AstraDBVectorStore#

class langchain_astradb.vectorstores.AstraDBVectorStore(*, collection_name: str, embedding: Embeddings | None = None, token: str | TokenProvider | None = None, api_endpoint: str | None = None, environment: str | None = None, namespace: str | None = None, metric: str | None = None, batch_size: int | None = None, bulk_insert_batch_concurrency: int | None = None, bulk_insert_overwrite_concurrency: int | None = None, bulk_delete_concurrency: int | None = None, setup_mode: SetupMode | None = None, pre_delete_collection: bool = False, metadata_indexing_include: Iterable[str] | None = None, metadata_indexing_exclude: Iterable[str] | None = None, collection_indexing_policy: dict[str, Any] | None = None, collection_vector_service_options: CollectionVectorServiceOptions | None = None, collection_embedding_api_key: str | EmbeddingHeadersProvider | None = None, content_field: str | None = None, ignore_invalid_documents: bool = False, autodetect_collection: bool = False, ext_callers: list[tuple[str | None, str | None] | str | None] | None = None, component_name: str = 'langchain_vectorstore', astra_db_client: AstraDBClient | None = None, async_astra_db_client: AsyncAstraDBClient | None = None)[source]#

AstraDB vector store integration.

Setup:

Install the langchain-astradb package and head to the AstraDB website, create an account, create a new database and create an application token.

pip install -qU langchain-astradb
Key init args — indexing params:
collection_name: str

Name of the collection.

embedding: Embeddings

Embedding function to use.

Key init args — client params:
api_endpoint: str

AstraDB API endpoint.

token: str

API token for Astra DB usage.

namespace: Optional[str]

Namespace (aka keyspace) where the collection is created

Instantiate:

Get your API endpoint and application token from the dashboard of your database.

import getpass
from langchain_astradb import AstraDBVectorStore
from langchain_openai import OpenAIEmbeddings

ASTRA_DB_API_ENDPOINT = getpass.getpass("ASTRA_DB_API_ENDPOINT = ")
ASTRA_DB_APPLICATION_TOKEN = getpass.getpass("ASTRA_DB_APPLICATION_TOKEN = ")

vector_store = AstraDBVectorStore(
    collection_name="astra_vector_langchain",
    embedding=OpenAIEmbeddings(),
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)

Have the vector store figure out its configuration (documents scheme on DB) from an existing collection, in the case of server-side-embeddings:

import getpass
from langchain_astradb import AstraDBVectorStore

ASTRA_DB_API_ENDPOINT = getpass.getpass("ASTRA_DB_API_ENDPOINT = ")
ASTRA_DB_APPLICATION_TOKEN = getpass.getpass("ASTRA_DB_APPLICATION_TOKEN = ")

vector_store = AstraDBVectorStore(
    collection_name="astra_vector_langchain",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
    autodetect_collection=True,
)
Add Documents:
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:
vector_store.delete(ids=["3"])
Search:
results = vector_store.similarity_search(query="thud",k=1)
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

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

thud [{'bar': 'baz'}]
Search with score:
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}]")

[SIM=0.916135] foo [{'baz': 'bar'}]
Async:
# 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}]")

[SIM=0.916135] foo [{'baz': 'bar'}]
Use as Retriever:
retriever = vector_store.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={"k": 1, "score_threshold": 0.5},
)
retriever.invoke("thud")

[Document(metadata={'bar': 'baz'}, page_content='thud')]

Wrapper around DataStax Astra DB for vector-store workloads.

For quickstart and details, visit https://docs.datastax.com/en/astra-db-serverless/index.html

Parameters:

  • embedding (Embeddings | None) – the embeddings function or service to use. This enables client-side embedding functions or calls to external embedding providers. If embedding is provided, arguments collection_vector_service_options and collection_embedding_api_key cannot be provided.

  • collection_name (str) – name of the Astra DB collection to create/use.

  • token (str | TokenProvider | None) – API token for Astra DB usage, either in the form of a string or a subclass of astrapy.authentication.TokenProvider. If not provided, the environment variable ASTRA_DB_APPLICATION_TOKEN is inspected.

  • api_endpoint (str | None) – full URL to the API endpoint, such as https://<DB-ID>-us-east1.apps.astra.datastax.com. If not provided, the environment variable ASTRA_DB_API_ENDPOINT is inspected.

  • environment (str | None) – a string specifying the environment of the target Data API. If omitted, defaults to “prod” (Astra DB production). Other values are in astrapy.constants.Environment enum class.

  • namespace (str | None) – namespace (aka keyspace) where the collection is created. If not provided, the environment variable ASTRA_DB_KEYSPACE is inspected. Defaults to the database’s “default namespace”.

  • metric (str | None) – similarity function to use out of those available in Astra DB. If left out, it will use Astra DB API’s defaults (i.e. “cosine” - but, for performance reasons, “dot_product” is suggested if embeddings are normalized to one).

  • batch_size (int | None) – Size of document chunks for each individual insertion API request. If not provided, astrapy defaults are applied.

