWithCollection]] [Required]

field sources: list[Source] [Required]

field total_time: float [Required]

field usage: Usage [Required]

display()

Display a pretty-printed summary of the QueryAgentResponse object.

Return type:

None

pydantic model weaviate_agents.classes.Source

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.

field collection: str [Required]

field object_id: str [Required]

class weaviate_agents.classes.ComparisonOperator(*values)

Bases: str, Enum

EQUALS = '='

LESS_THAN = '<'

GREATER_THAN = '>'

LESS_EQUAL = '<='

GREATER_EQUAL = '>='

NOT_EQUALS = '!='

LIKE = 'LIKE'

CONTAINS_ANY = 'contains_any'

CONTAINS_ALL = 'contains_all'

pydantic model weaviate_agents.classes.IntegerPropertyFilter

Bases: KnownPropertyFilterBase

Filter numeric properties using comparison operators.

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.

field filter_type: Literal[KnownFilterType.INTEGER] = KnownFilterType.INTEGER

field operator: ComparisonOperator [Required]

field value: float [Required]

pydantic model weaviate_agents.classes.TextPropertyFilter

Bases: KnownPropertyFilterBase

Filter text properties using equality or LIKE operators.

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.

field filter_type: Literal[KnownFilterType.TEXT] = KnownFilterType.TEXT

field operator: ComparisonOperator [Required]

field value: str [Required]

pydantic model weaviate_agents.classes.BooleanPropertyFilter

Bases: KnownPropertyFilterBase

Filter boolean properties using equality operators.

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.

field filter_type: Literal[KnownFilterType.BOOLEAN] = KnownFilterType.BOOLEAN

field operator: ComparisonOperator [Required]

field value: bool [Required]

pydantic model weaviate_agents.classes.QueryResult

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.

field filter_operators: Literal['AND', 'OR'] [Required]

field filters: list[list[PropertyFilter]] = []

field queries: list[str | None] [Required]

class weaviate_agents.classes.NumericMetrics(*values)

Bases: str, Enum

COUNT = 'COUNT'

MAX = 'MAXIMUM'

MEAN = 'MEAN'

MEDIAN = 'MEDIAN'

MIN = 'MINIMUM'

MODE = 'MODE'

SUM = 'SUM'

TYPE = 'TYPE'

class weaviate_agents.classes.TextMetrics(*values)

Bases: str, Enum

COUNT = 'COUNT'

TYPE = 'TYPE'

TOP_OCCURRENCES = 'TOP_OCCURRENCES'

class weaviate_agents.classes.BooleanMetrics(*values)

Bases: str, Enum

COUNT = 'COUNT'

TYPE = 'TYPE'

TOTAL_TRUE = 'TOTAL_TRUE'

TOTAL_FALSE = 'TOTAL_FALSE'

PERCENTAGE_TRUE = 'PERCENTAGE_TRUE'

PERCENTAGE_FALSE = 'PERCENTAGE_FALSE'

pydantic model weaviate_agents.classes.IntegerPropertyAggregation

Bases: KnownPropertyAggregationBase

Aggregate numeric properties using statistical functions.

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.

field aggregation_type: Literal[KnownAggregationType.INTEGER] = KnownAggregationType.INTEGER

field metrics: NumericMetrics [Required]

pydantic model weaviate_agents.classes.TextPropertyAggregation

Bases: KnownPropertyAggregationBase

Aggregate text properties using frequency analysis.

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.

field aggregation_type: Literal[KnownAggregationType.TEXT] = KnownAggregationType.TEXT

field metrics: TextMetrics [Required]

field top_occurrences_limit: int | None = None

pydantic model weaviate_agents.classes.BooleanPropertyAggregation

Bases: KnownPropertyAggregationBase

Aggregate boolean properties using statistical functions.

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.

field aggregation_type: Literal[KnownAggregationType.BOOLEAN] = KnownAggregationType.BOOLEAN

field metrics: BooleanMetrics [Required]

pydantic model weaviate_agents.classes.AggregationResult

Bases: BaseModel

The aggregations to be performed on a collection in a vector database.

They should be based on the original user query and can include multiple aggregations across different properties and metrics.

