@langchain/community/dist/vectorstores/momento_vector_index.d.ts.map

Third-party integrations for LangChain.js

{"version":3,"file":"momento_vector_index.d.ts","names":["IVectorIndexClient","Document","EmbeddingsInterface","MaxMarginalRelevanceSearchOptions","VectorStore","DocumentProps","MomentoVectorIndexLibArgs","DeleteProps","MomentoVectorIndex","Record","Promise"],"sources":["../../src/vectorstores/momento_vector_index.d.ts"],"sourcesContent":["import { IVectorIndexClient } from \"@gomomento/sdk-core\";\nimport { Document } from \"@langchain/core/documents\";\nimport type { EmbeddingsInterface } from \"@langchain/core/embeddings\";\nimport { MaxMarginalRelevanceSearchOptions, VectorStore } from \"@langchain/core/vectorstores\";\nexport interface DocumentProps {\n    ids: string[];\n}\nexport interface MomentoVectorIndexLibArgs {\n    /**\n     * The Momento Vector Index client.\n     */\n    client: IVectorIndexClient;\n    /**\n     * The name of the index to use to store the data.\n     * Defaults to \"default\".\n     */\n    indexName?: string;\n    /**\n     * The name of the metadata field to use to store the text of the document.\n     * Defaults to \"text\".\n     */\n    textField?: string;\n    /**\n     * Whether to create the index if it does not already exist.\n     * Defaults to true.\n     */\n    ensureIndexExists?: boolean;\n}\nexport interface DeleteProps {\n    /**\n     * The ids of the documents to delete.\n     */\n    ids: string[];\n}\n/**\n * A vector store that uses the Momento Vector Index.\n *\n * @remarks\n * To sign up for a free Momento account, visit https://console.gomomento.com.\n */\nexport declare class MomentoVectorIndex extends VectorStore {\n    private client;\n    private indexName;\n    private textField;\n    private _ensureIndexExists;\n    _vectorstoreType(): string;\n    /**\n     * Creates a new `MomentoVectorIndex` instance.\n     * @param embeddings The embeddings instance to use to generate embeddings from documents.\n     * @param args The arguments to use to configure the vector store.\n     */\n    constructor(embeddings: EmbeddingsInterface, args: MomentoVectorIndexLibArgs);\n    /**\n     * Returns the Momento Vector Index client.\n     * @returns The Momento Vector Index client.\n     */\n    getClient(): IVectorIndexClient;\n    private ensureIndexExists;\n    /**\n     * Converts the documents to a format that can be stored in the index.\n     *\n     * This is necessary because the Momento Vector Index requires that the metadata\n     * be a map of strings to strings.\n     * @param vectors The vectors to convert.\n     * @param documents The documents to convert.\n     * @param ids The ids to convert.\n     * @returns The converted documents.\n     */\n    private prepareItemBatch;\n    /**\n     * Adds vectors to the index.\n     *\n     * @remarks If the index does not already exist, it will be created if `ensureIndexExists` is true.\n     * @param vectors The vectors to add to the index.\n     * @param documents The documents to add to the index.\n     * @param documentProps The properties of the documents to add to the index, specifically the ids.\n     * @returns Promise that resolves when the vectors have been added to the index. Also returns the ids of the\n     * documents that were added.\n     */\n    addVectors(vectors: number[][], documents: Document<Record<string, any>>[], documentProps?: DocumentProps): Promise<void | string[]>;\n    /**\n     * Adds vectors to the index. Generates embeddings from the documents\n     * using the `Embeddings` instance passed to the constructor.\n     * @param documents Array of `Document` instances to be added to the index.\n     * @returns Promise that resolves when the documents have been added to the index.