VectorStoreIndexWrapper#

class langchain.indexes.vectorstore.VectorStoreIndexWrapper[source]#

Bases: BaseModel

Wrapper around a vectorstore for easy access.

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.

param vectorstore: VectorStore [Required]#
async aquery(question: str, llm: BaseLanguageModel | None = None, retriever_kwargs: Dict[str, Any] | None = None, **kwargs: Any) → str[source]#

Asynchronously query the vectorstore using the provided LLM.

Parameters:

  • question (str) – The question or prompt to query.

  • llm (BaseLanguageModel | None) – The language model to use. Must not be None.

  • retriever_kwargs (Dict[str, Any] | None) – Optional keyword arguments for the retriever.

  • **kwargs (Any) – Additional keyword arguments forwarded to the chain.

Returns:

The asynchronous result string from the RetrievalQA chain.

Return type:

str

async aquery_with_sources(question: str, llm: BaseLanguageModel | None = None, retriever_kwargs: Dict[str, Any] | None = None, **kwargs: Any) → dict[source]#

Asynchronously query the vectorstore and retrieve the answer and sources.

Parameters:

  • question (str) – The question or prompt to query.

  • llm (BaseLanguageModel | None) – The language model to use. Must not be None.

  • retriever_kwargs (Dict[str, Any] | None) – Optional keyword arguments for the retriever.

  • **kwargs (Any) – Additional keyword arguments forwarded to the chain.

Returns:

A dictionary containing the answer and source documents.

Return type:

dict

query(question: str, llm: BaseLanguageModel | None = None, retriever_kwargs: Dict[str, Any] | None = None, **kwargs: Any) → str[source]#

Query the vectorstore using the provided LLM.

Parameters:

  • question (str) – The question or prompt to query.

  • llm (BaseLanguageModel | None) – The language model to use. Must not be None.

  • retriever_kwargs (Dict[str, Any] | None) – Optional keyword arguments for the retriever.

  • **kwargs (Any) – Additional keyword arguments forwarded to the chain.

Returns:

The result string from the RetrievalQA chain.

Return type:

str

query_with_sources(question: str, llm: BaseLanguageModel | None = None, retriever_kwargs: Dict[str, Any] | None = None, **kwargs: Any) → dict[source]#

Query the vectorstore and retrieve the answer along with sources.

Parameters:

  • question (str) – The question or prompt to query.

  • llm (BaseLanguageModel | None) – The language model to use. Must not be None.

  • retriever_kwargs (Dict[str, Any] | None) – Optional keyword arguments for the retriever.

  • **kwargs (Any) – Additional keyword arguments forwarded to the chain.

Returns:

A dictionary containing the answer and source documents.

Return type:

dict