create(
cls: type[AsyncPGVectorStore],
engine: PGEngine,
embedding_service: Embeddings| Name | Type | Description |
|---|---|---|
engine* | PGEngine | Connection pool engine for managing connections to postgres database. |
embedding_service* | Embeddings | Text embedding model to use. |
table_name* | str | Name of an existing table. |
schema_name | str | Default: 'public' |
content_column | str | Default: 'content' |
embedding_column | str | Default: 'embedding' |
metadata_columns | list[str] | Default: None |
ignore_metadata_columns | list[str] | Default: None |
id_column | str | Default: 'langchain_id' |
metadata_json_column | str | Default: 'langchain_metadata' |
distance_strategy | DistanceStrategy | Default: DEFAULT_DISTANCE_STRATEGY |
k | int | Default: 4 |
fetch_k | int | Default: 20 |
lambda_mult | float | Default: 0.5 |
index_query_options | QueryOptions | Default: None |
hybrid_search_config | HybridSearchConfig | Default: None |
Create an AsyncPGVectorStore instance.
Name of the database schema. Defaults to "public".
Column that represent a Document's page_content. Defaults to "content".
Column for embedding vectors. The embedding is generated from the document value. Defaults to "embedding".
Column(s) that represent a document's metadata.
Column(s) to ignore in pre-existing tables for a document's metadata. Can not be used with metadata_columns. Defaults to None.
Column that represents the Document's id. Defaults to "langchain_id".
Column to store metadata as JSON. Defaults to "langchain_metadata".
Distance strategy to use for vector similarity search. Defaults to COSINE_DISTANCE.
Number of Documents to return from search. Defaults to 4.
Number of Documents to fetch to pass to MMR algorithm.
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 option.
Hybrid search configuration. Defaults to None.