langchain 0.0.202 → 0.0.204-rc.0

package/dist/vectorstores/weaviate.js

@@ -1,333 +1 @@
-import * as uuid from "uuid";
-import { VectorStore } from "./base.js";
-import { Document } from "../document.js";
-import { maximalMarginalRelevance } from "../util/math.js";
-// Note this function is not generic, it is designed specifically for Weaviate
-// https://weaviate.io/developers/weaviate/config-refs/datatypes#introduction
-export const flattenObjectForWeaviate = (
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-obj) => {
-    // eslint-disable-next-line @typescript-eslint/no-explicit-any
-    const flattenedObject = {};
-    for (const key in obj) {
-        if (!Object.hasOwn(obj, key)) {
-            continue;
-        }
-        const value = obj[key];
-        if (typeof obj[key] === "object" && !Array.isArray(value)) {
-            const recursiveResult = flattenObjectForWeaviate(value);
-            for (const deepKey in recursiveResult) {
-                if (Object.hasOwn(obj, key)) {
-                    flattenedObject[`${key}_${deepKey}`] = recursiveResult[deepKey];
-                }
-            }
-        }
-        else if (Array.isArray(value)) {
-            if (value.length > 0 &&
-                typeof value[0] !== "object" &&
-                // eslint-disable-next-line @typescript-eslint/no-explicit-any
-                value.every((el) => typeof el === typeof value[0])) {
-                // Weaviate only supports arrays of primitive types,
-                // where all elements are of the same type
-                flattenedObject[key] = value;
-            }
-        }
-        else {
-            flattenedObject[key] = value;
-        }
-    }
-    return flattenedObject;
-};
-/**
- * Class that extends the `VectorStore` base class. It provides methods to
- * interact with a Weaviate index, including adding vectors and documents,
- * deleting data, and performing similarity searches.
- */
-export class WeaviateStore extends VectorStore {
-    _vectorstoreType() {
-        return "weaviate";
-    }
-    constructor(embeddings, args) {
-        super(embeddings, args);
-        Object.defineProperty(this, "embeddings", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: embeddings
-        });
-        Object.defineProperty(this, "client", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "indexName", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "textKey", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "queryAttrs", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "tenant", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        this.client = args.client;
-        this.indexName = args.indexName;
-        this.textKey = args.textKey || "text";
-        this.queryAttrs = [this.textKey];
-        this.tenant = args.tenant;
-        if (args.metadataKeys) {
-            this.queryAttrs = [
-                ...new Set([
-                    ...this.queryAttrs,
-                    ...args.metadataKeys.filter((k) => {
-                        // https://spec.graphql.org/June2018/#sec-Names
-                        // queryAttrs need to be valid GraphQL Names
-                        const keyIsValid = /^[_A-Za-z][_0-9A-Za-z]*$/.test(k);
-                        if (!keyIsValid) {
-                            console.warn(`Skipping metadata key ${k} as it is not a valid GraphQL Name`);
-                        }
-                        return keyIsValid;
-                    }),
-                ]),
-            ];
-        }
-    }
-    /**
-     * Method to add vectors and corresponding documents to the Weaviate
-     * index.
-     * @param vectors Array of vectors to be added.
-     * @param documents Array of documents corresponding to the vectors.
-     * @param options Optional parameter that can include specific IDs for the documents.
-     * @returns An array of document IDs.
-     */
-    async addVectors(vectors, documents, options) {
-        const documentIds = options?.ids ?? documents.map((_) => uuid.v4());
-        const batch = documents.map((document, index) => {
-            if (Object.hasOwn(document.metadata, "id"))
-                throw new Error("Document inserted to Weaviate vectorstore should not have `id` in their metadata.");
-            const flattenedMetadata = flattenObjectForWeaviate(document.metadata);
-            return {
-                ...(this.tenant ? { tenant: this.tenant } : {}),
-                class: this.indexName,
-                id: documentIds[index],
-                vector: vectors[index],
-                properties: {
-                    [this.textKey]: document.pageContent,
-                    ...flattenedMetadata,
-                },
-            };
-        });
-        try {
-            const responses = await this.client.batch
-                .objectsBatcher()
-                .withObjects(...batch)
-                .do();
-            // if storing vectors fails, we need to know why
-            const errorMessages = [];
-            responses.forEach((response) => {
-                if (response?.result?.errors?.error) {
-                    errorMessages.push(...response.result.errors.error.map((err) => err.message ??
