Create cold-sloths-scream.md

- Add TypedAgentData interface for type-safe agent data management
- Implement AsyncAgentDataClient with full CRUD operations
- Add support for data extraction with retry logic
- Add filtering, sorting, and pagination support for listing
- Include comprehensive TypeScript types and documentation
- Add usage examples and README documentation

Implementation based on PR https://github.com/run-llama/llama_cloud_services/pull/782

.changeset/cold-sloths-scream.md

@@ -0,0 +1,5 @@
+---
+"@llamaindex/cloud": patch
+---
+
+feat: init agent api on cloud sdk

.changeset/funny-donuts-approve.md

@@ -0,0 +1,5 @@
+---
+"@llamaindex/cloud": patch
+---
+
+feat: init agent api on cloud sdk

.changeset/sixty-wasps-flow.md

@@ -0,0 +1,5 @@
+---
+"@llamaindex/core": patch
+---
+
+Fix createMemory factory when parsing options

apps/next/CHANGELOG.md

@@ -1,146 +1,5 @@
 # @llamaindex/doc
 
-## 0.2.47
-
-### Patch Changes
-
-- Updated dependencies [c3bf3c7]
-- Updated dependencies [f9f1de9]
-  - @llamaindex/cloud@4.0.28
-  - @llamaindex/core@0.6.19
-  - llamaindex@0.11.24
-  - @llamaindex/node-parser@2.0.19
-  - @llamaindex/openai@0.4.14
-  - @llamaindex/readers@3.1.18
-  - @llamaindex/workflow@1.1.20
-
-## 0.2.46
-
-### Patch Changes
-
-- Updated dependencies [f29799e]
-- Updated dependencies [7224c06]
-  - @llamaindex/workflow@1.1.19
-  - @llamaindex/core@0.6.18
-  - llamaindex@0.11.23
-  - @llamaindex/cloud@4.0.27
-  - @llamaindex/node-parser@2.0.18
-  - @llamaindex/openai@0.4.13
-  - @llamaindex/readers@3.1.17
-
-## 0.2.45
-
-### Patch Changes
-
-- Updated dependencies [9ed3195]
-  - @llamaindex/workflow@1.1.18
-  - llamaindex@0.11.22
-
-## 0.2.44
-
-### Patch Changes
-
-- 38da40b: feat: VectoryMemoryBlock
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-  - @llamaindex/cloud@4.0.26
-  - llamaindex@0.11.21
-  - @llamaindex/node-parser@2.0.17
-  - @llamaindex/openai@0.4.12
-  - @llamaindex/readers@3.1.16
-  - @llamaindex/workflow@1.1.17
-
-## 0.2.43
-
-### Patch Changes
-
-- ea15e75: Minor updates in deployment docs
-
-## 0.2.42
-
-### Patch Changes
-
-- a8ec08c: fix: ensure correct message content in agent workflow
-- Updated dependencies [a8ec08c]
-- Updated dependencies [2967d57]
-  - @llamaindex/core@0.6.16
-  - @llamaindex/workflow@1.1.16
-  - @llamaindex/cloud@4.0.25
-  - llamaindex@0.11.20
-  - @llamaindex/node-parser@2.0.16
-  - @llamaindex/openai@0.4.11
-  - @llamaindex/readers@3.1.15
-
-## 0.2.41
-
-### Patch Changes
-
-- Updated dependencies [856dd8c]
-  - @llamaindex/openai@0.4.10
-
-## 0.2.40
-
-### Patch Changes
-
-- Updated dependencies [7ad3411]
-- Updated dependencies [5da5b3c]
-- Updated dependencies [a1fdb07]
-  - @llamaindex/core@0.6.15
-  - @llamaindex/workflow@1.1.15
-  - @llamaindex/openai@0.4.9
-  - @llamaindex/cloud@4.0.24
-  - llamaindex@0.11.19
-  - @llamaindex/node-parser@2.0.15
-  - @llamaindex/readers@3.1.14
-
-## 0.2.39
-
-### Patch Changes
-
-- Updated dependencies [a1b1598]
-  - @llamaindex/cloud@4.0.23
-  - llamaindex@0.11.18
-
-## 0.2.38
-
-### Patch Changes
-
-- Updated dependencies [d2be868]
-  - @llamaindex/cloud@4.0.22
-  - llamaindex@0.11.17
-
-## 0.2.37
-
-### Patch Changes
-
-- Updated dependencies [579ca0c]
-  - @llamaindex/cloud@4.0.21
-  - llamaindex@0.11.16
-
-## 0.2.36
-
-### Patch Changes
-
-- Updated dependencies [48b0d88]
-- Updated dependencies [f185772]
-  - @llamaindex/cloud@4.0.20
-  - llamaindex@0.11.15
-
-## 0.2.35
-
-### Patch Changes
-
-- Updated dependencies [5a0ed1f]
-- Updated dependencies [5a0ed1f]
-- Updated dependencies [8eeac33]
-  - @llamaindex/cloud@4.0.19
-  - @llamaindex/core@0.6.14
-  - llamaindex@0.11.14
-  - @llamaindex/node-parser@2.0.14
-  - @llamaindex/openai@0.4.8
-  - @llamaindex/readers@3.1.13
-  - @llamaindex/workflow@1.1.14
-
 ## 0.2.34
 
