如果您正在 Cloudflare worker 中部署您的项目，您可以将 Cloudflare Vectorize 与 LangChain.js 结合使用。它是一个强大且方便的选项，直接内置于 Cloudflare 中。
兼容性Cloudflare Vectorize 目前处于公开测试阶段，需要拥有付费计划的 Cloudflare 账户才能使用。
$ npx wrangler vectorize create <index_name> --preset @cf/baai/bge-small-en-v1.5
vectorize 命令的完整选项列表。 然后，您需要更新 wrangler.toml 文件，以包含 [[vectorize]] 条目：[[vectorize]]
binding = "VECTORIZE_INDEX"
index_name = "<index_name>"
有关安装 LangChain 软件包的一般说明，请参阅此部分。 npm install @langchain/cloudflare @langchain/core
如果本地运行，请务必以 npx wrangler dev --remote 方式运行 wrangler！
name = "langchain-test"
main = "worker.ts"
compatibility_date = "2024-01-10"
[[vectorize]]
binding = "VECTORIZE_INDEX"
index_name = "langchain-test"
[ai]
binding = "AI"
// @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 });
},
};
filter 参数以按先前加载的元数据进行过滤。有关所需格式的信息，请参阅官方文档。
