Vector Stores

Class that provides methods for creating and managing a collection of documents in an AnalyticDB, adding documents or vectors to the collection, performing similarity search on vectors, and creating a

Example usage:

// Initialize the vector store
const vectorStore = new AzionVectorStore(embeddings, {
  dbName: "mydb",
  tableName: "documents"
});

// Setup database with hybrid search and meta

Azure AI Search vector store. To use this, you should have:

• the @azure/search-documents NPM package installed
• an endpoint and key to the Azure AI Search instance

If you directly provide a `Sear

Class for interacting with the Cassandra database. It extends the VectorStore class and provides methods for adding vectors and documents, searching for similar vectors, and creating instances from te

Chroma vector store integration.

Setup: Install @langchain/community and chromadb.

npm install @langchain/community chromadb

[Constructor args](https://api.js.langchain.com/class

Class for interacting with the ClickHouse database. It extends the VectorStore class and provides methods for adding vectors and documents, searching for similar vectors, and creating instances from t

Class that implements a vector store using Hierarchical Navigable Small World (HNSW) graphs. It extends the SaveableVectorStore class and provides methods for adding documents and vectors, performing

Class that implements a vector store using CloseVector, It extends the SaveableVectorStore class and provides methods for adding documents and vectors, performing similarity searches, and saving and l

Class that is a wrapper around Convex storage and vector search. It is used to insert embeddings in Convex documents with a vector search index, and perform a vector search on them.

ConvexVectorStore

Class for interacting with the Couchbase database using Query service for vector search. It extends the VectorStore class and provides methods for adding vectors and documents, and searching for simil

Class for interacting with the Couchbase database. It extends the VectorStore class and provides methods for adding vectors and documents, and searching for similar vectors. Initiate the class using i

Elasticsearch vector store supporting vector and hybrid search.

Hybrid search combines kNN vector search with BM25 full-text search using RRF. Enable by passing a HybridRetrievalStrategy to the con

Hybrid search strategy combining vector and BM25 search using RRF.

A class that wraps the FAISS (Facebook AI Similarity Search) vector database for efficient similarity search and clustering of dense vectors.

A Document that optionally includes the ID of the document.

A class that represents a connection to a Google Vertex AI Matching Engine instance.

Class that implements a vector store using Hierarchical Navigable Small World (HNSW) graphs. It extends the SaveableVectorStore class and provides methods for adding documents and vectors, performing

A wrapper for an open-source database for vector-search with persistent storage. It simplifies retrieval, filtering, and management of embeddings.

A vector store using LibSQL/Turso for storage and retrieval.

MariaDB vector store integration.

Setup: Install @langchain/community and mariadb.

If you wish to generate ids, you should also install the uuid package.

npm install @langchain/commun

Class for interacting with a Milvus database. Extends the VectorStore class.

A vector store that uses the Momento Vector Index.

Class for interacting with the MyScale database. It extends the VectorStore class and provides methods for adding vectors and documents, searching for similar vectors, and creating instances from text

Class that provides an interface to a Neon Postgres database. It extends the VectorStore base class and implements methods for adding documents and vectors, performing similarity searches, and ensur

Class that provides a wrapper around the OpenSearch service for vector search. It provides methods for adding documents and vectors to the OpenSearch index, searching for similar vectors, and managing

PGVector vector store integration.

Setup: Install @langchain/community and pg.

If you wish to generate ids, you should also install the uuid package.

npm install @langchain/community

A specific implementation of the VectorStore class that is designed to work with Prisma. It provides methods for adding models, documents, and vectors, as well as for performing similarity searches.

Exposes Rockset's vector store/search functionality

Error that is thrown when a RocksetStore function is called after destroy() is called (meaning the collection would be deleted).

Generic Rockset vector storage error

Class for interacting with SingleStoreDB, a high-performance distributed SQL database. It provides vector storage and vector functions.

Supabase vector store integration.

Setup: Install @langchain/community and @supabase/supabase-js.

npm install @langchain/community @supabase/supabase-js

See https://js.langchain.com

Class for managing and operating vector search applications with Tigris, an open-source Serverless NoSQL Database and Search Platform.

Class that provides an interface to a Postgres vector database. It extends the VectorStore base class and implements methods for adding documents and vectors, performing similarity searches, and ens

Class that extends the Document base class and adds an embedding property. It represents a document in the vector store.

Typesense vector store.

The main class that extends the 'VectorStore' class. It provides methods for interacting with Upstash index, such as adding documents, deleting documents, performing similarity search and more.

Class that extends SaveableVectorStore and provides methods for adding documents and vectors to a usearch index, performing similarity searches, and saving the index.

Class for interacting with the Vectara API. Extends the VectorStore class.