\n     */\n    addDocuments(documents: Document[], documentProps?: DocumentProps): Promise<void>;\n    /**\n     * Deletes vectors from the index by id.\n     * @param params The parameters to use to delete the vectors, specifically the ids.\n     */\n    delete(params: DeleteProps): Promise<void>;\n    /**\n     * Searches the index for the most similar vectors to the query vector.\n     * @param query The query vector.\n     * @param k The number of results to return.\n     * @returns Promise that resolves to the documents of the most similar vectors\n     * to the query vector.\n     */\n    similaritySearchVectorWithScore(query: number[], k: number): Promise<[Document<Record<string, any>>, number][]>;\n    /**\n     * Return documents selected using the maximal marginal relevance.\n     * Maximal marginal relevance optimizes for similarity to the query AND diversity\n     * among selected documents.\n     *\n     * @param {string} query - Text to look up documents similar to.\n     * @param {number} options.k - Number of documents to return.\n     * @param {number} options.fetchK - Number of documents to fetch before passing to the MMR algorithm.\n     * @param {number} options.lambda - Number between 0 and 1 that determines the degree of diversity among the results,\n     *                 where 0 corresponds to maximum diversity and 1 to minimum diversity.\n     * @param {this[\"FilterType\"]} options.filter - Optional filter\n     * @param _callbacks\n     *\n     * @returns {Promise<Document[]>} - List of documents selected by maximal marginal relevance.\n     */\n    maxMarginalRelevanceSearch(query: string, options: MaxMarginalRelevanceSearchOptions<this[\"FilterType\"]>): Promise<Document[]>;\n    /**\n     * Stores the documents in the index.\n     *\n     * Converts the documents to vectors using the `Embeddings` instance passed.\n     * @param texts The texts to store in the index.\n     * @param metadatas The metadata to store in the index.\n     * @param embeddings The embeddings instance to use to generate embeddings from the documents.\n     * @param dbConfig The configuration to use to instantiate the vector store.\n     * @param documentProps The properties of the documents to add to the index, specifically the ids.\n     * @returns Promise that resolves to the vector store.\n     */\n    static fromTexts(texts: string[], metadatas: object[] | object, embeddings: EmbeddingsInterface, dbConfig: MomentoVectorIndexLibArgs, documentProps?: DocumentProps): Promise<MomentoVectorIndex>;\n    /**\n     * Stores the documents in the index.\n     * @param docs The documents to store in the index.\n     * @param embeddings The embeddings instance to use to generate embeddings from the documents.\n     * @param dbConfig The configuration to use to instantiate the vector store.\n     * @param documentProps The properties of the documents to add to the index, specifically the ids.\n     * @returns Promise that resolves to the vector store.\n     */\n    static fromDocuments(docs: Document[], embeddings: EmbeddingsInterface, dbConfig: MomentoVectorIndexLibArgs, documentProps?: DocumentProps): Promise<MomentoVectorIndex>;\n}\n//# sourceMappingURL=momento_vector_index.d.ts.map"],"mappings":";;;;;;UAIiBK,aAAAA;;AAAjB;AAGiBC,UAAAA,yBAAAA,CAAyB;EAqBzBC;AAYjB;;EAWuDD,MAAAA,EAxC3CN,kBAwC2CM;EAKtCN;;;;EAuB+FU,SAAAA,CAAAA,EAAAA,MAAAA;EAOpFT;;;;EAKKS,SAAAA,CAAAA,EAAAA,MAAAA;EAQkDD;;;;EAgBoCR,iBAAAA,CAAAA,EAAAA,OAAAA;;AAYvCC,UAnG/DK,WAAAA,CAmG+DL;EAA+BI;;;EAA2DI,GAAAA,EAAAA,MAAAA,EAAAA;;;;;;;;AAvF/G,cAAtCF,kBAAAA,SAA2BJ,WAAAA,CAAW;;;;;;;;;;;0BAW/BF,2BAA2BI;;;;;eAKtCN;;;;;;;;;;;;;;;;;;;;;;;6CAuB8BC,SAASQ,wCAAwCJ,gBAAgBK;;;;;;;0BAOpFT,4BAA4BI,gBAAgBK;;;;;iBAKrDH,cAAcG;;;;;;;;+DAQgCA,SAAST,SAASQ;;;;;;;;;;;;;;;;qDAgB5BN,wDAAwDO,QAAQT;;;;;;;;;;;;8EAYvCC,+BAA+BI,2CAA2CD,gBAAgBK,QAAQF;;;;;;;;;6BASnJP,wBAAwBC,+BAA+BI,2CAA2CD,gBAAgBK,QAAQF"}