MongoDBAtlasSemanticCache

class langchain_mongodb.cache.MongoDBAtlasSemanticCache(connection_string: str, embedding: Embeddings, collection_name: str = 'default', database_name: str = 'default', index_name: str = 'default', wait_until_ready: float | None = None, score_threshold: float | None = None, **kwargs: Dict[str, Any])

MongoDB Atlas Semantic cache.

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

Initialize Atlas VectorSearch Cache. Assumes collection exists before instantiation

Parameters:

• connection_string (str) – MongoDB URI to connect to MongoDB Atlas cluster.

• embedding (Embeddings) – Text embedding model to use.

• collection_name (str) – MongoDB Collection to add the texts to. Defaults to “default”.

• database_name (str) – MongoDB Database where to store texts. Defaults to “default”.

• index_name (str) – Name of the Atlas Search index. defaults to ‘default’

• wait_until_ready (float) – Wait this time for Atlas to finish indexing the stored text. Defaults to None.

• score_threshold (float | None)

• kwargs (Dict[str, Any])

Attributes

LLM
RETURN_VAL
collection
embeddings	Access the query embedding object if available.

Methods

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

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

Initialize Atlas VectorSearch Cache. Assumes collection exists before instantiation

Parameters:

• connection_string (str) – MongoDB URI to connect to MongoDB Atlas cluster.

• embedding (Embeddings) – Text embedding model to use.

• collection_name (str) – MongoDB Collection to add the texts to. Defaults to “default”.

• database_name (str) – MongoDB Database where to store texts. Defaults to “default”.

• index_name (str) – Name of the Atlas Search index. defaults to ‘default’

• wait_until_ready (float) – Wait this time for Atlas to finish indexing the stored text. Defaults to None.

• score_threshold (float | None)

• kwargs (Dict[str, Any])

async aadd_documents(documents: list[Document], **kwargs: Any) → list[str]

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

Parameters:

• documents (list[Document]) – Documents to add to the vectorstore.

• kwargs (Any) – Additional keyword arguments.

Returns:

List of IDs of the added texts.

Raises:

ValueError – If the number of IDs does not match the number of documents.

Return type:

list[str]

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:

• texts (Iterable[str]) – Iterable of strings to add to the vectorstore.

• metadatas (list[dict] | None) – Optional list of metadatas associated with the texts. Default is None.

• ids (list[str] | None) – Optional list

• **kwargs (Any) – vectorstore specific parameters.

Returns:

List of ids from adding the texts into the vectorstore.

Raises:

• 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.

Return type:

list[str]

async aclear(**kwargs: Any) → None

Async clear cache that can take additional keyword arguments.

Parameters:

kwargs (Any)

Return type:

None

add_documents(documents: List[Document], ids: List[str] | None = None, batch_size: int = 100000, **kwargs: Any) → List[str]

Add documents to the vectorstore.

Parameters:

• documents (List[Document]) – Documents to add to the vectorstore.

• ids (List[str] | None) – Optional list of unique ids that will be used as index in VectorStore. See note on ids in add_texts.

• batch_size (int) – Number of documents to insert at a time. Tuning this may help with performance and sidestep MongoDB limits.

• kwargs (Any)

Returns:

List of IDs of the added texts.

Return type:

List[str]

add_texts(texts: Iterable[str], metadatas: List[Dict[str, Any]] | None = None, ids: List[str] | None = None, **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:

• texts (Iterable[str]) – Iterable of strings to add to the vectorstore.

• metadatas (List[Dict[str, Any]] | None) – Optional list of metadatas associated with the texts.

• ids (List[str] | None) – Optional list of unique ids that will be used as index in VectorStore. See note on ids.

• kwargs (Any)

Returns:

List of ids added to the vectorstore.

Return type:

List[str]

async adelete(ids: List[str] | None = None, **kwargs: Any) → bool | None

Delete by vector ID or other criteria.

Parameters:

• ids (List[str] | None) – List of ids to delete.

• **kwargs (Any) – Other keyword arguments that subclasses might use.

Returns:

True if deletion is successful, False otherwise, None if not implemented.

Return type:

Optional[bool]

async classmethod afrom_documents(documents: list[Document], embedding: Embeddings, **kwargs: Any) → VST

Async return VectorStore initialized from documents and embeddings.

Parameters:

• documents (list[Document]) – List of Documents to add to the vectorstore.

• embedding (Embeddings) – Embedding function to use.

• kwargs (Any) – Additional keyword arguments.

Returns:

VectorStore initialized from documents and embeddings.

Return type:

VectorStore

async classmethod afrom_texts(texts: list[str], embedding: Embeddings, metadatas: list[dict] | None = None, *, ids: list[str] | None = None, **kwargs: Any) → VST

Async return VectorStore initialized from texts and embeddings.

Parameters:

• texts (list[str]) – Texts to add to the vectorstore.