-                        "!! Unfortunately no error message was presented in the API response !!"));
-                }
-            });
-            if (errorMessages.length > 0) {
-                throw new Error(errorMessages.join("\n"));
-            }
-        }
-        catch (e) {
-            throw Error(`Error adding vectors: ${e}`);
-        }
-        return documentIds;
-    }
-    /**
-     * Method to add documents to the Weaviate index. It first generates
-     * vectors for the documents using the embeddings, then adds the vectors
-     * and documents to the index.
-     * @param documents Array of documents to be added.
-     * @param options Optional parameter that can include specific IDs for the documents.
-     * @returns An array of document IDs.
-     */
-    async addDocuments(documents, options) {
-        return this.addVectors(await this.embeddings.embedDocuments(documents.map((d) => d.pageContent)), documents, options);
-    }
-    /**
-     * Method to delete data from the Weaviate index. It can delete data based
-     * on specific IDs or a filter.
-     * @param params Object that includes either an array of IDs or a filter for the data to be deleted.
-     * @returns Promise that resolves when the deletion is complete.
-     */
-    async delete(params) {
-        const { ids, filter } = params;
-        if (ids && ids.length > 0) {
-            for (const id of ids) {
-                let deleter = this.client.data
-                    .deleter()
-                    .withClassName(this.indexName)
-                    .withId(id);
-                if (this.tenant) {
-                    deleter = deleter.withTenant(this.tenant);
-                }
-                await deleter.do();
-            }
-        }
-        else if (filter) {
-            let batchDeleter = this.client.batch
-                .objectsBatchDeleter()
-                .withClassName(this.indexName)
-                .withWhere(filter.where);
-            if (this.tenant) {
-                batchDeleter = batchDeleter.withTenant(this.tenant);
-            }
-            await batchDeleter.do();
-        }
-        else {
-            throw new Error(`This method requires either "ids" or "filter" to be set in the input object`);
-        }
-    }
-    /**
-     * Method to perform a similarity search on the stored vectors in the
-     * Weaviate index. It returns the top k most similar documents and their
-     * similarity scores.
-     * @param query The query vector.
-     * @param k The number of most similar documents to return.
-     * @param filter Optional filter to apply to the search.
-     * @returns An array of tuples, where each tuple contains a document and its similarity score.
-     */
-    async similaritySearchVectorWithScore(query, k, filter) {
-        const resultsWithEmbedding = await this.similaritySearchVectorWithScoreAndEmbedding(query, k, filter);
-        return resultsWithEmbedding.map(([document, score, _embedding]) => [
-            document,
-            score,
-        ]);
-    }
-    /**
-     * Method to perform a similarity search on the stored vectors in the
-     * Weaviate index. It returns the top k most similar documents, their
-     * similarity scores and embedding vectors.
-     * @param query The query vector.
-     * @param k The number of most similar documents to return.
-     * @param filter Optional filter to apply to the search.
-     * @returns An array of tuples, where each tuple contains a document, its similarity score and its embedding vector.
-     */
-    async similaritySearchVectorWithScoreAndEmbedding(query, k, filter) {
-        try {
-            let builder = this.client.graphql
-                .get()
-                .withClassName(this.indexName)
-                .withFields(`${this.queryAttrs.join(" ")} _additional { distance vector }`)
-                .withNearVector({
-                vector: query,
-                distance: filter?.distance,
-            })
-                .withLimit(k);
-            if (this.tenant) {
-                builder = builder.withTenant(this.tenant);
-            }
-            if (filter?.where) {
-                builder = builder.withWhere(filter.where);
-            }
-            const result = await builder.do();
-            const documents = [];
-            for (const data of result.data.Get[this.indexName]) {
-                const { [this.textKey]: text, _additional, ...rest } = data;
-                documents.push([
-                    new Document({
-                        pageContent: text,
-                        metadata: rest,
-                    }),
-                    _additional.distance,
-                    _additional.vector,
-                ]);
-            }
-            return documents;
-        }
-        catch (e) {
-            throw Error(`'Error in similaritySearch' ${e}`);
-        }
-    }
-    /**
-     * Return documents selected using the maximal marginal relevance.
-     * Maximal marginal relevance optimizes for similarity to the query AND diversity
-     * among selected documents.
-     *
-     * @param {string} query - Text to look up documents similar to.
-     * @param {number} options.k - Number of documents to return.
-     * @param {number} options.fetchK - Number of documents to fetch before passing to the MMR algorithm.