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.

field aggregations: list[PropertyAggregation] [Required]

field filters: list[PropertyFilter] = []

field groupby_property: str | None = None

field search_query: str | None = None

pydantic model weaviate_agents.classes.Usage

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.

field details: Dict[str, int] | Dict[str, str] | None = None

field request_tokens: int | str | None = None

field requests: int | str = 0

field response_tokens: int | str | None = None

field total_tokens: int | str | None = None

pydantic model weaviate_agents.classes.AggregationResultWithCollection

Bases: AggregationResult

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.

field collection: str [Required]

pydantic model weaviate_agents.classes.QueryResultWithCollection

Bases: QueryResult

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.

field collection: str [Required]

class weaviate_agents.classes.OperationType(*values)

Bases: str, Enum

Types of operations that can be performed on properties.

APPEND = 'append'

UPDATE = 'update'

pydantic model weaviate_agents.classes.OperationStep

Bases: BaseModel

Base model for a transformation operation step.

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.

field instruction: str [Required]

field operation_type: OperationType [Required]

field property_name: str [Required]

field view_properties: List[str] [Required]

pydantic model weaviate_agents.classes.AppendPropertyOperation

Bases: OperationStep

Operation to append a new 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.

field data_type: DataType [Required]

field operation_type: OperationType = OperationType.APPEND

pydantic model weaviate_agents.classes.UpdatePropertyOperation

Bases: OperationStep

Operation to update an existing 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.

field operation_type: OperationType = OperationType.UPDATE

pydantic model weaviate_agents.classes.DependentOperationStep

Bases: BaseModel

A wrapper for operation steps that have dependencies on other operations.

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.

field depends_on: List[OperationStep] | None = None

field operation: OperationStep [Required]

class weaviate_agents.classes.Operations

Bases: object

Factory class for creating transformation operations.

static append_property(property_name, data_type, view_properties, instruction)

Create an operation to append a new property.

Parameters:

• property_name (str) – Name of the new property to append

• data_type (DataType) – Data type of the new property

• view_properties (List[str]) – List of property names to use as context for the transformation

• instruction (str) – Instruction for how to generate the new property value

Returns:

An AppendPropertyOperation object

Return type:

AppendPropertyOperation

static update_property(property_name, view_properties, instruction)

Create an operation to update an existing property.

Parameters:

• property_name (str) – Name of the property to update

• view_properties (List[str]) – List of property names to use as context for the transformation

• instruction (str) – Instruction for how to update the property value

Returns:

An UpdatePropertyOperation object

Return type:

UpdatePropertyOperation

pydantic model weaviate_agents.classes.Persona

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.

field persona_id: UUID [Required]

field properties: Dict[str, Any] [Required]

pydantic model weaviate_agents.classes.PersonaInteraction

Bases: BaseModel

Interaction between a persona and an item.

If replace_previous_interactions is True, the interaction history for that specific item and persona pair will be replaced with the new interaction.

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.

field created_at: datetime | None = None

field item_id: UUID [Required]

field persona_id: UUID [Required]

field replace_previous_interactions: bool = False

field weight: float [Required]

pydantic model weaviate_agents.classes.PersonaInteractionResponse

Bases: BaseModel

Response model for persona interactions when retrieving them.

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.

field created_at: str [Required] (alias 'createdAt')

field item_id: UUID [Required] (alias 'uuid')

field weight: float [Required]

pydantic model weaviate_agents.classes.PersonalizationAgentGetObjectsResponse

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.

field objects: list[PersonalizedObject] [Required]

field ranking_rationale: str | None = None

field usage: Usage [Required]

pydantic model weaviate_agents.classes.PersonalizedObject

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.

field original_rank: int [Required]

field personalized_rank: int | None [Required]

field properties: Dict[str, Any] [Required]

field uuid: UUID [Required]

model_dump(**kwargs)

!!! abstract “Usage Documentation”

[model_dump](../concepts/serialization.md#python-mode)

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

Parameters:

• mode – The mode in which to_python should run. If mode is ‘json’, the output will only contain JSON serializable types. If mode is ‘python’, the output may contain non-JSON-serializable Python objects.

• include – A set of fields to include in the output.

• exclude – A set of fields to exclude from the output.

• context – Additional context to pass to the serializer.

• by_alias – Whether to use the field’s alias in the dictionary key if defined.

• exclude_unset – Whether to exclude fields that have not been explicitly set.

• exclude_defaults – Whether to exclude fields that are set to their default value.

• exclude_none – Whether to exclude fields that have a value of None.

• exclude_computed_fields – Whether to exclude computed fields. While this can be useful for round-tripping, it is usually recommended tu use the dedicated round_trip parameter instead.

• round_trip – If True, dumped values should be valid as input for non-idempotent types such as Json[T].