  • bulk_insert_batch_concurrency (int | None) – Number of threads or coroutines to insert batches concurrently.

  • bulk_insert_overwrite_concurrency (int | None) – Number of threads or coroutines in a batch to insert pre-existing entries.

  • bulk_delete_concurrency (int | None) – Number of threads or coroutines for multiple-entry deletes.

  • setup_mode (SetupMode | None) – mode used to create the collection (SYNC, ASYNC or OFF).

  • pre_delete_collection (bool) – whether to delete the collection before creating it. If False and the collection already exists, the collection will be used as is.

  • metadata_indexing_include (Iterable[str] | None) – an allowlist of the specific metadata subfields that should be indexed for later filtering in searches.

  • metadata_indexing_exclude (Iterable[str] | None) – a denylist of the specific metadata subfields that should not be indexed for later filtering in searches.

  • collection_indexing_policy (dict[str, Any] | None) – a full “indexing” specification for what fields should be indexed for later filtering in searches. This dict must conform to to the API specifications (see https://docs.datastax.com/en/astra-db-serverless/api-reference/collections.html#the-indexing-option)

  • collection_vector_service_options (CollectionVectorServiceOptions | None) – specifies the use of server-side embeddings within Astra DB. If passing this parameter, embedding cannot be provided.

  • collection_embedding_api_key (str | EmbeddingHeadersProvider | None) – for usage of server-side embeddings within Astra DB. With this parameter one can supply an API Key that will be passed to Astra DB with each data request. This parameter can be either a string or a subclass of astrapy.authentication.EmbeddingHeadersProvider. This is useful when the service is configured for the collection, but no corresponding secret is stored within Astra’s key management system.

  • content_field (str | None) – name of the field containing the textual content in the documents when saved on Astra DB. For vectorize collections, this cannot be specified; for non-vectorize collection, defaults to “content”. The special value “*” can be passed only if autodetect_collection=True. In this case, the actual name of the key for the textual content is guessed by inspection of a few documents from the collection, under the assumption that the longer strings are the most likely candidates. Please understand the limitations of this method and get some understanding of your data before passing "*" for this parameter.

  • ignore_invalid_documents (bool) – if False (default), exceptions are raised when a document is found on the Astra DB collection that does not have the expected shape. If set to True, such results from the database are ignored and a warning is issued. Note that in this case a similarity search may end up returning fewer results than the required k.

  • autodetect_collection (bool) – if True, turns on autodetect behavior. The store will look for an existing collection of the provided name and infer the store settings from it. Default is False. In autodetect mode, content_field can be given as "*", meaning that an attempt will be made to determine it by inspection (unless vectorize is enabled, in which case content_field is ignored). In autodetect mode, the store not only determines whether embeddings are client- or server-side, but - most importantly - switches automatically between “nested” and “flat” representations of documents on DB (i.e. having the metadata key-value pairs grouped in a metadata field or spread at the documents’ top-level). The former scheme is the native mode of the AstraDBVectorStore; the store resorts to the latter in case of vector collections populated with external means (such as a third-party data import tool) before applying an AstraDBVectorStore to them. Note that the following parameters cannot be used if this is True: metric, setup_mode, metadata_indexing_include, metadata_indexing_exclude, collection_indexing_policy, collection_vector_service_options.

  • ext_callers (list[tuple[str | None, str | None] | str | None] | None) – one or more caller identities to identify Data API calls in the User-Agent header. This is a list of (name, version) pairs, or just strings if no version info is provided, which, if supplied, becomes the leading part of the User-Agent string in all API requests related to this component.

  • component_name (str) – the string identifying this specific component in the stack of usage info passed as the User-Agent string to the Data API. Defaults to “langchain_vectorstore”, but can be overridden if this component actually serves as the building block for another component (such as a Graph Vector Store).

  • astra_db_client (AstraDBClient | None) – DEPRECATED starting from version 0.3.5. Please use ‘token’, ‘api_endpoint’ and optionally ‘environment’. you can pass an already-created ‘astrapy.db.AstraDB’ instance (alternatively to ‘token’, ‘api_endpoint’ and ‘environment’).

  • async_astra_db_client (AsyncAstraDBClient | None) – DEPRECATED starting from version 0.3.5. Please use ‘token’, ‘api_endpoint’ and optionally ‘environment’. you can pass an already-created ‘astrapy.db.AsyncAstraDB’ instance (alternatively to ‘token’, ‘api_endpoint’ and ‘environment’).

Note

For concurrency in synchronous add_texts():, as a rule of thumb, on a typical client machine it is suggested to keep the quantity bulk_insert_batch_concurrency * bulk_insert_overwrite_concurrency much below 1000 to avoid exhausting the client multithreading/networking resources. The hardcoded defaults are somewhat conservative to meet most machines’ specs, but a sensible choice to test may be:

  • bulk_insert_batch_concurrency = 80

  • bulk_insert_overwrite_concurrency = 10

A bit of experimentation is required to nail the best results here, depending on both the machine/network specs and the expected workload (specifically, how often a write is an update of an existing id). Remember you can pass concurrency settings to individual calls to add_texts() and add_documents() as well.