 ### Patch Changes

apps/next/next.config.mjs

@@ -27,33 +27,6 @@ const config = {
         destination: "/docs/workflows/:path*",
         permanent: true,
       },
-      {
-        source: "/docs/llamaindex/getting_started/installation/node.mdx",
-        destination:
-          "/docs/llamaindex/getting_started/installation/server-apis.mdx",
-        permanent: true,
-      },
-      {
-        source: "/docs/llamaindex/getting_started/installation/typescript.mdx",
-        destination: "/docs/llamaindex/getting_started/installation/index.mdx",
-        permanent: true,
-      },
-      {
-        source: "/docs/llamaindex/getting_started/installation/next.mdx",
-        destination: "/docs/llamaindex/getting_started/installation/nextjs.mdx",
-        permanent: true,
-      },
-      {
-        source: "/docs/llamaindex/getting_started/installation/vite.mdx",
-        destination: "/docs/llamaindex/getting_started/installation/index.mdx",
-        permanent: true,
-      },
-      {
-        source: "/docs/llamaindex/getting_started/installation/cloudflare.mdx",
-        destination:
-          "/docs/llamaindex/getting_started/installation/serverless.mdx",
-        permanent: true,
-      },
     ];
   },
   turbopack: {

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.47",
+  "version": "0.2.34",
   "private": true,
   "scripts": {
     "postinstall": "fumadocs-mdx",
@@ -76,21 +76,21 @@
     "@next/env": "^15.3.0",
     "@tailwindcss/postcss": "^4.0.9",
     "@types/mdx": "^2.0.13",
-    "@types/node": "24.0.13",
+    "@types/node": "22.9.0",
-    "@types/react": "^19.1.8",
+    "@types/react": "^19.0.10",
-    "@types/react-dom": "^19.1.6",
+    "@types/react-dom": "^19.0.4",
     "autoprefixer": "^10.4.20",
     "cross-env": "^7.0.3",
     "fast-glob": "^3.3.2",
     "gray-matter": "^4.0.3",
-    "postcss": "^8.5.6",
+    "postcss": "^8.5.3",
     "raw-loader": "^4.0.2",
     "remark": "^15.0.1",
     "remark-gfm": "^4.0.0",
     "remark-mdx": "^3.1.0",
     "remark-stringify": "^11.0.0",
-    "tailwindcss": "^4.1.11",
+    "tailwindcss": "^4.0.9",
-    "tsx": "^4.20.3",
+    "tsx": "^4.19.3",
     "typedoc": "0.28.3",
     "typedoc-plugin-markdown": "^4.6.2",
     "typedoc-plugin-merge-modules": " ^7.0.0",

apps/next/src/app/api/chat/route.ts

@@ -1,4 +1,4 @@
-import { MockLLM } from "@llamaindex/core/llms/mock";
+import { MockLLM } from "@llamaindex/core/utils";
 import { LlamaIndexAdapter, type Message } from "ai";
 import { Settings, SimpleChatEngine, type ChatMessage } from "llamaindex";
 import { NextResponse, type NextRequest } from "next/server";

apps/next/src/app/layout.tsx

@@ -1,6 +1,6 @@
 import { AIProvider } from "@/actions";
 import { TooltipProvider } from "@/components/ui/tooltip";
-import { GoogleAnalytics, GoogleTagManager } from "@next/third-parties/google";
+import { GoogleAnalytics } from "@next/third-parties/google";
 import { RootProvider } from "fumadocs-ui/provider";
 import { Inter } from "next/font/google";
 import type { ReactNode } from "react";
@@ -36,7 +36,6 @@ export default function Layout({ children }: { children: ReactNode }) {
           LlamaIndex.TS - Build LLM-powered document agents and workflows
         </title>
       </head>
-      <GoogleTagManager gtmId="GTM-WWRFB36R" />
       <body className="flex min-h-screen flex-col">
         <TooltipProvider>
           <AIProvider>

apps/next/src/content/docs/llamaindex/getting_started/create_llama.mdx

@@ -19,8 +19,3 @@ npm run dev
 to start the development server. You can then visit [http://localhost:3000](http://localhost:3000) to see your app, which should look something like this:
 
 ![create-llama interface](/images/create_llama.png)
-
-## Learn more
-
-- [Learn more about `create-llama`](https://github.com/run-llama/create-llama)
-- [Want to use the same UI components? You can use our React components](https://ui.llamaindex.ai/)

apps/next/src/content/docs/llamaindex/getting_started/examples.mdx

@@ -17,8 +17,7 @@ npm i
 Then you can run any example in the folder with `tsx`, e.g.:
 
 ```bash npm2yarn
-export OPENAI_API_KEY=your-api-key
+npx tsx ./vectorIndex.ts
-npx tsx ./agents/agent/openai.ts
 ```
 
 ## Try examples online

apps/next/src/content/docs/llamaindex/getting_started/installation/cloudflare.mdx

@@ -0,0 +1,70 @@
+---
+title: With Cloudflare Worker
+description: In this guide, you'll learn how to use LlamaIndex with CloudFlare Worker
+---
+
+Before you start, make sure you have try LlamaIndex.TS in Node.js to make sure you understand the basics.
+
+<Card
+  title="Getting Started with LlamaIndex.TS in Node.js"
+  href="/docs/llamaindex/getting_started/installation/node"
+/>
+
+Also, you need have the basic understanding of <a href='https://developers.cloudflare.com/workers/'><SiCloudflareworkers className="inline mr-2" color="#F38020" />Cloudflare Worker</a>.
+
+## Adding environment variables
+
+```ts
+export default {
+  async fetch(request: Request, env: Env): Promise<Response> {
+    const { setEnvs } = await import("@llamaindex/env");
+    setEnvs(env);
+    const { OpenAIAgent } = await import("@llamaindex/openai");
+    // Start your code here
+    return new Response("Hello, world!");
+  },
+};
+```
+
+Then, you need create `.dev.vars` and add LLM api keys for the local development, such as `OPENAI_API_KEY` for OpenAI API key.
+
+<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:
+
+- Some Node.js modules are not available in Cloudflare Worker, such as `node:fs`, `node:child_process`, `node:cluster`...
+- You are recommend to design your code using network request, such as use `fetch` API to communicate with database, instead of a long-running process in Node.js.
+- Some of LlamaIndex.TS packages are not available in Cloudflare Worker, for example `@llamaindex/readers` and `@llamaindex/huggingface`.
+- The main `llamaindex` 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.
+
+

apps/next/src/content/docs/llamaindex/getting_started/installation/index.mdx

@@ -1,177 +1,69 @@
 ---
 title: Installation
-description: How to install and set up LlamaIndex.TS for your project.
+description: How to install llamaindex packages.
 ---
 