• embedding (Embeddings) – Embedding function to use.

• metadatas (list[dict] | None) – Optional list of metadatas associated with the texts. Default is None.

• ids (list[str] | None) – Optional list of IDs associated with the texts.

• kwargs (Any) – Additional keyword arguments.

Returns:

VectorStore initialized from texts and embeddings.

Return type:

VectorStore

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:

ids (Sequence[str]) – List of ids to retrieve.

Returns:

List of Documents.

Return type:

list[Document]

Added in version 0.2.11.

async alookup(prompt: str, llm_string: str) → Sequence[Generation] | 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:

• 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.

• 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.

Returns:

On a cache miss, return None. On a cache hit, return the cached value. The cached value is a list of Generations (or subclasses).

Return type:

Sequence[Generation] | None

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:

• query (str) – Text to look up documents similar to.

• k (int) – Number of Documents to return. Defaults to 4.

• fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm. Default is 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.

• kwargs (Any)

Returns:

List of Documents selected by maximal marginal relevance.

Return type:

list[Document]

async amax_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, pre_filter: Dict[str, Any] | None = None, post_filter_pipeline: List[Dict] | None = None, oversampling_factor: int = 10, **kwargs: Any) → List[Document]

Return docs selected using the maximal marginal relevance.

Parameters:

• embedding (List[float])

• k (int)

• fetch_k (int)

• lambda_mult (float)

• pre_filter (Dict[str, Any] | None)

• post_filter_pipeline (List[Dict] | None)

• oversampling_factor (int)

• kwargs (Any)

Return type:

List[Document]

as_retriever(**kwargs: Any) → VectorStoreRetriever

Return VectorStoreRetriever initialized from this VectorStore.

Parameters:

**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:

Retriever class for VectorStore.

Return type:

VectorStoreRetriever

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'}}
)

async asearch(query: str, search_type: str, **kwargs: Any) → list[Document]

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

Parameters:

• query (str) – Input text.

• search_type (str) – Type of search to perform. Can be “similarity”, “mmr”, or “similarity_score_threshold”.

• **kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query.

Raises:

ValueError – If search_type is not one of “similarity”, “mmr”, or “similarity_score_threshold”.

Return type:

list[Document]

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

Async return docs most similar to query.

Parameters:

• query (str) – Input text.

• k (int) – Number of Documents to return. Defaults to 4.

• **kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query.

Return type:

list[Document]

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

Async return docs most similar to embedding vector.

Parameters:

• embedding (list[float]) – Embedding to look up documents similar to.

• k (int) – Number of Documents to return. Defaults to 4.

• **kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query vector.

Return type:

list[Document]

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:

• query (str) – Input text.

• k (int) – Number of Documents to return. Defaults to 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:

List of Tuples of (doc, similarity_score)

Return type:

list[tuple[Document, float]]

async asimilarity_search_with_score(*args: Any, **kwargs: Any) → list[tuple[Document, float]]

Async run similarity search with distance.

Parameters:

• *args (Any) – Arguments to pass to the search method.

• **kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Tuples of (doc, similarity_score).

Return type:

list[tuple[Document, float]]

async aupdate(prompt: str, llm_string: str, return_val: Sequence[Generation]) → 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:

• 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.

• 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.

• return_val (Sequence[Generation]) – The value to be cached. The value is a list of Generations (or subclasses).

Return type:

None

bulk_embed_and_insert_texts(texts: List[str] | Iterable[str], metadatas: List[dict] | Generator[dict, Any, Any], ids: List[str] | None = None) → List[str]

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

See add_texts for additional details.

Parameters:

• texts (List[str] | Iterable[str])

• metadatas (List[dict] | Generator[dict, Any, Any])

• ids (List[str] | None)

Return type:

List[str]

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”)

Parameters:

kwargs (Any)

Return type:

None

create_vector_search_index(dimensions: int, filters: List[str] | None = None, update: bool = False, wait_until_complete: float | None = None) → 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:

• dimensions (int) – Number of dimensions in embedding

• filters (Optional[List[Dict[str, str]]], optional) – additional filters

• definition. (for index) – Defaults to None.

• update (Optional[bool]) – Updates existing vectorSearch index. Defaults to 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.

Return type:

None

delete(ids: List[str] | None = None, **kwargs: Any) → bool | None

Delete documents from VectorStore by ids.

Parameters:

• ids (List[str] | None) – List of ids to delete.

• **kwargs (Any) – Other keyword arguments passed to Collection.delete_many()

Returns:

True if deletion is successful, False otherwise, None if not implemented.

Return type:

Optional[bool]

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:

• connection_string (str) – A valid MongoDB connection URI.

• namespace (str) – A valid MongoDB namespace (database and collection).

• embedding (Embeddings) – The text embedding model to use for the vector store.

• kwargs (Any)

Returns:

A new MongoDBAtlasVectorSearch instance.

