`langchain-azure-postgresql`¶

Reference docs

This page contains reference documentation for Azure AI. See the docs for conceptual guides, tutorials, and examples on using Azure AI.

langchain_azure_postgresql ¶

Common utilities and models for Azure PostgreSQL AI integrations.

FUNCTION	DESCRIPTION
`async_check_connection`	Check if the connection to Azure Database for PostgreSQL is valid and required extensions are installed.
`check_connection`	Check if the connection to Azure Database for PostgreSQL is valid and required extensions are installed.
`create_extensions`	Create required extensions in the Azure Database for PostgreSQL connection.

HNSW ¶

Bases: Algorithm[HNSWSearchParams]

HNSW algorithm settings.

Provides build-time and (via :class:HNSWSearchParams) search-time parameters for HNSW vector indexes.

:param m: The maximum number of connections per layer for HNSW index building. :type m: PositiveInt | None :param ef_construction: The size of the dynamic candidate list for constructing the HNSW graph. :type ef_construction: PositiveInt | None

Notes:¶

If ef_construction is not at least twice the value of m, a ValueError will be raised during validation.

METHOD	DESCRIPTION
`index_settings`	Return the general index settings for the algorithm.
`build_settings`	Return the specific index build settings for the algorithm.
`default_search_params`	Return the default search parameters for the algorithm.

index_settings ¶

index_settings(exclude_none: bool = True) -> dict[str, Any]

Return the general index settings for the algorithm.

:param exclude_none: Whether to exclude keys with None values in the dictionary. :type exclude_none: bool :return: A dictionary containing the index settings. :rtype: dict[str, Any]

build_settings ¶

build_settings(exclude_none=True)

Return the specific index build settings for the algorithm.

:param exclude_none: Whether to exclude keys with None values in the dictionary. :type exclude_none: bool :return: A dictionary containing the settings. :rtype: dict[str, Any]

default_search_params ¶

default_search_params() -> HNSWSearchParams

Return the default search parameters for the algorithm.

:return: An instance of the search parameters model. :rtype: SP

Algorithm ¶

Bases: BaseModel, Generic[SP]

Base class for vector index algorithms and their settings.

Subclasses provide index build-time settings via :meth:build_settings and the default search-time settings via :meth:default_search_params.

The generic type parameter SP is a :class:SearchParams subtype that models the search-time parameters for the algorithm.

:param op_class: The operator class to use for the vector index. :type op_class: VectorOpClass :param maintenance_work_mem: The amount of memory to use for maintenance operations. :type maintenance_work_mem: str | None :param max_parallel_maintenance_workers: The maximum number of parallel workers for maintenance operations. :type max_parallel_maintenance_workers: NonNegativeInt | None :param max_parallel_workers: The maximum number of parallel workers for query execution. :type max_parallel_workers: NonNegativeInt | None

METHOD	DESCRIPTION
`default_search_params`	Return the default search parameters for the algorithm.
`build_settings`	Return the specific index build settings for the algorithm.
`index_settings`	Return the general index settings for the algorithm.

default_search_params `abstractmethod` ¶

default_search_params() -> SP

Return the default search parameters for the algorithm.

:return: An instance of the search parameters model. :rtype: SP

build_settings `abstractmethod` ¶

build_settings(exclude_none: bool = True) -> dict[str, Any]

Return the specific index build settings for the algorithm.

:param exclude_none: Whether to exclude keys with None values in the dictionary. :type exclude_none: bool :return: A dictionary containing the settings. :rtype: dict[str, Any]

index_settings ¶

index_settings(exclude_none: bool = True) -> dict[str, Any]

Return the general index settings for the algorithm.

:param exclude_none: Whether to exclude keys with None values in the dictionary. :type exclude_none: bool :return: A dictionary containing the index settings. :rtype: dict[str, Any]

AsyncAzurePGConnectionPool ¶

Bases: AsyncConnectionPool

Async connection pool for Azure Database for PostgreSQL connections.

AsyncConnectionInfo ¶

Bases: BaseConnectionInfo

Base connection information for Azure Database for PostgreSQL connections.

:param host: Hostname of the Azure Database for PostgreSQL server. :type host: str | None :param dbname: Name of the database to connect to. :type dbname: str :param port: Port number for the connection. :type port: int :param credentials: Credentials for authentication. :type credentials: BasicAuth | AsyncTokenCredential :param sslmode: SSL mode for the connection. :type sslmode: SSLMode

AzurePGConnectionPool ¶

Bases: ConnectionPool

Connection pool for Azure Database for PostgreSQL connections.

BasicAuth ¶

Bases: BaseModel

Basic username/password authentication for Azure Database for PostgreSQL connections.

:param username: Username for the connection. :type username: str :param password: Password for the connection. :type password: str

ConnectionInfo ¶

Bases: BaseConnectionInfo

Base connection information for Azure Database for PostgreSQL connections.

:param host: Hostname of the Azure Database for PostgreSQL server. :type host: str | None :param dbname: Name of the database to connect to. :type dbname: str :param port: Port number for the connection. :type port: int :param sslmode: SSL mode for the connection. :type sslmode: SSLMode :param credentials: Credentials for the connection. :type credentials: BasicAuth | TokenCredential

DiskANN ¶

Bases: Algorithm[DiskANNSearchParams]

DiskANN algorithm settings.

Provides build-time and (via :class:DiskANNSearchParams) search-time parameters for DiskANN vector indexes.

:param max_neighbors: The maximum number of edges per node in the graph. :type max_neighbors: PositiveInt | None :param l_value_ib: The value of the L parameter for DiskANN index building. :type l_value_ib: PositiveInt | None :param product_quantized: Whether to use product quantization (PQ) for the index. :type product_quantized: bool | None :param pq_param_num_chunks: Number of chunks for product quantization (PQ). :type pq_param_num_chunks: NonNegativeInt | None :param pq_param_training_samples: Number of training samples for product quantization (PQ). :type pq_param_training_samples: NonNegativeInt | None

Notes:¶

If product_quantized is True, pq_param_num_chunks and pq_param_training_samples can be provided. Otherwise, these parameters are invalid and raise a ValueError during validation.

METHOD	DESCRIPTION
`index_settings`	Return the general index settings for the algorithm.
`build_settings`	Return the specific index build settings for the algorithm.
`default_search_params`	Return the default search parameters for the algorithm.

index_settings ¶

index_settings(exclude_none: bool = True) -> dict[str, Any]

Return the general index settings for the algorithm.

:param exclude_none: Whether to exclude keys with None values in the dictionary. :type exclude_none: bool :return: A dictionary containing the index settings. :rtype: dict[str, Any]

build_settings ¶

build_settings(exclude_none: bool = True) -> dict[str, Any]

Return the specific index build settings for the algorithm.

:param exclude_none: Whether to exclude keys with None values in the dictionary. :type exclude_none: bool :return: A dictionary containing the settings. :rtype: dict[str, Any]

default_search_params ¶

default_search_params() -> DiskANNSearchParams

Return the default search parameters for the algorithm.

:return: An instance of the search parameters model. :rtype: SP

DiskANNIterativeScanMode ¶

Bases: str, Enum

Enumeration for DiskANN iterative scan modes.

DiskANNSearchParams ¶

Bases: SearchParams

Search-time parameters for DiskANN indexes.

All settings are exported with the diskann. prefix when used in SQL.

:param l_value_is: The value of the L parameter for DiskANN index searching. :type l_value_is: PositiveInt | None :param iterative_search: The iterative search mode for DiskANN index searching. :type iterative_search: DiskANNIterativeScanMode | None

METHOD	DESCRIPTION
`search_settings`	Return the specific index search settings for the algorithm.

search_settings ¶

search_settings(exclude_none=True)

Return the specific index search settings for the algorithm.