-## Quick Start
+To install llamaindex, run the following command:
-
-Install the core package:
 
 ```package-install
 npm i llamaindex
 ```
 
-In most cases, you'll also need an LLM provider and the Workflow package:
+In most cases, you'll also need an LLM package and the Workflow package to use LlamaIndex. For example, to use the OpenAI LLM with agents, you would install the following:
 
 ```package-install
 npm i @llamaindex/openai @llamaindex/workflow
 ```
 
-## Environment Setup
+Go to [LLM APIs](/docs/llamaindex/modules/models/llms) to find out how to use other LLMs.
 
-### API Keys
 
-Most LLM providers require API keys. Set your OpenAI key (or other provider):
+## Frameworks
 
-```bash
+LlamaIndex supports a wide range of frameworks and runtimes. Click on the card below to learn more.
-export OPENAI_API_KEY=your-api-key
-```
-
-Or use a `.env` file:
-
-```bash
-echo "OPENAI_API_KEY=your-api-key" > .env
-```
-
-<Callout type="warn">Never commit API keys to your repository.</Callout>
-
-### Loading Environment Variables
-
-For Node.js applications:
-
-```bash
-node --env-file .env your-script.js
-```
-
-For other environments, see the deployment-specific guides below.
-
-## TypeScript Configuration
-
-LlamaIndex.TS is built with TypeScript and provides excellent type safety. Add these settings to your `tsconfig.json`:
-
-```json5
-{
-  "compilerOptions": {
-    // Essential for module resolution
-    "moduleResolution": "bundler", // or "nodenext" | "node16" | "node"
-    
-    // Required for Web Stream API support
-    "lib": ["DOM.AsyncIterable"],
-    
-    // Recommended for better compatibility
-    "target": "es2020",
-    "module": "esnext"
-  }
-}
-```
-
-## Running your first agent
-
-### Set up
-
-If you don't already have a project, you can create a new one in a new folder:
-
-```package-install
-npm init
-npm i -D typescript @types/node
-npm i @llamaindex/openai @llamaindex/workflow llamaindex zod
-```
-
-### Run the agent
-
-Create the file `example.ts`. This code will:
-
-- Create two tools for use by the agent:
-  - A `sumNumbers` tool that adds two numbers
-  - A `divideNumbers` tool that divides numbers
-- Give an example of the data structure we wish to generate
-- Prompt the LLM with instructions and the example, plus a sample transcript
-
-<include cwd>../../examples/agents/agent/openai.ts</include>
-
-To run the code:
-
-```package-install
-npx tsx example.ts
-```
-
-You should expect output something like:
-
-```
-{
-  result: '5 + 5 is 10. Then, 10 divided by 2 is 5.',
-  state: {
-    memory: Memory {
-      messages: [Array],
-      tokenLimit: 30000,
-      shortTermTokenLimitRatio: 0.7,
-      memoryBlocks: [],
-      memoryCursor: 0,
-      adapters: [Object]
-    },
-    scratchpad: [],
-    currentAgentName: 'Agent',
-    agents: [ 'Agent' ],
-    nextAgentName: null
-  }
-}
-Done
-```
-
-## Performance Optimization
-
-### Tokenization Speed
-
-Install `gpt-tokenizer` for 60x faster tokenization (Node.js environments only):
-
-```package-install
-npm i gpt-tokenizer
-```
-
-LlamaIndex will automatically use this when available.
-
-## Deployment Guides
-
-Choose your deployment target:
 
 <Cards>
-  <Card 
+	<Card title={
-    title="Server APIs & Backends" 
+		<>
-    description="Express, Fastify, Koa, standalone Node.js servers"
+			<SiNodedotjs className="inline" color="#5FA04E" /> Node.js
-    href="/docs/llamaindex/getting_started/installation/server-apis" 
+		</>
-  />
+	} href="/docs/llamaindex/getting_started/installation/node" />
-  <Card 
+	<Card title={
-    title="Serverless Functions" 
+		<>
-    description="Vercel, Netlify, AWS Lambda, Cloudflare Workers"
+			<SiTypescript className="inline" color="#3178C6" /> TypeScript
-    href="/docs/llamaindex/getting_started/installation/serverless" 
+		</>
-  />
+	} href="/docs/llamaindex/getting_started/installation/typescript" />
-  <Card 
+	<Card title={
-    title="Next.js Applications" 
+		<>
-    description="API routes, server components, edge runtime"
+			<SiVite className='inline' color='#646CFF' /> Vite
-    href="/docs/llamaindex/getting_started/installation/nextjs" 
+		</>
-  />
+	} href="/docs/llamaindex/getting_started/installation/vite" />
-  <Card 
+	<Card
-    title="Troubleshooting" 
+		title={
-    description="Common issues, bundle optimization, compatibility"
+			<>
-    href="/docs/llamaindex/getting_started/installation/troubleshooting" 
+				<SiNextdotjs className='inline' /> Next.js (React Server Component)
-  />
+			</>
+		}
+		href="/docs/llamaindex/getting_started/installation/next"
+	/>
+	<Card title={
+		<>
+			<SiCloudflareworkers className='inline' color='#F38020' /> Cloudflare Workers
+		</>
+	} href="/docs/llamaindex/getting_started/installation/cloudflare" />
 </Cards>
 
-## LLM/Embedding Providers
+## What's next?
-
-Go to [LLM APIs](/docs/llamaindex/modules/models/llms) and [Embedding APIs](/docs/llamaindex/modules/models/embeddings) to find out how to use different LLM and embedding providers beyond OpenAI.
-
-## What's Next?
 