Attributes

embeddings

Accesses the supplied embeddings object.

Methods

__init__(*, collection_name[, embedding, ...])

Wrapper around DataStax Astra DB for vector-store workloads.

aadd_documents(documents, **kwargs)

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

aadd_texts(texts[, metadatas, ids, ...])

Run texts through the embeddings and add them to the vectorstore.

aclear()

Empty the collection of all its stored entries.

add_documents(documents, **kwargs)

Add or update documents in the vectorstore.

add_texts(texts[, metadatas, ids, ...])

Run texts through the embeddings and add them to the vectorstore.

adelete([ids, concurrency])

Delete by vector ids.

adelete_by_document_id(document_id)

Remove a single document from the store, given its document ID.

adelete_by_metadata_filter(filter)

Delete all documents matching a certain metadata filtering condition.

adelete_collection()

Completely delete the collection from the database.

afrom_documents(documents[, embedding])

Create an Astra DB vectorstore from a document list.

afrom_texts(texts[, embedding, metadatas, ids])

Create an Astra DB vectorstore from raw texts.

aget_by_document_id(document_id)

Retrieve a single document from the store, given its document ID.

aget_by_ids(ids, /)

Async get documents by their IDs.

amax_marginal_relevance_search(query[, k, ...])

Return docs selected using the maximal marginal relevance.

amax_marginal_relevance_search_by_vector(...)

Return docs selected using the maximal marginal relevance.

ametadata_search([filter, n])

Get documents via a metadata search.

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, filter])

Return docs most similar to query.

asimilarity_search_by_vector(embedding[, k, ...])

Return docs most similar to embedding vector.

asimilarity_search_with_embedding(query[, ...])

Return docs most similar to the query with embedding.

asimilarity_search_with_embedding_by_vector(...)

Return docs most similar to embedding vector with embedding.

asimilarity_search_with_relevance_scores(query)

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

asimilarity_search_with_score(query[, k, filter])

Return docs most similar to query with score.

asimilarity_search_with_score_by_vector(...)

Return docs most similar to embedding vector with score.

asimilarity_search_with_score_id(query[, k, ...])

Return docs most similar to the query with score and id.

asimilarity_search_with_score_id_by_vector(...)

Return docs most similar to embedding vector with score and id.

aupdate_metadata(id_to_metadata, *[, ...])

Add/overwrite the metadata of existing documents.

clear()

Empty the collection of all its stored entries.

delete([ids, concurrency])

Delete by vector ids.

delete_by_document_id(document_id)

Remove a single document from the store, given its document ID.

delete_by_metadata_filter(filter)

Delete all documents matching a certain metadata filtering condition.

delete_collection()

Completely delete the collection from the database.

filter_to_query(filter_dict)

Prepare a query for use on DB based on metadata filter.

from_documents(documents[, embedding])

Create an Astra DB vectorstore from a document list.

from_texts(texts[, embedding, metadatas, ids])

Create an Astra DB vectorstore from raw texts.

get_by_document_id(document_id)

Retrieve a single document from the store, given its document ID.

get_by_ids(ids, /)

Get documents by their IDs.

max_marginal_relevance_search(query[, k, ...])

Return docs selected using the maximal marginal relevance.

max_marginal_relevance_search_by_vector(...)

Return docs selected using the maximal marginal relevance.

metadata_search([filter, n])

Get documents via a metadata search.

search(query, search_type, **kwargs)

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

similarity_search(query[, k, filter])

Return docs most similar to query.

similarity_search_by_vector(embedding[, k, ...])

Return docs most similar to embedding vector.

similarity_search_with_embedding(query[, k, ...])

Return docs most similar to the query with embedding.

similarity_search_with_embedding_by_vector(...)

Return docs most similar to embedding vector with embedding.

similarity_search_with_relevance_scores(query)

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

similarity_search_with_score(query[, k, filter])

Return docs most similar to query with score.

similarity_search_with_score_by_vector(embedding)

Return docs most similar to embedding vector with score.

similarity_search_with_score_id(query[, k, ...])

Return docs most similar to the query with score and id.

similarity_search_with_score_id_by_vector(...)

Return docs most similar to embedding vector with score and id.

update_metadata(id_to_metadata, *[, ...])