:param exclude_none: Whether to exclude keys with None values in the dictionary. :type exclude_none: bool :return: A dictionary containing the search settings. :rtype: dict[str, Any]

Extension ¶

Bases: BaseModel

Model representing a PostgreSQL extension.

:param ext_name: Name of the extension to be created, checked or dropped. :type ext_name: str :param ext_version: Optional version of the extension to be created or checked. :type ext_version: str | None :param schema_name: Optional schema name where the extension should be created or checked. :type schema_name: str | None :param cascade: Whether to automatically install the extension dependencies or drop the objects that depend on the extension. :type cascade: bool

HNSWIterativeScanMode ¶

Bases: str, Enum

Enumeration for HNSW iterative scan modes.

HNSWSearchParams ¶

Bases: SearchParams

Search-time parameters for HNSW indexes.

All settings are exported with the hnsw. prefix when used in SQL.

:param ef_search: Size of the dynamic candidate list for HNSW index searching. :type ef_search: PositiveInt | None :param iterative_scan: The iterative search mode for HNSW index searching. :type iterative_scan: HNSWIterativeScanMode | None :param max_scan_tuples: The maximum number of tuples to visit during HNSW index searching. :type max_scan_tuples: PositiveInt | None :param scan_mem_multiplier: The maximum amount of memory to use, as a multiple of work_mem, during HNSW index searching. :type scan_mem_multiplier: PositiveFloat | None

METHOD	DESCRIPTION
`search_settings`	Return the specific index search settings for the algorithm.

search_settings ¶

search_settings(exclude_none=True)

Return the specific index search settings for the algorithm.

:param exclude_none: Whether to exclude keys with None values in the dictionary. :type exclude_none: bool :return: A dictionary containing the search settings. :rtype: dict[str, Any]

IVFFlat ¶

Bases: Algorithm[IVFFlatSearchParams]

IVF-Flat algorithm settings.

Provides build-time and (via :class:IVFFlatSearchParams) search-time parameters for IVF-Flat vector indexes.

:param lists: The number of inverted lists to use for IVF-Flat indexing. :type lists: PositiveInt | None

METHOD	DESCRIPTION
`index_settings`	Return the general index settings for the algorithm.
`build_settings`	Return the specific index build settings for the algorithm.
`default_search_params`	Return the default search parameters for the algorithm.

index_settings ¶

index_settings(exclude_none: bool = True) -> dict[str, Any]

Return the general index settings for the algorithm.

:param exclude_none: Whether to exclude keys with None values in the dictionary. :type exclude_none: bool :return: A dictionary containing the index settings. :rtype: dict[str, Any]

build_settings ¶

build_settings(exclude_none: bool = True) -> dict[str, Any]

Return the specific index build settings for the algorithm.

:param exclude_none: Whether to exclude keys with None values in the dictionary. :type exclude_none: bool :return: A dictionary containing the settings. :rtype: dict[str, Any]

default_search_params ¶

default_search_params() -> IVFFlatSearchParams

Return the default search parameters for the algorithm.

:return: An instance of the search parameters model. :rtype: SP

IVFFlatIterativeScanMode ¶

Bases: str, Enum

Enumeration for IVFFlat iterative scan modes.

IVFFlatSearchParams ¶

Bases: SearchParams

Search-time parameters for IVF-Flat indexes.

All settings are exported with the ivfflat. prefix when used in SQL.

:param probes: The number of probes to use during IVF-Flat index searching. :type probes: PositiveInt | None :param iterative_scan: The iterative search mode for IVF-Flat index searching. :type iterative_scan: IVFFlatIterativeScanMode | None :param max_probes: The maximum number of probes to use during IVF-Flat index searching. :type max_probes: PositiveInt | None

METHOD	DESCRIPTION
`search_settings`	Return the specific index search settings for the algorithm.

search_settings ¶

search_settings(exclude_none=True)

Return the specific index search settings for the algorithm.

:param exclude_none: Whether to exclude keys with None values in the dictionary. :type exclude_none: bool :return: A dictionary containing the search settings. :rtype: dict[str, Any]

SSLMode ¶

Bases: str, Enum

SSL mode for Azure Database for PostgreSQL connections.

VectorOpClass ¶

Bases: str, Enum

Enumeration for operator classes used in vector indexes.

METHOD	DESCRIPTION
`to_operator`	Return the distance operator as a string.

to_operator ¶

to_operator() -> str

Return the distance operator as a string.

:return: The distance operator string. :rtype: str :raises ValueError: If the vector operator class is unsupported.

VectorType ¶

Bases: str, Enum

Enumeration for vector types used in vector similarity search.

AsyncAzurePGVectorStore ¶

Bases: BaseModel, VectorStore

LangChain VectorStore backed by Azure Database for PostgreSQL (async).

The store validates or creates the backing table on initialization, and optionally discovers an existing vector index configuration. It supports inserting, deleting, fetching by id, similarity search, and MMR search.

Fields such as schema_name, table_name, and column names control the schema layout. embedding_type, embedding_dimension, and embedding_index describe the vector column and its index behavior.

Metadata can be stored in a single JSONB column by passing a string (default "metadata"), in multiple typed columns via a list of strings/tuples, or disabled by setting metadata_columns=None.

:param embedding: The embedding model to use for embedding vector generation. :type embedding: Embeddings | None :param connection: The database connection or connection pool to use. :type connection: AsyncConnection | AsyncConnectionPool :param schema_name: The name of the database schema to use. :type schema_name: str :param table_name: The name of the database table to use. :type table_name: str :param id_column: The name of the column containing document IDs (UUIDs). :type id_column: str :param content_column: The name of the column containing document content. :type content_column: str :param embedding_column: The name of the column containing document embeddings. :type embedding_column: str :param embedding_type: The type of the embedding vectors. :type embedding_type: VectorType | None :param embedding_dimension: The dimensionality of the embedding vectors. :type embedding_dimension: PositiveInt | None :param embedding_index: The algorithm used for indexing the embedding vectors. :type embedding_index: Algorithm | None :param _embedding_index_name: (internal) The name of the discovered or created index. :type _embedding_index_name: str | None :param metadata_columns: The columns to use for storing metadata. :type metadata_columns: list[str] | list[tuple[str, str]] | str | None

METHOD	DESCRIPTION
`asearch`	Async return docs most similar to query using a specified search type.
`asimilarity_search_with_relevance_scores`	Async return docs and relevance scores in the range `[0, 1]`.
`as_retriever`	Return `VectorStoreRetriever` initialized from this `VectorStore`.
`create_index`	Create the vector index on the embedding column (if not already exists).
`reindex`	Reindex the existing vector index.
`afrom_documents`	Create a store and add documents in one step.
`afrom_texts`	Create a store and add texts with optional metadata.
`aadd_documents`	Insert or upsert a batch of LangChain `documents`.
`aadd_texts`	Insert or upsert `texts` with optional `metadatas` and embeddings.
`adelete`	Delete by ids or truncate the table.
`aget_by_ids`	Fetch documents by their `ids`.
`asimilarity_search`	Similarity search for a query string using the configured index.
`asimilarity_search_with_score`	Similarity search returning (document, distance) pairs.
`asimilarity_search_by_vector`	Similarity search for a precomputed embedding vector.
`amax_marginal_relevance_search`	MMR search for a query string.
`amax_marginal_relevance_search_by_vector`	MMR search for a precomputed embedding vector.
`from_documents`	Return `VectorStore` initialized from documents and embeddings.
`from_texts`	Return `VectorStore` initialized from texts and embeddings.
`add_documents`	Add or update documents in the `VectorStore`.
`add_texts`	Run more texts through the embeddings and add to the `VectorStore`.
`delete`	Delete by vector ID or other criteria.
`get_by_ids`	Get documents by their IDs.
`search`	Return docs most similar to query using a specified search type.
`similarity_search`	Return docs most similar to query.
`similarity_search_with_score`	Run similarity search with distance.
`similarity_search_by_vector`	Return docs most similar to embedding vector.
`similarity_search_with_relevance_scores`	Return docs and relevance scores in the range `[0, 1]`.
`max_marginal_relevance_search`	Return docs selected using the maximal marginal relevance.
`max_marginal_relevance_search_by_vector`	Return docs selected using the maximal marginal relevance.

embeddings `property` ¶

embeddings: Embeddings | None

Access the query embedding object if available.

asearch `async` ¶

asearch(query: str, search_type: str, **kwargs: Any) -> list[Document]

Async return docs most similar to query using a specified search type.