 <Cards>
-  <Card
+	<Card
-    title="Learn LlamaIndex.TS"
+		title="Learn LlamaIndex.TS"
-    description="Learn how to use LlamaIndex.TS by starting with one of our tutorials."
+		description="Learn how to use LlamaIndex.TS by starting with one of our tutorials."
-    href="/docs/llamaindex/tutorials/basic_agent"
+		href="/docs/llamaindex/tutorials/rag"
-  />
+	/>
-  <Card
+	<Card
-    title="Show me code examples"
+		title="Show me code examples"
-    description="Explore code examples using LlamaIndex.TS."
+		description="Explore code examples using LlamaIndex.TS."
-    href="/docs/llamaindex/getting_started/examples"
+		href="/docs/llamaindex/getting_started/examples"
-  />
+	/>
 </Cards>

apps/next/src/content/docs/llamaindex/getting_started/installation/meta.json

@@ -1,4 +1,4 @@
 {
   "title": "Installation",
-  "pages": ["server-apis", "serverless", "nextjs", "troubleshooting"]
+  "pages": ["node", "typescript", "next", "vite", "cloudflare"]
 }

apps/next/src/content/docs/llamaindex/getting_started/installation/next.mdx

@@ -0,0 +1,41 @@
+---
+title: With Next.js
+description: In this guide, you'll learn how to use LlamaIndex with Next.js.
+---
+
+Before you start, make sure you have try LlamaIndex.TS in Node.js to make sure you understand the basics.
+
+<Card
+  title="Getting Started with LlamaIndex.TS in Node.js"
+  href="/docs/llamaindex/getting_started/installation/node"
+/>
+
+## Differences between Node.js and Next.js
+
+Next.js is a React framework that has both server side compatibility and client side compatibility.
+This means that you need to be careful when using LlamaIndex.TS in Next.js.
+Don't leak the import data like API keys to the client side.
+
+Also, in Next.js, there is build time and runtime. Some computations can be done at build time like Document embedding could be done at build time for better performance.
+Where as the `llamaindex` package is working with Next.js, some provider packages like `@llamaindex/huggingface` are not working well with Next.js. This is due to the upstream dependencies used by the provider package. 
+
+Make sure to use `withLlamaIndex` to make sure that LlamaIndex.TS works well with Next.js.
+
+```js
+// next.config.mjs / next.config.ts
+import withLlamaIndex from "llamaindex/next";
+
+/** @type {import('next').NextConfig} */
+const nextConfig = {};
+
+export default withLlamaIndex(nextConfig);
+```
+
+If you see any dependency issues, you are welcome to open an issue on the GitHub.
+
+## Edge Runtime
+
+[Vercel Edge Runtime](https://edge-runtime.vercel.app/) is a subset of Node.js APIs. Similar to [Cloudflare Workers](/docs/llamaindex/getting_started/installation/cloudflare#difference-between-nodejs-and-cloudflare-worker),
+it is a serverless platform that runs your code on the edge.
+
+Not all features of Node.js are supported in Vercel Edge Runtime, so does LlamaIndex.TS, we are working on more compatibility with all JavaScript runtimes.

