Class RedisVectorStore

Deprecated

Install and import from the "@langchain/redis" integration package instead. Class representing a RedisVectorStore. It extends the VectorStore class and includes methods for adding documents and vectors, performing similarity searches, managing the index, and more.

Hierarchy

  • VectorStore
    • RedisVectorStore

Constructors

constructor

Properties

FilterType contentKey createIndexOptions embeddings filter? indexName indexOptions keyPrefix metadataKey vectorKey

Methods

addDocuments addVectors asRetriever checkIndexExists createIndex delete dropIndex maxMarginalRelevanceSearch? similaritySearch similaritySearchVectorWithScore similaritySearchWithScore toJSON toJSONNotImplemented fromDocuments fromTexts

Constructors

constructor

Properties

FilterType

FilterType: RedisVectorStoreFilterType

contentKey

contentKey: string

createIndexOptions

createIndexOptions: CreateOptions

embeddings

embeddings: EmbeddingsInterface

Embeddings interface for generating vector embeddings from text queries, enabling vector-based similarity searches.

Optionalfilter

filter?: RedisVectorStoreFilterType

indexName

indexName: string

indexOptions

indexOptions: CreateSchemaFlatVectorField | CreateSchemaHNSWVectorField

keyPrefix

keyPrefix: string

metadataKey

metadataKey: string

vectorKey

vectorKey: string

Methods

addDocuments

  • addDocuments(documents, options?): Promise<void>

  • Method for adding documents to the RedisVectorStore. It first converts the documents to texts and then adds them as vectors.

    Parameters

    • documents: Document<Record<string, any>>[]

      The documents to add.

    • Optionaloptions: RedisAddOptions

      Optional parameters for adding the documents.

    Returns Promise<void>

    A promise that resolves when the documents have been added.

addVectors

  • addVectors(vectors, documents, __namedParameters?): Promise<void>

  • Method for adding vectors to the RedisVectorStore. It checks if the index exists and creates it if it doesn't, then adds the vectors in batches.

    Parameters

    • vectors: number[][]

      The vectors to add.

    • documents: Document<Record<string, any>>[]

      The documents associated with the vectors.

    • __namedParameters: RedisAddOptions = {}

    Returns Promise<void>

    A promise that resolves when the vectors have been added.

asRetriever

  • asRetriever(kOrFields?, filter?, callbacks?, tags?, metadata?, verbose?): VectorStoreRetriever<RedisVectorStore>

  • Creates a VectorStoreRetriever instance with flexible configuration options.

    Parameters

    • OptionalkOrFields: number | Partial<VectorStoreRetrieverInput<RedisVectorStore>>

      If a number is provided, it sets the k parameter (number of items to retrieve).

      • If an object is provided, it should contain various configuration options.
    • Optionalfilter: RedisVectorStoreFilterType

      Optional filter criteria to limit the items retrieved based on the specified filter type.

    • Optionalcallbacks: Callbacks

      Optional callbacks that may be triggered at specific stages of the retrieval process.

    • Optionaltags: string[]

      Tags to categorize or label the VectorStoreRetriever. Defaults to an empty array if not provided.

    • Optionalmetadata: Record<string, unknown>

      Additional metadata as key-value pairs to add contextual information for the retrieval process.

    • Optionalverbose: boolean

      If true, enables detailed logging for the retrieval process. Defaults to false.

    Returns VectorStoreRetriever<RedisVectorStore>

    • A configured VectorStoreRetriever instance based on the provided parameters.

    Example

    Basic usage with a k value:

    const retriever = myVectorStore.asRetriever(5);

    Usage with a configuration object:

    const retriever = myVectorStore.asRetriever({
      k: 10,
      filter: myFilter,
      tags: ['example', 'test'],
      verbose: true,
      searchType: 'mmr',
      searchKwargs: { alpha: 0.5 },
    });

checkIndexExists

createIndex

  • createIndex(dimensions?): Promise<void>

  • Method for creating an index in the RedisVectorStore. If the index already exists, it does nothing.

    Parameters

    • dimensions: number = 1536

      The dimensions of the index

    Returns Promise<void>

    A promise that resolves when the index has been created.

delete

  • delete(params): Promise<void>

  • Deletes vectors from the vector store.

    Parameters

    • params: {
          deleteAll: boolean;
      }

      The parameters for deleting vectors.