-     * @param {number} options.lambda - Number between 0 and 1 that determines the degree of diversity among the results,
-     *                 where 0 corresponds to maximum diversity and 1 to minimum diversity.
-     * @param {this["FilterType"]} options.filter - Optional filter
-     * @param _callbacks
-     *
-     * @returns {Promise<Document[]>} - List of documents selected by maximal marginal relevance.
-     */
-    async maxMarginalRelevanceSearch(query, options, _callbacks) {
-        const { k, fetchK = 20, lambda = 0.5, filter } = options;
-        const queryEmbedding = await this.embeddings.embedQuery(query);
-        const allResults = await this.similaritySearchVectorWithScoreAndEmbedding(queryEmbedding, fetchK, filter);
-        const embeddingList = allResults.map(([_doc, _score, embedding]) => embedding);
-        const mmrIndexes = maximalMarginalRelevance(queryEmbedding, embeddingList, lambda, k);
-        return mmrIndexes
-            .filter((idx) => idx !== -1)
-            .map((idx) => allResults[idx][0]);
-    }
-    /**
-     * Static method to create a new `WeaviateStore` instance from a list of
-     * texts. It first creates documents from the texts and metadata, then
-     * adds the documents to the Weaviate index.
-     * @param texts Array of texts.
-     * @param metadatas Metadata for the texts. Can be a single object or an array of objects.
-     * @param embeddings Embeddings to be used for the texts.
-     * @param args Arguments required to create a new `WeaviateStore` instance.
-     * @returns A new `WeaviateStore` instance.
-     */
-    static fromTexts(texts, metadatas, embeddings, args) {
-        const docs = [];
-        for (let i = 0; i < texts.length; i += 1) {
-            const metadata = Array.isArray(metadatas) ? metadatas[i] : metadatas;
-            const newDoc = new Document({
-                pageContent: texts[i],
-                metadata,
-            });
-            docs.push(newDoc);
-        }
-        return WeaviateStore.fromDocuments(docs, embeddings, args);
-    }
-    /**
-     * Static method to create a new `WeaviateStore` instance from a list of
-     * documents. It adds the documents to the Weaviate index.
-     * @param docs Array of documents.
-     * @param embeddings Embeddings to be used for the documents.
-     * @param args Arguments required to create a new `WeaviateStore` instance.
-     * @returns A new `WeaviateStore` instance.
-     */
-    static async fromDocuments(docs, embeddings, args) {
-        const instance = new this(embeddings, args);
-        await instance.addDocuments(docs);
-        return instance;
-    }
-    /**
-     * Static method to create a new `WeaviateStore` instance from an existing
-     * Weaviate index.
-     * @param embeddings Embeddings to be used for the Weaviate index.
-     * @param args Arguments required to create a new `WeaviateStore` instance.
-     * @returns A new `WeaviateStore` instance.
-     */
-    static async fromExistingIndex(embeddings, args) {
-        return new this(embeddings, args);
-    }
-}
+export * from "@langchain/community/vectorstores/weaviate";

package/dist/vectorstores/xata.cjs

@@ -1,110 +1,17 @@
 "use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.XataVectorSearch = void 0;
-const base_js_1 = require("./base.cjs");
-const document_js_1 = require("../document.cjs");
-/**
- * Class for interacting with a Xata database as a VectorStore. Provides
- * methods to add documents and vectors to the database, delete entries,
- * and perform similarity searches.
- */
-class XataVectorSearch extends base_js_1.VectorStore {
-    _vectorstoreType() {
-        return "xata";
-    }
-    constructor(embeddings, args) {
-        super(embeddings, args);
-        Object.defineProperty(this, "client", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "table", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        this.client = args.client;
-        this.table = args.table;
-    }
-    /**
-     * Method to add documents to the Xata database. Maps the page content of
-     * each document, embeds the documents using the embeddings, and adds the
-     * vectors to the database.
-     * @param documents Array of documents to be added.
-     * @param options Optional object containing an array of ids.
-     * @returns Promise resolving to an array of ids of the added documents.
-     */
-    async addDocuments(documents, options) {
-        const texts = documents.map(({ pageContent }) => pageContent);
-        return this.addVectors(await this.embeddings.embedDocuments(texts), documents, options);
-    }
-    /**
-     * Method to add vectors to the Xata database. Maps each vector to a row
-     * with the document's content, embedding, and metadata. Creates or
-     * replaces these rows in the Xata database.
-     * @param vectors Array of vectors to be added.