• warnings – How to handle serialization errors. False/”none” ignores them, True/”warn” logs errors, “error” raises a [PydanticSerializationError][pydantic_core.PydanticSerializationError].

• fallback – A function to call when an unknown value is encountered. If not provided, a [PydanticSerializationError][pydantic_core.PydanticSerializationError] error is raised.

• serialize_as_any – Whether to serialize fields with duck-typing serialization behavior.

Returns:

A dictionary representation of the model.

pydantic model weaviate_agents.classes.PersonalizedQueryResponse

Bases: BaseModel, QueryReturn

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.

field usage: Usage [Required]

pydantic model weaviate_agents.classes.BooleanArrayPropertyFilter

Bases: KnownPropertyFilterBase

Filter boolean-array properties using equality operators.

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.

field filter_type: Literal[KnownFilterType.BOOLEAN_ARRAY] = KnownFilterType.BOOLEAN_ARRAY

field operator: ComparisonOperator [Required]

field value: list[bool] [Required]

pydantic model weaviate_agents.classes.DateArrayPropertyFilter

Bases: KnownPropertyFilterBase

Filter datetime properties using equality operators.

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.

field filter_type: Literal[KnownFilterType.DATE_ARRAY] = KnownFilterType.DATE_ARRAY

field operator: ComparisonOperator [Required]

field value: list[str] [Required]

class weaviate_agents.classes.DateMetrics(*values)

Bases: str, Enum

COUNT = 'COUNT'

MAX = 'MAXIMUM'

MEDIAN = 'MEDIAN'

MIN = 'MINIMUM'

MODE = 'MODE'

pydantic model weaviate_agents.classes.DatePropertyAggregation

Bases: KnownPropertyAggregationBase

Aggregate datetime properties using statistical functions.

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.

field aggregation_type: Literal[KnownAggregationType.DATE] = KnownAggregationType.DATE

field metrics: DateMetrics [Required]

pydantic model weaviate_agents.classes.DatePropertyFilter

Bases: KnownPropertyFilterBase

Filter datetime properties using equality operators.

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.

field filter_type: Literal[KnownFilterType.DATE] = KnownFilterType.DATE

field value: DateExact | DateRangeFrom | DateRangeTo | DateRangeBetween [Required]

pydantic model weaviate_agents.classes.IntegerArrayPropertyFilter

Bases: KnownPropertyFilterBase

Filter numeric-array properties using comparison operators.

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.

field filter_type: Literal[KnownFilterType.INTEGER_ARRAY] = KnownFilterType.INTEGER_ARRAY

field operator: ComparisonOperator [Required]

field value: list[float] [Required]

pydantic model weaviate_agents.classes.GeoPropertyFilter

Bases: KnownPropertyFilterBase

Filter geo-coordinates properties.

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.

field filter_type: Literal[KnownFilterType.GEO] = KnownFilterType.GEO

field latitude: float [Required]

field longitude: float [Required]

field max_distance_meters: float [Required]

pydantic model weaviate_agents.classes.TextArrayPropertyFilter

Bases: KnownPropertyFilterBase

Filter text-array properties using equality or LIKE operators.

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.

field filter_type: Literal[KnownFilterType.TEXT_ARRAY] = KnownFilterType.TEXT_ARRAY

field operator: ComparisonOperator [Required]

field value: list[str] [Required]

pydantic model weaviate_agents.classes.UnknownPropertyAggregation

Bases: BaseModel

Catch-all aggregation for unknown aggregation types, to preserve future back-compatibility.

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.

field aggregation_type: None [Required]

Validated by:

• ensure_filter_type_unknown

model_post_init(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:

context (Any)

Return type:

None

pydantic model weaviate_agents.classes.UnknownPropertyFilter

Bases: BaseModel

Catch-all filter for unknown filter types, to preserve future back-compatibility.

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.

field filter_type: None [Required]

Validated by:

• ensure_filter_type_unknown

model_post_init(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:

context (Any)

Return type:

None

class weaviate_agents.classes.ProgressDetails

Bases: TypedDict

queries: list[QueryWithCollection]

pydantic model weaviate_agents.classes.ProgressMessage

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.

field details: ProgressDetails = {}

field message: str [Required]

field output_type: Literal['progress_message'] = 'progress_message'

field stage: str [Required]

class weaviate_agents.classes.QueryWithCollection

Bases: TypedDict

query: str

collection: str

pydantic model weaviate_agents.classes.StreamedTokens

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.

field delta: str [Required]

field output_type: Literal['streamed_tokens'] = 'streamed_tokens'

pydantic model weaviate_agents.classes.IsNullPropertyFilter

Bases: KnownPropertyFilterBase

Filter by property null state.