PARAMETER	DESCRIPTION
`query`	Input text. TYPE: `str`
`search_type`	Type of search to perform. Can be `'similarity'`, `'mmr'`, or `'similarity_score_threshold'`. TYPE: `str`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects most similar to the query.

RAISES	DESCRIPTION
`ValueError`	If `search_type` is not one of `'similarity'`, `'mmr'`, or `'similarity_score_threshold'`.

asimilarity_search_with_relevance_scores `async` ¶

asimilarity_search_with_relevance_scores(
    query: str, k: int = 4, **kwargs: Any
) -> list[tuple[Document, float]]

Async return docs and relevance scores in the range [0, 1].

0 is dissimilar, 1 is most similar.

PARAMETER	DESCRIPTION
`query`	Input text. TYPE: `str`
`k`	Number of `Document` objects to return. TYPE: `int` DEFAULT: `4`
`**kwargs`	Kwargs to be passed to similarity search. Should include `score_threshold`, an optional floating point value between `0` to `1` to filter the resulting set of retrieved docs. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[tuple[Document, float]]`	List of tuples of `(doc, similarity_score)`

as_retriever ¶

as_retriever(**kwargs: Any) -> VectorStoreRetriever

Return VectorStoreRetriever initialized from this VectorStore.

PARAMETER DESCRIPTION

**kwargs

Keyword arguments to pass to the search function.

Can include:

search_type: Defines the type of search that the Retriever should perform. Can be 'similarity' (default), 'mmr', or 'similarity_score_threshold'.
search_kwargs: Keyword arguments to pass to the search function.

Can include things like:
- k: Amount of documents to return (Default: 4)
- score_threshold: Minimum relevance threshold for similarity_score_threshold
- fetch_k: Amount of documents to pass to MMR algorithm (Default: 20)
- lambda_mult: Diversity of results returned by MMR; 1 for minimum diversity and 0 for maximum. (Default: 0.5)
- filter: Filter by document metadata

TYPE: Any DEFAULT: {}

RETURNS	DESCRIPTION
`VectorStoreRetriever`	Retriever class for `VectorStore`.

Examples:

# Retrieve more documents with higher diversity
# Useful if your dataset has many similar documents
docsearch.as_retriever(
    search_type="mmr", search_kwargs={"k": 6, "lambda_mult": 0.25}
)

# Fetch more documents for the MMR algorithm to consider
# But only return the top 5
docsearch.as_retriever(search_type="mmr", search_kwargs={"k": 5, "fetch_k": 50})

# Only retrieve documents that have a relevance score
# Above a certain threshold
docsearch.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={"score_threshold": 0.8},
)

# Only get the single most similar document from the dataset
docsearch.as_retriever(search_kwargs={"k": 1})

# Use a filter to only retrieve documents from a specific paper
docsearch.as_retriever(
    search_kwargs={"filter": {"paper_title": "GPT-4 Technical Report"}}
)

create_index `async` ¶

create_index(*, concurrently: bool = False) -> bool

Create the vector index on the embedding column (if not already exists).

Builds a vector index for the configured embedding_column using the algorithm specified by embedding_index (DiskANN, HNSW or IVFFlat). The effective index type name is inferred from the concrete Algorithm instance and the index name is generated as <table>_<column>_<type>_idx. If an index has already been discovered (_embedding_index_name is not None) the operation is skipped.

Prior to executing create index the per-build tuning parameters (returned by :meth:Algorithm.index_settings) are applied via set GUCs so they only affect this session. Build-time options (returned by :meth:Algorithm.build_settings) are appended in a with (...) clause.

For quantized operator classes: - halfvec_* (scalar quantization) casts both the stored column and future query vectors to halfvec(dim). - bit_* (binary quantization) wraps the column with binary_quantize(col)::bit(dim). Otherwise the raw column is indexed.

:param concurrently: When True uses create index concurrently to avoid long write-locks at the expense of a slower build. :type concurrently: bool :return: True if the index was created, False when an existing index prevented creation. :rtype: bool :raises AssertionError: If required attributes (embedding_index or embedding_dimension) are unexpectedly None.

reindex `async` ¶

reindex(*, concurrently: bool = False, verbose: bool = False) -> bool

Reindex the existing vector index.

Issues a reindex (concurrently <bool>, verbose <bool>) index command for the previously discovered or created index (tracked in _embedding_index_name). The session-level index tuning GUCs (returned by :meth:Algorithm.index_settings) are applied beforehand to influence the reindex process (useful for algorithms whose maintenance cost or accuracy depends on these settings).

:param concurrently: When True performs a concurrent reindex to minimize locking, trading speed for availability. :type concurrently: bool :param verbose: When True enables PostgreSQL verbose output, which may aid in diagnosing build performance issues. :type verbose: bool :return: True if reindex succeeded, False if no index existed. :rtype: bool :raises AssertionError: If embedding_index is unexpectedly None.

afrom_documents `async` `classmethod` ¶

afrom_documents(
    documents: list[Document], embedding: Embeddings, **kwargs: Any
) -> Self

Create a store and add documents in one step.

:param documents: The list of documents to add to the store. :type documents: list[Document] :param embedding: The embedding model to use for embedding vector generation. :type embedding: Embeddings

Kwargs¶

connection: (required) psycopg AsyncConnection or AsyncConnectionPool
schema_name, table_name, id_column, content_column, embedding_column: customize table/column names
embedding_type: VectorType of the embedding column
embedding_dimension: dimension of the vector column
embedding_index: Algorithm describing the vector index
metadata_columns: str | list[str | (str, str)] | None to configure metadata storage
on_conflict_update (passed to add): bool to upsert existing rows

:return: The created vector store instance. :rtype: Self

afrom_texts `async` `classmethod` ¶

afrom_texts(
    texts: list[str],
    embedding: Embeddings,
    metadatas: list[dict] | None = None,
    *,
    ids: list[str] | None = None,
    **kwargs: Any,
) -> Self

Create a store and add texts with optional metadata.

:param texts: The list of texts to add to the store. :type texts: list[str] :param embedding: The embedding model to use for embedding vector generation. :type embedding: Embeddings :param metadatas: The list of metadata dictionaries corresponding to each text. :type metadatas: list[dict] | None :param ids: The list of custom IDs corresponding to each text. When ids are not provided, UUIDs are generated. :type ids: list[str] | None

Kwargs¶

See :meth:afrom_documents for required and/or supported kwargs.

:return: The created vector store instance. :rtype: Self

aadd_documents `async` ¶

aadd_documents(documents: list[Document], **kwargs: Any) -> list[str]

Insert or upsert a batch of LangChain documents.