Add/overwrite the metadata of existing documents.
__init__(*, collection_name: str, embedding: Embeddings | None = None, token: str | TokenProvider | None = None, api_endpoint: str | None = None, environment: str | None = None, namespace: str | None = None, metric: str | None = None, batch_size: int | None = None, bulk_insert_batch_concurrency: int | None = None, bulk_insert_overwrite_concurrency: int | None = None, bulk_delete_concurrency: int | None = None, setup_mode: SetupMode | None = None, pre_delete_collection: bool = False, metadata_indexing_include: Iterable[str] | None = None, metadata_indexing_exclude: Iterable[str] | None = None, collection_indexing_policy: dict[str, Any] | None = None, collection_vector_service_options: CollectionVectorServiceOptions | None = None, collection_embedding_api_key: str | EmbeddingHeadersProvider | None = None, content_field: str | None = None, ignore_invalid_documents: bool = False, autodetect_collection: bool = False, ext_callers: list[tuple[str | None, str | None] | str | None] | None = None, component_name: str = 'langchain_vectorstore', astra_db_client: AstraDBClient | None = None, async_astra_db_client: AsyncAstraDBClient | None = None) → None[source]#

Wrapper around DataStax Astra DB for vector-store workloads.

For quickstart and details, visit https://docs.datastax.com/en/astra-db-serverless/index.html

Parameters:

  • embedding (Embeddings | None) – the embeddings function or service to use. This enables client-side embedding functions or calls to external embedding providers. If embedding is provided, arguments collection_vector_service_options and collection_embedding_api_key cannot be provided.

  • collection_name (str) – name of the Astra DB collection to create/use.

  • token (str | TokenProvider | None) – API token for Astra DB usage, either in the form of a string or a subclass of astrapy.authentication.TokenProvider. If not provided, the environment variable ASTRA_DB_APPLICATION_TOKEN is inspected.

  • api_endpoint (str | None) – full URL to the API endpoint, such as https://<DB-ID>-us-east1.apps.astra.datastax.com. If not provided, the environment variable ASTRA_DB_API_ENDPOINT is inspected.

  • environment (str | None) – a string specifying the environment of the target Data API. If omitted, defaults to “prod” (Astra DB production). Other values are in astrapy.constants.Environment enum class.

  • namespace (str | None) – namespace (aka keyspace) where the collection is created. If not provided, the environment variable ASTRA_DB_KEYSPACE is inspected. Defaults to the database’s “default namespace”.

  • metric (str | None) – similarity function to use out of those available in Astra DB. If left out, it will use Astra DB API’s defaults (i.e. “cosine” - but, for performance reasons, “dot_product” is suggested if embeddings are normalized to one).

  • batch_size (int | None) – Size of document chunks for each individual insertion API request. If not provided, astrapy defaults are applied.

  • bulk_insert_batch_concurrency (int | None) – Number of threads or coroutines to insert batches concurrently.

  • bulk_insert_overwrite_concurrency (int | None) – Number of threads or coroutines in a batch to insert pre-existing entries.

  • bulk_delete_concurrency (int | None) – Number of threads or coroutines for multiple-entry deletes.

  • setup_mode (SetupMode | None) – mode used to create the collection (SYNC, ASYNC or OFF).

  • pre_delete_collection (bool) – whether to delete the collection before creating it. If False and the collection already exists, the collection will be used as is.

  • metadata_indexing_include (Iterable[str] | None) – an allowlist of the specific metadata subfields that should be indexed for later filtering in searches.

  • metadata_indexing_exclude (Iterable[str] | None) – a denylist of the specific metadata subfields that should not be indexed for later filtering in searches.

  • collection_indexing_policy (dict[str, Any] | None) – a full “indexing” specification for what fields should be indexed for later filtering in searches. This dict must conform to to the API specifications (see https://docs.datastax.com/en/astra-db-serverless/api-reference/collections.html#the-indexing-option)

  • collection_vector_service_options (CollectionVectorServiceOptions | None) – specifies the use of server-side embeddings within Astra DB. If passing this parameter, embedding cannot be provided.

  • collection_embedding_api_key (str | EmbeddingHeadersProvider | None) – for usage of server-side embeddings within Astra DB. With this parameter one can supply an API Key that will be passed to Astra DB with each data request. This parameter can be either a string or a subclass of astrapy.authentication.EmbeddingHeadersProvider. This is useful when the service is configured for the collection, but no corresponding secret is stored within Astra’s key management system.

  • content_field (str | None) – name of the field containing the textual content in the documents when saved on Astra DB. For vectorize collections, this cannot be specified; for non-vectorize collection, defaults to “content”. The special value “*” can be passed only if autodetect_collection=True. In this case, the actual name of the key for the textual content is guessed by inspection of a few documents from the collection, under the assumption that the longer strings are the most likely candidates. Please understand the limitations of this method and get some understanding of your data before passing "*" for this parameter.

  • ignore_invalid_documents (bool) – if False (default), exceptions are raised when a document is found on the Astra DB collection that does not have the expected shape. If set to True, such results from the database are ignored and a warning is issued. Note that in this case a similarity search may end up returning fewer results than the required k.

  • autodetect_collection (bool) – if True, turns on autodetect behavior. The store will look for an existing collection of the provided name and infer the store settings from it. Default is False. In autodetect mode, content_field can be given as "*", meaning that an attempt will be made to determine it by inspection (unless vectorize is enabled, in which case content_field is ignored). In autodetect mode, the store not only determines whether embeddings are client- or server-side, but - most importantly - switches automatically between “nested” and “flat” representations of documents on DB (i.e. having the metadata key-value pairs grouped in a metadata field or spread at the documents’ top-level). The former scheme is the native mode of the AstraDBVectorStore; the store resorts to the latter in case of vector collections populated with external means (such as a third-party data import tool) before applying an AstraDBVectorStore to them. Note that the following parameters cannot be used if this is True: metric, setup_mode, metadata_indexing_include, metadata_indexing_exclude, collection_indexing_policy, collection_vector_service_options.