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.

field filter_type: Literal[KnownFilterType.IS_NULL] = KnownFilterType.IS_NULL

field is_null: bool [Required]

pydantic model weaviate_agents.classes.SearchModeResponseBase

Bases: BaseModel, ABC, Generic[SearcherT]

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.

field search_results: QueryReturn [Required]

field searches: list[QueryResultWithCollectionNormalized] | None = None

field total_time: float [Required]

field usage: ModelUnitUsage [Required]

model_post_init(context, /)

This function is meant to behave like a BaseModel method to initialise private attributes.

It takes context as an argument since that’s what pydantic-core passes when calling it.

Parameters:

• self (BaseModel) – The BaseModel instance.

• context (Any) – The context.

Return type:

None

abstractmethod next(limit=20, offset=0)

Parameters:

• self (SearchModeResponseT)

• limit (int)

• offset (int)

Return type:

SearchModeResponseT | Coroutine[Any, Any, SearchModeResponseT]

class weaviate_agents.classes.ChatMessage

Bases: TypedDict

role: Literal['user', 'assistant']

content: str

pydantic model weaviate_agents.classes.AskModeResponse

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.

field aggregations: list[AggregationResultWithCollectionNormalized] [Required]

field final_answer: str [Required]

field is_partial_answer: bool | None [Required]

field missing_information: list[str] | None [Required]

field output_type: Literal['final_state'] = 'final_state'

field searches: list[QueryResultWithCollectionNormalized] [Required]

field sources: list[Source] | None [Required]

field total_time: float [Required]

field usage: ModelUnitUsage [Required]

display()

Display a pretty-printed summary of the AskModeResponse object.

Return type:

None

pydantic model weaviate_agents.classes.ModelUnitUsage

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.

field model_units: int [Required]

field remaining_plan_requests: int [Required]

field usage_in_plan: bool [Required]

pydantic model weaviate_agents.classes.FilterAndOr

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.

field combine: Literal['AND', 'OR'] [Required]

field filters: list[PropertyFilter | FilterAndOr] [Required]

pydantic model weaviate_agents.classes.QueryResultWithCollectionNormalized

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.

field collection: str [Required]

field filters: PropertyFilter | FilterAndOr | None [Required]

field query: str | None [Required]

field sort_property: QuerySort | None = None

pydantic model weaviate_agents.classes.AggregationResultWithCollectionNormalized

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.

field aggregation: PropertyAggregation [Required]

field collection: str [Required]

field filters: PropertyFilter | FilterAndOr | None [Required]

field groupby_property: str | None [Required]

pydantic model weaviate_agents.classes.QuerySort

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.

field order: Literal['ascending', 'descending'] [Required]

field property_name: str [Required]

field tie_break: QuerySort | None [Required]

Subpackages

weaviate_agents.classes.personalization

pydantic model weaviate_agents.classes.personalization.Persona

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.

field persona_id: UUID [Required]

field properties: Dict[str, Any] [Required]

pydantic model weaviate_agents.classes.personalization.PersonaInteraction

Bases: BaseModel

Interaction between a persona and an item.

If replace_previous_interactions is True, the interaction history for that specific item and persona pair will be replaced with the new interaction.

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.

field created_at: datetime | None = None

field item_id: UUID [Required]

field persona_id: UUID [Required]

field replace_previous_interactions: bool = False

field weight: float [Required]

pydantic model weaviate_agents.classes.personalization.PersonaInteractionResponse

Bases: BaseModel

Response model for persona interactions when retrieving them.

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.

field created_at: str [Required] (alias 'createdAt')

field item_id: UUID [Required] (alias 'uuid')

field weight: float [Required]

pydantic model weaviate_agents.classes.personalization.PersonalizationAgentGetObjectsResponse

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.

field objects: list[PersonalizedObject] [Required]

field ranking_rationale: str | None = None

field usage: Usage [Required]

pydantic model weaviate_agents.classes.personalization.PersonalizedObject

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.

field original_rank: int [Required]

field personalized_rank: int | None [Required]

field properties: Dict[str, Any] [Required]

field uuid: UUID [Required]

model_dump(**kwargs)

!!! abstract “Usage Documentation”

[model_dump](../concepts/serialization.md#python-mode)

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

Parameters:

• mode – The mode in which to_python should run. If mode is ‘json’, the output will only contain JSON serializable types. If mode is ‘python’, the output may contain non-JSON-serializable Python objects.