Kwargs¶

ids: list[str] custom ids, otherwise UUIDs or doc.id are used
on_conflict_update: bool to update existing rows on id conflict

:return: Inserted ids. :rtype: list[str]

aadd_texts `async` ¶

aadd_texts(
    texts: Iterable[str],
    metadatas: list[dict] | None = None,
    *,
    ids: list[str] | None = None,
    **kwargs: Any,
) -> list[str]

Insert or upsert texts with optional metadatas and embeddings.

If an embeddings model is present, embeddings are computed and stored. When metadata_columns is a string, metadata is written as JSONB; otherwise only provided keys matching configured columns are stored.

Kwargs¶

ids: list[str] custom ids, otherwise UUIDs are used
on_conflict_update: bool to update existing rows on id conflict

:return: Inserted ids. :rtype: list[str] :raises ValueError: If the length of 'metadatas', 'texts', and 'ids' do not match.

adelete `async` ¶

adelete(ids: list[str] | None = None, **kwargs: Any) -> bool | None

Delete by ids or truncate the table.

If ids is None, the table is truncated.

Kwargs¶

restart: bool to restart (when True) or continue (when False) identity, when truncating
cascade: bool to cascade (when True) or restrict (when False), when truncating

:return: True if the operation was successful, False otherwise. :rtype: bool | None

aget_by_ids `async` ¶

aget_by_ids(ids: Sequence[str]) -> list[Document]

Fetch documents by their ids.

:param ids: Sequence of string ids. :type ids: Sequence[str] :return: Documents with metadata reconstructed from configured columns. :rtype: list[Document]

asimilarity_search `async` ¶

asimilarity_search(query: str, k: int = 4, **kwargs: Any) -> list[Document]

Similarity search for a query string using the configured index.

:param query: Query text to embed and search. :type query: str :param k: Number of most similar documents. :type k: int

Kwargs¶

filter: Filter | None; Optional filter to apply to the search.
top_m: int; Number of top results to prefetch when re-ranking (default: 5 * k).

:return: Top-k documents. :rtype: list[Document]

asimilarity_search_with_score `async` ¶

asimilarity_search_with_score(
    query: str, k: int = 4, **kwargs: Any
) -> list[tuple[Document, float]]

Similarity search returning (document, distance) pairs.

:param query: Query text to embed and search. :type query: str :param k: Number of most similar documents. :type k: int

Kwargs¶

See :meth:asimilarity_search for supported kwargs.

:return: Top-k (document, distance) pairs. :rtype: list[tuple[Document, float]]

asimilarity_search_by_vector `async` ¶

asimilarity_search_by_vector(
    embedding: list[float], k: int = 4, **kwargs: Any
) -> list[Document]

Similarity search for a precomputed embedding vector.

:param embedding: The precomputed embedding vector to search for. :type embedding: list[float] :param k: Number of most similar documents. :type k: int

Kwargs¶

See :meth:asimilarity_search for supported kwargs.

:return: Top-k documents. :rtype: list[Document]

amax_marginal_relevance_search `async` ¶

amax_marginal_relevance_search(
    query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any
) -> list[Document]

MMR search for a query string.

:param query: The query string to search for. :type query: str :param k: Number of most similar documents to return. :type k: int :param fetch_k: Candidate pool size before MMR reranking. :type fetch_k: int :param lambda_mult: Diversity vs. relevance trade-off parameter. :type lambda_mult: float

Kwargs¶

See :meth:similarity_search for supported kwargs.

:return: Top-k documents. :rtype: list[Document]

amax_marginal_relevance_search_by_vector `async` ¶

amax_marginal_relevance_search_by_vector(
    embedding: list[float],
    k: int = 4,
    fetch_k: int = 20,
    lambda_mult: float = 0.5,
    **kwargs: Any,
) -> list[Document]

MMR search for a precomputed embedding vector.

:param embedding: The precomputed embedding vector to search for. :type embedding: list[float] :param k: Number of most similar documents to return. :type k: int :param fetch_k: Candidate pool size before MMR reranking. :type fetch_k: int :param lambda_mult: Diversity vs. relevance trade-off parameter. :type lambda_mult: float

Kwargs¶

See :meth:similarity_search for supported kwargs.

:return: Top-k documents. :rtype: list[Document]

from_documents `classmethod` ¶

from_documents(documents: list[Document], embedding: Embeddings, **kwargs: Any) -> Self

Return VectorStore initialized from documents and embeddings.

PARAMETER	DESCRIPTION
`documents`	List of `Document` objects to add to the `VectorStore`. TYPE: `list[Document]`
`embedding`	Embedding function to use. TYPE: `Embeddings`
`**kwargs`	Additional keyword arguments. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`Self`	`VectorStore` initialized from documents and embeddings.

from_texts `classmethod` ¶

from_texts(
    texts: list[str],
    embedding: Embeddings,
    metadatas: list[dict] | None = None,
    *,
    ids: list[str] | None = None,
    **kwargs: Any,
) -> Self

Return VectorStore initialized from texts and embeddings.

PARAMETER	DESCRIPTION
`texts`	Texts to add to the `VectorStore`. TYPE: `list[str]`
`embedding`	Embedding function to use. TYPE: `Embeddings`
`metadatas`	Optional list of metadatas associated with the texts. TYPE: `list[dict] \| None` DEFAULT: `None`
`ids`	Optional list of IDs associated with the texts. TYPE: `list[str] \| None` DEFAULT: `None`
`**kwargs`	Additional keyword arguments. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`VST`	`VectorStore` initialized from texts and embeddings.

add_documents ¶

add_documents(documents: list[Document], **kwargs: Any) -> list[str]

Add or update documents in the VectorStore.

PARAMETER	DESCRIPTION
`documents`	Documents to add to the `VectorStore`. TYPE: `list[Document]`
`**kwargs`	Additional keyword arguments. If kwargs contains IDs and documents contain ids, the IDs in the kwargs will receive precedence. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[str]`	List of IDs of the added texts.

add_texts ¶

add_texts(
    texts: Iterable[str],
    metadatas: list[dict] | None = None,
    *,
    ids: list[str] | None = None,
    **kwargs: Any,
) -> list[str]

Run more texts through the embeddings and add to the VectorStore.

PARAMETER	DESCRIPTION
`texts`	Iterable of strings to add to the `VectorStore`. TYPE: `Iterable[str]`
`metadatas`	Optional list of metadatas associated with the texts. TYPE: `list[dict] \| None` DEFAULT: `None`
`ids`	Optional list of IDs associated with the texts. TYPE: `list[str] \| None` DEFAULT: `None`
`**kwargs`	`VectorStore` specific parameters. One of the kwargs should be `ids` which is a list of ids associated with the texts. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[str]`	List of IDs from adding the texts into the `VectorStore`.

RAISES	DESCRIPTION
`ValueError`	If the number of metadatas does not match the number of texts.
`ValueError`	If the number of IDs does not match the number of texts.

delete ¶

delete(ids: list[str] | None = None, **kwargs: Any) -> bool | None

Delete by vector ID or other criteria.

PARAMETER	DESCRIPTION
`ids`	List of IDs to delete. If `None`, delete all. TYPE: `list[str] \| None` DEFAULT: `None`
`**kwargs`	Other keyword arguments that subclasses might use. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`bool \| None`	`True` if deletion is successful, `False` otherwise, `None` if not implemented.

get_by_ids ¶

get_by_ids(ids: Sequence[str]) -> list[Document]

Get documents by their IDs.

The returned documents are expected to have the ID field set to the ID of the document in the vector store.

Fewer documents may be returned than requested if some IDs are not found or if there are duplicated IDs.

Users should not assume that the order of the returned documents matches the order of the input IDs. Instead, users should rely on the ID field of the returned documents.

This method should NOT raise exceptions if no documents are found for some IDs.