apps/next/src/content/docs/llamaindex/getting_started/installation/nextjs.mdx

@@ -1,405 +0,0 @@
----
-title: Next.js Applications
-description: Deploy LlamaIndex.TS in Next.js applications with API routes, server components, and edge runtime.
----
-
-This guide covers integrating LlamaIndex.TS agents with Next.js applications.
-
-## Essential Configuration
-
-### Next.js Config
-
-Use `withLlamaIndex` to ensure compatibility:
-
-```javascript
-// next.config.mjs
-import withLlamaIndex from "llamaindex/next";
-
-/** @type {import('next').NextConfig} */
-const nextConfig = {
-  // Your existing config
-};
-
-export default withLlamaIndex(nextConfig);
-```
-
-## API Routes
-
-### App Router (Recommended)
-
-```typescript
-// app/api/chat/route.ts
-import { agent } from "@llamaindex/workflow";
-import { tool } from "llamaindex";
-import { openai } from "@llamaindex/openai";
-import { z } from "zod";
-import { NextRequest, NextResponse } from "next/server";
-
-// Initialize agent once (consider using a singleton pattern)
-let myAgent: any = null;
-
-async function initializeAgent() {
-  if (myAgent) return myAgent;
-  
-  try {
-    const greetTool = tool({
-      name: "greet",
-      description: "Greets a user with their name",
-      parameters: z.object({
-        name: z.string(),
-      }),
-      execute: ({ name }) => `Hello, ${name}! How can I help you today?`,
-    });
-
-    myAgent = agent({
-      tools: [greetTool],
-      llm: openai({ model: "gpt-4o-mini" }),
-    });
-    
-    return myAgent;
-  } catch (error) {
-    console.error("Failed to initialize agent:", error);
-    throw error;
-  }
-}
-
-export async function POST(request: NextRequest) {
-  try {
-    const { message } = await request.json();
-    
-    if (!message || typeof message !== 'string') {
-      return NextResponse.json(
-        { error: "Message is required and must be a string" },
-        { status: 400 }
-      );
-    }
-    
-    const agent = await initializeAgent();
-    const result = await agent.run(message);
-    
-    return NextResponse.json({ response: result.data });
-  } catch (error) {
-    console.error("Chat error:", error);
-    return NextResponse.json(
-      { error: "Internal server error" },
-      { status: 500 }
-    );
-  }
-}
-```
-
-### Pages Router (Legacy)
-
-```typescript
-// pages/api/chat.ts
-import { agent } from "@llamaindex/workflow";
-import { tool } from "llamaindex";
-import { openai } from "@llamaindex/openai";
-import { z } from "zod";
-import type { NextApiRequest, NextApiResponse } from "next";
-
-let myAgent: any = null;
-
-async function initializeAgent() {
-  if (myAgent) return myAgent;
-  
-  const timeTool = tool({
-    name: "getCurrentTime",
-    description: "Gets the current time",
-    parameters: z.object({}),
-    execute: () => new Date().toISOString(),
-  });
-
-  myAgent = agent({
-    tools: [timeTool],
-    llm: openai({ model: "gpt-4o-mini" }),
-  });
-  
-  return myAgent;
-}
-
-export default async function handler(
-  req: NextApiRequest,
-  res: NextApiResponse
-) {
-  if (req.method !== "POST") {
-    return res.status(405).json({ error: "Method not allowed" });
-  }
-  
-  try {
-    const { message } = req.body;
-    
-    const agent = await initializeAgent();
-    const result = await agent.run(message);
-    
-    res.json({ response: result.data });
-  } catch (error) {
-    console.error("Chat error:", error);
-    res.status(500).json({ error: "Internal server error" });
-  }
-}
-```
-
-## Server Components
-
-Initialize agents in server components:
-
-```typescript
-// app/chat/page.tsx
-import { agent } from "@llamaindex/workflow";
-import { tool } from "llamaindex";
-import { openai } from "@llamaindex/openai";
-import { z } from "zod";
-
-async function initializeAgent() {
-  const helpTool = tool({
-    name: "getHelp",
-    description: "Provides help information",
-    parameters: z.object({
-      topic: z.string().optional(),
-    }),
-    execute: ({ topic }) => {
-      if (topic) {
-        return `Here's help for ${topic}: This is a helpful resource about ${topic}.`;
-      }
-      return "Available topics: general, troubleshooting, api, deployment";
-    },
-  });
-
-  return agent({
-    tools: [helpTool],
-    llm: openai({ model: "gpt-4o-mini" }),
-  });
-}
-
-export default async function ChatPage() {
-  const chatAgent = await initializeAgent();
-  
-  return (
-    <div>
-      <h1>Chat Interface</h1>
-      <p>Agent initialized and ready to help!</p>
-      {/* Your chat UI components */}
-    </div>
-  );
-}
-```
-
-## Edge Runtime
-
-The Edge Runtime has limited Node.js API access:
-
-```typescript
-// app/api/chat-edge/route.ts
-import { NextRequest, NextResponse } from "next/server";
-
-export const runtime = "edge";
-
-export async function POST(request: NextRequest) {
-  const { setEnvs } = await import("@llamaindex/env");
-  setEnvs(process.env);
-  
-  try {
-    const { message } = await request.json();
-    
-    const { agent } = await import("@llamaindex/workflow");
-    const { tool } = await import("llamaindex");
-    const { openai } = await import("@llamaindex/openai");
-    const { z } = await import("zod");
-
-    const timeTool = tool({
-      name: "time",
-      description: "Gets current time",
-      parameters: z.object({}),
-      execute: () => new Date().toISOString(),
-    });
-
-    const myAgent = agent({
-      tools: [timeTool],
-      llm: openai({ model: "gpt-4o-mini" }),
-    });
-
-    const result = await myAgent.run(message);
-    return NextResponse.json({ response: result.data });
-  } catch (error) {
-    return NextResponse.json({ error: error.message }, { status: 500 });
-  }
-}
-```
-
-## Streaming Responses
-
-Implement streaming for better user experience:
-
-```typescript
-// app/api/chat-stream/route.ts
-import { agent } from "@llamaindex/workflow";
-import { tool } from "llamaindex";
-import { openai } from "@llamaindex/openai";
-import { agentStreamEvent } from "@llamaindex/workflow";
-import { NextRequest } from "next/server";
-import { z } from "zod";
-
-// Initialize agent once (consider using a singleton pattern)
-let myAgent: any = null;
-
-async function initializeAgent() {
-  if (myAgent) return myAgent;
-  
-  try {
-    const greetTool = tool({
-      name: "greet",
-      description: "Greets a user with their name",
-      parameters: z.object({
-        name: z.string(),
-      }),
-      execute: ({ name }) => `Hello, ${name}! How can I help you today?`,
-    });
-
-    myAgent = agent({
-      tools: [greetTool],
-      llm: openai({ model: "gpt-4o-mini" }),
-    });
-    
-    return myAgent;
-  } catch (error) {
-    console.error("Failed to initialize agent:", error);
-    throw error;
-  }
-}
-
-export async function POST(request: NextRequest) {
-  const { message } = await request.json();
-  
-  const stream = new ReadableStream({
-    async start(controller) {
-      try {
-        const agent = await initializeAgent();
-        const events = agent.runStream(message);
-        
-        for await (const event of events) {
-          if (agentStreamEvent.include(event)) {
-            controller.enqueue(new TextEncoder().encode(event.data.delta));
-          }
-        }
-        
-        controller.close();
-      } catch (error) {
-        controller.error(error);
-      }
-    },
-  });
-  
-  return new Response(stream, {
-    headers: {
-      "Content-Type": "text/plain",
-      "Transfer-Encoding": "chunked",
-    },
-  });
-}
-```
-
-## Client-side Integration
-
-### React Hook for API Calls
-
-```typescript
-// hooks/useAgentChat.ts
-import { useState } from "react";
-
-export function useAgentChat() {
-  const [loading, setLoading] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-  const [response, setResponse] = useState<string | null>(null);
-  
-  const chat = async (message: string) => {
-    setLoading(true);
-    setError(null);
-    
-    try {
-      const res = await fetch("/api/chat", {
-        method: "POST",
-        headers: { "Content-Type": "application/json" },
-        body: JSON.stringify({ message }),
-      });
-      
-      if (!res.ok) {
-        throw new Error(`HTTP error! status: ${res.status}`);
-      }
-      
-      const data = await res.json();
-      setResponse(data.response);
-    } catch (err) {
-      setError(err instanceof Error ? err.message : "An error occurred");
-    } finally {
-      setLoading(false);
-    }
-  };
-  
-  return { chat, loading, error, response };
-}
-```
-
-### Chat Component
-
-```typescript
-// components/ChatInterface.tsx
-"use client";
-
-import { useState } from "react";
-import { useAgentChat } from "@/hooks/useAgentChat";
-
-export default function ChatInterface() {
-  const [message, setMessage] = useState("");
-  const { chat, loading, error, response } = useAgentChat();
-  
-  const handleSubmit = async (e: React.FormEvent) => {
-    e.preventDefault();
-    if (!message.trim()) return;
-    
-    await chat(message);
-    setMessage("");
-  };
-  
-  return (
-    <div className="max-w-2xl mx-auto p-4">
-      <form onSubmit={handleSubmit} className="mb-4">
-        <input
-          type="text"
-          value={message}
-          onChange={(e) => setMessage(e.target.value)}
-          placeholder="Send a message..."
-          className="w-full p-2 border rounded"
-          disabled={loading}
-        />
-        <button
-          type="submit"
-          disabled={loading || !message.trim()}
-          className="mt-2 px-4 py-2 bg-blue-500 text-white rounded disabled:opacity-50"
-        >
-          {loading ? "Thinking..." : "Send"}
-        </button>
-      </form>
-      
-      {error && (
-        <div className="p-3 mb-4 bg-red-100 border border-red-400 text-red-700 rounded">
-          Error: {error}
-        </div>
-      )}
-      
-      {response && (
-        <div className="p-3 bg-gray-100 border rounded">
-          <strong>Agent:</strong>
-          <p>{response}</p>
-        </div>
-      )}
-    </div>
-  );
-}
-```
-
-## Next Steps
-
-- Learn about [serverless deployment](/docs/llamaindex/getting_started/installation/serverless)
-- Explore [server APIs](/docs/llamaindex/getting_started/installation/server-apis)
-- Check [troubleshooting guide](/docs/llamaindex/getting_started/installation/troubleshooting) for common issues 

