feat: add cloudflare worker full example (#1521)

.changeset/strong-mice-dance.md

@@ -0,0 +1,5 @@
+---
+"@llamaindex/env": patch
+---
+
+fix: async local storage on cloudflare worker

apps/next/src/content/docs/llamaindex/setup/cloudflare.mdx

@@ -37,6 +37,33 @@ Then, you need create `.dev.vars` and add LLM api keys for the local development
 
 <Callout type="warn">Do not commit the api key to git repository.</Callout>
 
+## Integrating with Hono
+
+```ts
+import { Hono } from "hono";
+
+type Bindings = {
+  OPENAI_API_KEY: string;
+};
+
+const app = new Hono<{
+  Bindings: Bindings;
+}>();
+
+app.post("/llm", async (c) => {
+  const { setEnvs } = await import("@llamaindex/env");
+  setEnvs(c.env);
+
+  // ...
+
+  return new Response('Hello, world!');
+})
+
+export default {
+  fetch: app.fetch,
+};
+```
+
 ## Difference between Node.js and Cloudflare Worker
 
 In Cloudflare Worker and similar serverless JS environment, you need to be aware of the following differences:
@@ -46,3 +73,7 @@ In Cloudflare Worker and similar serverless JS environment, you need to be aware
 - Some of LlamaIndex.TS modules are not available in Cloudflare Worker, for example `SimpleDirectoryReader` (requires `node:fs`), Some multimodal API that relies on [`onnxruntime-node`](https://www.npmjs.com/package/onnxruntime-node)(we might port to HTTP based module in the future).
 - `@llamaindex/core` is designed to work in all JavaScript environment, including Cloudflare Worker. If you find any issue, please report to us.
 - `@llamaindex/env` is a JS environment binding module, which polyfill some Node.js/Modern Web API (for example, we have a memory based `fs` module, and Crypto API polyfill). It is designed to work in all JavaScript environment, including Cloudflare Worker.
+
+## Known issues
+
+- `llamaindex` not work perfectly in Cloudflare Worker, bundle size will be larger than 1MB, which is the limit of Cloudflare Worker. You will need import submodule instead of the whole `llamaindex` module.

e2e/examples/cloudflare-hono/.gitignore

@@ -0,0 +1,172 @@
+# Logs
+
+logs
+_.log
+npm-debug.log_
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+
+report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
+
+# Runtime data
+
+pids
+_.pid
+_.seed
+\*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+
+lib-cov
+
+# Coverage directory used by tools like istanbul
+
+coverage
+\*.lcov
+
+# nyc test coverage
+
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+
+bower_components
+
+# node-waf configuration
+
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+
+build/Release
+
+# Dependency directories
+
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+
+web_modules/
+
+# TypeScript cache
+
+\*.tsbuildinfo
+
+# Optional npm cache directory
+
+.npm
+
+# Optional eslint cache
+
+.eslintcache
+
+# Optional stylelint cache
+
+.stylelintcache
+
+# Microbundle cache
+
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+
+.node_repl_history
+
+# Output of 'npm pack'
+
+\*.tgz
+
+# Yarn Integrity file
+
+.yarn-integrity
+
+# dotenv environment variable files
+
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+
+.cache
+.parcel-cache
+
+# Next.js build output
+
+.next
+out
+
+# Nuxt.js build / generate output
+
+.nuxt
+dist
+
+# Gatsby files
+
+.cache/
+
+# Comment in the public line in if your project uses Gatsby and not Next.js
+
+# https://nextjs.org/blog/next-9-1#public-directory-support
+
+# public
+
+# vuepress build output
+
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+
+.temp
+.cache
+
+# Docusaurus cache and generated files
+
+.docusaurus
+
+# Serverless directories
+
+.serverless/
+
+# FuseBox cache
+
+.fusebox/
+
+# DynamoDB Local files
+
+.dynamodb/
+
+# TernJS port file
+
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+
+.vscode-test
+
+# yarn v2
+
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.\*
+
+# wrangler project
+
+.dev.vars
+.wrangler/

e2e/examples/cloudflare-hono/package.json

@@ -0,0 +1,20 @@
+{
+  "name": "@llamaindex/cloudflare-hono",
+  "version": "0.0.0",
+  "private": true,
+  "scripts": {
+    "deploy": "wrangler deploy",
+    "build": "wrangler deploy --dry-run --outdir dist",
+    "dev": "wrangler dev",
+    "start": "wrangler dev",
+    "cf-typegen": "wrangler types"
+  },
+  "devDependencies": {
+    "@cloudflare/workers-types": "^4.20241112.0",
+    "typescript": "^5.5.2",
+    "wrangler": "^3.89.0"
+  },
+  "dependencies": {
+    "hono": "^4.6.11"
+  }
+}