PARAMETER	DESCRIPTION
`ids`	List of IDs to retrieve. TYPE: `Sequence[str]`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects.

search ¶

search(query: str, search_type: str, **kwargs: Any)

Return docs most similar to query using a specified search type.

PARAMETER	DESCRIPTION
`query`	Input text. TYPE: `str`
`search_type`	Type of search to perform. Can be `'similarity'`, `'mmr'`, or `'similarity_score_threshold'`. TYPE: `str`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects most similar to the query.

RAISES	DESCRIPTION
`ValueError`	If `search_type` is not one of `'similarity'`, `'mmr'`, or `'similarity_score_threshold'`.

similarity_search ¶

similarity_search(query: str, k: int = 4, **kwargs: Any) -> list[Document]

Return docs most similar to query.

PARAMETER	DESCRIPTION
`query`	Input text. TYPE: `str`
`k`	Number of `Document` objects to return. TYPE: `int` DEFAULT: `4`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects most similar to the query.

similarity_search_with_score ¶

similarity_search_with_score(
    query: str, k: int = 4, **kwargs: Any
) -> list[tuple[Document, float]]

Run similarity search with distance.

PARAMETER	DESCRIPTION
`*args`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `()`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[tuple[Document, float]]`	List of tuples of `(doc, similarity_score)`.

similarity_search_by_vector ¶

similarity_search_by_vector(
    embedding: list[float], k: int = 4, **kwargs: Any
) -> list[Document]

Return docs most similar to embedding vector.

PARAMETER	DESCRIPTION
`embedding`	Embedding to look up documents similar to. TYPE: `list[float]`
`k`	Number of `Document` objects to return. TYPE: `int` DEFAULT: `4`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects most similar to the query vector.

similarity_search_with_relevance_scores ¶

similarity_search_with_relevance_scores(query, k=4, **kwargs)

Return docs and relevance scores in the range [0, 1].

0 is dissimilar, 1 is most similar.

PARAMETER	DESCRIPTION
`query`	Input text. TYPE: `str`
`k`	Number of `Document` objects to return. TYPE: `int` DEFAULT: `4`
`**kwargs`	Kwargs to be passed to similarity search. Should include `score_threshold`, an optional floating point value between `0` to `1` to filter the resulting set of retrieved docs. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[tuple[Document, float]]`	List of tuples of `(doc, similarity_score)`.

max_marginal_relevance_search ¶

max_marginal_relevance_search(
    query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any
) -> list[Document]

Return docs selected using the maximal marginal relevance.

Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

PARAMETER	DESCRIPTION
`query`	Text to look up documents similar to. TYPE: `str`
`k`	Number of `Document` objects to return. TYPE: `int` DEFAULT: `4`
`fetch_k`	Number of `Document` objects to fetch to pass to MMR algorithm. TYPE: `int` DEFAULT: `20`
`lambda_mult`	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. TYPE: `float` DEFAULT: `0.5`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects selected by maximal marginal relevance.

max_marginal_relevance_search_by_vector ¶

max_marginal_relevance_search_by_vector(
    embedding: list[float],
    k: int = 4,
    fetch_k: int = 20,
    lambda_mult: float = 0.5,
    **kwargs: Any,
) -> list[Document]

Return docs selected using the maximal marginal relevance.

Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

PARAMETER	DESCRIPTION
`embedding`	Embedding to look up documents similar to. TYPE: `list[float]`
`k`	Number of `Document` objects to return. TYPE: `int` DEFAULT: `4`
`fetch_k`	Number of `Document` objects to fetch to pass to MMR algorithm. TYPE: `int` DEFAULT: `20`
`lambda_mult`	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. TYPE: `float` DEFAULT: `0.5`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects selected by maximal marginal relevance.

AzurePGVectorStore ¶

Bases: BaseModel, VectorStore

LangChain VectorStore backed by Azure Database for PostgreSQL (sync).

The store validates or creates the backing table on initialization, and optionally discovers an existing vector index configuration. It supports inserting, deleting, fetching by id, similarity search, and MMR search.

Fields such as schema_name, table_name, and column names control the schema layout. embedding_type, embedding_dimension, and embedding_index describe the vector column and its index behavior.

Metadata can be stored in a single JSONB column by passing a string (default "metadata"), in multiple typed columns via a list of strings/tuples, or disabled by setting metadata_columns=None.

:param embedding: The embedding model to use for embedding vector generation. :type embedding: Embeddings | None :param connection: The database connection or connection pool to use. :type connection: Connection | ConnectionPool :param schema_name: The name of the database schema to use. :type schema_name: str :param table_name: The name of the database table to use. :type table_name: str :param id_column: The name of the column containing document IDs (UUIDs). :type id_column: str :param content_column: The name of the column containing document content. :type content_column: str :param embedding_column: The name of the column containing document embeddings. :type embedding_column: str :param embedding_type: The type of the embedding vectors. :type embedding_type: VectorType | None :param embedding_dimension: The dimensionality of the embedding vectors. :type embedding_dimension: PositiveInt | None :param embedding_index: The algorithm used for indexing the embedding vectors. :type embedding_index: Algorithm | None :param _embedding_index_name: (internal) The name of the discovered or created index. :type _embedding_index_name: str | None :param metadata_columns: The columns to use for storing metadata. :type metadata_columns: list[str] | list[tuple[str, str]] | str | None

METHOD	DESCRIPTION
`search`	Return docs most similar to query using a specified search type.
`similarity_search_with_relevance_scores`	Return docs and relevance scores in the range `[0, 1]`.
`as_retriever`	Return `VectorStoreRetriever` initialized from this `VectorStore`.
`create_index`	Create the vector index on the embedding column (if not already exists).
`reindex`	Reindex the existing vector index.
`from_documents`	Create a store and add documents in one step.
`from_texts`	Create a store and add texts with optional metadata.
`add_documents`	Insert or upsert a batch of LangChain `documents`.
`add_texts`	Insert or upsert `texts` with optional `metadatas` and embeddings.
`delete`	Delete by ids or truncate the table.
`get_by_ids`	Fetch documents by their `ids`.
`similarity_search`	Similarity search for a query string using the configured index.
`similarity_search_with_score`	Similarity search returning (document, distance) pairs.
`similarity_search_by_vector`	Similarity search for a precomputed embedding vector.
`max_marginal_relevance_search`	MMR search for a query string.
`max_marginal_relevance_search_by_vector`	MMR search for a precomputed embedding vector.
`afrom_documents`	Async return `VectorStore` initialized from documents and embeddings.
`afrom_texts`	Async return `VectorStore` initialized from texts and embeddings.
`aadd_documents`	Async run more documents through the embeddings and add to the `VectorStore`.
`aadd_texts`	Async run more texts through the embeddings and add to the `VectorStore`.
`adelete`	Async delete by vector ID or other criteria.
`aget_by_ids`	Async get documents by their IDs.
`asearch`	Async return docs most similar to query using a specified search type.
`asimilarity_search`	Async return docs most similar to query.
`asimilarity_search_with_score`	Async run similarity search with distance.
`asimilarity_search_by_vector`	Async return docs most similar to embedding vector.
`asimilarity_search_with_relevance_scores`	Async return docs and relevance scores in the range `[0, 1]`.
`amax_marginal_relevance_search`	Async return docs selected using the maximal marginal relevance.
`amax_marginal_relevance_search_by_vector`	Async return docs selected using the maximal marginal relevance.

embeddings `property` ¶

embeddings: Embeddings | None

Access the query embedding object if available.

search ¶

search(query: str, search_type: str, **kwargs: Any) -> list[Document]

Return docs most similar to query using a specified search type.