-     * @param documents Array of documents corresponding to the vectors.
-     * @param options Optional object containing an array of ids.
-     * @returns Promise resolving to an array of ids of the added vectors.
-     */
-    async addVectors(vectors, documents, options) {
-        const rows = vectors
-            .map((embedding, idx) => ({
-            content: documents[idx].pageContent,
-            embedding,
-            ...documents[idx].metadata,
-        }))
-            .map((row, idx) => {
-            if (options?.ids) {
-                return { id: options.ids[idx], ...row };
-            }
-            return row;
-        });
-        const res = await this.client.db[this.table].createOrReplace(rows);
-        // Since we have an untyped BaseClient, it doesn't know the
-        // actual return type of the overload.
-        const results = res;
-        const returnedIds = results.map((row) => row.id);
-        return returnedIds;
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
     }
-    /**
-     * Method to delete entries from the Xata database. Deletes the entries
-     * with the provided ids.
-     * @param params Object containing an array of ids of the entries to be deleted.
-     * @returns Promise resolving to void.
-     */
-    async delete(params) {
-        const { ids } = params;
-        await this.client.db[this.table].delete(ids);
-    }
-    /**
-     * Method to perform a similarity search in the Xata database. Returns the
-     * k most similar documents along with their scores.
-     * @param query Query vector for the similarity search.
-     * @param k Number of most similar documents to return.
-     * @param filter Optional filter for the search.
-     * @returns Promise resolving to an array of tuples, each containing a Document and its score.
-     */
-    async similaritySearchVectorWithScore(query, k, filter) {
-        const { records } = await this.client.db[this.table].vectorSearch("embedding", query, {
-            size: k,
-            filter,
-        });
-        return (
-        // eslint-disable-next-line @typescript-eslint/no-explicit-any
-        records?.map((record) => [
-            new document_js_1.Document({
-                pageContent: record.content,
-                metadata: Object.fromEntries(Object.entries(record).filter(([key]) => key !== "content" &&
-                    key !== "embedding" &&
-                    key !== "xata" &&
-                    key !== "id")),
-            }),
-            record.xata.score,
-        ]) ?? []);
-    }
-}
-exports.XataVectorSearch = XataVectorSearch;
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __exportStar = (this && this.__exportStar) || function(m, exports) {
+    for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+__exportStar(require("@langchain/community/vectorstores/xata"), exports);

package/dist/vectorstores/xata.d.ts

@@ -1,70 +1 @@
-import { BaseClient } from "@xata.io/client";
-import { VectorStore } from "./base.js";
-import { Embeddings } from "../embeddings/base.js";
-import { Document } from "../document.js";
-/**
- * Interface for the arguments required to create a XataClient. Includes
- * the client instance and the table name.
- */
-export interface XataClientArgs<XataClient> {
-    readonly client: XataClient;
-    readonly table: string;
-}
-/**
- * Type for the filter object used in Xata database queries.
- */
-type XataFilter = object;
-/**
- * Class for interacting with a Xata database as a VectorStore. Provides
- * methods to add documents and vectors to the database, delete entries,
- * and perform similarity searches.
- */
-export declare class XataVectorSearch<XataClient extends BaseClient> extends VectorStore {
-    FilterType: XataFilter;
-    private readonly client;
-    private readonly table;
-    _vectorstoreType(): string;
-    constructor(embeddings: Embeddings, args: XataClientArgs<XataClient>);
-    /**
-     * Method to add documents to the Xata database. Maps the page content of
-     * each document, embeds the documents using the embeddings, and adds the
-     * vectors to the database.
-     * @param documents Array of documents to be added.
-     * @param options Optional object containing an array of ids.
-     * @returns Promise resolving to an array of ids of the added documents.
-     */
-    addDocuments(documents: Document[], options?: {
-        ids?: string[];
-    }): Promise<string[]>;
-    /**
-     * Method to add vectors to the Xata database. Maps each vector to a row
-     * with the document's content, embedding, and metadata. Creates or
-     * replaces these rows in the Xata database.
-     * @param vectors Array of vectors to be added.
-     * @param documents Array of documents corresponding to the vectors.
-     * @param options Optional object containing an array of ids.
-     * @returns Promise resolving to an array of ids of the added vectors.
-     */
-    addVectors(vectors: number[][], documents: Document[], options?: {
-        ids?: string[];
-    }): Promise<string[]>;
-    /**
-     * Method to delete entries from the Xata database. Deletes the entries
-     * with the provided ids.