• include – A set of fields to include in the output.

• exclude – A set of fields to exclude from the output.

• context – Additional context to pass to the serializer.

• by_alias – Whether to use the field’s alias in the dictionary key if defined.

• exclude_unset – Whether to exclude fields that have not been explicitly set.

• exclude_defaults – Whether to exclude fields that are set to their default value.

• exclude_none – Whether to exclude fields that have a value of None.

• exclude_computed_fields – Whether to exclude computed fields. While this can be useful for round-tripping, it is usually recommended tu use the dedicated round_trip parameter instead.

• round_trip – If True, dumped values should be valid as input for non-idempotent types such as Json[T].

• warnings – How to handle serialization errors. False/”none” ignores them, True/”warn” logs errors, “error” raises a [PydanticSerializationError][pydantic_core.PydanticSerializationError].

• fallback – A function to call when an unknown value is encountered. If not provided, a [PydanticSerializationError][pydantic_core.PydanticSerializationError] error is raised.

• serialize_as_any – Whether to serialize fields with duck-typing serialization behavior.

Returns:

A dictionary representation of the model.

pydantic model weaviate_agents.classes.personalization.PersonalizedQueryResponse

Bases: BaseModel, QueryReturn

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.

field objects: List[Object[P, R]] [Required]

Validated by:

• _ensure_metadata_type

field usage: Usage [Required]

pydantic model weaviate_agents.classes.personalization.Usage

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.

field details: Dict[str, int] | Dict[str, str] | None = None

field request_tokens: int | str | None = None

field requests: int | str = 0

field response_tokens: int | str | None = None

field total_tokens: int | str | None = None

weaviate_agents.classes.query

pydantic model weaviate_agents.classes.query.QueryAgentCollectionConfig

Bases: BaseModel

A collection configuration for the QueryAgent.

name

The name of the collection to query.

tenant

Tenant name for collections with multi-tenancy enabled.

view_properties

Optional list of property names the agent has the ability to view for this specific collection.

target_vector

Optional target vector name(s) for collections with named vectors. Can be a single vector name or a list of vector names.

additional_filters

Optional filters to apply when the query is executed, in addition to filters selected by the Query Agent (i.e., there are AND combined).

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.

field additional_filters: Annotated[_Filters, PlainSerializer(func=serialise_filter, return_type=PydanticUndefined, when_used=always)] | None = None

field name: str [Required]

field target_vector: str | list[str] | None = None

field tenant: str | None = None

field view_properties: list[str] | None = None

pydantic model weaviate_agents.classes.query.QueryAgentResponse

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.

field aggregations: list[list[AggregationResultWithCollection]] [Required]

field collection_names: list[str] [Required]

field final_answer: str [Required]

field is_partial_answer: bool [Required]

field missing_information: list[str] [Required]

field original_query: str [Required]

field output_type: Literal['final_state'] = 'final_state'

field searches: list[list[QueryResultWithCollection]] [Required]

field sources: list[Source] [Required]

field total_time: float [Required]

field usage: Usage [Required]

display()

Display a pretty-printed summary of the QueryAgentResponse object.

Return type:

None

pydantic model weaviate_agents.classes.query.Source

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.

field collection: str [Required]

field object_id: str [Required]

class weaviate_agents.classes.query.ComparisonOperator(*values)

Bases: str, Enum

EQUALS = '='

LESS_THAN = '<'

GREATER_THAN = '>'

LESS_EQUAL = '<='

GREATER_EQUAL = '>='

NOT_EQUALS = '!='

LIKE = 'LIKE'

CONTAINS_ANY = 'contains_any'

CONTAINS_ALL = 'contains_all'

pydantic model weaviate_agents.classes.query.IntegerPropertyFilter

Bases: KnownPropertyFilterBase

Filter numeric properties using comparison operators.

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.

field filter_type: Literal[KnownFilterType.INTEGER] = KnownFilterType.INTEGER

field operator: ComparisonOperator [Required]

field property_name: str [Required]

field value: float [Required]

pydantic model weaviate_agents.classes.query.TextPropertyFilter

Bases: KnownPropertyFilterBase

Filter text properties using equality or LIKE operators.

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.

field filter_type: Literal[KnownFilterType.TEXT] = KnownFilterType.TEXT

field operator: ComparisonOperator [Required]

field property_name: str [Required]

field value: str [Required]

pydantic model weaviate_agents.classes.query.BooleanPropertyFilter

Bases: KnownPropertyFilterBase

Filter boolean properties using equality operators.

