Class AzureAISearchVectorStore

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 SearchClient instance, you need to ensure that an index has been created. When using and endpoint and key, the index will be created automatically if it does not exist.

Hierarchy

  • VectorStore
    • AzureAISearchVectorStore

Constructors

constructor

Properties

FilterType embeddings

Methods

addDocuments addVectors asRetriever createSearchIndexDefinition delete ensureIndexExists hybridSearchVectorWithScore maxMarginalRelevanceSearch semanticHybridSearchVectorWithScore similaritySearch similaritySearchVectorWithScore similaritySearchWithScore toJSON toJSONNotImplemented fromDocuments fromTexts

Constructors

constructor

Properties

FilterType

FilterType: AzureAISearchFilterType

embeddings

embeddings: EmbeddingsInterface

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

Methods

addDocuments

addVectors

  • addVectors(vectors, documents, options?): Promise<string[]>

  • Adds vectors to the AzureAISearchVectorStore.

    Parameters

    • vectors: number[][]

      Vectors to be added.

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

      Corresponding documents to be added.

    • Optionaloptions: AzureAISearchAddDocumentsOptions

      Options for adding documents.

    Returns Promise<string[]>

    A promise that resolves to the ids of the added documents.

asRetriever

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

  • Creates a VectorStoreRetriever instance with flexible configuration options.

    Parameters

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

      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: AzureAISearchFilterType

      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<AzureAISearchVectorStore>

    • 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 },
    });

ProtectedcreateSearchIndexDefinition

delete

  • delete(params): Promise<void>

  • Removes specified documents from the AzureAISearchVectorStore using IDs or a filter.

    Parameters

    • params: {
          filter?: AzureAISearchFilterType;
          ids?: string | string[];
      }

      Object that includes either an array of IDs or a filter for the data to be deleted.

    Returns Promise<void>

    A promise that resolves when the documents have been removed.

ProtectedensureIndexExists

  • ensureIndexExists(indexClient): Promise<void>
  • Protected

    Ensures that an index exists on the AzureAISearchVectorStore.

    Parameters

    • indexClient: SearchIndexClient

      The Azure AI Search index client.

    Returns Promise<void>

    A promise that resolves when the AzureAISearchVectorStore index has been initialized.

hybridSearchVectorWithScore

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

  • Performs a hybrid search using query text.

    Parameters

    • query: string

      Query text for the similarity search.

    • OptionalqueryVector: number[]

      Query vector for the similarity search. If not provided, the query text will be embedded.

    • k: number = 4
    • filter: undefined | AzureAISearchFilterType = undefined

      Optional filter options for the documents.

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

    Promise that resolves to a list of documents and their corresponding similarity scores.

maxMarginalRelevanceSearch

  • maxMarginalRelevanceSearch(query, options): Promise<Document<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<AzureAISearchFilterType>

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

    List of documents selected by maximal marginal relevance.

semanticHybridSearchVectorWithScore

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

  • Performs a hybrid search with semantic reranker using query text.

    Parameters

    • query: string

      Query text for the similarity search.

    • OptionalqueryVector: number[]

      Query vector for the similarity search. If not provided, the query text will be embedded.

    • k: number = 4
    • filter: undefined | AzureAISearchFilterType = undefined

      Optional filter options for the documents.

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

    Promise that resolves to a list of documents and their corresponding similarity scores.

similaritySearch

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

  • Performs a similarity search using query type specified in configuration. If the query type is not specified, it defaults to similarity search.

    Parameters

    • query: string

      Query text for the similarity search.

    • k: number = 4
    • filter: undefined | AzureAISearchFilterType = undefined

      Optional filter options for the documents.

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

    Promise that resolves to a list of documents and their corresponding similarity scores.

similaritySearchVectorWithScore

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

  • Performs a similarity search on the vectors stored in the collection.

    Parameters

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

    Promise that resolves to a list of documents and their corresponding similarity scores.

similaritySearchWithScore

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

  • Performs a similarity search using query type specified in configuration. If the query type is not specified, it defaults to similarity hybrid search.

    Parameters

    • query: string

      Query text for the similarity search.

    • k: number = 4
    • filter: undefined | AzureAISearchFilterType = undefined

      Optional filter options for the documents.

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

    Promise that resolves to a list of documents and their corresponding similarity scores.

toJSON

  • toJSON(): Serialized

  • Returns Serialized

toJSONNotImplemented

StaticfromDocuments

StaticfromTexts

  • fromTexts(texts, metadatas, embeddings, config): Promise<AzureAISearchVectorStore>

  • Static method to create an instance of AzureAISearchVectorStore from a list of texts. It first converts the texts to vectors and then adds them to the collection.

    Parameters

    • texts: string[]

      List of texts to be converted to vectors.

    • metadatas: object | object[]

      Metadata for the texts.

    • embeddings: EmbeddingsInterface

      Embeddings to be used for conversion.

    • config: AzureAISearchConfig

      Database configuration for Azure AI Search.

    Returns Promise<AzureAISearchVectorStore>

    Promise that resolves to a new instance of AzureAISearchVectorStore.

Settings

Member Visibility

On This Page

Constructors
Properties
Methods