Return type:

MongoDBAtlasVectorSearch

classmethod from_documents(documents: list[Document], embedding: Embeddings, **kwargs: Any) → VST

Return VectorStore initialized from documents and embeddings.

Parameters:

• documents (list[Document]) – List of Documents to add to the vectorstore.

• embedding (Embeddings) – Embedding function to use.

• kwargs (Any) – Additional keyword arguments.

Returns:

VectorStore initialized from documents and embeddings.

Return type:

VectorStore

classmethod from_texts(texts: List[str], embedding: Embeddings, metadatas: List[Dict] | None = None, collection: Collection | None = None, ids: List[str] | None = None, **kwargs: Any) → MongoDBAtlasVectorSearch

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

This is a user-friendly interface that:

1. Embeds documents.

2. 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

Parameters:

• texts (List[str])

• embedding (Embeddings)

• metadatas (List[Dict] | None)

• collection (Collection | None)

• ids (List[str] | None)

• kwargs (Any)

Return type:

MongoDBAtlasVectorSearch

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:

ids (Sequence[str]) – List of ids to retrieve.

Returns:

List of Documents.

Return type:

list[Document]

Added in version 0.2.11.

lookup(prompt: str, llm_string: str) → Sequence[Generation] | None

Look up based on prompt and llm_string.

Parameters:

• prompt (str)

• llm_string (str)

Return type:

Sequence[Generation] | None

max_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, pre_filter: Dict[str, Any] | None = None, post_filter_pipeline: List[Dict] | None = 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:

• query (str) – Text to look up documents similar to.

• k (int) – (Optional) number of documents to return. Defaults to 4.

• fetch_k (int) – (Optional) number of documents to fetch before passing to MMR algorithm. Defaults to 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.

• pre_filter (Dict[str, Any] | None) – List of MQL match expressions comparing an indexed field

• post_filter_pipeline (List[Dict] | None) – (Optional) pipeline of MongoDB aggregation stages following the $vectorSearch stage.

• kwargs (Any)

Returns:

List of documents selected by maximal marginal relevance.

Return type:

List[Document]

max_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, pre_filter: Dict[str, Any] | None = None, post_filter_pipeline: List[Dict] | None = 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:

• embedding (List[float]) – Embedding to look up documents similar to.

• k (int) – Number of Documents to return. Defaults to 4.

• fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm.

• 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.

• pre_filter (Dict[str, Any] | None) – (Optional) dictionary of arguments to filter document fields on.

• post_filter_pipeline (List[Dict] | None) – (Optional) pipeline of MongoDB aggregation stages following the vectorSearch stage.

• oversampling_factor (int) – Multiple of k used when generating number of candidates in HNSW Vector Search,

• kwargs (Any) – Additional arguments are specific to the search_type

Returns:

List of Documents selected by maximal marginal relevance.

Return type:

List[Document]

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

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

Parameters:

• query (str) – Input text

• search_type (str) – Type of search to perform. Can be “similarity”, “mmr”, or “similarity_score_threshold”.

• **kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query.

Raises:

ValueError – If search_type is not one of “similarity”, “mmr”, or “similarity_score_threshold”.

Return type:

list[Document]

similarity_search(query: str, k: int = 4, pre_filter: Dict[str, Any] | None = None, post_filter_pipeline: List[Dict] | None = 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:

List of documents most similar to the query and their scores.

Parameters:

• query (str)

• k (int)

• pre_filter (Dict[str, Any] | None)

• post_filter_pipeline (List[Dict] | None)

• oversampling_factor (int)

• include_scores (bool)

• include_embeddings (bool)

• kwargs (Any)

Return type:

List[Document]

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

Return docs most similar to embedding vector.

Parameters:

• embedding (list[float]) – Embedding to look up documents similar to.

• k (int) – Number of Documents to return. Defaults to 4.

• **kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query vector.

Return type:

list[Document]

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:

• query (str) – Input text.

• k (int) – Number of Documents to return. Defaults to 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:

List of Tuples of (doc, similarity_score).

Return type:

list[tuple[Document, float]]

similarity_search_with_score(query: str, k: int = 4, pre_filter: Dict[str, Any] | None = None, post_filter_pipeline: List[Dict] | None = 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:

List of documents most similar to the query and their scores.

Parameters:

• query (str)

• k (int)

• pre_filter (Dict[str, Any] | None)

• post_filter_pipeline (List[Dict] | None)

• oversampling_factor (int)

• include_embeddings (bool)

• kwargs (Any)

Return type:

List[Tuple[Document, float]]

update(prompt: str, llm_string: str, return_val: Sequence[Generation], wait_until_ready: float | None = None) → None

Update cache based on prompt and llm_string.

Parameters:

• prompt (str)

• llm_string (str)

• return_val (Sequence[Generation])

• wait_until_ready (float | None)

Return type:

None