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.

field filter_type: Literal[KnownFilterType.BOOLEAN] = KnownFilterType.BOOLEAN

field operator: ComparisonOperator [Required]

field property_name: str [Required]

field value: bool [Required]

pydantic model weaviate_agents.classes.query.QueryResult

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.

field filter_operators: Literal['AND', 'OR'] [Required]

field filters: list[list[PropertyFilter]] = []

field queries: list[str | None] [Required]

class weaviate_agents.classes.query.NumericMetrics(*values)

Bases: str, Enum

COUNT = 'COUNT'

MAX = 'MAXIMUM'

MEAN = 'MEAN'

MEDIAN = 'MEDIAN'

MIN = 'MINIMUM'

MODE = 'MODE'

SUM = 'SUM'

TYPE = 'TYPE'

class weaviate_agents.classes.query.TextMetrics(*values)

Bases: str, Enum

COUNT = 'COUNT'

TYPE = 'TYPE'

TOP_OCCURRENCES = 'TOP_OCCURRENCES'

class weaviate_agents.classes.query.BooleanMetrics(*values)

Bases: str, Enum

COUNT = 'COUNT'

TYPE = 'TYPE'

TOTAL_TRUE = 'TOTAL_TRUE'

TOTAL_FALSE = 'TOTAL_FALSE'

PERCENTAGE_TRUE = 'PERCENTAGE_TRUE'

PERCENTAGE_FALSE = 'PERCENTAGE_FALSE'

pydantic model weaviate_agents.classes.query.IntegerPropertyAggregation

Bases: KnownPropertyAggregationBase

Aggregate numeric properties using statistical functions.

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.

field aggregation_type: Literal[KnownAggregationType.INTEGER] = KnownAggregationType.INTEGER

field metrics: NumericMetrics [Required]

field property_name: str [Required]

pydantic model weaviate_agents.classes.query.TextPropertyAggregation

Bases: KnownPropertyAggregationBase

Aggregate text properties using frequency analysis.

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.

field aggregation_type: Literal[KnownAggregationType.TEXT] = KnownAggregationType.TEXT

field metrics: TextMetrics [Required]

field property_name: str [Required]

field top_occurrences_limit: int | None = None

pydantic model weaviate_agents.classes.query.BooleanPropertyAggregation

Bases: KnownPropertyAggregationBase

Aggregate boolean properties using statistical functions.

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.

field aggregation_type: Literal[KnownAggregationType.BOOLEAN] = KnownAggregationType.BOOLEAN

field metrics: BooleanMetrics [Required]

field property_name: str [Required]

pydantic model weaviate_agents.classes.query.AggregationResult

Bases: BaseModel

The aggregations to be performed on a collection in a vector database.

They should be based on the original user query and can include multiple aggregations across different properties and metrics.

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.

field aggregations: list[PropertyAggregation] [Required]

field filters: list[PropertyFilter] = []

field groupby_property: str | None = None

field search_query: str | None = None

pydantic model weaviate_agents.classes.query.Usage

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.

field details: Dict[str, int] | Dict[str, str] | None = None

field request_tokens: int | str | None = None

field requests: int | str = 0

field response_tokens: int | str | None = None

field total_tokens: int | str | None = None

pydantic model weaviate_agents.classes.query.AggregationResultWithCollection

Bases: AggregationResult

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.

field aggregations: list[PropertyAggregation] [Required]

field collection: str [Required]

field filters: list[PropertyFilter] = []

field groupby_property: str | None = None

field search_query: str | None = None

pydantic model weaviate_agents.classes.query.QueryResultWithCollection

Bases: QueryResult

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.

field collection: str [Required]

field filter_operators: Literal['AND', 'OR'] [Required]

field filters: list[list[PropertyFilter]] = []

field queries: list[str | None] [Required]

pydantic model weaviate_agents.classes.query.BooleanArrayPropertyFilter

Bases: KnownPropertyFilterBase

Filter boolean-array properties using equality operators.

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.

field filter_type: Literal[KnownFilterType.BOOLEAN_ARRAY] = KnownFilterType.BOOLEAN_ARRAY

field operator: ComparisonOperator [Required]

field property_name: str [Required]

field value: list[bool] [Required]

pydantic model weaviate_agents.classes.query.DateArrayPropertyFilter

Bases: KnownPropertyFilterBase

Filter datetime properties using equality operators.

