Skip to main content
这将帮助你开始使用 LangChain 的 Cloudflare Workers AI 嵌入模型。有关 CloudflareWorkersAIEmbeddings 功能和配置选项的详细文档，请参阅 API 参考。

​
概览

​
集成详情

类包本地Py 支持下载量版本
CloudflareWorkersAIEmbeddings@langchain/cloudflare❌❌NPM - DownloadsNPM - Version

​
设置

要访问 Cloudflare 嵌入模型，你需要创建一个 Cloudflare 账户并安装 @langchain/cloudflare 集成包。此集成旨在在 Cloudflare Worker 中运行并接受绑定。 请按照官方文档设置你的 worker。 你的 wrangler.toml 文件应该类似于这样： 
name = "langchain-test"
main = "worker.js"
compatibility_date = "2024-01-10"

[[vectorize]]
binding = "VECTORIZE_INDEX"
index_name = "langchain-test"

[ai]
binding = "AI"

​
凭证

如果你想获得模型调用的自动追踪，你也可以通过取消下面的注释来设置你的 LangSmith API 密钥： 
# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"

​
安装

LangChain CloudflareWorkersAIEmbeddings 集成位于 @langchain/cloudflare 包中： 
npm install @langchain/cloudflare @langchain/core

​
用法

下面是一个示例 worker，它使用 Workers AI 嵌入与 Cloudflare Vectorize 向量存储。 
// @ts-nocheck

import type {
  VectorizeIndex,
  Fetcher,
  Request,
} from "@cloudflare/workers-types";

import {
  CloudflareVectorizeStore,
  CloudflareWorkersAIEmbeddings,
} from "@langchain/cloudflare";

export interface Env {
  VECTORIZE_INDEX: VectorizeIndex;
  AI: Fetcher;
}

export default {
  async fetch(request: Request, env: Env) {
    const { pathname } = new URL(request.url);
    const embeddings = new CloudflareWorkersAIEmbeddings({
      binding: env.AI,
      model: "@cf/baai/bge-small-en-v1.5",
    });
    const store = new CloudflareVectorizeStore(embeddings, {
      index: env.VECTORIZE_INDEX,
    });
    if (pathname === "/") {
      const results = await store.similaritySearch("hello", 5);
      return Response.json(results);
    } else if (pathname === "/load") {
      // Upsertion by id is supported
      await store.addDocuments(
        [
          {
            pageContent: "hello",
            metadata: {},
          },
          {
            pageContent: "world",
            metadata: {},
          },
          {
            pageContent: "hi",
            metadata: {},
          },
        ],
        { ids: ["id1", "id2", "id3"] }
      );

      return Response.json({ success: true });
    } else if (pathname === "/clear") {
      await store.delete({ ids: ["id1", "id2", "id3"] });
      return Response.json({ success: true });
    }

    return Response.json({ error: "Not Found" }, { status: 404 });
  },
};

​
API 参考

有关所有 CloudflareWorkersAIEmbeddings 功能和配置的详细文档，请参阅 API 参考。
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.