Vector Store Retrievers

Base vector store index query.

class llama_index.indices.vector_store.retrievers.retriever.VectorIndexRetriever(index: VectorStoreIndex, similarity_top_k: int = 2, vector_store_query_mode: VectorStoreQueryMode = VectorStoreQueryMode.DEFAULT, filters: Optional[MetadataFilters] = None, alpha: Optional[float] = None, doc_ids: Optional[List[str]] = None, **kwargs: Any)

Vector index retriever.

Parameters

• index (VectorStoreIndex) – vector store index.

• similarity_top_k (int) – number of top k results to return.

• vector_store_query_mode (str) – vector store query mode See reference for VectorStoreQueryMode for full list of supported modes.

• filters (Optional[MetadataFilters]) – metadata filters, defaults to None

• alpha (float) – weight for sparse/dense retrieval, only used for hybrid query mode.

• doc_ids (Optional[List[str]]) – list of documents to constrain search.

• vector_store_kwargs (dict) – Additional vector store specific kwargs to pass through to the vector store at query time.

retrieve(str_or_query_bundle: Union[str, QueryBundle]) → List[NodeWithScore]

Retrieve nodes given query.

Parameters

str_or_query_bundle (QueryType) – Either a query string or a QueryBundle object.

class llama_index.indices.vector_store.retrievers.auto_retriever.auto_retriever.VectorIndexAutoRetriever(index: VectorStoreIndex, vector_store_info: VectorStoreInfo, prompt_template_str: Optional[str] = None, service_context: Optional[ServiceContext] = None, max_top_k: int = 10)

Vector store auto retriever.

A retriever for vector store index that uses an LLM to automatically set vector store query parameters.

Parameters

• index (VectorStoreIndex) – vector store index

• vector_store_info (VectorStoreInfo) – additional information information about vector store content and supported metadata filters. The natural language description is used by an LLM to automatically set vector store query parameters.

• prompt_template_str – custom prompt template string for LLM. Uses default template string if None.

• service_context – service context containing reference to LLMPredictor. Uses service context from index be default if None.

• max_top_k – the maximum top_k allowed. The top_k set by LLM will be clamped to this value.

retrieve(str_or_query_bundle: Union[str, QueryBundle]) → List[NodeWithScore]

Retrieve nodes given query.

Parameters

str_or_query_bundle (QueryType) – Either a query string or a QueryBundle object.

Vector store index types.

class llama_index.vector_stores.types.ExactMatchFilter(*, key: str, value: Union[str, int, float])

Exact match metadata filter for vector stores.

classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) → Model

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values

copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters

• include – fields to include in new model

• exclude – fields to exclude from new model, as with values this takes precedence over include

• update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

• deep – set to True to make a deep copy of the model

Returns

new model instance

dict(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) → DictStrAny

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

json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) → unicode

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

classmethod update_forward_refs(**localns: Any) → None

Try to update ForwardRefs on fields based on this Model, globalns and localns.

class llama_index.vector_stores.types.MetadataFilters(*, filters: List[ExactMatchFilter])

Metadata filters for vector stores.

Currently only supports exact match filters. TODO: support more advanced expressions.

classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) → Model

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values

copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters

• include – fields to include in new model

• exclude – fields to exclude from new model, as with values this takes precedence over include

• update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

• deep – set to True to make a deep copy of the model

Returns

new model instance

dict(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) → DictStrAny

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

json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) → unicode

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

classmethod update_forward_refs(**localns: Any) → None

Try to update ForwardRefs on fields based on this Model, globalns and localns.

class llama_index.vector_stores.types.MetadataInfo(*, name: str, type: str, description: str)

Information about a metadata filter supported by a vector store.

Currently only used by VectorIndexAutoRetriever.

classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) → Model

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values

copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters

• include – fields to include in new model

• exclude – fields to exclude from new model, as with values this takes precedence over include

• update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

• deep – set to True to make a deep copy of the model

Returns

new model instance

dict(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) → DictStrAny

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

json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) → unicode

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

classmethod update_forward_refs(**localns: Any) → None

Try to update ForwardRefs on fields based on this Model, globalns and localns.

class llama_index.vector_stores.types.VectorStoreInfo(*, metadata_info: List[MetadataInfo], content_info: str)

Information about a vector store (content and supported metadata filters).

Currently only used by VectorIndexAutoRetriever.

classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) → Model

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values

copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters

• include – fields to include in new model

• exclude – fields to exclude from new model, as with values this takes precedence over include

• update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

• deep – set to True to make a deep copy of the model

Returns

new model instance

dict(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) → DictStrAny

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

json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) → unicode

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

classmethod update_forward_refs(**localns: Any) → None

Try to update ForwardRefs on fields based on this Model, globalns and localns.

class llama_index.vector_stores.types.VectorStoreQueryMode(value)

Vector store query mode.