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.

field filter_type: Literal[KnownFilterType.DATE_ARRAY] = KnownFilterType.DATE_ARRAY

field operator: ComparisonOperator [Required]

field property_name: str [Required]

field value: list[str] [Required]

class weaviate_agents.classes.query.DateMetrics(*values)

Bases: str, Enum

COUNT = 'COUNT'

MAX = 'MAXIMUM'

MEDIAN = 'MEDIAN'

MIN = 'MINIMUM'

MODE = 'MODE'

pydantic model weaviate_agents.classes.query.DatePropertyAggregation

Bases: KnownPropertyAggregationBase

Aggregate datetime properties using statistical functions.

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.

field aggregation_type: Literal[KnownAggregationType.DATE] = KnownAggregationType.DATE

field metrics: DateMetrics [Required]

field property_name: str [Required]

pydantic model weaviate_agents.classes.query.DatePropertyFilter

Bases: KnownPropertyFilterBase

Filter datetime properties using equality operators.

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.

field filter_type: Literal[KnownFilterType.DATE] = KnownFilterType.DATE

field property_name: str [Required]

field value: DateExact | DateRangeFrom | DateRangeTo | DateRangeBetween [Required]

pydantic model weaviate_agents.classes.query.IntegerArrayPropertyFilter

Bases: KnownPropertyFilterBase

Filter numeric-array properties using comparison operators.

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.

field filter_type: Literal[KnownFilterType.INTEGER_ARRAY] = KnownFilterType.INTEGER_ARRAY

field operator: ComparisonOperator [Required]

field property_name: str [Required]

field value: list[float] [Required]

pydantic model weaviate_agents.classes.query.TextArrayPropertyFilter

Bases: KnownPropertyFilterBase

Filter text-array properties using equality or LIKE operators.

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.

field filter_type: Literal[KnownFilterType.TEXT_ARRAY] = KnownFilterType.TEXT_ARRAY

field operator: ComparisonOperator [Required]

field property_name: str [Required]

field value: list[str] [Required]

pydantic model weaviate_agents.classes.query.GeoPropertyFilter

Bases: KnownPropertyFilterBase

Filter geo-coordinates properties.

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.

field filter_type: Literal[KnownFilterType.GEO] = KnownFilterType.GEO

field latitude: float [Required]

field longitude: float [Required]

field max_distance_meters: float [Required]

field property_name: str [Required]

pydantic model weaviate_agents.classes.query.UnknownPropertyAggregation

Bases: BaseModel

Catch-all aggregation for unknown aggregation types, to preserve future back-compatibility.

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.

field aggregation_type: None [Required]

Validated by:

• ensure_filter_type_unknown

model_post_init(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:

context (Any)

Return type:

None

pydantic model weaviate_agents.classes.query.UnknownPropertyFilter

Bases: BaseModel

Catch-all filter for unknown filter types, to preserve future back-compatibility.

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.

field filter_type: None [Required]

Validated by:

• ensure_filter_type_unknown

model_post_init(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:

context (Any)

Return type:

None

class weaviate_agents.classes.query.ProgressDetails

Bases: TypedDict

queries: list[QueryWithCollection]

pydantic model weaviate_agents.classes.query.ProgressMessage

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.

field details: ProgressDetails = {}

field message: str [Required]

field output_type: Literal['progress_message'] = 'progress_message'

field stage: str [Required]

class weaviate_agents.classes.query.QueryWithCollection

Bases: TypedDict

query: str

collection: str

pydantic model weaviate_agents.classes.query.StreamedTokens

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.

field delta: str [Required]

field output_type: Literal['streamed_tokens'] = 'streamed_tokens'

pydantic model weaviate_agents.classes.query.IsNullPropertyFilter

Bases: KnownPropertyFilterBase

Filter by property null state.

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.

field filter_type: Literal[KnownFilterType.IS_NULL] = KnownFilterType.IS_NULL

field is_null: bool [Required]

field property_name: str [Required]

pydantic model weaviate_agents.classes.query.SearchModeResponseBase

Bases: BaseModel, ABC, Generic[SearcherT]

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.

field search_results: QueryReturn [Required]

field searches: list[QueryResultWithCollectionNormalized] | None = None

field total_time: float [Required]

field usage: ModelUnitUsage [Required]

model_post_init(context, /)

This function is meant to behave like a BaseModel method to initialise private attributes.

It takes context as an argument since that’s what pydantic-core passes when calling it.