Class that provides an interface to a Vercel Postgres vector database. It extends the VectorStore base class and implements methods for adding documents and vectors and performing similarity searche

Class that extends VectorStore. It allows to perform similarity search using Voi similarity search engine. The class requires passing Voy Client as an input parameter.

Class for interacting with a Xata database as a VectorStore. Provides methods to add documents and vectors to the database, delete entries, and perform similarity searches.

ZepVectorStore is a VectorStore implementation that uses the Zep long-term memory store as a backend.

If the collection does not exist, it will be created automatically.

Requires zep-js to be inst

ZepCloudVectorStore is a VectorStore implementation that uses the Zep long-term memory store as a backend.

If the collection does not exist, it will be created automatically.

Requires `@getzep/zep-c

Interface defining the arguments required to create an instance of AnalyticDBVectorStore.

Interface for the arguments required to initialize an Azion library.

Configuration options for the AzureAISearchStore constructor.

Azure AI Search settings.

Extends the DataStax driver's client options with additional configurations for service providers, enabling the customization of Cassandra client instances based on specific service requirements. This

Defines the parameters for the delete method in the Chroma class. It can either contain an array of ids of the documents to be deleted or a filter object to specify the documents to be deleted

Type for filtering search results in the ClickHouse database.

Arguments for the ClickHouseStore class, which include the host, port, protocol, username, password, index type, index parameters, index query params, column map, database, table.

Mapping of columns in the ClickHouse database.

Arguments for creating a CloseVectorNode instance, extending CloseVectorHNSWLibArgs.

Arguments for creating a CloseVectorWeb instance, extending CloseVectorHNSWLibArgs.

This interface define the optional fields for adding vector

• ids - vector of ids for each document. If undefined, then uuid will be used
• metadata - vector of metadata object for each document

This interface defines the fields required to initialize a query vector store These are the fields part of config:

Interface for create_index method parameters

This interface define the optional fields for adding vector

• ids - vector of ids for each document. If undefined, then uuid will be used
• metadata - vector of metadata object for each document

This interface defines the fields required to initialize a vector store These are the fields part of config:

Interface defining the arguments required to create an Elasticsearch client.

Configuration options for hybrid retrieval strategy.

Interface for the arguments required to initialize a FaissStore instance.

Allows us to create IdDocument classes that contain the ID.

Parameters necessary to configure the Matching Engine.

Used to represent parameters that are necessary to delete documents from the matching engine. These must be a list of string IDs

Information about the Matching Engine public API endpoint. Primarily exported to allow for testing.

Interface defining the arguments required to create an instance of HanaDB.

Interface for the arguments that can be passed to the HNSWLib constructor. It extends HNSWLibBase and includes properties for the document store and HNSW index.

Interface for the base configuration of HNSWLib. It includes the space name and the number of dimensions.

Interface for LibSQLVectorStore configuration options.

Interface that defines the arguments required to create a MariaDBStore instance. It includes MariaDB connection options, table name and verbosity level.

Interface for the arguments required by the Milvus class constructor.

Mapping of columns in the MyScale database.

Type for filtering search results in the MyScale database.

Arguments for the MyScaleStore class, which include the host, port, protocol, username, password, index type, index parameters, column map, database, table, and metric.

Interface that defines the arguments required to create a NeonPostgres instance. It includes Postgres connection options, table name, filter, and verbosity level.

Interface defining the arguments required to create an instance of the OpenSearchVectorStore class. It includes the OpenSearch client, index name, and vector search options.

Interface that defines the arguments required to create a PGVectorStore instance. It includes Postgres connection options, table name, filter, and verbosity level.

Configuration for column types to enable proper type casting in SQL queries. This is particularly important for columns that require explicit casting, such as UUID columns in PostgreSQL.

Vector store arguments RocksetStore

Interface for the arguments required to initialize a Supabase library.

Interface that defines the arguments required to create a TypeORMVectorStore instance. It includes Postgres connection options, table name, filter, and verbosity level.

Typesense vector store configuration.

This interface defines the arguments for the UpstashVectorStore class.

Interface that defines the arguments that can be passed to the USearch constructor. It includes optional properties for a docstore, index, and mapping.

Interface for the context configuration used in Vectara API calls.

Interface for the file objects to be uploaded to Vectara.

Interface for the arguments required to initialize a VectaraStore instance.

Interface that defines the arguments required to create a VercelPostgres instance. It includes Postgres connection options, table name, filter, and verbosity level.

Interface for the arguments required to create a XataClient. Includes the client instance and the table name.

Interface for the arguments required to initialize a ZepVectorStore instance.

Interface for the configuration options for a ZepVectorStore instance.

Interface for the parameters required to delete documents from a ZepVectorStore instance.

Interface for the configuration options for a ZepCloudVectorStore instance.

Interface for the parameters required to delete documents from a ZepCloudVectorStore instance.