apps/next/src/content/docs/llamaindex/getting_started/installation/node.mdx

@@ -0,0 +1,40 @@
+---
+title: With Node.js/Bun/Deno
+description: In this guide, you'll learn how to use LlamaIndex with Node.js, Bun, and Deno.
+---
+
+## Adding environment variables
+
+By default, LlamaIndex uses OpenAI provider, which requires an API key. You can set the `OPENAI_API_KEY` environment variable to authenticate with OpenAI.
+
+```shell
+export OPENAI_API_KEY=your-api-key
+```
+
+Or you can use a `.env` file:
+
+```shell
+echo "OPENAI_API_KEY=your-api-key" > .env
+node --env-file .env your-script.js
+```
+
+<Callout type="warn">Do not commit the api key to git repository.</Callout>
+
+For more information, see the [How to read environment variables from Node.js](https://nodejs.org/en/learn/command-line/how-to-read-environment-variables-from-nodejs).
+
+## Performance Optimization
+
+By the default, we are using `js-tiktoken` for tokenization. You can install `gpt-tokenizer` which is then automatically used by LlamaIndex to get a 60x speedup for tokenization:
+
+```package-install
+npm i gpt-tokenizer
+```
+
+**Note**: This only works for Node.js
+
+## TypeScript support
+
+<Card
+	title="Getting Started with LlamaIndex.TS in TypeScript"
+	href="/docs/llamaindex/getting_started/installation/typescript"
+/>

apps/next/src/content/docs/llamaindex/getting_started/installation/server-apis.mdx

