@langchain/community
Version:
Third-party integrations for LangChain.js
203 lines (202 loc) • 8.48 kB
JavaScript
;
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]; } };
}
Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
o["default"] = v;
});
var __importStar = (this && this.__importStar) || function (mod) {
if (mod && mod.__esModule) return mod;
var result = {};
if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
__setModuleDefault(result, mod);
return result;
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.CloudflareVectorizeStore = void 0;
const uuid = __importStar(require("uuid"));
const vectorstores_1 = require("@langchain/core/vectorstores");
const documents_1 = require("@langchain/core/documents");
const async_caller_1 = require("@langchain/core/utils/async_caller");
const chunk_array_1 = require("@langchain/core/utils/chunk_array");
/**
* @deprecated Install and import from "@langchain/cloudflare" instead.
*
* Class that extends the VectorStore class and provides methods to
* interact with the Cloudflare Vectorize vector database.
*/
class CloudflareVectorizeStore extends vectorstores_1.VectorStore {
_vectorstoreType() {
return "cloudflare_vectorize";
}
constructor(embeddings, args) {
super(embeddings, args);
Object.defineProperty(this, "textKey", {
enumerable: true,
configurable: true,
writable: true,
value: void 0
});
Object.defineProperty(this, "namespace", {
enumerable: true,
configurable: true,
writable: true,
value: void 0
});
Object.defineProperty(this, "index", {
enumerable: true,
configurable: true,
writable: true,
value: void 0
});
Object.defineProperty(this, "caller", {
enumerable: true,
configurable: true,
writable: true,
value: void 0
});
this.embeddings = embeddings;
const { index, textKey, ...asyncCallerArgs } = args;
if (!index) {
throw new Error("Must supply a Vectorize index binding, eg { index: env.VECTORIZE }");
}
this.index = index;
this.textKey = textKey ?? "text";
this.caller = new async_caller_1.AsyncCaller({
maxConcurrency: 6,
maxRetries: 0,
...asyncCallerArgs,
});
}
/**
* Method that adds documents to the Vectorize database.
* @param documents Array of documents to add.
* @param options Optional ids for the documents.
* @returns Promise that resolves with the 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 that adds vectors to the Vectorize database.
* @param vectors Array of vectors to add.
* @param documents Array of documents associated with the vectors.
* @param options Optional ids for the vectors.
* @returns Promise that resolves with the ids of the added vectors.
*/
async addVectors(vectors, documents, options) {
const ids = Array.isArray(options) ? options : options?.ids;
const documentIds = ids == null ? documents.map(() => uuid.v4()) : ids;
const vectorizeVectors = vectors.map((values, idx) => {
const metadata = {
...documents[idx].metadata,
[this.textKey]: documents[idx].pageContent,
};
return {
id: documentIds[idx],
metadata,
values,
};
});
// Stick to a limit of 500 vectors per upsert request
const chunkSize = 500;
const chunkedVectors = (0, chunk_array_1.chunkArray)(vectorizeVectors, chunkSize);
const batchRequests = chunkedVectors.map((chunk) => this.caller.call(async () => this.index.upsert(chunk)));
await Promise.all(batchRequests);
return documentIds;
}
/**
* Method that deletes vectors from the Vectorize database.
* @param params Parameters for the delete operation.
* @returns Promise that resolves when the delete operation is complete.
*/
async delete(params) {
const batchSize = 1000;
const batchedIds = (0, chunk_array_1.chunkArray)(params.ids, batchSize);
const batchRequests = batchedIds.map((batchIds) => this.caller.call(async () => this.index.deleteByIds(batchIds)));
await Promise.all(batchRequests);
}
/**
* Method that performs a similarity search in the Vectorize database and
* returns the results along with their scores.
* @param query Query vector for the similarity search.
* @param k Number of top results to return.
* @returns Promise that resolves with an array of documents and their scores.
*/
async similaritySearchVectorWithScore(query, k) {
const results = await this.index.query(query, {
returnVectors: true,
topK: k,
});
const result = [];
if (results.matches) {
for (const res of results.matches) {
const { [this.textKey]: pageContent, ...metadata } = res.vector?.metadata ?? {};
result.push([
new documents_1.Document({ metadata, pageContent: pageContent }),
res.score,
]);
}
}
return result;
}
/**
* Static method that creates a new instance of the CloudflareVectorizeStore class
* from texts.
* @param texts Array of texts to add to the Vectorize database.
* @param metadatas Metadata associated with the texts.
* @param embeddings Embeddings to use for the texts.
* @param dbConfig Configuration for the Vectorize database.
* @param options Optional ids for the vectors.
* @returns Promise that resolves with a new instance of the CloudflareVectorizeStore class.
*/
static async fromTexts(texts, metadatas, embeddings, dbConfig) {
const docs = [];
for (let i = 0; i < texts.length; i += 1) {
const metadata = Array.isArray(metadatas) ? metadatas[i] : metadatas;
const newDoc = new documents_1.Document({
pageContent: texts[i],
metadata,
});
docs.push(newDoc);
}
return CloudflareVectorizeStore.fromDocuments(docs, embeddings, dbConfig);
}
/**
* Static method that creates a new instance of the CloudflareVectorizeStore class
* from documents.
* @param docs Array of documents to add to the Vectorize database.
* @param embeddings Embeddings to use for the documents.
* @param dbConfig Configuration for the Vectorize database.
* @param options Optional ids for the vectors.
* @returns Promise that resolves with a new instance of the CloudflareVectorizeStore class.
*/
static async fromDocuments(docs, embeddings, dbConfig) {
const instance = new this(embeddings, dbConfig);
await instance.addDocuments(docs);
return instance;
}
/**
* Static method that creates a new instance of the CloudflareVectorizeStore class
* from an existing index.
* @param embeddings Embeddings to use for the documents.
* @param dbConfig Configuration for the Vectorize database.
* @returns Promise that resolves with a new instance of the CloudflareVectorizeStore class.
*/
static async fromExistingIndex(embeddings, dbConfig) {
const instance = new this(embeddings, dbConfig);
return instance;
}
}
exports.CloudflareVectorizeStore = CloudflareVectorizeStore;