`langchain-mongodb`¶

Integrate your operational database and vector search in a single, unified, fully managed platform with full vector database capabilities on MongoDB Atlas.

Store your operational data, metadata, and vector embeddings in oue VectorStore, MongoDBAtlasVectorSearch. Insert into a Chain via a Vector, FullText, or Hybrid Retriever.

Modules:

Name	Description
`agent_toolkit`
`cache`	LangChain MongoDB Caches.
`chat_message_histories`
`docstores`
`graphrag`
`index`	Search Index Commands
`indexes`
`loaders`
`pipelines`	Aggregation pipeline components used in Atlas Full-Text, Vector, and Hybrid Search
`retrievers`	Search Retrievers of various types.
`utils`	Various Utility Functions
`vectorstores`

Classes:

Name	Description
`MongoDBAtlasSemanticCache`	MongoDB Atlas Semantic cache.
`MongoDBCache`	MongoDB Atlas cache
`MongoDBChatMessageHistory`	Chat message history that stores history in MongoDB.
`MongoDBAtlasVectorSearch`	MongoDB Atlas vector store integration.

MongoDBAtlasSemanticCache ¶

Bases: BaseCache, MongoDBAtlasVectorSearch

MongoDB Atlas Semantic cache.

A Cache backed by a MongoDB Atlas server with vector-store support

Methods:

Name	Description
`add_texts`	Add texts, create embeddings, and add to the Collection and index.
`delete`	Delete documents from VectorStore by ids.
`get_by_ids`	Get documents by their IDs.
`aget_by_ids`	Async get documents by their IDs.
`adelete`	Delete by vector ID or other criteria.
`aadd_texts`	Async run more texts through the embeddings and add to the vectorstore.
`add_documents`	Add documents to the vectorstore.
`aadd_documents`	Async run more documents through the embeddings and add to the vectorstore.
`search`	Return docs most similar to query using a specified search type.
`asearch`	Async return docs most similar to query using a specified search type.
`similarity_search`	Return MongoDB documents most similar to the given query.
`similarity_search_with_score`	Return MongoDB documents most similar to the given query and their scores.
`asimilarity_search_with_score`	Async run similarity search with distance.
`similarity_search_with_relevance_scores`	Return docs and relevance scores in the range [0, 1].
`asimilarity_search_with_relevance_scores`	Async return docs and relevance scores in the range [0, 1].
`asimilarity_search`	Async return docs most similar to query.
`similarity_search_by_vector`	Return docs most similar to embedding vector.
`asimilarity_search_by_vector`	Async return docs most similar to embedding vector.
`max_marginal_relevance_search`	Return documents selected using the maximal marginal relevance.
`amax_marginal_relevance_search`	Async return docs selected using the maximal marginal relevance.
`max_marginal_relevance_search_by_vector`	Return docs selected using the maximal marginal relevance.
`amax_marginal_relevance_search_by_vector`	Return docs selected using the maximal marginal relevance.
`from_documents`	Return VectorStore initialized from documents and embeddings.
`afrom_documents`	Async return VectorStore initialized from documents and embeddings.
`from_texts`	Construct a `MongoDB Atlas Vector Search` vector store from raw documents.
`afrom_texts`	Async return VectorStore initialized from texts and embeddings.
`as_retriever`	Return VectorStoreRetriever initialized from this VectorStore.
`from_connection_string`	Construct a `MongoDB Atlas Vector Search` vector store
`close`	Close the resources used by the MongoDBAtlasVectorSearch.
`bulk_embed_and_insert_texts`	Bulk insert single batch of texts, embeddings, and optionally ids.
`create_vector_search_index`	Creates a MongoDB Atlas vectorSearch index for the VectorStore
`alookup`	Async look up based on prompt and llm_string.
`aupdate`	Async update cache based on prompt and llm_string.
`aclear`	Async clear cache that can take additional keyword arguments.
`__init__`	Initialize Atlas VectorSearch Cache.
`lookup`	Look up based on prompt and llm_string.
`update`	Update cache based on prompt and llm_string.
`clear`	Clear cache that can take additional keyword arguments.

add_texts ¶

add_texts(
    texts: Iterable[str],
    metadatas: Optional[List[Dict[str, Any]]] = None,
    ids: Optional[List[str]] = None,
    batch_size: int = DEFAULT_INSERT_BATCH_SIZE,
    **kwargs: Any
) -> List[str]

Add texts, create embeddings, and add to the Collection and index.

Important notes on ids

If _id or id is a key in the metadatas dicts, one must pop them and provide as separate list.
They must be unique.
If they are not provided, the VectorStore will create unique ones, stored as bson.ObjectIds internally, and strings in Langchain. These will appear in Document.metadata with key, '_id'.

Parameters:

Name	Type	Description	Default
`texts`	`Iterable[str]`	Iterable of strings to add to the vectorstore.	required
`metadatas`	`Optional[List[Dict[str, Any]]]`	Optional list of metadatas associated with the texts.	`None`
`ids`	`Optional[List[str]]`	Optional list of unique ids that will be used as index in VectorStore. See note on ids.	`None`
`batch_size`	`int`	Number of documents to insert at a time. Tuning this may help with performance and sidestep MongoDB limits.	`DEFAULT_INSERT_BATCH_SIZE`

Returns:

Type	Description
`List[str]`	List of ids added to the vectorstore.

delete ¶

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

Delete documents from VectorStore by ids.

Parameters:

Name	Type	Description	Default
`ids`	`Optional[List[str]]`	List of ids to delete.	`None`
`**kwargs`	`Any`	Other keyword arguments passed to Collection.delete_many()	`{}`

Returns:

Type	Description
`Optional[bool]`	Optional[bool]: True if deletion is successful,
`Optional[bool]`	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.

Parameters:

Name	Type	Description	Default
`ids`	`Sequence[str]`	List of ids to retrieve.	required

Returns:

Type	Description
`list[Document]`	List of Documents.

.. versionadded:: 0.6.0

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.

Parameters:

Name	Type	Description	Default
`ids`	`Sequence[str]`	List of ids to retrieve.	required

Returns:

Type	Description
`list[Document]`	List of Documents.

Added in version 0.2.11

adelete `async` ¶

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

Delete by vector ID or other criteria.

Parameters:

Name	Type	Description	Default
`ids`	`Optional[List[str]]`	List of ids to delete.	`None`
`**kwargs`	`Any`	Other keyword arguments that subclasses might use.	`{}`

Returns:

Type	Description
`Optional[bool]`	Optional[bool]: True if deletion is successful,
`Optional[bool]`	False otherwise, None if not implemented.

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.

Parameters:

Name	Type	Description	Default
`texts`	`Iterable[str]`	Iterable of strings to add to the vectorstore.	required
`metadatas`	`list[dict] \| None`	Optional list of metadatas associated with the texts. Default is None.	`None`
`ids`	`list[str] \| None`	Optional list	`None`
`**kwargs`	`Any`	vectorstore specific parameters.	`{}`

Returns:

Type	Description
`list[str]`	List of ids from adding the texts into the vectorstore.

Raises:

Type	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.

add_documents ¶

add_documents(
    documents: List[Document],
    ids: Optional[List[str]] = None,
    batch_size: int = DEFAULT_INSERT_BATCH_SIZE,
    **kwargs: Any
) -> List[str]

Add documents to the vectorstore.