@@ -1,211 +0,0 @@
----
-title: Server APIs & Backends
-description: Deploy LlamaIndex.TS in server environments like Express, Fastify, and standalone Node.js applications.
----
-
-This guide covers adding LlamaIndex.TS agents to traditional server environments where you have full Node.js runtime access.
-
-## Supported Runtimes
-
-LlamaIndex.TS works seamlessly with:
-
-- **Node.js** (v18+)
-- **Bun** (v1.0+)
-- **Deno** (v1.30+)
-
-## Common Server Frameworks
-
-### Express.js
-
-```typescript
-import express from 'express';
-import { agent } from '@llamaindex/workflow';
-import { tool } from 'llamaindex';
-import { openai } from '@llamaindex/openai';
-import { z } from 'zod';
-
-const app = express();
-app.use(express.json());
-
-// Initialize agent once at startup
-let myAgent: any;
-
-async function initializeAgent() {
-  // Create tools for the agent
-  const sumTool = tool({
-    name: "sum",
-    description: "Adds two numbers",
-    parameters: z.object({
-      a: z.number(),
-      b: z.number(),
-    }),
-    execute: ({ a, b }) => a + b,
-  });
-
-  const multiplyTool = tool({
-    name: "multiply",
-    description: "Multiplies two numbers",
-    parameters: z.object({
-      a: z.number(),
-      b: z.number(),
-    }),
-    execute: ({ a, b }) => a * b,
-  });
-
-  // Create the agent
-  myAgent = agent({
-    tools: [sumTool, multiplyTool],
-    llm: openai({ model: "gpt-4o-mini" }),
-  });
-}
-
-app.post('/api/chat', async (req, res) => {
-  try {
-    const { message } = req.body;
-    const result = await myAgent.run(message);
-    res.json({ response: result.data });
-  } catch (error) {
-    res.status(500).json({ error: 'Chat failed' });
-  }
-});
-
-// Initialize and start server
-initializeAgent().then(() => {
-  app.listen(3000, () => {
-    console.log('Server running on port 3000');
-  });
-});
-```
-
-### Fastify
-
-```typescript
-import Fastify from 'fastify';
-import { agent } from '@llamaindex/workflow';
-import { tool } from 'llamaindex';
-import { openai } from '@llamaindex/openai';
-import { z } from 'zod';
-
-const fastify = Fastify();
-let myAgent: any;
-
-async function initializeAgent() {
-  const sumTool = tool({
-    name: "sum",
-    description: "Adds two numbers",
-    parameters: z.object({
-      a: z.number(),
-      b: z.number(),
-    }),
-    execute: ({ a, b }) => a + b,
-  });
-
-  myAgent = agent({
-    tools: [sumTool],
-    llm: openai({ model: "gpt-4o-mini" }),
-  });
-}
-
-fastify.post('/api/chat', async (request, reply) => {
-  try {
-    const { message } = request.body as { message: string };
-    const result = await myAgent.run(message);
-    return { response: result.data };
-  } catch (error) {
-    reply.status(500).send({ error: 'Chat failed' });
-  }
-});
-
-const start = async () => {
-  await initializeAgent();
-  await fastify.listen({ port: 3000 });
-  console.log('Server running on port 3000');
-};
-
-start();
-```
-
-### Hono
-
-```typescript
-import { Hono } from "hono";
-import { agent } from "@llamaindex/workflow";
-import { tool } from "llamaindex";
-import { openai } from "@llamaindex/openai";
-import { z } from "zod";
-
-type Bindings = {
-  OPENAI_API_KEY: string;
-};
-
-const app = new Hono<{ Bindings: Bindings }>();
-
-app.post("/api/chat", async (c) => {
-  const { setEnvs } = await import("@llamaindex/env");
-  setEnvs(c.env);
-  
-  const { message } = await c.req.json();
-  
-  const greetTool = tool({
-    name: "greet",
-    description: "Greets a user",
-    parameters: z.object({
-      name: z.string(),
-    }),
-    execute: ({ name }) => `Hello, ${name}!`,
-  });
-
-  const myAgent = agent({
-    tools: [greetTool],
-    llm: openai({ model: "gpt-4o-mini" }),
-  });
-  
-  try {
-    const result = await myAgent.run(message);
-    return c.json({ response: result.data });
-  } catch (error) {
-    return c.json({ error: error.message }, 500);
-  }
-});
-
-export default app;
-```
-
-## Streaming Responses
-
-For real-time agent responses:
-
-```typescript
-import { agentStreamEvent } from "@llamaindex/workflow";
-
-app.post('/api/chat-stream', async (req, res) => {
-  const { message } = req.body;
-  
-  res.writeHead(200, {
-    'Content-Type': 'text/plain',
-    'Transfer-Encoding': 'chunked',
-  });
-  
-  try {
-    const events = myAgent.runStream(message);
-    
-    for await (const event of events) {
-      if (agentStreamEvent.include(event)) {
-        res.write(event.data.delta);
-      }
-    }
-    
-    res.end();
-  } catch (error) {
-    res.write('Error: ' + error.message);
-    res.end();
-  }
-});
-```
-
-
-## Next Steps
-
-- Learn about [serverless deployment](/docs/llamaindex/getting_started/installation/serverless)
-- Explore [Next.js integration](/docs/llamaindex/getting_started/installation/nextjs)
-- Check [troubleshooting guide](/docs/llamaindex/getting_started/installation/troubleshooting) for common issues 

apps/next/src/content/docs/llamaindex/getting_started/installation/serverless.mdx