  • ext_callers (list[tuple[str | None, str | None] | str | None] | None) – one or more caller identities to identify Data API calls in the User-Agent header. This is a list of (name, version) pairs, or just strings if no version info is provided, which, if supplied, becomes the leading part of the User-Agent string in all API requests related to this component.

  • component_name (str) – the string identifying this specific component in the stack of usage info passed as the User-Agent string to the Data API. Defaults to “langchain_vectorstore”, but can be overridden if this component actually serves as the building block for another component (such as a Graph Vector Store).

  • astra_db_client (AstraDBClient | None) – DEPRECATED starting from version 0.3.5. Please use ‘token’, ‘api_endpoint’ and optionally ‘environment’. you can pass an already-created ‘astrapy.db.AstraDB’ instance (alternatively to ‘token’, ‘api_endpoint’ and ‘environment’).

  • async_astra_db_client (AsyncAstraDBClient | None) – DEPRECATED starting from version 0.3.5. Please use ‘token’, ‘api_endpoint’ and optionally ‘environment’. you can pass an already-created ‘astrapy.db.AsyncAstraDB’ instance (alternatively to ‘token’, ‘api_endpoint’ and ‘environment’).

Return type:

None

Note

For concurrency in synchronous add_texts():, as a rule of thumb, on a typical client machine it is suggested to keep the quantity bulk_insert_batch_concurrency * bulk_insert_overwrite_concurrency much below 1000 to avoid exhausting the client multithreading/networking resources. The hardcoded defaults are somewhat conservative to meet most machines’ specs, but a sensible choice to test may be:

  • bulk_insert_batch_concurrency = 80

  • bulk_insert_overwrite_concurrency = 10

A bit of experimentation is required to nail the best results here, depending on both the machine/network specs and the expected workload (specifically, how often a write is an update of an existing id). Remember you can pass concurrency settings to individual calls to add_texts() and add_documents() as well.

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, *, batch_size: int | None = None, batch_concurrency: int | None = None, overwrite_concurrency: int | None = None, **kwargs: Any) → list[str][source]#

Run texts through the embeddings and add them to the vectorstore.

If passing explicit ids, those entries whose id is in the store already will be replaced.

Parameters:

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

  • metadatas (list[dict] | None) – Optional list of metadatas.

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

  • batch_size (int | None) – Size of document chunks for each individual insertion API request. If not provided, defaults to the vector-store overall defaults (which in turn falls to astrapy defaults).

  • batch_concurrency (int | None) – number of simultaneous coroutines to process insertion batches concurrently. Defaults to the vector-store overall setting if not provided.

  • overwrite_concurrency (int | None) – number of simultaneous coroutines to process pre-existing documents in each batch. Defaults to the vector-store overall setting if not provided.

  • **kwargs (Any) – Additional arguments are ignored.

Return type:

list[str]

Note

There are constraints on the allowed field names in the metadata dictionaries, coming from the underlying Astra DB API. For instance, the $ (dollar sign) cannot be used in the dict keys. See this document for details: https://docs.datastax.com/en/astra-db-serverless/api-reference/overview.html#limits

Returns:

The list of ids of the added texts.

Parameters:

  • texts (Iterable[str])

  • metadatas (list[dict] | None)

  • ids (list[str] | None)

  • batch_size (int | None)

  • batch_concurrency (int | None)

  • overwrite_concurrency (int | None)

  • kwargs (Any)

Return type:

list[str]

async aclear() → None[source]#

Empty the collection of all its stored entries.

Return type:

None

add_documents(documents: list[Document], **kwargs: Any) → list[str]#

Add or update documents in the vectorstore.

Parameters:

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

  • kwargs (Any) – Additional keyword arguments. if kwargs contains ids and documents contain ids, the ids in the kwargs will receive precedence.

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]

add_texts(texts: Iterable[str], metadatas: list[dict] | None = None, ids: list[str] | None = None, *, batch_size: int | None = None, batch_concurrency: int | None = None, overwrite_concurrency: int | None = None, **kwargs: Any) → list[str][source]#

Run texts through the embeddings and add them to the vectorstore.

If passing explicit ids, those entries whose id is in the store already will be replaced.

Parameters:

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

  • metadatas (list[dict] | None) – Optional list of metadatas.

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

  • batch_size (int | None) – Size of document chunks for each individual insertion API request. If not provided, defaults to the vector-store overall defaults (which in turn falls to astrapy defaults).

  • batch_concurrency (int | None) – number of threads to process insertion batches concurrently. Defaults to the vector-store overall setting if not provided.