Parameters:

Name	Type	Description	Default
`documents`	`List[Document]`	Documents to add to the vectorstore.	required
`ids`	`Optional[List[str]]`	Optional list of unique ids that will be used as index in VectorStore. See note on ids in add_texts.	`None`
`batch_size`	`int`	Number of documents to insert at a time. Tuning this may help with performance and sidestep MongoDB limits.	`DEFAULT_INSERT_BATCH_SIZE`

Returns:

Type	Description
`List[str]`	List of IDs of the added texts.

aadd_documents `async` ¶

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

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

Parameters:

Name	Type	Description	Default
`documents`	`list[Document]`	Documents to add to the vectorstore.	required
`kwargs`	`Any`	Additional keyword arguments.	`{}`

Returns:

Type	Description
`list[str]`	List of IDs of the added texts.

search ¶

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

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

Parameters:

Name	Type	Description	Default
`query`	`str`	Input text	required
`search_type`	`str`	Type of search to perform. Can be "similarity", "mmr", or "similarity_score_threshold".	required
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[Document]`	List of Documents most similar to the query.

Raises:

Type	Description
`ValueError`	If search_type is not one of "similarity", "mmr", or "similarity_score_threshold".

asearch `async` ¶

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

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

Parameters:

Name	Type	Description	Default
`query`	`str`	Input text.	required
`search_type`	`str`	Type of search to perform. Can be "similarity", "mmr", or "similarity_score_threshold".	required
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[Document]`	List of Documents most similar to the query.

Raises:

Type	Description
`ValueError`	If search_type is not one of "similarity", "mmr", or "similarity_score_threshold".

similarity_search ¶

similarity_search(
    query: str,
    k: int = 4,
    pre_filter: Optional[Dict[str, Any]] = None,
    post_filter_pipeline: Optional[List[Dict]] = None,
    oversampling_factor: int = 10,
    include_scores: bool = False,
    include_embeddings: bool = False,
    **kwargs: Any
) -> List[Document]

Return MongoDB documents most similar to the given query.

Atlas Vector Search eliminates the need to run a separate search system alongside your database.

Args: query: Input text of semantic query k: (Optional) number of documents to return. Defaults to 4. pre_filter: List of MQL match expressions comparing an indexed field post_filter_pipeline: (Optional) Pipeline of MongoDB aggregation stages to filter/process results after $vectorSearch. oversampling_factor: Multiple of k used when generating number of candidates at each step in the HNSW Vector Search, include_scores: If True, the query score of each result will be included in metadata. include_embeddings: If True, the embedding vector of each result will be included in metadata. kwargs: Additional arguments are specific to the search_type

Returns:

Type	Description
`List[Document]`	List of documents most similar to the query and their scores.

similarity_search_with_score ¶

similarity_search_with_score(
    query: str,
    k: int = 4,
    pre_filter: Optional[Dict[str, Any]] = None,
    post_filter_pipeline: Optional[List[Dict]] = None,
    oversampling_factor: int = 10,
    include_embeddings: bool = False,
    **kwargs: Any
) -> List[Tuple[Document, float]]

Return MongoDB documents most similar to the given query and their scores.

Atlas Vector Search eliminates the need to run a separate search system alongside your database.

Args: query: Input text of semantic query k: Number of documents to return. Also known as top_k. pre_filter: List of MQL match expressions comparing an indexed field post_filter_pipeline: (Optional) Arbitrary pipeline of MongoDB aggregation stages applied after the search is complete. oversampling_factor: This times k is the number of candidates chosen at each step in the in HNSW Vector Search include_embeddings: If True, the embedding vector of each result will be included in metadata. kwargs: Additional arguments are specific to the search_type

Returns:

Type	Description
`List[Tuple[Document, float]]`	List of documents most similar to the query and their scores.

asimilarity_search_with_score `async` ¶

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

Async run similarity search with distance.

Parameters:

Name	Type	Description	Default
`*args`	`Any`	Arguments to pass to the search method.	`()`
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[tuple[Document, float]]`	List of Tuples of (doc, similarity_score).

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.

Parameters:

Name	Type	Description	Default
`query`	`str`	Input text.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`**kwargs`	`Any`	kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 to filter the resulting set of retrieved docs.	`{}`

Returns:

Type	Description
`list[tuple[Document, float]]`	List of Tuples of (doc, similarity_score).

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.

Parameters:

Name	Type	Description	Default
`query`	`str`	Input text.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`**kwargs`	`Any`	kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 to filter the resulting set of retrieved docs	`{}`

Returns:

Type	Description
`list[tuple[Document, float]]`	List of Tuples of (doc, similarity_score)

asimilarity_search `async` ¶

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

Async return docs most similar to query.

Parameters:

Name	Type	Description	Default
`query`	`str`	Input text.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[Document]`	List of Documents most similar to the query.

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.

Parameters:

Name	Type	Description	Default
`embedding`	`list[float]`	Embedding to look up documents similar to.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[Document]`	List of Documents most similar to the query vector.

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.

Parameters:

Name	Type	Description	Default
`embedding`	`list[float]`	Embedding to look up documents similar to.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[Document]`	List of Documents most similar to the query vector.

max_marginal_relevance_search ¶

max_marginal_relevance_search(
    query: str,
    k: int = 4,
    fetch_k: int = 20,
    lambda_mult: float = 0.5,
    pre_filter: Optional[Dict[str, Any]] = None,
    post_filter_pipeline: Optional[List[Dict]] = None,
    **kwargs: Any
) -> List[Document]

Return documents selected using the maximal marginal relevance.

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

Parameters:

Name	Type	Description	Default
`query`	`str`	Text to look up documents similar to.	required
`k`	`int`	(Optional) number of documents to return. Defaults to 4.	`4`
`fetch_k`	`int`	(Optional) number of documents to fetch before passing to MMR algorithm. Defaults to 20.	`20`
`lambda_mult`	`float`	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.	`0.5`
`pre_filter`	`Optional[Dict[str, Any]]`	List of MQL match expressions comparing an indexed field	`None`
`post_filter_pipeline`	`Optional[List[Dict]]`	(Optional) pipeline of MongoDB aggregation stages following the $vectorSearch stage.	`None`

Returns: List of documents selected by maximal marginal relevance.

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.

Parameters:

Name	Type	Description	Default
`query`	`str`	Text to look up documents similar to.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`fetch_k`	`int`	Number of Documents to fetch to pass to MMR algorithm. Default is 20.	`20`
`lambda_mult`	`float`	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.	`0.5`
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[Document]`	List of Documents 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,
    pre_filter: Optional[Dict[str, Any]] = None,
    post_filter_pipeline: Optional[List[Dict]] = None,
    oversampling_factor: int = 10,
    **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.

Parameters:

Name	Type	Description	Default
`embedding`	`List[float]`	Embedding to look up documents similar to.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`fetch_k`	`int`	Number of Documents to fetch to pass to MMR algorithm.	`20`
`lambda_mult`	`float`	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.	`0.5`
`pre_filter`	`Optional[Dict[str, Any]]`	(Optional) dictionary of arguments to filter document fields on.	`None`
`post_filter_pipeline`	`Optional[List[Dict]]`	(Optional) pipeline of MongoDB aggregation stages following the vectorSearch stage.	`None`
`oversampling_factor`	`int`	Multiple of k used when generating number of candidates in HNSW Vector Search,	`10`
`kwargs`	`Any`	Additional arguments are specific to the search_type	`{}`

Returns:

Type	Description
`List[Document]`	List of Documents 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,
    pre_filter: Optional[Dict[str, Any]] = None,
    post_filter_pipeline: Optional[List[Dict]] = None,
    oversampling_factor: int = 10,
    **kwargs: Any
) -> List[Document]

Return docs selected using the maximal marginal relevance.

from_documents `classmethod` ¶

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

Return VectorStore initialized from documents and embeddings.

Parameters:

Name	Type	Description	Default
`documents`	`list[Document]`	List of Documents to add to the vectorstore.	required
`embedding`	`Embeddings`	Embedding function to use.	required
`kwargs`	`Any`	Additional keyword arguments.	`{}`

Returns:

Name	Type	Description
`VectorStore`	`Self`	VectorStore initialized from documents and embeddings.

afrom_documents `async` `classmethod` ¶

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

Async return VectorStore initialized from documents and embeddings.

