Class OpenSearchVectorStore

constructor

• new OpenSearchVectorStore(embeddings, args): OpenSearchVectorStore

• Parameters

  • embeddings: EmbeddingsInterface
  • args: OpenSearchClientArgs

  Returns OpenSearchVectorStore

FilterType

addDocuments

• addDocuments(documents): Promise<void>

• Method to add documents to the OpenSearch index. It first converts the documents to vectors using the embeddings, then adds the vectors to the index.

  Parameters

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

    The documents to be added to the OpenSearch index.

  Returns Promise<void>

  Promise resolving to void.

addVectors

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

• Method to add vectors to the OpenSearch index. It ensures the index exists, then adds the vectors and associated documents to the index.

  Parameters

  • vectors: number[][]

    The vectors to be added to the OpenSearch index.
  • documents: Document<Record<string, any>>[]

    The documents associated with the vectors.
  • Optionaloptions: {
        ids?: string[];
    }

    Optional parameter that can contain the IDs for the documents.

    • Optionalids?: string[]

  Returns Promise<void>

  Promise resolving to void.

buildMetadataTerms

• buildMetadataTerms(filter): object

• Builds metadata terms for OpenSearch queries.

  This function takes a filter object and constructs an array of query terms compatible with OpenSearch 2.x. It supports a variety of query types including term, terms, terms_set, ids, range, prefix, exists, fuzzy, wildcard, and regexp. Reference: https://opensearch.org/docs/latest/query-dsl/term/index/

  Parameters

  • filter: undefined | OpenSearchFilter

    The filter object used to construct query terms. Each key represents a field, and the value specifies the type of query and its parameters.

  Returns object

  An array of OpenSearch query terms.

  Example

  // Example filter:
  const filter = {
    status: { "exists": true },
    age: { "gte": 30, "lte": 40 },
    tags: ["tag1", "tag2"],
    description: { "wildcard": "*test*" },
  
  };
  
  // Resulting query terms:
  const queryTerms = buildMetadataTerms(filter);
  // queryTerms would be an array of OpenSearch query objects.
  Copy

deleteIfExists

• deleteIfExists(): Promise<void>

• Method to delete the OpenSearch index if it exists.

  Returns Promise<void>

  Promise resolving to void.

doesIndexExist

• doesIndexExist(): Promise<boolean>

• Method to check if the OpenSearch index exists.

  Returns Promise<boolean>

  Promise resolving to a boolean indicating whether the index exists.

similaritySearchVectorWithScore

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

• Method to perform a similarity search on the OpenSearch index using a query vector. It returns the k most similar documents and their scores.

  Parameters

  • query: number[]

    The query vector.
  • k: number

    The number of similar documents to return.
  • Optionalfilter: OpenSearchFilter

    Optional filter for the OpenSearch query.

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

  Promise resolving to an array of tuples, each containing a Document and its score.

StaticfromDocuments

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

• Static method to create a new OpenSearchVectorStore from an array of Documents, embeddings, and OpenSearch client arguments.

  Parameters

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

    The documents to be added to the OpenSearch index.
  • embeddings: EmbeddingsInterface

    The embeddings used to convert the documents into vectors.
  • dbConfig: OpenSearchClientArgs

    The OpenSearch client arguments.

  Returns Promise<OpenSearchVectorStore>

  Promise resolving to a new instance of OpenSearchVectorStore.

StaticfromExistingIndex

• fromExistingIndex(embeddings, dbConfig): Promise<OpenSearchVectorStore>

• Static method to create a new OpenSearchVectorStore from an existing OpenSearch index, embeddings, and OpenSearch client arguments.

  Parameters

  • embeddings: EmbeddingsInterface

    The embeddings used to convert the documents into vectors.
  • dbConfig: OpenSearchClientArgs

    The OpenSearch client arguments.

  Returns Promise<OpenSearchVectorStore>

  Promise resolving to a new instance of OpenSearchVectorStore.

StaticfromTexts

• fromTexts(texts, metadatas, embeddings, args): Promise<OpenSearchVectorStore>

• Static method to create a new OpenSearchVectorStore from an array of texts, their metadata, embeddings, and OpenSearch client arguments.

  Parameters

  • texts: string[]

    The texts to be converted into documents and added to the OpenSearch index.
  • metadatas: object | object[]

    The metadata associated with the texts. Can be an array of objects or a single object.
  • embeddings: EmbeddingsInterface

    The embeddings used to convert the texts into vectors.
  • args: OpenSearchClientArgs

    The OpenSearch client arguments.

  Returns Promise<OpenSearchVectorStore>

  Promise resolving to a new instance of OpenSearchVectorStore.