  • overwrite_concurrency (int | None) – number of threads to process pre-existing documents in each batch. Defaults to the vector-store overall setting if not provided.

  • **kwargs (Any) – Additional arguments are ignored.

Return type:

list[str]

Note

There are constraints on the allowed field names in the metadata dictionaries, coming from the underlying Astra DB API. For instance, the $ (dollar sign) cannot be used in the dict keys. See this document for details: https://docs.datastax.com/en/astra-db-serverless/api-reference/overview.html#limits

Returns:

The list of ids of the added texts.

Parameters:

  • texts (Iterable[str])

  • metadatas (list[dict] | None)

  • ids (list[str] | None)

  • batch_size (int | None)

  • batch_concurrency (int | None)

  • overwrite_concurrency (int | None)

  • kwargs (Any)

Return type:

list[str]

async adelete(ids: list[str] | None = None, concurrency: int | None = None, **kwargs: Any) → bool | None[source]#

Delete by vector ids.

Parameters:

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

  • concurrency (int | None) – max number of simultaneous coroutines for single-doc delete requests. Defaults to vector-store overall setting.

  • **kwargs (Any) – Additional arguments are ignored.

Returns:

True if deletion is (entirely) successful, False otherwise.

Return type:

bool | None

async adelete_by_document_id(document_id: str) → bool[source]#

Remove a single document from the store, given its document ID.

Parameters:

document_id (str) – The document ID

Returns:

True if a document has indeed been deleted, False if ID not found.

Return type:

bool

async adelete_by_metadata_filter(filter: dict[str, Any]) → int[source]#

Delete all documents matching a certain metadata filtering condition.

This operation does not use the vector embeddings in any way, it simply removes all documents whose metadata match the provided condition.

Parameters:

filter (dict[str, Any]) – Filter on the metadata to apply. The filter cannot be empty.

Returns:

A number expressing the amount of deleted documents.

Return type:

int

async adelete_collection() → None[source]#

Completely delete the collection from the database.

Completely delete the collection from the database (as opposed to aclear(), which empties it only). Stored data is lost and unrecoverable, resources are freed. Use with caution.

Return type:

None

async classmethod afrom_documents(documents: list[Document], embedding: Embeddings | None = None, **kwargs: Any) → AstraDBVectorStore[source]#

Create an Astra DB vectorstore from a document list.

Utility method that defers to afrom_texts() (see that one).

Args: see afrom_texts(), except here you have to supply documents

in place of texts and metadatas.

Returns:

an AstraDBVectorStore vectorstore.

Parameters:
Return type:

AstraDBVectorStore

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

Create an Astra DB vectorstore from raw texts.

Parameters:

  • texts (list[str]) – the texts to insert.

  • embedding (Embeddings | None) – embedding function to use.

  • metadatas (list[dict] | None) – metadata dicts for the texts.

  • ids (list[str] | None) – ids to associate to the texts.

  • **kwargs (Any) – you can pass any argument that you would to aadd_texts() and/or to the AstraDBVectorStore constructor (see these methods for details). These arguments will be routed to the respective methods as they are.

Returns:

an AstraDBVectorStore vectorstore.

Return type:

AstraDBVectorStore

async aget_by_document_id(document_id: str) → Document | None[source]#

Retrieve a single document from the store, given its document ID.

Parameters:

document_id (str) – The document ID

Returns:

The the document if it exists. Otherwise None.

Return type:

Document | None

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.

Return docs selected using the maximal marginal relevance.

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

Parameters:

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

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

  • 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.

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

  • **kwargs (Any) – Additional arguments are ignored.

Returns:

The 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, filter: dict[str, Any] | None = None, **kwargs: Any) → list[Document][source]#

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.

  • 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.

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

  • **kwargs (Any) – Additional arguments are ignored.

Returns:

The list of Documents selected by maximal marginal relevance.

Return type:

list[Document]

Get documents via a metadata search.

Parameters:

  • filter (dict[str, Any] | None) – the metadata to query for.

  • n (int) – the maximum number of documents to return.

Return type:

Iterable[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]

Return docs most similar to query.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

  • **kwargs (Any) – Additional arguments are ignored.

Returns:

The list of Documents most similar to the query.

Return type:

list[Document]

async asimilarity_search_by_vector(embedding: list[float], k: int = 4, filter: dict[str, Any] | None = None, **kwargs: Any) → list[Document][source]#

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.

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

  • **kwargs (Any) – Additional arguments are ignored.

Returns:

The list of Documents most similar to the query vector.

Return type:

list[Document]

async asimilarity_search_with_embedding(query: str, k: int = 4, filter: dict[str, Any] | None = None) → tuple[list[float], list[tuple[Document, list[float]]]][source]#

Return docs most similar to the query with embedding.

Also includes the query embedding vector.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

Returns:

(The query embedding vector, The list of (Document, embedding), the most similar to the query vector.).