Parameters:

Name	Type	Description	Default
`documents`	`list[Document]`	List of Documents to add to the vectorstore.	required
`embedding`	`Embeddings`	Embedding function to use.	required
`kwargs`	`Any`	Additional keyword arguments.	`{}`

Returns:

Name	Type	Description
`VectorStore`	`Self`	VectorStore initialized from documents and embeddings.

from_texts `classmethod` ¶

from_texts(
    texts: List[str],
    embedding: Embeddings,
    metadatas: Optional[List[Dict]] = None,
    collection: Optional[Collection] = None,
    ids: Optional[List[str]] = None,
    **kwargs: Any
) -> MongoDBAtlasVectorSearch

Construct a MongoDB Atlas Vector Search vector store from raw documents.

This is a user-friendly interface that

Embeds documents.
Adds the documents to a provided MongoDB Atlas Vector Search index (Lucene)

This is intended to be a quick way to get started.

See MongoDBAtlasVectorSearch for kwargs and further description.

Example

.. code-block:: python from pymongo import MongoClient

from langchain_mongodb import MongoDBAtlasVectorSearch
from langchain_openai import OpenAIEmbeddings

mongo_client = MongoClient("<YOUR-CONNECTION-STRING>")
collection = mongo_client["<db_name>"]["<collection_name>"]
embeddings = OpenAIEmbeddings()
vectorstore = MongoDBAtlasVectorSearch.from_texts(
    texts,
    embeddings,
    metadatas=metadatas,
    collection=collection
)

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.

Parameters:

Name	Type	Description	Default
`texts`	`list[str]`	Texts to add to the vectorstore.	required
`embedding`	`Embeddings`	Embedding function to use.	required
`metadatas`	`list[dict] \| None`	Optional list of metadatas associated with the texts. Default is None.	`None`
`ids`	`list[str] \| None`	Optional list of IDs associated with the texts.	`None`
`kwargs`	`Any`	Additional keyword arguments.	`{}`

Returns:

Name	Type	Description
`VectorStore`	`Self`	VectorStore initialized from texts and embeddings.

as_retriever ¶

as_retriever(**kwargs: Any) -> VectorStoreRetriever

Return VectorStoreRetriever initialized from this VectorStore.

Parameters:

Name	Type	Description	Default
`**kwargs`	`Any`	Keyword arguments to pass to the search function. Can include: search_type (Optional[str]): Defines the type of search that the Retriever should perform. Can be "similarity" (default), "mmr", or "similarity_score_threshold". search_kwargs (Optional[Dict]): 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	`{}`

Returns:

Name	Type	Description
`VectorStoreRetriever`	`VectorStoreRetriever`	Retriever class for VectorStore.

Examples:

.. code-block:: python

# 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"}}
)

from_connection_string `classmethod` ¶

from_connection_string(
    connection_string: str,
    namespace: str,
    embedding: Embeddings,
    **kwargs: Any
) -> MongoDBAtlasVectorSearch

Construct a MongoDB Atlas Vector Search vector store from a MongoDB connection URI.

Parameters:

Name	Type	Description	Default
`connection_string`	`str`	A valid MongoDB connection URI.	required
`namespace`	`str`	A valid MongoDB namespace (database and collection).	required
`embedding`	`Embeddings`	The text embedding model to use for the vector store.	required

Returns:

Type	Description
`MongoDBAtlasVectorSearch`	A new MongoDBAtlasVectorSearch instance.

close ¶

close() -> None

Close the resources used by the MongoDBAtlasVectorSearch.

bulk_embed_and_insert_texts ¶

bulk_embed_and_insert_texts(
    texts: Union[List[str], Iterable[str]],
    metadatas: Union[List[dict], Generator[dict, Any, Any]],
    ids: Optional[List[str]] = None,
) -> List[str]

Bulk insert single batch of texts, embeddings, and optionally ids.

See add_texts for additional details.

create_vector_search_index ¶

create_vector_search_index(
    dimensions: int,
    filters: Optional[List[str]] = None,
    update: bool = False,
    wait_until_complete: Optional[float] = None,
    **kwargs: Any
) -> None

Creates a MongoDB Atlas vectorSearch index for the VectorStore

Note**: This method may fail as it requires a MongoDB Atlas with these pre-requisites <https://www.mongodb.com/docs/atlas/atlas-vector-search/create-index/#prerequisites>. Currently, vector and full-text search index operations need to be performed manually on the Atlas UI for shared M0 clusters.

Parameters:

Name	Type	Description	Default
`dimensions`	`int`	Number of dimensions in embedding	required
`filters`	`Optional[List[Dict[str, str]]]`	additional filters	`None`
`update`	`Optional[bool]`	Updates existing vectorSearch index. Defaults to False.	`False`
`wait_until_complete`	`Optional[float]`	If given, a TimeoutError is raised if search index is not ready after this number of seconds. If not given, the default, operation will not wait.	`None`
`kwargs`	`Any`	(Optional): Keyword arguments supplying any additional options to SearchIndexModel.	`{}`

alookup `async` ¶

alookup(
    prompt: str, llm_string: str
) -> RETURN_VAL_TYPE | None

Async look up based on prompt and llm_string.

A cache implementation is expected to generate a key from the 2-tuple of prompt and llm_string (e.g., by concatenating them with a delimiter).

Parameters:

Name	Type	Description	Default
`prompt`	`str`	a string representation of the prompt. In the case of a Chat model, the prompt is a non-trivial serialization of the prompt into the language model.	required
`llm_string`	`str`	A string representation of the LLM configuration. This is used to capture the invocation parameters of the LLM (e.g., model name, temperature, stop tokens, max tokens, etc.). These invocation parameters are serialized into a string representation.	required

Returns:

Type	Description
`RETURN_VAL_TYPE \| None`	On a cache miss, return None. On a cache hit, return the cached value.
`RETURN_VAL_TYPE \| None`	The cached value is a list of Generations (or subclasses).

aupdate `async` ¶

aupdate(
    prompt: str,
    llm_string: str,
    return_val: RETURN_VAL_TYPE,
) -> None

Async update cache based on prompt and llm_string.

The prompt and llm_string are used to generate a key for the cache. The key should match that of the look up method.

Parameters:

Name	Type	Description	Default
`prompt`	`str`	a string representation of the prompt. In the case of a Chat model, the prompt is a non-trivial serialization of the prompt into the language model.	required
`llm_string`	`str`	A string representation of the LLM configuration. This is used to capture the invocation parameters of the LLM (e.g., model name, temperature, stop tokens, max tokens, etc.). These invocation parameters are serialized into a string representation.	required
`return_val`	`RETURN_VAL_TYPE`	The value to be cached. The value is a list of Generations (or subclasses).	required

aclear `async` ¶

aclear(**kwargs: Any) -> None

Async clear cache that can take additional keyword arguments.

init ¶

__init__(
    connection_string: str,
    embedding: Embeddings,
    collection_name: str = "default",
    database_name: str = "default",
    index_name: str = "default",
    wait_until_ready: Optional[float] = None,
    score_threshold: Optional[float] = None,
    **kwargs: Dict[str, Any]
)

Initialize Atlas VectorSearch Cache. Assumes collection exists before instantiation

Parameters:

Name	Type	Description	Default
`connection_string`	`str`	MongoDB URI to connect to MongoDB Atlas cluster.	required
`embedding`	`Embeddings`	Text embedding model to use.	required
`collection_name`	`str`	MongoDB Collection to add the texts to. Defaults to "default".	`'default'`
`database_name`	`str`	MongoDB Database where to store texts. Defaults to "default".	`'default'`
`index_name`	`str`	Name of the Atlas Search index. defaults to 'default'	`'default'`
`wait_until_ready`	`float`	Wait this time for Atlas to finish indexing the stored text. Defaults to None.	`None`

lookup ¶

lookup(
    prompt: str, llm_string: str
) -> Optional[RETURN_VAL_TYPE]