PARAMETER	DESCRIPTION
`query`	Input text. TYPE: `str`
`search_type`	Type of search to perform. Can be `'similarity'`, `'mmr'`, or `'similarity_score_threshold'`. TYPE: `str`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects most similar to the query.

RAISES	DESCRIPTION
`ValueError`	If `search_type` is not one of `'similarity'`, `'mmr'`, or `'similarity_score_threshold'`.

similarity_search_with_relevance_scores ¶

similarity_search_with_relevance_scores(
    query: str, k: int = 4, **kwargs: Any
) -> list[tuple[Document, float]]

Return docs and relevance scores in the range [0, 1].

0 is dissimilar, 1 is most similar.

PARAMETER	DESCRIPTION
`query`	Input text. TYPE: `str`
`k`	Number of `Document` objects to return. TYPE: `int` DEFAULT: `4`
`**kwargs`	Kwargs to be passed to similarity search. Should include `score_threshold`, an optional floating point value between `0` to `1` to filter the resulting set of retrieved docs. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[tuple[Document, float]]`	List of tuples of `(doc, similarity_score)`.

as_retriever ¶

as_retriever(**kwargs: Any) -> VectorStoreRetriever

Return VectorStoreRetriever initialized from this VectorStore.

PARAMETER DESCRIPTION

**kwargs

Keyword arguments to pass to the search function.

Can include:

search_type: Defines the type of search that the Retriever should perform. Can be 'similarity' (default), 'mmr', or 'similarity_score_threshold'.
search_kwargs: Keyword arguments to pass to the search function.

Can include things like:
- k: Amount of documents to return (Default: 4)
- score_threshold: Minimum relevance threshold for similarity_score_threshold
- fetch_k: Amount of documents to pass to MMR algorithm (Default: 20)
- lambda_mult: Diversity of results returned by MMR; 1 for minimum diversity and 0 for maximum. (Default: 0.5)
- filter: Filter by document metadata

TYPE: Any DEFAULT: {}

RETURNS	DESCRIPTION
`VectorStoreRetriever`	Retriever class for `VectorStore`.

Examples:

# Retrieve more documents with higher diversity
# Useful if your dataset has many similar documents
docsearch.as_retriever(
    search_type="mmr", search_kwargs={"k": 6, "lambda_mult": 0.25}
)

# Fetch more documents for the MMR algorithm to consider
# But only return the top 5
docsearch.as_retriever(search_type="mmr", search_kwargs={"k": 5, "fetch_k": 50})

# Only retrieve documents that have a relevance score
# Above a certain threshold
docsearch.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={"score_threshold": 0.8},
)

# Only get the single most similar document from the dataset
docsearch.as_retriever(search_kwargs={"k": 1})

# Use a filter to only retrieve documents from a specific paper
docsearch.as_retriever(
    search_kwargs={"filter": {"paper_title": "GPT-4 Technical Report"}}
)

create_index ¶

create_index(*, concurrently: bool = False) -> bool

Create the vector index on the embedding column (if not already exists).

Builds a vector index for the configured embedding_column using the algorithm specified by embedding_index (DiskANN, HNSW or IVFFlat). The effective index type name is inferred from the concrete Algorithm instance and the index name is generated as <table>_<column>_<type>_idx. If an index has already been discovered (_embedding_index_name is not None) the operation is skipped.

Prior to executing create index the per-build tuning parameters (returned by :meth:Algorithm.index_settings) are applied via set GUCs so they only affect this session. Build-time options (returned by :meth:Algorithm.build_settings) are appended in a with (...) clause.

For quantized operator classes: - halfvec_* (scalar quantization) casts both the stored column and future query vectors to halfvec(dim). - bit_* (binary quantization) wraps the column with binary_quantize(col)::bit(dim). Otherwise the raw column is indexed.

:param concurrently: When True uses create index concurrently to avoid long write-locks at the expense of a slower build. :type concurrently: bool :return: True if the index was created, False when an existing index prevented creation. :rtype: bool :raises AssertionError: If required attributes (embedding_index or embedding_dimension) are unexpectedly None.

reindex ¶

reindex(*, concurrently: bool = False, verbose: bool = False) -> bool

Reindex the existing vector index.

Issues a reindex (concurrently <bool>, verbose <bool>) index command for the previously discovered or created index (tracked in _embedding_index_name). The session-level index tuning GUCs (returned by :meth:Algorithm.index_settings) are applied beforehand to influence the reindex process (useful for algorithms whose maintenance cost or accuracy depends on these settings).

:param concurrently: When True performs a concurrent reindex to minimize locking, trading speed for availability. :type concurrently: bool :param verbose: When True enables PostgreSQL verbose output, which may aid in diagnosing build performance issues. :type verbose: bool :return: True if reindex succeeded, False if no index existed. :rtype: bool :raises AssertionError: If embedding_index is unexpectedly None.

from_documents `classmethod` ¶

from_documents(documents: list[Document], embedding: Embeddings, **kwargs: Any) -> Self

Create a store and add documents in one step.

:param documents: The list of documents to add to the store. :type documents: list[Document] :param embedding: The embedding model to use for embedding vector generation. :type embedding: Embeddings

Kwargs¶

connection: (required) psycopg Connection or ConnectionPool
schema_name, table_name, id_column, content_column, embedding_column: customize table/column names
embedding_type: VectorType of the embedding column
embedding_dimension: dimension of the vector column
embedding_index: Algorithm describing the vector index
metadata_columns: str | list[str | (str, str)] | None to configure metadata storage
on_conflict_update (passed to add): bool to upsert existing rows

:return: The created vector store instance. :rtype: Self

from_texts `classmethod` ¶

from_texts(
    texts: list[str],
    embedding: Embeddings,
    metadatas: list[dict] | None = None,
    *,
    ids: list[str] | None = None,
    **kwargs: Any,
) -> Self

Create a store and add texts with optional metadata.

:param texts: The list of texts to add to the store. :type texts: list[str] :param embedding: The embedding model to use for embedding vector generation. :type embedding: Embeddings :param metadatas: The list of metadata dictionaries corresponding to each text. :type metadatas: list[dict] | None :param ids: The list of custom IDs corresponding to each text. When ids are not provided, UUIDs are generated. :type ids: list[str] | None

Kwargs¶

See :meth:from_documents for required and/or supported kwargs.

:return: The created vector store instance. :rtype: Self

add_documents ¶

add_documents(documents: list[Document], **kwargs: Any) -> list[str]

Insert or upsert a batch of LangChain documents.

Kwargs¶

ids: list[str] custom ids, otherwise UUIDs or doc.id are used
on_conflict_update: bool to update existing rows on id conflict

:return: Inserted ids. :rtype: list[str]

add_texts ¶

add_texts(
    texts: Iterable[str],
    metadatas: list[dict] | None = None,
    *,
    ids: list[str] | None = None,
    **kwargs: Any,
) -> list[str]

Insert or upsert texts with optional metadatas and embeddings.

If an embeddings model is present, embeddings are computed and stored. When metadata_columns is a string, metadata is written as JSONB; otherwise only provided keys matching configured columns are stored.

Kwargs¶

ids: list[str] custom ids, otherwise UUIDs are used
on_conflict_update: bool to update existing rows on id conflict

:return: Inserted ids. :rtype: list[str] :raises ValueError: If the length of 'metadatas', 'texts', and 'ids' do not match.

delete ¶

delete(ids: list[str] | None = None, **kwargs: Any) -> bool | None

Delete by ids or truncate the table.

If ids is None, the table is truncated.

Kwargs¶

restart: bool to restart (when True) or continue (when False) identity, when truncating
cascade: bool to cascade (when True) or restrict (when False), when truncating

:return: True if the operation was successful, False otherwise. :rtype: bool | None

get_by_ids ¶

get_by_ids(ids: Sequence[str]) -> list[Document]

Fetch documents by their ids.