e2e/examples/cloudflare-hono/src/index.ts

@@ -0,0 +1,91 @@
+import { Hono } from "hono";
+
+type Bindings = {
+  OPENAI_API_KEY: string;
+  PINECONE_API_KEY: string;
+};
+
+const app = new Hono<{
+  Bindings: Bindings;
+}>();
+
+app.post("/llm", async (c) => {
+  //#region init envs
+  const { setEnvs } = await import("@llamaindex/env");
+  setEnvs(c.env);
+  //#endregion
+
+  const { message } = await c.req.json();
+
+  const { extractText } = await import("@llamaindex/core/utils");
+
+  const {
+    QueryEngineTool,
+    serviceContextFromDefaults,
+    VectorStoreIndex,
+    OpenAIAgent,
+    Settings,
+    OpenAI,
+    OpenAIEmbedding,
+  } = await import("llamaindex");
+
+  const { PineconeVectorStore } = await import(
+    "llamaindex/vector-store/PineconeVectorStore"
+  );
+
+  const llm = new OpenAI({
+    model: "gpt-4o-mini",
+    apiKey: c.env.OPENAI_API_KEY,
+  });
+
+  Settings.embedModel = new OpenAIEmbedding({
+    model: "text-embedding-3-small",
+    apiKey: c.env.OPENAI_API_KEY,
+  });
+
+  const serviceContext = serviceContextFromDefaults({
+    llm,
+    chunkSize: 8191,
+    chunkOverlap: 0,
+  });
+
+  const store = new PineconeVectorStore({
+    namespace: "8xolsn4ulEQGdhnhP76yCzfLHdOZ",
+  });
+
+  const index = await VectorStoreIndex.fromVectorStore(store, serviceContext);
+
+  const retriever = index.asRetriever({
+    similarityTopK: 3,
+  });
+
+  // Create a query engine
+  const queryEngine = index.asQueryEngine({
+    retriever,
+  });
+
+  const tools = [
+    new QueryEngineTool({
+      queryEngine: queryEngine,
+      metadata: {
+        name: "business_info_tool",
+        description:
+          "This tool can answer questions based " +
+          "on business information. Return not found if you" +
+          " can't find the answer in the documents.",
+      },
+    }),
+  ];
+
+  const agent = new OpenAIAgent({ tools });
+
+  const response = await agent.chat({
+    message: message,
+  });
+
+  return new Response(extractText(response.message.content));
+});
+
+export default {
+  fetch: app.fetch,
+};

e2e/examples/cloudflare-hono/tsconfig.json

@@ -0,0 +1,39 @@
+{
+  "extends": "../../tsconfig.json",
+  "compilerOptions": {
+    /* Visit https://aka.ms/tsconfig.json to read more about this file */
+
+    /* Set the JavaScript language version for emitted JavaScript and include compatible library declarations. */
+    "target": "es2021",
+    /* Specify a set of bundled library declaration files that describe the target runtime environment. */
+    "lib": ["es2021", "DOM.AsyncIterable"],
+    /* Specify what JSX code is generated. */
+    "jsx": "react-jsx",
+    /* Specify what module code is generated. */
+    "module": "es2022",
+    /* Specify how TypeScript looks up a file from a given module specifier. */
+    "moduleResolution": "Bundler",
+    /* Specify type package names to be included without being referenced in a source file. */
+    "types": ["@cloudflare/workers-types/2023-07-01"],
+    /* Enable importing .json files */
+    "resolveJsonModule": true,
+    /* Allow JavaScript files to be a part of your program. Use the `checkJS` option to get errors from these files. */
+    "allowJs": true,
+    /* Enable error reporting in type-checked JavaScript files. */
+    "checkJs": false,
+    /* Disable emitting files from a compilation. */
+    "noEmit": true,
+    /* Ensure that each file can be safely transpiled without relying on other imports. */
+    "isolatedModules": true,
+    /* Allow 'import x from y' when a module doesn't have a default export. */
+    "allowSyntheticDefaultImports": true,
+    /* Ensure that casing is correct in imports. */
+    "forceConsistentCasingInFileNames": true,
+    /* Enable all strict type-checking options. */
+    "strict": true,
+    /* Skip type checking all .d.ts files. */
+    "skipLibCheck": true
+  },
+  "exclude": ["test"],
+  "include": ["vitest.config.mts", "worker-configuration.d.ts", "src/**/*.ts"]
+}

e2e/examples/cloudflare-hono/worker-configuration.d.ts

@@ -0,0 +1,4 @@
+// Generated by Wrangler by running `wrangler types`
+
+// eslint-disable-next-line @typescript-eslint/no-empty-object-type
+interface Env {}

e2e/examples/cloudflare-hono/wrangler.toml

@@ -0,0 +1,7 @@
+name = "llamaindex-cloudflare-hono-example"
+main = "src/index.ts"
+compatibility_date = "2024-11-12"
+compatibility_flags = ["nodejs_als"]
+
+[observability]
+enabled = true

packages/env/src/als/index.workerd.ts

@@ -0,0 +1 @@
+export { AsyncLocalStorage } from "node:async_hooks";

packages/env/src/index.workerd.ts

@@ -7,7 +7,7 @@
  */
 import { INTERNAL_ENV } from "./utils/index.js";
 
-export * from "./als/index.non-node.js";
+export * from "./als/index.workerd.js";
 export { NotSupportCurrentRuntimeClass } from "./utils/shared.js";
 
 export * from "./node-polyfill.js";