Look up based on prompt and llm_string.

update ¶

update(
    prompt: str,
    llm_string: str,
    return_val: RETURN_VAL_TYPE,
    wait_until_ready: Optional[float] = None,
) -> None

Update cache based on prompt and llm_string.

clear ¶

clear(**kwargs: Any) -> None

Clear cache that can take additional keyword arguments. Any additional arguments will propagate as filtration criteria for what gets deleted. It will delete any locally cached content regardless

E.g. # Delete only entries that have llm_string as "fake-model" self.clear(llm_string="fake-model")

MongoDBCache ¶

Bases: BaseCache

MongoDB Atlas cache

A cache that uses MongoDB Atlas as a backend

Methods:

Name	Description
`alookup`	Async look up based on prompt and llm_string.
`aupdate`	Async update cache based on prompt and llm_string.
`aclear`	Async clear cache that can take additional keyword arguments.
`__init__`	Initialize Atlas Cache. Creates collection on instantiation
`close`	Close the MongoClient used by the MongoDBCache.
`lookup`	Look up based on prompt and llm_string.
`update`	Update cache based on prompt and llm_string.
`clear`	Clear cache that can take additional keyword arguments.

Attributes:

Name	Type	Description
`database`	`Database`	Returns the database used to store cache values.
`collection`	`Collection`	Returns the collection used to store cache values.

database `property` ¶

database: Database

Returns the database used to store cache values.

collection `property` ¶

collection: Collection

Returns the collection used to store cache values.

alookup `async` ¶

alookup(
    prompt: str, llm_string: str
) -> RETURN_VAL_TYPE | None

Async look up based on prompt and llm_string.

A cache implementation is expected to generate a key from the 2-tuple of prompt and llm_string (e.g., by concatenating them with a delimiter).

Parameters:

Name	Type	Description	Default
`prompt`	`str`	a string representation of the prompt. In the case of a Chat model, the prompt is a non-trivial serialization of the prompt into the language model.	required
`llm_string`	`str`	A string representation of the LLM configuration. This is used to capture the invocation parameters of the LLM (e.g., model name, temperature, stop tokens, max tokens, etc.). These invocation parameters are serialized into a string representation.	required

Returns:

Type	Description
`RETURN_VAL_TYPE \| None`	On a cache miss, return None. On a cache hit, return the cached value.
`RETURN_VAL_TYPE \| None`	The cached value is a list of Generations (or subclasses).

aupdate `async` ¶

aupdate(
    prompt: str,
    llm_string: str,
    return_val: RETURN_VAL_TYPE,
) -> None

Async update cache based on prompt and llm_string.

The prompt and llm_string are used to generate a key for the cache. The key should match that of the look up method.

Parameters:

Name	Type	Description	Default
`prompt`	`str`	a string representation of the prompt. In the case of a Chat model, the prompt is a non-trivial serialization of the prompt into the language model.	required
`llm_string`	`str`	A string representation of the LLM configuration. This is used to capture the invocation parameters of the LLM (e.g., model name, temperature, stop tokens, max tokens, etc.). These invocation parameters are serialized into a string representation.	required
`return_val`	`RETURN_VAL_TYPE`	The value to be cached. The value is a list of Generations (or subclasses).	required

aclear `async` ¶

aclear(**kwargs: Any) -> None

Async clear cache that can take additional keyword arguments.

init ¶

__init__(
    connection_string: str,
    collection_name: str = "default",
    database_name: str = "default",
    **kwargs: Dict[str, Any]
) -> None

Initialize Atlas Cache. Creates collection on instantiation

Parameters:

Name	Type	Description	Default
`collection_name`	`str`	Name of collection for cache to live. Defaults to "default".	`'default'`
`connection_string`	`str`	Connection URI to MongoDB Atlas. Defaults to "default".	required
`database_name`	`str`	Name of database for cache to live. Defaults to "default".	`'default'`

close ¶

close() -> None

Close the MongoClient used by the MongoDBCache.

lookup ¶

lookup(
    prompt: str, llm_string: str
) -> Optional[RETURN_VAL_TYPE]

Look up based on prompt and llm_string.

update ¶

update(
    prompt: str,
    llm_string: str,
    return_val: RETURN_VAL_TYPE,
) -> None

Update cache based on prompt and llm_string.

clear ¶

clear(**kwargs: Any) -> None

Clear cache that can take additional keyword arguments. Any additional arguments will propagate as filtration criteria for what gets deleted.

E.g. # Delete only entries that have llm_string as "fake-model" self.clear(llm_string="fake-model")

MongoDBChatMessageHistory ¶

Bases: BaseChatMessageHistory

Chat message history that stores history in MongoDB.

Setup

Install langchain-mongodb python package.

.. code-block:: bash

pip install langchain-mongodb

Instantiate

.. code-block:: python

from langchain_mongodb import MongoDBChatMessageHistory


history = MongoDBChatMessageHistory(
    connection_string="mongodb://your-host:your-port/",  # mongodb://localhost:27017/
    session_id = "your-session-id",
)

Add and retrieve messages

.. code-block:: python

# Add single message
history.add_message(message)

# Add batch messages
history.add_messages([message1, message2, message3, ...])

# Add human message
history.add_user_message(human_message)

# Add ai message
history.add_ai_message(ai_message)

# Retrieve messages
messages = history.messages

Methods:

Name	Description
`aget_messages`	Async version of getting messages.
`add_user_message`	Convenience method for adding a human message string to the store.
`add_ai_message`	Convenience method for adding an AI message string to the store.
`add_messages`	Add a list of messages.
`aadd_messages`	Async add a list of messages.
`aclear`	Async remove all messages from the store.
`__str__`	Return a string representation of the chat history.
`__init__`	Initialize with a MongoDBChatMessageHistory instance.
`close`	Close the resources used by the MongoDBChatMessageHistory.
`add_message`	Append the message to the record in MongoDB
`clear`	Clear session memory from MongoDB

Attributes:

Name	Type	Description
`messages`	`List[BaseMessage]`	Retrieve the messages from MongoDB

messages `property` ¶

messages: List[BaseMessage]

Retrieve the messages from MongoDB

aget_messages `async` ¶

aget_messages() -> list[BaseMessage]

Async version of getting messages.

Can over-ride this method to provide an efficient async implementation.

In general, fetching messages may involve IO to the underlying persistence layer.

Returns:

Type	Description
`list[BaseMessage]`	The messages.

add_user_message ¶

add_user_message(message: HumanMessage | str) -> None

Convenience method for adding a human message string to the store.

Note

This is a convenience method. Code should favor the bulk add_messages interface instead to save on round-trips to the persistence layer.

This method may be deprecated in a future release.

Parameters:

Name	Type	Description	Default
`message`	`HumanMessage \| str`	The human message to add to the store.	required

add_ai_message ¶

add_ai_message(message: AIMessage | str) -> None

Convenience method for adding an AI message string to the store.

Note

This is a convenience method. Code should favor the bulk add_messages interface instead to save on round-trips to the persistence layer.

This method may be deprecated in a future release.

Parameters:

Name	Type	Description	Default
`message`	`AIMessage \| str`	The AI message to add.	required

add_messages ¶

add_messages(messages: Sequence[BaseMessage]) -> None

Add a list of messages.

Implementations should over-ride this method to handle bulk addition of messages in an efficient manner to avoid unnecessary round-trips to the underlying store.