Return type:

tuple[list[float], list[tuple[Document, list[float]]]]

async asimilarity_search_with_embedding_by_vector(embedding: list[float], k: int = 4, filter: dict[str, Any] | None = None) → list[tuple[Document, list[float]]][source]#

Return docs most similar to embedding vector with embedding.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

Returns:

(The query embedding vector, The list of (Document, embedding), the most similar to the query vector.).

Return type:

list[tuple[Document, list[float]]]

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(query: str, k: int = 4, filter: dict[str, Any] | None = None) → list[tuple[Document, float]][source]#

Return docs most similar to query with score.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

Returns:

The list of (Document, score), the most similar to the query vector.

Return type:

list[tuple[Document, float]]

async asimilarity_search_with_score_by_vector(embedding: list[float], k: int = 4, filter: dict[str, Any] | None = None) → list[tuple[Document, float]][source]#

Return docs most similar to embedding vector with score.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

Returns:

The list of (Document, score), the most similar to the query vector.

Return type:

list[tuple[Document, float]]

async asimilarity_search_with_score_id(query: str, k: int = 4, filter: dict[str, Any] | None = None) → list[tuple[Document, float, str]][source]#

Return docs most similar to the query with score and id.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

Returns:

The list of (Document, score, id), the most similar to the query.

Return type:

list[tuple[Document, float, str]]

async asimilarity_search_with_score_id_by_vector(embedding: list[float], k: int = 4, filter: dict[str, Any] | None = None) → list[tuple[Document, float, str]][source]#

Return docs most similar to embedding vector with score and id.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

Returns:

The list of (Document, score, id), the most similar to the query vector.

Return type:

list[tuple[Document, float, str]]

async aupdate_metadata(id_to_metadata: dict[str, dict], *, overwrite_concurrency: int | None = None) → int[source]#

Add/overwrite the metadata of existing documents.

For each document to update, the new metadata dictionary is appended to the existing metadata, overwriting individual keys that existed already.

Parameters:

  • id_to_metadata (dict[str, dict]) – map from the Document IDs to modify to the new metadata for updating. Keys in this dictionary that do not correspond to an existing document will be silently ignored. The values of this map are metadata dictionaries for updating the documents. Any pre-existing metadata will be merged with these entries, which take precedence on a key-by-key basis.

  • overwrite_concurrency (int | None) – number of asynchronous tasks to process the updates. Defaults to the vector-store overall setting if not provided.

Returns:

the number of documents successfully updated (i.e. found to exist, since even an update with {} as the new metadata counts as successful.)

Return type:

int

clear() → None[source]#

Empty the collection of all its stored entries.

Return type:

None

delete(ids: list[str] | None = None, concurrency: int | None = None, **kwargs: Any) → bool | None[source]#

Delete by vector ids.

Parameters:

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

  • concurrency (int | None) – max number of threads issuing single-doc delete requests. Defaults to vector-store overall setting.

  • **kwargs (Any) – Additional arguments are ignored.

Returns:

True if deletion is (entirely) successful, False otherwise.

Return type:

bool | None

delete_by_document_id(document_id: str) → bool[source]#

Remove a single document from the store, given its document ID.

Parameters:

document_id (str) – The document ID

Returns:

True if a document has indeed been deleted, False if ID not found.

Return type:

bool

delete_by_metadata_filter(filter: dict[str, Any]) → int[source]#

Delete all documents matching a certain metadata filtering condition.

This operation does not use the vector embeddings in any way, it simply removes all documents whose metadata match the provided condition.

Parameters:

filter (dict[str, Any]) – Filter on the metadata to apply. The filter cannot be empty.

Returns:

A number expressing the amount of deleted documents.

Return type:

int

delete_collection() → None[source]#

Completely delete the collection from the database.

Completely delete the collection from the database (as opposed to clear(), which empties it only). Stored data is lost and unrecoverable, resources are freed. Use with caution.

Return type:

None

filter_to_query(filter_dict: dict[str, Any] | None) → dict[str, Any][source]#

Prepare a query for use on DB based on metadata filter.

Encode an “abstract” filter clause on metadata into a query filter condition aware of the collection schema choice.

Parameters:

filter_dict (dict[str, Any] | None) – a metadata condition in the form {“field”: “value”} or related.

Returns:

the corresponding mapping ready for use in queries, aware of the details of the schema used to encode the document on DB.

Return type:

dict[str, Any]

classmethod from_documents(documents: list[Document], embedding: Embeddings | None = None, **kwargs: Any) → AstraDBVectorStore[source]#

Create an Astra DB vectorstore from a document list.

Utility method that defers to from_texts() (see that one).

Parameters:

  • texts – the texts to insert.

  • documents (list[Document]) – a list of Document objects for insertion in the store.

  • embedding (Embeddings | None) – the embedding function to use in the store.

  • **kwargs (Any) – you can pass any argument that you would to add_texts() and/or to the AstraDBVectorStore constructor (see these methods for details). These arguments will be routed to the respective methods as they are.

Returns:

an AstraDBVectorStore vectorstore.