      • deleteAll: boolean

    Returns Promise<void>

    A promise that resolves when the vectors have been deleted.

dropIndex

  • dropIndex(deleteDocuments?): Promise<boolean>

  • Method for dropping an index from the RedisVectorStore.

    Parameters

    • OptionaldeleteDocuments: boolean

      Optional boolean indicating whether to drop the associated documents.

    Returns Promise<boolean>

    A promise that resolves to a boolean indicating whether the index was dropped.

OptionalmaxMarginalRelevanceSearch

  • maxMarginalRelevanceSearch(query, options, _callbacks): Promise<DocumentInterface<Record<string, any>>[]>

  • Return documents selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to the query AND diversity among selected documents.

    Parameters

    • query: string

      Text to look up documents similar to.

    • options: MaxMarginalRelevanceSearchOptions<RedisVectorStoreFilterType>
    • _callbacks: undefined | Callbacks

    Returns Promise<DocumentInterface<Record<string, any>>[]>

    • List of documents selected by maximal marginal relevance.

similaritySearch

  • similaritySearch(query, k?, filter?, _callbacks?): Promise<DocumentInterface<Record<string, any>>[]>

  • Searches for documents similar to a text query by embedding the query and performing a similarity search on the resulting vector.

    Parameters

    • query: string

      Text query for finding similar documents.

    • Optionalk: number

      Number of similar results to return. Defaults to 4.

    • Optionalfilter: RedisVectorStoreFilterType

      Optional filter based on FilterType.

    • Optional_callbacks: Callbacks

      Optional callbacks for monitoring search progress

    Returns Promise<DocumentInterface<Record<string, any>>[]>

    A promise resolving to an array of DocumentInterface instances representing similar documents.

similaritySearchVectorWithScore

  • similaritySearchVectorWithScore(query, k, filter?): Promise<[Document<Record<string, any>>, number][]>

  • Method for performing a similarity search in the RedisVectorStore. It returns the documents and their scores.

    Parameters

    • query: number[]

      The query vector.

    • k: number

      The number of nearest neighbors to return.

    • Optionalfilter: RedisVectorStoreFilterType

      Optional filter to apply to the search.

    Returns Promise<[Document<Record<string, any>>, number][]>

    A promise that resolves to an array of documents and their scores.

similaritySearchWithScore

  • similaritySearchWithScore(query, k?, filter?, _callbacks?): Promise<[DocumentInterface<Record<string, any>>, number][]>

  • Searches for documents similar to a text query by embedding the query, and returns results with similarity scores.

    Parameters

    • query: string

      Text query for finding similar documents.

    • Optionalk: number

      Number of similar results to return. Defaults to 4.

    • Optionalfilter: RedisVectorStoreFilterType

      Optional filter based on FilterType.

    • Optional_callbacks: Callbacks

      Optional callbacks for monitoring search progress

    Returns Promise<[DocumentInterface<Record<string, any>>, number][]>

    A promise resolving to an array of tuples, each containing a document and its similarity score.

toJSON

  • toJSON(): Serialized

  • Returns Serialized

toJSONNotImplemented

StaticfromDocuments

  • fromDocuments(docs, embeddings, dbConfig): Promise<RedisVectorStore>

  • Static method for creating a new instance of RedisVectorStore from documents. It adds the documents to the RedisVectorStore.

    Parameters

    • docs: Document<Record<string, any>>[]

      The documents to add.

    • embeddings: EmbeddingsInterface

      The embeddings to use.

    • dbConfig: RedisVectorStoreConfig

      The configuration for the RedisVectorStore.

    Returns Promise<RedisVectorStore>

    A promise that resolves to a new instance of RedisVectorStore.

StaticfromTexts

  • fromTexts(texts, metadatas, embeddings, dbConfig): Promise<RedisVectorStore>

  • Static method for creating a new instance of RedisVectorStore from texts. It creates documents from the texts and metadata, then adds them to the RedisVectorStore.

    Parameters

    • texts: string[]

      The texts to add.

    • metadatas: object | object[]

      The metadata associated with the texts.

    • embeddings: EmbeddingsInterface

      The embeddings to use.

    • dbConfig: RedisVectorStoreConfig

      The configuration for the RedisVectorStore.

    Returns Promise<RedisVectorStore>

    A promise that resolves to a new instance of RedisVectorStore.

Settings

Member Visibility

On This Page

Constructors
Properties
Methods