:param ids: Sequence of string ids. :type ids: Sequence[str] :return: Documents with metadata reconstructed from configured columns. :rtype: list[Document]

similarity_search ¶

similarity_search(query: str, k: int = 4, **kwargs: Any) -> list[Document]

Similarity search for a query string using the configured index.

:param query: Query text to embed and search. :type query: str :param k: Number of most similar documents. :type k: int

Kwargs¶

filter: Filter | None; Optional filter to apply to the search.
top_m: int; Number of top results to prefetch when re-ranking (default: 5 * k).

:return: Top-k documents. :rtype: list[Document]

similarity_search_with_score ¶

similarity_search_with_score(
    query: str, k: int = 4, **kwargs: Any
) -> list[tuple[Document, float]]

Similarity search returning (document, distance) pairs.

:param query: Query text to embed and search. :type query: str :param k: Number of most similar documents (and their distances). :type k: int

Kwargs¶

See :meth:similarity_search for supported kwargs.

:return: Top-k (document, distance) pairs. :rtype: list[tuple[Document, float]]

similarity_search_by_vector ¶

similarity_search_by_vector(
    embedding: list[float], k: int = 4, **kwargs: Any
) -> list[Document]

Similarity search for a precomputed embedding vector.

:param embedding: The precomputed embedding vector to search for. :type embedding: list[float] :param k: Number of most similar documents. :type k: int

Kwargs¶

See :meth:similarity_search for supported kwargs.

:return: Top-k documents. :rtype: list[Document]

max_marginal_relevance_search ¶

max_marginal_relevance_search(
    query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any
) -> list[Document]

MMR search for a query string.

:param query: The query string to search for. :type query: str :param k: Number of most similar documents to return. :type k: int :param fetch_k: Candidate pool size before MMR reranking. :type fetch_k: int :param lambda_mult: Diversity vs. relevance trade-off parameter. :type lambda_mult: float

Kwargs¶

See :meth:similarity_search for supported kwargs.

:return: Top-k documents. :rtype: list[Document]

max_marginal_relevance_search_by_vector ¶

max_marginal_relevance_search_by_vector(
    embedding: list[float],
    k: int = 4,
    fetch_k: int = 20,
    lambda_mult: float = 0.5,
    **kwargs: Any,
) -> list[Document]

MMR search for a precomputed embedding vector.

:param embedding: The precomputed embedding vector to search for. :type embedding: list[float] :param k: Number of most similar documents to return. :type k: int :param fetch_k: Candidate pool size before MMR reranking. :type fetch_k: int :param lambda_mult: Diversity vs. relevance trade-off parameter. :type lambda_mult: float

Kwargs¶

See :meth:similarity_search for supported kwargs.

:return: Top-k documents. :rtype: list[Document]

afrom_documents `async` `classmethod` ¶

afrom_documents(
    documents: list[Document], embedding: Embeddings, **kwargs: Any
) -> Self

Async return VectorStore initialized from documents and embeddings.

PARAMETER	DESCRIPTION
`documents`	List of `Document` objects to add to the `VectorStore`. TYPE: `list[Document]`
`embedding`	Embedding function to use. TYPE: `Embeddings`
`**kwargs`	Additional keyword arguments. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`Self`	`VectorStore` initialized from documents and embeddings.

afrom_texts `async` `classmethod` ¶

afrom_texts(
    texts: list[str],
    embedding: Embeddings,
    metadatas: list[dict] | None = None,
    *,
    ids: list[str] | None = None,
    **kwargs: Any,
) -> Self

Async return VectorStore initialized from texts and embeddings.

PARAMETER	DESCRIPTION
`texts`	Texts to add to the `VectorStore`. TYPE: `list[str]`
`embedding`	Embedding function to use. TYPE: `Embeddings`
`metadatas`	Optional list of metadatas associated with the texts. TYPE: `list[dict] \| None` DEFAULT: `None`
`ids`	Optional list of IDs associated with the texts. TYPE: `list[str] \| None` DEFAULT: `None`
`**kwargs`	Additional keyword arguments. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`Self`	`VectorStore` initialized from texts and embeddings.

aadd_documents `async` ¶

aadd_documents(documents: list[Document], **kwargs: Any) -> list[str]

Async run more documents through the embeddings and add to the VectorStore.

PARAMETER	DESCRIPTION
`documents`	Documents to add to the `VectorStore`. TYPE: `list[Document]`
`**kwargs`	Additional keyword arguments. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[str]`	List of IDs of the added texts.

aadd_texts `async` ¶

aadd_texts(
    texts: Iterable[str],
    metadatas: list[dict] | None = None,
    *,
    ids: list[str] | None = None,
    **kwargs: Any,
) -> list[str]

Async run more texts through the embeddings and add to the VectorStore.

PARAMETER	DESCRIPTION
`texts`	Iterable of strings to add to the `VectorStore`. TYPE: `Iterable[str]`
`metadatas`	Optional list of metadatas associated with the texts. TYPE: `list[dict] \| None` DEFAULT: `None`
`ids`	Optional list TYPE: `list[str] \| None` DEFAULT: `None`
`**kwargs`	`VectorStore` specific parameters. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[str]`	List of IDs from adding the texts into the `VectorStore`.

RAISES	DESCRIPTION
`ValueError`	If the number of metadatas does not match the number of texts.
`ValueError`	If the number of IDs does not match the number of texts.

adelete `async` ¶

adelete(ids: list[str] | None = None, **kwargs: Any) -> bool | None

Async delete by vector ID or other criteria.

PARAMETER	DESCRIPTION
`ids`	List of IDs to delete. If `None`, delete all. TYPE: `list[str] \| None` DEFAULT: `None`
`**kwargs`	Other keyword arguments that subclasses might use. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`bool \| None`	`True` if deletion is successful, `False` otherwise, `None` if not implemented.

aget_by_ids `async` ¶

aget_by_ids(ids: Sequence[str]) -> list[Document]

Async get documents by their IDs.

The returned documents are expected to have the ID field set to the ID of the document in the vector store.

Fewer documents may be returned than requested if some IDs are not found or if there are duplicated IDs.

Users should not assume that the order of the returned documents matches the order of the input IDs. Instead, users should rely on the ID field of the returned documents.

This method should NOT raise exceptions if no documents are found for some IDs.

PARAMETER	DESCRIPTION
`ids`	List of IDs to retrieve. TYPE: `Sequence[str]`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects.

asearch `async` ¶

asearch(query: str, search_type: str, **kwargs: Any) -> list[Document]

Async return docs most similar to query using a specified search type.

PARAMETER	DESCRIPTION
`query`	Input text. TYPE: `str`
`search_type`	Type of search to perform. Can be `'similarity'`, `'mmr'`, or `'similarity_score_threshold'`. TYPE: `str`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects most similar to the query.

RAISES	DESCRIPTION
`ValueError`	If `search_type` is not one of `'similarity'`, `'mmr'`, or `'similarity_score_threshold'`.

asimilarity_search `async` ¶

asimilarity_search(query: str, k: int = 4, **kwargs: Any) -> list[Document]

Async return docs most similar to query.

PARAMETER	DESCRIPTION
`query`	Input text. TYPE: `str`
`k`	Number of `Document` objects to return. TYPE: `int` DEFAULT: `4`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects most similar to the query.

asimilarity_search_with_score `async` ¶

asimilarity_search_with_score(
    *args: Any, **kwargs: Any
) -> list[tuple[Document, float]]

Async run similarity search with distance.