Parameters:

Name	Type	Description	Default
`messages`	`Sequence[BaseMessage]`	A sequence of BaseMessage objects to store.	required

aadd_messages `async` ¶

aadd_messages(messages: Sequence[BaseMessage]) -> None

Async add a list of messages.

Parameters:

Name	Type	Description	Default
`messages`	`Sequence[BaseMessage]`	A sequence of BaseMessage objects to store.	required

aclear `async` ¶

aclear() -> None

Async remove all messages from the store.

str ¶

__str__() -> str

Return a string representation of the chat history.

init ¶

__init__(
    connection_string: Optional[str],
    session_id: str,
    database_name: str = DEFAULT_DBNAME,
    collection_name: str = DEFAULT_COLLECTION_NAME,
    *,
    session_id_key: str = DEFAULT_SESSION_ID_KEY,
    history_key: str = DEFAULT_HISTORY_KEY,
    create_index: bool = True,
    history_size: Optional[int] = None,
    index_kwargs: Optional[Dict] = None,
    client: Optional[MongoClient] = None
)

Initialize with a MongoDBChatMessageHistory instance.

Parameters:

Name	Type	Description	Default
`connection_string`	`Optional[str]`	Optional[str] connection string to connect to MongoDB. Can be None if mongo_client is provided.	required
`session_id`	`str`	str arbitrary key that is used to store the messages of a single chat session.	required
`database_name`	`str`	Optional[str] name of the database to use.	`DEFAULT_DBNAME`
`collection_name`	`str`	Optional[str] name of the collection to use.	`DEFAULT_COLLECTION_NAME`
`session_id_key`	`str`	Optional[str] name of the field that stores the session id.	`DEFAULT_SESSION_ID_KEY`
`history_key`	`str`	Optional[str] name of the field that stores the chat history.	`DEFAULT_HISTORY_KEY`
`create_index`	`bool`	Optional[bool] whether to create an index on the session id field.	`True`
`history_size`	`Optional[int]`	Optional[int] count of (most recent) messages to fetch from MongoDB.	`None`
`index_kwargs`	`Optional[Dict]`	Optional[Dict] additional keyword arguments to pass to the index creation.	`None`
`client`	`Optional[MongoClient]`	Optional[MongoClient] an existing MongoClient instance. If provided, connection_string is ignored.	`None`

close ¶

close() -> None

Close the resources used by the MongoDBChatMessageHistory.

add_message ¶

add_message(message: BaseMessage) -> None

Append the message to the record in MongoDB

clear ¶

clear() -> None

Clear session memory from MongoDB

MongoDBAtlasVectorSearch ¶

Bases: VectorStore

MongoDB Atlas vector store integration.

MongoDBAtlasVectorSearch performs data operations on text, embeddings and arbitrary data. In addition to CRUD operations, the VectorStore provides Vector Search based on similarity of embedding vectors following the Hierarchical Navigable Small Worlds (HNSW) algorithm.

This supports a number of models to ascertain scores, "similarity" (default), "MMR", and "similarity_score_threshold". These are described in the search_type argument to as_retriever, which provides the Runnable.invoke(query) API, allowing MongoDBAtlasVectorSearch to be used within a chain.

Setup

Set up a MongoDB Atlas cluster. The free tier M0 will allow you to start. Search Indexes are only available on Atlas, the fully managed cloud service, not the self-managed MongoDB. Follow this guide
Create a Collection and a Vector Search Index. The procedure is described here. You can optionally supply a dimensions argument to programmatically create a Vector Search Index.
Install langchain-mongodb

.. code-block:: bash

pip install -qU langchain-mongodb pymongo

.. code-block:: python

import getpass
MONGODB_ATLAS_CONNECTION_STRING = getpass.getpass("MongoDB Atlas Connection String:")

Key init args — indexing params: embedding: Embeddings Embedding function to use.

Key init args — client params: collection: Collection MongoDB collection to use. index_name: str Name of the Atlas Search index.

Instantiate

.. code-block:: python

from pymongo import MongoClient
from langchain_mongodb.vectorstores import MongoDBAtlasVectorSearch
from pymongo import MongoClient
from langchain_openai import OpenAIEmbeddings

vector_store = MongoDBAtlasVectorSearch.from_connection_string(
    connection_string=os=MONGODB_ATLAS_CONNECTION_STRING,
    namespace="db_name.collection_name",
    embedding=OpenAIEmbeddings(),
    index_name="vector_index",
    text_key="text_field"
)

Add Documents

.. code-block:: python

from langchain_core.documents import Document

document_1 = Document(page_content="foo", metadata={"baz": "bar"})
document_2 = Document(page_content="thud", metadata={"bar": "baz"})
document_3 = Document(page_content="i will be deleted :(")

documents = [document_1, document_2, document_3]
ids = ["1", "2", "3"]
vector_store.add_documents(documents=documents, ids=ids)

Delete Documents

.. code-block:: python

vector_store.delete(ids=["3"])

Search

.. code-block:: python

results = vector_store.similarity_search(query="thud",k=1)
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

.. code-block:: python

* thud [{'_id': '2', 'baz': 'baz'}]

Search with filter

.. code-block:: python

results = vector_store.similarity_search(query="thud",k=1,post_filter=[{"bar": "baz"]})
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

.. code-block:: python

* thud [{'_id': '2', 'baz': 'baz'}]

Search with score

.. code-block:: python

results = vector_store.similarity_search_with_score(query="qux",k=1)
for doc, score in results:
    print(f"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]")

.. code-block:: python

* [SIM=0.916096] foo [{'_id': '1', 'baz': 'bar'}]

Async

.. code-block:: python

# add documents
# await vector_store.aadd_documents(documents=documents, ids=ids)

# delete documents
# await vector_store.adelete(ids=["3"])

# search
# results = vector_store.asimilarity_search(query="thud",k=1)

# search with score
results = await vector_store.asimilarity_search_with_score(query="qux",k=1)
for doc,score in results:
    print(f"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]")

.. code-block:: python

* [SIM=0.916096] foo [{'_id': '1', 'baz': 'bar'}]

Use as Retriever:

.. code-block:: python

    retriever = vector_store.as_retriever(
        search_type="mmr",
        search_kwargs={"k": 1, "fetch_k": 2, "lambda_mult": 0.5},
    )
    retriever.invoke("thud")

.. code-block:: python

    [Document(metadata={'_id': '2', 'embedding': [-0.01850726455450058, -0.0014740974875167012, -0.009762819856405258, ...], 'baz': 'baz'}, page_content='thud')]

Methods:

Name	Description
`aget_by_ids`	Async get documents by their IDs.
`aadd_texts`	Async run more texts through the embeddings and add to the vectorstore.
`aadd_documents`	Async run more documents through the embeddings and add to the vectorstore.
`search`	Return docs most similar to query using a specified search type.
`asearch`	Async return docs most similar to query using a specified search type.
`asimilarity_search_with_score`	Async run similarity search with distance.
`similarity_search_with_relevance_scores`	Return docs and relevance scores in the range [0, 1].
`asimilarity_search_with_relevance_scores`	Async return docs and relevance scores in the range [0, 1].
`asimilarity_search`	Async return docs most similar to query.
`similarity_search_by_vector`	Return docs most similar to embedding vector.
`asimilarity_search_by_vector`	Async return docs most similar to embedding vector.
`amax_marginal_relevance_search`	Async return docs selected using the maximal marginal relevance.
`from_documents`	Return VectorStore initialized from documents and embeddings.
`afrom_documents`	Async return VectorStore initialized from documents and embeddings.
`afrom_texts`	Async return VectorStore initialized from texts and embeddings.
`as_retriever`	Return VectorStoreRetriever initialized from this VectorStore.
`__init__`	Args:
`from_connection_string`	Construct a `MongoDB Atlas Vector Search` vector store
`close`	Close the resources used by the MongoDBAtlasVectorSearch.
`add_texts`	Add texts, create embeddings, and add to the Collection and index.
`get_by_ids`	Get documents by their IDs.
`bulk_embed_and_insert_texts`	Bulk insert single batch of texts, embeddings, and optionally ids.
`add_documents`	Add documents to the vectorstore.
`similarity_search_with_score`	Return MongoDB documents most similar to the given query and their scores.
`similarity_search`	Return MongoDB documents most similar to the given query.
`max_marginal_relevance_search`	Return documents selected using the maximal marginal relevance.
`from_texts`	Construct a `MongoDB Atlas Vector Search` vector store from raw documents.
`delete`	Delete documents from VectorStore by ids.
`adelete`	Delete by vector ID or other criteria.
`max_marginal_relevance_search_by_vector`	Return docs selected using the maximal marginal relevance.
`amax_marginal_relevance_search_by_vector`	Return docs selected using the maximal marginal relevance.
`create_vector_search_index`	Creates a MongoDB Atlas vectorSearch index for the VectorStore

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.