Return type:

AstraDBVectorStore

classmethod from_texts(texts: list[str], embedding: Embeddings | None = None, metadatas: list[dict] | None = None, ids: list[str] | None = None, **kwargs: Any) → AstraDBVectorStore[source]#

Create an Astra DB vectorstore from raw texts.

Parameters:

  • texts (list[str]) – the texts to insert.

  • embedding (Embeddings | None) – the embedding function to use in the store.

  • metadatas (list[dict] | None) – metadata dicts for the texts.

  • ids (list[str] | None) – ids to associate to the texts.

  • **kwargs (Any) – you can pass any argument that you would to add_texts() and/or to the AstraDBVectorStore constructor (see these methods for details). These arguments will be routed to the respective methods as they are.

Returns:

an AstraDBVectorStore vectorstore.

Return type:

AstraDBVectorStore

get_by_document_id(document_id: str) → Document | None[source]#

Retrieve a single document from the store, given its document ID.

Parameters:

document_id (str) – The document ID

Returns:

The the document if it exists. Otherwise None.

Return type:

Document | None

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.

Return docs selected using the maximal marginal relevance.

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

Parameters:

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

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

  • 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.

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

  • **kwargs (Any) – Additional arguments are ignored.

Returns:

The 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, filter: dict[str, Any] | None = None, **kwargs: Any) → list[Document][source]#

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.

  • 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.

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

  • **kwargs (Any) – Additional arguments are ignored.

Returns:

The list of Documents selected by maximal marginal relevance.

Return type:

list[Document]

Get documents via a metadata search.

Parameters:

  • filter (dict[str, Any] | None) – the metadata to query for.

  • n (int) – the maximum number of documents to return.

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]

Return docs most similar to query.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

  • **kwargs (Any) – Additional arguments are ignored.

Returns:

The list of Documents most similar to the query.

Return type:

list[Document]

similarity_search_by_vector(embedding: list[float], k: int = 4, filter: dict[str, Any] | None = None, **kwargs: Any) → list[Document][source]#

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.

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

  • **kwargs (Any) – Additional arguments are ignored.

Returns:

The list of Documents most similar to the query vector.

Return type:

list[Document]

similarity_search_with_embedding(query: str, k: int = 4, filter: dict[str, Any] | None = None) → tuple[list[float], list[tuple[Document, list[float]]]][source]#

Return docs most similar to the query with embedding.

Also includes the query embedding vector.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

Returns:

(The query embedding vector, The list of (Document, embedding), the most similar to the query vector.).

Return type:

tuple[list[float], list[tuple[Document, list[float]]]]

similarity_search_with_embedding_by_vector(embedding: list[float], k: int = 4, filter: dict[str, Any] | None = None) → list[tuple[Document, list[float]]][source]#

Return docs most similar to embedding vector with embedding.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

Returns:

(The query embedding vector, The list of (Document, embedding), the most similar to the query vector.).

Return type:

list[tuple[Document, list[float]]]

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, filter: dict[str, Any] | None = None) → list[tuple[Document, float]][source]#

Return docs most similar to query with score.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

Returns:

The list of (Document, score), the most similar to the query vector.

Return type:

list[tuple[Document, float]]

similarity_search_with_score_by_vector(embedding: list[float], k: int = 4, filter: dict[str, Any] | None = None) → list[tuple[Document, float]][source]#

Return docs most similar to embedding vector with score.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

Returns:

The list of (Document, score), the most similar to the query vector.

Return type:

list[tuple[Document, float]]

similarity_search_with_score_id(query: str, k: int = 4, filter: dict[str, Any] | None = None) → list[tuple[Document, float, str]][source]#

Return docs most similar to the query with score and id.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

Returns:

The list of (Document, score, id), the most similar to the query.

Return type:

list[tuple[Document, float, str]]

similarity_search_with_score_id_by_vector(embedding: list[float], k: int = 4, filter: dict[str, Any] | None = None) → list[tuple[Document, float, str]][source]#

Return docs most similar to embedding vector with score and id.

Parameters:

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

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

  • filter (dict[str, Any] | None) – Filter on the metadata to apply.

Returns:

The list of (Document, score, id), the most similar to the query vector.

Return type:

list[tuple[Document, float, str]]

update_metadata(id_to_metadata: dict[str, dict], *, overwrite_concurrency: int | None = None) → int[source]#

Add/overwrite the metadata of existing documents.

For each document to update, the new metadata dictionary is appended to the existing metadata, overwriting individual keys that existed already.

Parameters:

  • id_to_metadata (dict[str, dict]) – map from the Document IDs to modify to the new metadata for updating. Keys in this dictionary that do not correspond to an existing document will be silently ignored. The values of this map are metadata dictionaries for updating the documents. Any pre-existing metadata will be merged with these entries, which take precedence on a key-by-key basis.

  • overwrite_concurrency (int | None) – number of threads to process the updates. Defaults to the vector-store overall setting if not provided.

Returns:

the number of documents successfully updated (i.e. found to exist, since even an update with {} as the new metadata counts as successful.)

Return type:

int