@roadiehq/rag-ai-storage-pgvector/dist/index.d.ts

import { LoggerService, DatabaseService } from '@backstage/backend-plugin-api';
import { RoadieVectorStore, EmbeddingDoc, EmbeddingDocMetadata } from '@roadiehq/rag-ai-node';
import { Config } from '@backstage/config';
import { Embeddings } from '@langchain/core/embeddings';
import { Knex } from 'knex';

interface PgVectorStoreInitConfig {
    logger: LoggerService;
    database: DatabaseService;
    config: Config;
}
interface RoadiePgVectorStoreOptions {
    chunkSize?: number;
    amount?: number;
}
declare function createRoadiePgVectorStore({ logger, database, config, }: PgVectorStoreInitConfig): Promise<RoadieVectorStore>;

interface RoadiePgVectorStoreConfig {
    logger: LoggerService;
    db: Knex;
    /**
     * The amount of documents to chunk by when
     * adding vectors.
     * @default 500
     */
    chunkSize?: number;
    /**
     * The default amount of embeddings to return when querying vectors with similarity search
     */
    amount?: number;
}
/**
 * A class representing a vector store that uses PostgreSQL as the backend.
 */
declare class RoadiePgVectorStore implements RoadieVectorStore {
    protected readonly tableName: string;
    protected readonly client: Knex;
    protected readonly chunkSize: number;
    protected readonly amount: number;
    protected embeddings?: Embeddings;
    protected readonly logger: LoggerService;
    /**
     * Initializes the RoadiePgVectorStore.
     *
     * @param {RoadiePgVectorStoreConfig} config - The configuration for RoadiePgVectorStore.
     *
     * @return {Promise<RoadiePgVectorStore>} A Promise that resolves to an instance of RoadiePgVectorStore.
     */
    static initialize(config: RoadiePgVectorStoreConfig): Promise<RoadiePgVectorStore>;
    /**
     * Constructor for RoadiePgVectorStore class.
     *
     * @param {RoadiePgVectorStoreConfig} config - The configuration object for RoadiePgVectorStore.
     * @param {string} config.db - The database client to connect.
     * @param {Object} config.logger - The logger object for logging.
     * @param {number} [config.chunkSize=500] - The size of chunks for processing.
     */
    protected constructor(config: RoadiePgVectorStoreConfig);
    connectEmbeddings(embeddings: Embeddings): void;
    table(): Knex.QueryBuilder<any, {
        _base: any;
        _hasSelection: false;
        _keys: never;
        _aliases: {};
        _single: false;
        _intersectProps: {};
        _unionProps: never;
    }[]>;
    /**
     * Add documents to the vector store.
     *
     * @param {EmbeddingDoc[]} documents - The array of documents to be added.
     * @throws {Error} When no embeddings are configured for the vector store.
     * @returns {Promise<void>} Resolves when the documents have been added successfully.
     */
    addDocuments(documents: EmbeddingDoc[]): Promise<void>;
    /**
     * Adds vectors to the database along with corresponding documents.
     *
     * @param {number[][]} vectors - The vectors to be added.
     * @param {EmbeddingDoc[]} documents - The corresponding documents.
     * @return {Promise<void>} - A promise that resolves when the vectors are added successfully.
     * @throws {Error} - If there is an error inserting the vectors.
     */
    protected addVectors(vectors: number[][], documents: EmbeddingDoc[]): Promise<void>;
    /**
     * Deletes records from the database table by their ids.
     *
     * @param {string[]} ids - The array of ids of the records to be deleted.
     * @returns {Promise<void>} - A promise that resolves when the deletion is complete.
     */
    protected deleteById(ids: string[]): Promise<void>;
    /**
     * Deletes rows from the table based on the specified filter.
     *
     * @param {EmbeddingDocMetadata} filter - The filter to apply for deletion.
     * @returns {Promise} - A Promise that resolves when the deletion is complete.
     */
    protected deleteByFilter(filter: EmbeddingDocMetadata): Promise<any>;
    /**
     * Deletes documents based on the provided deletion parameters.
     * Either `ids` or `filter` must be specified.
     *
     * @param {Object} deletionParams - The deletion parameters.
     * @param {Array<string>} [deletionParams.ids] - The document IDs to delete.
     * @param {EmbeddingDocMetadata} [deletionParams.filter] - The filter to match documents to be deleted.
     *
     * @return {Promise<void>} - A Promise that resolves once the documents have been deleted.
     */
    deleteDocuments(deletionParams: {
        ids?: string[];
        filter?: EmbeddingDocMetadata;
    }): Promise<void>;
    /**
     * Finds the most similar documents to a given query vector, along with their similarity scores.
     *
     * @param {number[]} query - The query vector to compare against.
     * @param {number} amount - The maximum number of results to return.
     * @param {EmbeddingDocMetadata} [filter] - Optional filter to limit the search results.
     * @returns {Promise<[EmbeddingDoc, number][]>} - An array of document similarity results, where each
     * result is a tuple containing the document and its similarity score.
     */
    protected similaritySearchVectorWithScore(query: number[], amount: number, filter?: EmbeddingDocMetadata): Promise<[EmbeddingDoc, number][]>;
    /**
     * Performs a similarity search using the given query and filter.
     *
     * @param {string} query - The query to perform the similarity search on.
     * @param {EmbeddingDocMetadata} filter - The filter to apply to the search results.
     * @param {number} [amount=4] - The number of results to return.
     * @return {Promise<EmbeddingDoc[]>} - A promise that resolves to an array of RoadieEmbeddingDoc objects representing the search results.
     * @throws {Error} - Throws an error if there are no embeddings configured for the vector store.
     */
    similaritySearch(query: string, filter: EmbeddingDocMetadata, amount?: number): Promise<EmbeddingDoc[]>;
}

export { type PgVectorStoreInitConfig, RoadiePgVectorStore, type RoadiePgVectorStoreConfig, type RoadiePgVectorStoreOptions, createRoadiePgVectorStore };