Parameters:

Name	Type	Description	Default
`ids`	`Sequence[str]`	List of ids to retrieve.	required

Returns:

Type	Description
`list[Document]`	List of Documents.

Added in version 0.2.11

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.

Parameters:

Name	Type	Description	Default
`texts`	`Iterable[str]`	Iterable of strings to add to the vectorstore.	required
`metadatas`	`list[dict] \| None`	Optional list of metadatas associated with the texts. Default is None.	`None`
`ids`	`list[str] \| None`	Optional list	`None`
`**kwargs`	`Any`	vectorstore specific parameters.	`{}`

Returns:

Type	Description
`list[str]`	List of ids from adding the texts into the vectorstore.

Raises:

Type	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.

aadd_documents `async` ¶

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

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

Parameters:

Name	Type	Description	Default
`documents`	`list[Document]`	Documents to add to the vectorstore.	required
`kwargs`	`Any`	Additional keyword arguments.	`{}`

Returns:

Type	Description
`list[str]`	List of IDs of the added texts.

search ¶

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

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

Parameters:

Name	Type	Description	Default
`query`	`str`	Input text	required
`search_type`	`str`	Type of search to perform. Can be "similarity", "mmr", or "similarity_score_threshold".	required
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[Document]`	List of Documents most similar to the query.

Raises:

Type	Description
`ValueError`	If search_type is not one of "similarity", "mmr", or "similarity_score_threshold".

asearch `async` ¶

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

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

Parameters:

Name	Type	Description	Default
`query`	`str`	Input text.	required
`search_type`	`str`	Type of search to perform. Can be "similarity", "mmr", or "similarity_score_threshold".	required
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[Document]`	List of Documents most similar to the query.

Raises:

Type	Description
`ValueError`	If search_type is not one of "similarity", "mmr", or "similarity_score_threshold".

asimilarity_search_with_score `async` ¶

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

Async run similarity search with distance.

Parameters:

Name	Type	Description	Default
`*args`	`Any`	Arguments to pass to the search method.	`()`
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[tuple[Document, float]]`	List of Tuples of (doc, similarity_score).

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.

Parameters:

Name	Type	Description	Default
`query`	`str`	Input text.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`**kwargs`	`Any`	kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 to filter the resulting set of retrieved docs.	`{}`

Returns:

Type	Description
`list[tuple[Document, float]]`	List of Tuples of (doc, similarity_score).

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.

Parameters:

Name	Type	Description	Default
`query`	`str`	Input text.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`**kwargs`	`Any`	kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 to filter the resulting set of retrieved docs	`{}`

Returns:

Type	Description
`list[tuple[Document, float]]`	List of Tuples of (doc, similarity_score)

asimilarity_search `async` ¶

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

Async return docs most similar to query.

Parameters:

Name	Type	Description	Default
`query`	`str`	Input text.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[Document]`	List of Documents most similar to the query.

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.

Parameters:

Name	Type	Description	Default
`embedding`	`list[float]`	Embedding to look up documents similar to.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[Document]`	List of Documents most similar to the query vector.

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.

Parameters:

Name	Type	Description	Default
`embedding`	`list[float]`	Embedding to look up documents similar to.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[Document]`	List of Documents most similar to the query vector.

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.

Parameters:

Name	Type	Description	Default
`query`	`str`	Text to look up documents similar to.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`fetch_k`	`int`	Number of Documents to fetch to pass to MMR algorithm. Default is 20.	`20`
`lambda_mult`	`float`	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.	`0.5`
`**kwargs`	`Any`	Arguments to pass to the search method.	`{}`

Returns:

Type	Description
`list[Document]`	List of Documents selected by maximal marginal relevance.

from_documents `classmethod` ¶

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

Return VectorStore initialized from documents and embeddings.

Parameters:

Name	Type	Description	Default
`documents`	`list[Document]`	List of Documents to add to the vectorstore.	required
`embedding`	`Embeddings`	Embedding function to use.	required
`kwargs`	`Any`	Additional keyword arguments.	`{}`

Returns:

Name	Type	Description
`VectorStore`	`Self`	VectorStore initialized from documents and embeddings.

afrom_documents `async` `classmethod` ¶

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

Async return VectorStore initialized from documents and embeddings.

Parameters:

Name	Type	Description	Default
`documents`	`list[Document]`	List of Documents to add to the vectorstore.	required
`embedding`	`Embeddings`	Embedding function to use.	required
`kwargs`	`Any`	Additional keyword arguments.	`{}`

Returns:

Name	Type	Description
`VectorStore`	`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.

Parameters:

Name	Type	Description	Default
`texts`	`list[str]`	Texts to add to the vectorstore.	required
`embedding`	`Embeddings`	Embedding function to use.	required
`metadatas`	`list[dict] \| None`	Optional list of metadatas associated with the texts. Default is None.	`None`
`ids`	`list[str] \| None`	Optional list of IDs associated with the texts.	`None`
`kwargs`	`Any`	Additional keyword arguments.	`{}`

Returns:

Name	Type	Description
`VectorStore`	`Self`	VectorStore initialized from texts and embeddings.

as_retriever ¶

as_retriever(**kwargs: Any) -> VectorStoreRetriever

Return VectorStoreRetriever initialized from this VectorStore.

Parameters:

Name	Type	Description	Default
`**kwargs`	`Any`	Keyword arguments to pass to the search function. Can include: search_type (Optional[str]): Defines the type of search that the Retriever should perform. Can be "similarity" (default), "mmr", or "similarity_score_threshold". search_kwargs (Optional[Dict]): 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	`{}`

Returns:

Name	Type	Description
`VectorStoreRetriever`	`VectorStoreRetriever`	Retriever class for VectorStore.

Examples:

.. code-block:: python

# 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"}}
)

init ¶

__init__(
    collection: Collection[Dict[str, Any]],
    embedding: Embeddings,
    index_name: str = "vector_index",
    text_key: Union[str, List[str]] = "text",
    embedding_key: str = "embedding",
    relevance_score_fn: str = "cosine",
    dimensions: int = -1,
    auto_create_index: bool | None = None,
    auto_index_timeout: int = 15,
    **kwargs: Any
)

Parameters:

Name	Type	Description	Default
`collection`	`Collection[Dict[str, Any]]`	MongoDB collection to add the texts to	required
`embedding`	`Embeddings`	Text embedding model to use	required
`text_key`	`Union[str, List[str]]`	MongoDB field that will contain the text for each document. It is possible to parse a list of fields. The first one will be used as text key. Default: 'text'	`'text'`
`index_name`	`str`	Existing Atlas Vector Search Index	`'vector_index'`
`embedding_key`	`str`	Field that will contain the embedding for each document	`'embedding'`
`relevance_score_fn`	`str`	The similarity score used for the index Currently supported: 'euclidean', 'cosine', and 'dotProduct'	`'cosine'`
`auto_create_index`	`bool \| None`	Whether to automatically create an index if it does not exist.	`None`
`dimensions`	`int`	Number of dimensions in embedding. If the value is not provided, and `auto_create_index` is `true`, the value will be inferred.	`-1`
`auto_index_timeout`	`int`	Timeout in seconds to wait for an auto-created index to be ready.	`15`

from_connection_string `classmethod` ¶

from_connection_string(
    connection_string: str,
    namespace: str,
    embedding: Embeddings,
    **kwargs: Any
) -> MongoDBAtlasVectorSearch

Construct a MongoDB Atlas Vector Search vector store from a MongoDB connection URI.