Parameters:

• self (BaseModel) – The BaseModel instance.

• context (Any) – The context.

Return type:

None

abstractmethod next(limit=20, offset=0)

Parameters:

• self (SearchModeResponseT)

• limit (int)

• offset (int)

Return type:

SearchModeResponseT | Coroutine[Any, Any, SearchModeResponseT]

class weaviate_agents.classes.query.ChatMessage

Bases: TypedDict

role: Literal['user', 'assistant']

content: str

pydantic model weaviate_agents.classes.query.AskModeResponse

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.

field aggregations: list[AggregationResultWithCollectionNormalized] [Required]

field final_answer: str [Required]

field is_partial_answer: bool | None [Required]

field missing_information: list[str] | None [Required]

field output_type: Literal['final_state'] = 'final_state'

field searches: list[QueryResultWithCollectionNormalized] [Required]

field sources: list[Source] | None [Required]

field total_time: float [Required]

field usage: ModelUnitUsage [Required]

display()

Display a pretty-printed summary of the AskModeResponse object.

Return type:

None

pydantic model weaviate_agents.classes.query.ModelUnitUsage

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.

field model_units: int [Required]

field remaining_plan_requests: int [Required]

field usage_in_plan: bool [Required]

pydantic model weaviate_agents.classes.query.FilterAndOr

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.

field combine: Literal['AND', 'OR'] [Required]

field filters: list[PropertyFilter | FilterAndOr] [Required]

pydantic model weaviate_agents.classes.query.QueryResultWithCollectionNormalized

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.

field collection: str [Required]

field filters: PropertyFilter | FilterAndOr | None [Required]

field query: str | None [Required]

field sort_property: QuerySort | None = None

pydantic model weaviate_agents.classes.query.AggregationResultWithCollectionNormalized

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.

field aggregation: PropertyAggregation [Required]

field collection: str [Required]

field filters: PropertyFilter | FilterAndOr | None [Required]

field groupby_property: str | None [Required]

pydantic model weaviate_agents.classes.query.QuerySort

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.

field order: Literal['ascending', 'descending'] [Required]

field property_name: str [Required]

field tie_break: QuerySort | None [Required]

weaviate_agents.classes.transformation

class weaviate_agents.classes.transformation.OperationType(*values)

Bases: str, Enum

Types of operations that can be performed on properties.

APPEND = 'append'

UPDATE = 'update'

pydantic model weaviate_agents.classes.transformation.OperationStep

Bases: BaseModel

Base model for a transformation operation step.

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.

field instruction: str [Required]

field operation_type: OperationType [Required]

field property_name: str [Required]

field view_properties: List[str] [Required]

pydantic model weaviate_agents.classes.transformation.AppendPropertyOperation

Bases: OperationStep

Operation to append a new 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.

field data_type: DataType [Required]

field instruction: str [Required]

field operation_type: OperationType = OperationType.APPEND

field property_name: str [Required]

field view_properties: List[str] [Required]

pydantic model weaviate_agents.classes.transformation.UpdatePropertyOperation

Bases: OperationStep

Operation to update an existing 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.

field instruction: str [Required]

field operation_type: OperationType = OperationType.UPDATE

field property_name: str [Required]

field view_properties: List[str] [Required]

pydantic model weaviate_agents.classes.transformation.DependentOperationStep

Bases: BaseModel

A wrapper for operation steps that have dependencies on other operations.

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.

field depends_on: List[OperationStep] | None = None

field operation: OperationStep [Required]

pydantic model weaviate_agents.classes.transformation.TransformationResponse

Bases: BaseModel

Response from a transformation operation.

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.

field workflow_id: str [Required]

class weaviate_agents.classes.transformation.Operations

Bases: object

Factory class for creating transformation operations.

static append_property(property_name, data_type, view_properties, instruction)

Create an operation to append a new property.

Parameters:

• property_name (str) – Name of the new property to append

• data_type (DataType) – Data type of the new property

• view_properties (List[str]) – List of property names to use as context for the transformation

• instruction (str) – Instruction for how to generate the new property value

Returns:

An AppendPropertyOperation object

Return type:

AppendPropertyOperation

static update_property(property_name, view_properties, instruction)

Create an operation to update an existing property.

Parameters:

• property_name (str) – Name of the property to update

• view_properties (List[str]) – List of property names to use as context for the transformation

• instruction (str) – Instruction for how to update the property value

Returns:

An UpdatePropertyOperation object

Return type:

UpdatePropertyOperation