-     * @param params Object containing an array of ids of the entries to be deleted.
-     * @returns Promise resolving to void.
-     */
-    delete(params: {
-        ids: string[];
-    }): Promise<void>;
-    /**
-     * Method to perform a similarity search in the Xata database. Returns the
-     * k most similar documents along with their scores.
-     * @param query Query vector for the similarity search.
-     * @param k Number of most similar documents to return.
-     * @param filter Optional filter for the search.
-     * @returns Promise resolving to an array of tuples, each containing a Document and its score.
-     */
-    similaritySearchVectorWithScore(query: number[], k: number, filter?: XataFilter | undefined): Promise<[Document, number][]>;
-}
-export {};
+export * from "@langchain/community/vectorstores/xata";

package/dist/vectorstores/xata.js

@@ -1,106 +1 @@
-import { VectorStore } from "./base.js";
-import { Document } from "../document.js";
-/**
- * Class for interacting with a Xata database as a VectorStore. Provides
- * methods to add documents and vectors to the database, delete entries,
- * and perform similarity searches.
- */
-export class XataVectorSearch extends VectorStore {
-    _vectorstoreType() {
-        return "xata";
-    }
-    constructor(embeddings, args) {
-        super(embeddings, args);
-        Object.defineProperty(this, "client", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        Object.defineProperty(this, "table", {
-            enumerable: true,
-            configurable: true,
-            writable: true,
-            value: void 0
-        });
-        this.client = args.client;
-        this.table = args.table;
-    }
-    /**
-     * Method to add documents to the Xata database. Maps the page content of
-     * each document, embeds the documents using the embeddings, and adds the
-     * vectors to the database.
-     * @param documents Array of documents to be added.
-     * @param options Optional object containing an array of ids.
-     * @returns Promise resolving to an array of ids of the added documents.
-     */
-    async addDocuments(documents, options) {
-        const texts = documents.map(({ pageContent }) => pageContent);
-        return this.addVectors(await this.embeddings.embedDocuments(texts), documents, options);
-    }
-    /**
-     * Method to add vectors to the Xata database. Maps each vector to a row
-     * with the document's content, embedding, and metadata. Creates or
-     * replaces these rows in the Xata database.
-     * @param vectors Array of vectors to be added.
-     * @param documents Array of documents corresponding to the vectors.
-     * @param options Optional object containing an array of ids.
-     * @returns Promise resolving to an array of ids of the added vectors.
-     */
-    async addVectors(vectors, documents, options) {
-        const rows = vectors
-            .map((embedding, idx) => ({
-            content: documents[idx].pageContent,
-            embedding,
-            ...documents[idx].metadata,
-        }))
-            .map((row, idx) => {
-            if (options?.ids) {
-                return { id: options.ids[idx], ...row };
-            }
-            return row;
-        });
-        const res = await this.client.db[this.table].createOrReplace(rows);
-        // Since we have an untyped BaseClient, it doesn't know the
-        // actual return type of the overload.
-        const results = res;
-        const returnedIds = results.map((row) => row.id);
-        return returnedIds;
-    }
-    /**
-     * Method to delete entries from the Xata database. Deletes the entries
-     * with the provided ids.
-     * @param params Object containing an array of ids of the entries to be deleted.
-     * @returns Promise resolving to void.
-     */
-    async delete(params) {
-        const { ids } = params;
-        await this.client.db[this.table].delete(ids);
-    }
-    /**
-     * Method to perform a similarity search in the Xata database. Returns the
-     * k most similar documents along with their scores.
-     * @param query Query vector for the similarity search.
-     * @param k Number of most similar documents to return.
-     * @param filter Optional filter for the search.
-     * @returns Promise resolving to an array of tuples, each containing a Document and its score.
-     */
-    async similaritySearchVectorWithScore(query, k, filter) {
-        const { records } = await this.client.db[this.table].vectorSearch("embedding", query, {
-            size: k,
-            filter,
-        });
-        return (
-        // eslint-disable-next-line @typescript-eslint/no-explicit-any
-        records?.map((record) => [
-            new Document({
-                pageContent: record.content,
-                metadata: Object.fromEntries(Object.entries(record).filter(([key]) => key !== "content" &&
-                    key !== "embedding" &&
-                    key !== "xata" &&
-                    key !== "id")),
-            }),
-            record.xata.score,
-        ]) ?? []);
-    }
-}
+export * from "@langchain/community/vectorstores/xata";