Parameters:

Name	Type	Description	Default
`connection_string`	`str`	A valid MongoDB connection URI.	required
`namespace`	`str`	A valid MongoDB namespace (database and collection).	required
`embedding`	`Embeddings`	The text embedding model to use for the vector store.	required

Returns:

Type	Description
`MongoDBAtlasVectorSearch`	A new MongoDBAtlasVectorSearch instance.

close ¶

close() -> None

Close the resources used by the MongoDBAtlasVectorSearch.

add_texts ¶

add_texts(
    texts: Iterable[str],
    metadatas: Optional[List[Dict[str, Any]]] = None,
    ids: Optional[List[str]] = None,
    batch_size: int = DEFAULT_INSERT_BATCH_SIZE,
    **kwargs: Any
) -> List[str]

Add texts, create embeddings, and add to the Collection and index.

Important notes on ids

If _id or id is a key in the metadatas dicts, one must pop them and provide as separate list.
They must be unique.
If they are not provided, the VectorStore will create unique ones, stored as bson.ObjectIds internally, and strings in Langchain. These will appear in Document.metadata with key, '_id'.

Parameters:

Name	Type	Description	Default
`texts`	`Iterable[str]`	Iterable of strings to add to the vectorstore.	required
`metadatas`	`Optional[List[Dict[str, Any]]]`	Optional list of metadatas associated with the texts.	`None`
`ids`	`Optional[List[str]]`	Optional list of unique ids that will be used as index in VectorStore. See note on ids.	`None`
`batch_size`	`int`	Number of documents to insert at a time. Tuning this may help with performance and sidestep MongoDB limits.	`DEFAULT_INSERT_BATCH_SIZE`

Returns:

Type	Description
`List[str]`	List of ids added to the vectorstore.

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.

Parameters:

Name	Type	Description	Default
`ids`	`Sequence[str]`	List of ids to retrieve.	required

Returns:

Type	Description
`list[Document]`	List of Documents.

.. versionadded:: 0.6.0

bulk_embed_and_insert_texts ¶

bulk_embed_and_insert_texts(
    texts: Union[List[str], Iterable[str]],
    metadatas: Union[List[dict], Generator[dict, Any, Any]],
    ids: Optional[List[str]] = None,
) -> List[str]

Bulk insert single batch of texts, embeddings, and optionally ids.

See add_texts for additional details.

add_documents ¶

add_documents(
    documents: List[Document],
    ids: Optional[List[str]] = None,
    batch_size: int = DEFAULT_INSERT_BATCH_SIZE,
    **kwargs: Any
) -> List[str]

Add documents to the vectorstore.

Parameters:

Name	Type	Description	Default
`documents`	`List[Document]`	Documents to add to the vectorstore.	required
`ids`	`Optional[List[str]]`	Optional list of unique ids that will be used as index in VectorStore. See note on ids in add_texts.	`None`
`batch_size`	`int`	Number of documents to insert at a time. Tuning this may help with performance and sidestep MongoDB limits.	`DEFAULT_INSERT_BATCH_SIZE`

Returns:

Type	Description
`List[str]`	List of IDs of the added texts.

similarity_search_with_score ¶

similarity_search_with_score(
    query: str,
    k: int = 4,
    pre_filter: Optional[Dict[str, Any]] = None,
    post_filter_pipeline: Optional[List[Dict]] = None,
    oversampling_factor: int = 10,
    include_embeddings: bool = False,
    **kwargs: Any
) -> List[Tuple[Document, float]]

Return MongoDB documents most similar to the given query and their scores.

Atlas Vector Search eliminates the need to run a separate search system alongside your database.

Args: query: Input text of semantic query k: Number of documents to return. Also known as top_k. pre_filter: List of MQL match expressions comparing an indexed field post_filter_pipeline: (Optional) Arbitrary pipeline of MongoDB aggregation stages applied after the search is complete. oversampling_factor: This times k is the number of candidates chosen at each step in the in HNSW Vector Search include_embeddings: If True, the embedding vector of each result will be included in metadata. kwargs: Additional arguments are specific to the search_type

Returns:

Type	Description
`List[Tuple[Document, float]]`	List of documents most similar to the query and their scores.

similarity_search ¶

similarity_search(
    query: str,
    k: int = 4,
    pre_filter: Optional[Dict[str, Any]] = None,
    post_filter_pipeline: Optional[List[Dict]] = None,
    oversampling_factor: int = 10,
    include_scores: bool = False,
    include_embeddings: bool = False,
    **kwargs: Any
) -> List[Document]

Return MongoDB documents most similar to the given query.

Atlas Vector Search eliminates the need to run a separate search system alongside your database.

Args: query: Input text of semantic query k: (Optional) number of documents to return. Defaults to 4. pre_filter: List of MQL match expressions comparing an indexed field post_filter_pipeline: (Optional) Pipeline of MongoDB aggregation stages to filter/process results after $vectorSearch. oversampling_factor: Multiple of k used when generating number of candidates at each step in the HNSW Vector Search, include_scores: If True, the query score of each result will be included in metadata. include_embeddings: If True, the embedding vector of each result will be included in metadata. kwargs: Additional arguments are specific to the search_type

Returns:

Type	Description
`List[Document]`	List of documents most similar to the query and their scores.

max_marginal_relevance_search ¶

max_marginal_relevance_search(
    query: str,
    k: int = 4,
    fetch_k: int = 20,
    lambda_mult: float = 0.5,
    pre_filter: Optional[Dict[str, Any]] = None,
    post_filter_pipeline: Optional[List[Dict]] = None,
    **kwargs: Any
) -> List[Document]

Return documents selected using the maximal marginal relevance.

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

Parameters:

Name	Type	Description	Default
`query`	`str`	Text to look up documents similar to.	required
`k`	`int`	(Optional) number of documents to return. Defaults to 4.	`4`
`fetch_k`	`int`	(Optional) number of documents to fetch before passing to MMR algorithm. Defaults to 20.	`20`
`lambda_mult`	`float`	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.	`0.5`
`pre_filter`	`Optional[Dict[str, Any]]`	List of MQL match expressions comparing an indexed field	`None`
`post_filter_pipeline`	`Optional[List[Dict]]`	(Optional) pipeline of MongoDB aggregation stages following the $vectorSearch stage.	`None`

Returns: List of documents selected by maximal marginal relevance.

from_texts `classmethod` ¶

from_texts(
    texts: List[str],
    embedding: Embeddings,
    metadatas: Optional[List[Dict]] = None,
    collection: Optional[Collection] = None,
    ids: Optional[List[str]] = None,
    **kwargs: Any
) -> MongoDBAtlasVectorSearch

Construct a MongoDB Atlas Vector Search vector store from raw documents.

This is a user-friendly interface that

Embeds documents.
Adds the documents to a provided MongoDB Atlas Vector Search index (Lucene)

This is intended to be a quick way to get started.

See MongoDBAtlasVectorSearch for kwargs and further description.

