Method●Since v0.0

afrom_documents

Create an PGVectorStore instance from documents.

afrom_documents(
  cls: type[PGVectorStore],
  documents: list[Document],
  embedding: Embeddings,
  engine: PGEngine,
  table_name: str,
  schema_name: str = 'public',
  ids: Optional[list] = None,
  content_column: str = 'content',
  embedding_column: str = 'embedding',
  metadata_columns: Optional[list[str]] = None,
  ignore_metadata_columns: Optional[list[str]] = None,
  id_column: str = 'langchain_id',
  metadata_json_column: str = 'langchain_metadata',
  distance_strategy: DistanceStrategy = DEFAULT_DISTANCE_STRATEGY,
  k: int = 4,
  fetch_k: int = 20,
  lambda_mult: float = 0.5,
  index_query_options: Optional[QueryOptions] = None,
  hybrid_search_config: Optional[HybridSearchConfig] = None,
  **kwargs: Any = {}
) -> PGVectorStore

Parameters

Name	Type	Description
`documents`*	`list[Document]`	Documents to add to the vector store.
`embedding`*	`Embeddings`	Text embedding model to use.
`engine`*	`PGEngine`	Connection pool engine for managing connections to postgres database.
`table_name`*	`str`	Name of an existing table.
`schema_name`	`str`	Default:`'public'` Name of the database schema. Defaults to "public".
`ids`	`Optional[list]`	Default:`None` (Optional[list]): List of IDs to add to table records. Defaults to None.
`content_column`	`str`	Default:`'content'` Column that represent a Document's page_content. Defaults to "content".
`embedding_column`	`str`	Default:`'embedding'` Column for embedding vectors. The embedding is generated from the document value. Defaults to "embedding".
`metadata_columns`	`list[str]`	Default:`None` Column(s) that represent a document's metadata. Defaults to an empty list.
`ignore_metadata_columns`	`Optional[list[str]]`	Default:`None` Column(s) to ignore in pre-existing tables for a document's metadata. Can not be used with metadata_columns. Defaults to None.
`id_column`	`str`	Default:`'langchain_id'` Column that represents the Document's id. Defaults to "langchain_id".
`metadata_json_column`	`str`	Default:`'langchain_metadata'` Column to store metadata as JSON. Defaults to "langchain_metadata".
`distance_strategy`	`DistanceStrategy`	Default:`DEFAULT_DISTANCE_STRATEGY` Distance strategy to use for vector similarity search. Defaults to COSINE_DISTANCE.
`k`	`int`	Default:`4` Number of Documents to return from search. Defaults to 4.
`fetch_k`	`int`	Default:`20` Number of Documents to fetch to pass to MMR algorithm.
`lambda_mult`	`float`	Default:`0.5` Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.
`index_query_options`	`QueryOptions`	Default:`None` Index query option.
`hybrid_search_config`	`HybridSearchConfig`	Default:`None` Hybrid search configuration. Defaults to None.

View source on GitHub

afrom_documents( cls: type[PGVectorStore], documents: list[Document], embedding: Embeddings, engine: PGEngine, table_name: str, schema_name: str = 'public', ids: Optional[list] = None, content_column: str = 'content', embedding_column: str = 'embedding', metadata_columns: Optional[list[str]] = None, ignore_metadata_columns: Optional[list[str]] = None, id_column: str = 'langchain_id', metadata_json_column: str = 'langchain_metadata', distance_strategy: DistanceStrategy = DEFAULT_DISTANCE_STRATEGY, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, index_query_options: Optional[QueryOptions] = None, hybrid_search_config: Optional[HybridSearchConfig] = None, **kwargs: Any = {} ) -> PGVectorStore

Parameters

Name	Type	Description
`documents`*	`list[Document]`	Documents to add to the vector store.
`embedding`*	`Embeddings`	Text embedding model to use.
`engine`*	`PGEngine`	Connection pool engine for managing connections to postgres database.
`table_name`*	`str`	Name of an existing table.
`schema_name`	`str`	Default:`'public'` Name of the database schema. Defaults to "public".
`ids`	`Optional[list]`	Default:`None` (Optional[list]): List of IDs to add to table records. Defaults to None.
`content_column`	`str`	Default:`'content'` Column that represent a Document's page_content. Defaults to "content".
`embedding_column`	`str`	Default:`'embedding'` Column for embedding vectors. The embedding is generated from the document value. Defaults to "embedding".
`metadata_columns`	`list[str]`	Default:`None` Column(s) that represent a document's metadata. Defaults to an empty list.
`ignore_metadata_columns`	`Optional[list[str]]`	Default:`None` Column(s) to ignore in pre-existing tables for a document's metadata. Can not be used with metadata_columns. Defaults to None.
`id_column`	`str`	Default:`'langchain_id'` Column that represents the Document's id. Defaults to "langchain_id".
`metadata_json_column`	`str`	Default:`'langchain_metadata'` Column to store metadata as JSON. Defaults to "langchain_metadata".
`distance_strategy`	`DistanceStrategy`	Default:`DEFAULT_DISTANCE_STRATEGY` Distance strategy to use for vector similarity search. Defaults to COSINE_DISTANCE.
`k`	`int`	Default:`4` Number of Documents to return from search. Defaults to 4.
`fetch_k`	`int`	Default:`20` Number of Documents to fetch to pass to MMR algorithm.
`lambda_mult`	`float`	Default:`0.5` Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.
`index_query_options`	`QueryOptions`	Default:`None` Index query option.
`hybrid_search_config`	`HybridSearchConfig`	Default:`None` Hybrid search configuration. Defaults to None.

afrom_documents

Parameters

LangChain Assistant

Menu

afrom_documents

Parameters