PARAMETER	DESCRIPTION
`*args`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `()`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[tuple[Document, float]]`	List of tuples of `(doc, similarity_score)`.

asimilarity_search_by_vector `async` ¶

asimilarity_search_by_vector(
    embedding: list[float], k: int = 4, **kwargs: Any
) -> list[Document]

Async return docs most similar to embedding vector.

PARAMETER	DESCRIPTION
`embedding`	Embedding to look up documents similar to. TYPE: `list[float]`
`k`	Number of `Document` objects to return. TYPE: `int` DEFAULT: `4`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects most similar to the query vector.

asimilarity_search_with_relevance_scores `async` ¶

asimilarity_search_with_relevance_scores(
    query: str, k: int = 4, **kwargs: Any
) -> list[tuple[Document, float]]

Async return docs and relevance scores in the range [0, 1].

0 is dissimilar, 1 is most similar.

PARAMETER	DESCRIPTION
`query`	Input text. TYPE: `str`
`k`	Number of `Document` objects to return. TYPE: `int` DEFAULT: `4`
`**kwargs`	Kwargs to be passed to similarity search. Should include `score_threshold`, an optional floating point value between `0` to `1` to filter the resulting set of retrieved docs. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[tuple[Document, float]]`	List of tuples of `(doc, similarity_score)`

amax_marginal_relevance_search `async` ¶

amax_marginal_relevance_search(
    query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any
) -> list[Document]

Async return docs selected using the maximal marginal relevance.

Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

PARAMETER	DESCRIPTION
`query`	Text to look up documents similar to. TYPE: `str`
`k`	Number of `Document` objects to return. TYPE: `int` DEFAULT: `4`
`fetch_k`	Number of `Document` objects to fetch to pass to MMR algorithm. TYPE: `int` DEFAULT: `20`
`lambda_mult`	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. TYPE: `float` DEFAULT: `0.5`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects selected by maximal marginal relevance.

amax_marginal_relevance_search_by_vector `async` ¶

amax_marginal_relevance_search_by_vector(
    embedding: list[float],
    k: int = 4,
    fetch_k: int = 20,
    lambda_mult: float = 0.5,
    **kwargs: Any,
) -> list[Document]

Async return docs selected using the maximal marginal relevance.

Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

PARAMETER	DESCRIPTION
`embedding`	Embedding to look up documents similar to. TYPE: `list[float]`
`k`	Number of `Document` objects to return. TYPE: `int` DEFAULT: `4`
`fetch_k`	Number of `Document` objects to fetch to pass to MMR algorithm. TYPE: `int` DEFAULT: `20`
`lambda_mult`	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. TYPE: `float` DEFAULT: `0.5`
`**kwargs`	Arguments to pass to the search method. TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`list[Document]`	List of `Document` objects selected by maximal marginal relevance.

async_check_connection `async` ¶

async_check_connection(
    conn: AsyncConnection, /, required_extensions: list[Extension] = []
)

Check if the connection to Azure Database for PostgreSQL is valid and required extensions are installed.

:param conn: Async connection to the Azure Database for PostgreSQL. :type conn: AsyncConnection :param required_extensions: List of required extensions to check if they are installed. :type required_extensions: list[Extension] :raises RuntimeError: If the connection check fails or required extensions are not installed.

check_connection ¶

check_connection(conn: Connection, /, required_extensions: list[Extension] = [])

Check if the connection to Azure Database for PostgreSQL is valid and required extensions are installed.

:param conn: Connection to the Azure Database for PostgreSQL. :type conn: Connection :param required_extensions: List of required extensions to check if they are installed. :type required_extensions: list[Extension] :raises RuntimeError: If the connection check fails or required extensions are not installed.

create_extensions ¶

create_extensions(conn: Connection, /, required_extensions: list[Extension] = [])

Create required extensions in the Azure Database for PostgreSQL connection.

:param conn: Connection to the Azure Database for PostgreSQL. :type conn: Connection :param required_extensions: List of required extensions to create. :type required_extensions: list[Extension] :raises Exception: If the connection is not valid or if an error occurs during extension creation.

langchain-azure-postgresql¶

langchain_azure_postgresql ¶

HNSW ¶

Notes:¶

index_settings ¶

build_settings ¶

default_search_params ¶

Algorithm ¶

default_search_params abstractmethod ¶

build_settings abstractmethod ¶

index_settings ¶

AsyncAzurePGConnectionPool ¶

AsyncConnectionInfo ¶

AzurePGConnectionPool ¶

BasicAuth ¶

ConnectionInfo ¶

DiskANN ¶

Notes:¶

index_settings ¶

build_settings ¶

default_search_params ¶

DiskANNIterativeScanMode ¶

DiskANNSearchParams ¶

search_settings ¶

Extension ¶

HNSWIterativeScanMode ¶

HNSWSearchParams ¶

search_settings ¶

IVFFlat ¶

index_settings ¶

build_settings ¶

default_search_params ¶

IVFFlatIterativeScanMode ¶

IVFFlatSearchParams ¶

search_settings ¶

SSLMode ¶

VectorOpClass ¶

to_operator ¶

VectorType ¶

AsyncAzurePGVectorStore ¶

embeddings property ¶

asearch async ¶

asimilarity_search_with_relevance_scores async ¶

as_retriever ¶

create_index async ¶

reindex async ¶

afrom_documents async classmethod ¶

Kwargs¶

afrom_texts async classmethod ¶

Kwargs¶

aadd_documents async ¶

Kwargs¶

aadd_texts async ¶

Kwargs¶

adelete async ¶

Kwargs¶

aget_by_ids async ¶

asimilarity_search async ¶

Kwargs¶

asimilarity_search_with_score async ¶

Kwargs¶

asimilarity_search_by_vector async ¶

Kwargs¶

amax_marginal_relevance_search async ¶

Kwargs¶

amax_marginal_relevance_search_by_vector async ¶

Kwargs¶

from_documents classmethod ¶

from_texts classmethod ¶

add_documents ¶

add_texts ¶

delete ¶

get_by_ids ¶

search ¶

similarity_search ¶

similarity_search_with_score ¶

similarity_search_by_vector ¶

similarity_search_with_relevance_scores ¶

max_marginal_relevance_search ¶

max_marginal_relevance_search_by_vector ¶

`langchain-azure-postgresql`¶

default_search_params `abstractmethod` ¶

build_settings `abstractmethod` ¶

embeddings `property` ¶

asearch `async` ¶

asimilarity_search_with_relevance_scores `async` ¶

create_index `async` ¶

reindex `async` ¶

afrom_documents `async` `classmethod` ¶

afrom_texts `async` `classmethod` ¶

aadd_documents `async` ¶

aadd_texts `async` ¶

adelete `async` ¶

aget_by_ids `async` ¶

asimilarity_search `async` ¶

asimilarity_search_with_score `async` ¶

asimilarity_search_by_vector `async` ¶

amax_marginal_relevance_search `async` ¶

amax_marginal_relevance_search_by_vector `async` ¶

from_documents `classmethod` ¶

from_texts `classmethod` ¶

embeddings `property` ¶

from_documents `classmethod` ¶

from_texts `classmethod` ¶

afrom_documents `async` `classmethod` ¶

afrom_texts `async` `classmethod` ¶

aadd_documents `async` ¶

aadd_texts `async` ¶

adelete `async` ¶

aget_by_ids `async` ¶

asearch `async` ¶

asimilarity_search `async` ¶

asimilarity_search_with_score `async` ¶

asimilarity_search_by_vector `async` ¶

asimilarity_search_with_relevance_scores `async` ¶

amax_marginal_relevance_search `async` ¶

amax_marginal_relevance_search_by_vector `async` ¶

async_check_connection `async` ¶