Example

.. code-block:: python from pymongo import MongoClient

from langchain_mongodb import MongoDBAtlasVectorSearch
from langchain_openai import OpenAIEmbeddings

mongo_client = MongoClient("<YOUR-CONNECTION-STRING>")
collection = mongo_client["<db_name>"]["<collection_name>"]
embeddings = OpenAIEmbeddings()
vectorstore = MongoDBAtlasVectorSearch.from_texts(
    texts,
    embeddings,
    metadatas=metadatas,
    collection=collection
)

delete ¶

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

Delete documents from VectorStore by ids.

Parameters:

Name	Type	Description	Default
`ids`	`Optional[List[str]]`	List of ids to delete.	`None`
`**kwargs`	`Any`	Other keyword arguments passed to Collection.delete_many()	`{}`

Returns:

Type	Description
`Optional[bool]`	Optional[bool]: True if deletion is successful,
`Optional[bool]`	False otherwise, None if not implemented.

adelete `async` ¶

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

Delete by vector ID or other criteria.

Parameters:

Name	Type	Description	Default
`ids`	`Optional[List[str]]`	List of ids to delete.	`None`
`**kwargs`	`Any`	Other keyword arguments that subclasses might use.	`{}`

Returns:

Type	Description
`Optional[bool]`	Optional[bool]: True if deletion is successful,
`Optional[bool]`	False otherwise, None if not implemented.

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,
    pre_filter: Optional[Dict[str, Any]] = None,
    post_filter_pipeline: Optional[List[Dict]] = None,
    oversampling_factor: int = 10,
    **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.

Parameters:

Name	Type	Description	Default
`embedding`	`List[float]`	Embedding to look up documents similar to.	required
`k`	`int`	Number of Documents to return. Defaults to 4.	`4`
`fetch_k`	`int`	Number of Documents to fetch to pass to MMR algorithm.	`20`
`lambda_mult`	`float`	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.	`0.5`
`pre_filter`	`Optional[Dict[str, Any]]`	(Optional) dictionary of arguments to filter document fields on.	`None`
`post_filter_pipeline`	`Optional[List[Dict]]`	(Optional) pipeline of MongoDB aggregation stages following the vectorSearch stage.	`None`
`oversampling_factor`	`int`	Multiple of k used when generating number of candidates in HNSW Vector Search,	`10`
`kwargs`	`Any`	Additional arguments are specific to the search_type	`{}`

Returns:

Type	Description
`List[Document]`	List of Documents 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,
    pre_filter: Optional[Dict[str, Any]] = None,
    post_filter_pipeline: Optional[List[Dict]] = None,
    oversampling_factor: int = 10,
    **kwargs: Any
) -> List[Document]

Return docs selected using the maximal marginal relevance.

create_vector_search_index ¶

create_vector_search_index(
    dimensions: int,
    filters: Optional[List[str]] = None,
    update: bool = False,
    wait_until_complete: Optional[float] = None,
    **kwargs: Any
) -> None

Creates a MongoDB Atlas vectorSearch index for the VectorStore

Note**: This method may fail as it requires a MongoDB Atlas with these pre-requisites <https://www.mongodb.com/docs/atlas/atlas-vector-search/create-index/#prerequisites>. Currently, vector and full-text search index operations need to be performed manually on the Atlas UI for shared M0 clusters.

Parameters:

Name	Type	Description	Default
`dimensions`	`int`	Number of dimensions in embedding	required
`filters`	`Optional[List[Dict[str, str]]]`	additional filters	`None`
`update`	`Optional[bool]`	Updates existing vectorSearch index. Defaults to False.	`False`
`wait_until_complete`	`Optional[float]`	If given, a TimeoutError is raised if search index is not ready after this number of seconds. If not given, the default, operation will not wait.	`None`
`kwargs`	`Any`	(Optional): Keyword arguments supplying any additional options to SearchIndexModel.	`{}`

langchain-mongodb¶

MongoDBAtlasSemanticCache ¶

add_texts ¶

delete ¶

get_by_ids ¶

aget_by_ids async ¶

adelete async ¶

aadd_texts async ¶

add_documents ¶

aadd_documents async ¶

search ¶

asearch async ¶

similarity_search ¶

similarity_search_with_score ¶

asimilarity_search_with_score async ¶

similarity_search_with_relevance_scores ¶

asimilarity_search_with_relevance_scores async ¶

asimilarity_search async ¶

similarity_search_by_vector ¶

asimilarity_search_by_vector async ¶

max_marginal_relevance_search ¶

amax_marginal_relevance_search async ¶

max_marginal_relevance_search_by_vector ¶

amax_marginal_relevance_search_by_vector async ¶

from_documents classmethod ¶

afrom_documents async classmethod ¶

from_texts classmethod ¶

afrom_texts async classmethod ¶

as_retriever ¶

from_connection_string classmethod ¶

close ¶

bulk_embed_and_insert_texts ¶

create_vector_search_index ¶

alookup async ¶

aupdate async ¶

aclear async ¶

__init__ ¶

lookup ¶

update ¶

clear ¶

MongoDBCache ¶

database property ¶

collection property ¶

alookup async ¶

aupdate async ¶

aclear async ¶

__init__ ¶

close ¶

lookup ¶

update ¶

clear ¶

MongoDBChatMessageHistory ¶

messages property ¶

aget_messages async ¶

add_user_message ¶

add_ai_message ¶

add_messages ¶

aadd_messages async ¶

aclear async ¶

__str__ ¶

__init__ ¶

close ¶

add_message ¶

clear ¶

MongoDBAtlasVectorSearch ¶

aget_by_ids async ¶

aadd_texts async ¶

aadd_documents async ¶

search ¶

asearch async ¶

asimilarity_search_with_score async ¶

similarity_search_with_relevance_scores ¶

asimilarity_search_with_relevance_scores async ¶

asimilarity_search async ¶

similarity_search_by_vector ¶

asimilarity_search_by_vector async ¶

amax_marginal_relevance_search async ¶

from_documents classmethod ¶

afrom_documents async classmethod ¶

afrom_texts async classmethod ¶

`langchain-mongodb`¶

aget_by_ids `async` ¶

adelete `async` ¶

aadd_texts `async` ¶

aadd_documents `async` ¶

asearch `async` ¶

asimilarity_search_with_score `async` ¶

asimilarity_search_with_relevance_scores `async` ¶

asimilarity_search `async` ¶

asimilarity_search_by_vector `async` ¶

amax_marginal_relevance_search `async` ¶

amax_marginal_relevance_search_by_vector `async` ¶

from_documents `classmethod` ¶

afrom_documents `async` `classmethod` ¶

from_texts `classmethod` ¶

afrom_texts `async` `classmethod` ¶

from_connection_string `classmethod` ¶

alookup `async` ¶

aupdate `async` ¶

aclear `async` ¶

init ¶

database `property` ¶

collection `property` ¶

alookup `async` ¶

aupdate `async` ¶

aclear `async` ¶

init ¶

messages `property` ¶

aget_messages `async` ¶

aadd_messages `async` ¶

aclear `async` ¶

str ¶

init ¶

aget_by_ids `async` ¶

aadd_texts `async` ¶

aadd_documents `async` ¶

asearch `async` ¶

asimilarity_search_with_score `async` ¶

asimilarity_search_with_relevance_scores `async` ¶

asimilarity_search `async` ¶

asimilarity_search_by_vector `async` ¶

amax_marginal_relevance_search `async` ¶

from_documents `classmethod` ¶

afrom_documents `async` `classmethod` ¶

afrom_texts `async` `classmethod` ¶

init ¶

from_connection_string `classmethod` ¶

from_texts `classmethod` ¶

adelete `async` ¶

amax_marginal_relevance_search_by_vector `async` ¶