@@ -1,240 +0,0 @@
----
-title: Serverless Functions
-description: Deploy LlamaIndex.TS in serverless environments like Vercel, Netlify, AWS Lambda, and Cloudflare Workers.
----
-
-This guide covers adding LlamaIndex.TS agents to serverless environments where you have execution time and memory constraints.
-
-## Cloudflare Workers
-
-```typescript
-export default {
-  async fetch(request: Request, env: Env): Promise<Response> {
-    const { setEnvs } = await import("@llamaindex/env");
-    setEnvs(env);
-    
-    const { agent } = await import("@llamaindex/workflow");
-    const { openai } = await import("@llamaindex/openai");
-    const { tool } = await import("llamaindex");
-    const { z } = await import("zod");
-
-    const timeTool = tool({
-      name: "getCurrentTime",
-      description: "Gets the current time",
-      parameters: z.object({}),
-      execute: () => new Date().toISOString(),
-    });
-
-    const myAgent = agent({
-      tools: [timeTool],
-      llm: openai({ model: "gpt-4o-mini" }),
-    });
-
-    try {
-      const { message } = await request.json();
-      const result = await myAgent.run(message);
-      
-      return new Response(JSON.stringify({ response: result.data }), {
-        headers: { "Content-Type": "application/json" },
-      });
-    } catch (error) {
-      return new Response(JSON.stringify({ error: error.message }), {
-        status: 500,
-        headers: { "Content-Type": "application/json" },
-      });
-    }
-  },
-};
-```
-
-
-
-## Vercel Functions
-
-### Node.js Runtime
-
-```typescript
-// pages/api/chat.ts or app/api/chat/route.ts
-import { agent } from "@llamaindex/workflow";
-import { tool } from "llamaindex";
-import { openai } from "@llamaindex/openai";
-import { z } from "zod";
-
-export default async function handler(req, res) {
-  if (req.method !== 'POST') {
-    return res.status(405).json({ error: 'Method not allowed' });
-  }
-  
-  const { message } = req.body;
-  
-  const weatherTool = tool({
-    name: "getWeather",
-    description: "Get weather information",
-    parameters: z.object({
-      city: z.string(),
-    }),
-    execute: ({ city }) => `Weather in ${city}: 72°F, sunny`,
-  });
-
-  const myAgent = agent({
-    tools: [weatherTool],
-    llm: openai({ model: "gpt-4o-mini" }),
-  });
-  
-  try {
-    const result = await myAgent.run(message);
-    res.json({ response: result.data });
-  } catch (error) {
-    res.status(500).json({ error: error.message });
-  }
-}
-```
-
-### Edge Runtime
-
-```typescript
-// app/api/chat/route.ts
-import { NextRequest, NextResponse } from "next/server";
-
-export const runtime = "edge";
-
-export async function POST(request: NextRequest) {
-  const { setEnvs } = await import("@llamaindex/env");
-  setEnvs(process.env);
-  
-  const { message } = await request.json();
-  
-  try {
-    // Use simpler tools for edge runtime
-    const { agent } = await import("@llamaindex/workflow");
-    const { tool } = await import("llamaindex");
-    const { openai } = await import("@llamaindex/openai");
-    const { z } = await import("zod");
-
-    const timeTool = tool({
-      name: "time",
-      description: "Gets current time",
-      parameters: z.object({}),
-      execute: () => new Date().toISOString(),
-    });
-
-    const myAgent = agent({
-      tools: [timeTool],
-      llm: openai({ model: "gpt-4o-mini" }),
-    });
-
-    const result = await myAgent.run(message);
-    return NextResponse.json({ response: result.data });
-  } catch (error) {
-    return NextResponse.json({ error: error.message }, { status: 500 });
-  }
-}
-```
-
-## AWS Lambda
-
-```typescript
-import { APIGatewayProxyHandler } from "aws-lambda";
-import { agent } from "@llamaindex/workflow";
-import { tool } from "llamaindex";
-import { openai } from "@llamaindex/openai";
-import { z } from "zod";
-
-export const handler: APIGatewayProxyHandler = async (event, context) => {
-  const { message } = JSON.parse(event.body || "{}");
-  
-  const calculatorTool = tool({
-    name: "calculate",
-    description: "Performs basic math",
-    parameters: z.object({
-      expression: z.string(),
-    }),
-    execute: ({ expression }) => {
-      // Simple calculator implementation
-      try {
-        return `Result: ${eval(expression)}`;
-      } catch {
-        return "Invalid expression";
-      }
-    },
-  });
-
-  const myAgent = agent({
-    tools: [calculatorTool],
-    llm: openai({ model: "gpt-4o-mini" }),
-  });
-  
-  try {
-    const result = await myAgent.run(message);
-    
-    return {
-      statusCode: 200,
-      headers: {
-        "Content-Type": "application/json",
-        "Access-Control-Allow-Origin": "*",
-      },
-      body: JSON.stringify({ response: result.data }),
-    };
-  } catch (error) {
-    return {
-      statusCode: 500,
-      body: JSON.stringify({ error: error.message }),
-    };
-  }
-};
-```
-
-## Netlify Functions
-
-```typescript
-// netlify/functions/chat.ts
-import { Handler } from "@netlify/functions";
-import { agent } from "@llamaindex/workflow";
-import { tool } from "llamaindex";
-import { openai } from "@llamaindex/openai";
-import { z } from "zod";
-
-export const handler: Handler = async (event, context) => {
-  if (event.httpMethod !== "POST") {
-    return { statusCode: 405, body: "Method Not Allowed" };
-  }
-  
-  const { message } = JSON.parse(event.body || "{}");
-  
-  const helpTool = tool({
-    name: "help",
-    description: "Provides help information",
-    parameters: z.object({
-      topic: z.string().optional(),
-    }),
-    execute: ({ topic }) => {
-      return topic ? `Help for ${topic}` : "Available help topics";
-    },
-  });
-
-  const myAgent = agent({
-    tools: [helpTool],
-    llm: openai({ model: "gpt-4o-mini" }),
-  });
-  
-  try {
-    const result = await myAgent.run(message);
-    
-    return {
-      statusCode: 200,
-      body: JSON.stringify({ response: result.data }),
-    };
-  } catch (error) {
-    return {
-      statusCode: 500,
-      body: JSON.stringify({ error: error.message }),
-    };
-  }
-};
-```
-
-## Next Steps
-
-- Learn about [Next.js integration](/docs/llamaindex/getting_started/installation/nextjs)
-- Explore [server deployment](/docs/llamaindex/getting_started/installation/server-apis)
-- Check [troubleshooting guide](/docs/llamaindex/getting_started/installation/troubleshooting) for common issues 

apps/next/src/content/docs/llamaindex/getting_started/installation/troubleshooting.mdx

@@ -1,501 +0,0 @@
----
-title: Troubleshooting
-description: Common issues and solutions when installing and deploying LlamaIndex.TS applications.
----
-
-This guide addresses common issues you might encounter when installing and deploying LlamaIndex.TS applications across different environments.
-
-## Installation Issues
-
-### Module Resolution Errors
-
-**Problem:** Import errors or module not found errors
-
-**Solution:** Ensure your `tsconfig.json` is properly configured:
-
-```json5
-{
-  "compilerOptions": {
-    "moduleResolution": "bundler", // or "nodenext" | "node16" | "node"
-    "lib": ["DOM.AsyncIterable"],
-    "target": "es2020",
-    "module": "esnext"
-  }
-}
-```
-
-**Alternative solution:** Try different module resolution strategies:
-
-```bash
-# Clear node_modules and reinstall
-rm -rf node_modules package-lock.json
-npm install
-
-# Or try with different package manager
-pnpm install
-# or
-yarn install
-```
-
-### TypeScript Errors
-
-**Problem:** TypeScript compilation errors with LlamaIndex imports
-
-**Solution:** Ensure you have the correct TypeScript configuration:
-
-```json5
-{
-  "compilerOptions": {
-    "strict": true,
-    "skipLibCheck": true, // Skip type checking of node_modules
-    "allowSyntheticDefaultImports": true,
-    "esModuleInterop": true
-  }
-}
-```
-
-### Package Compatibility Issues
-
-**Problem:** Some packages don't work in certain environments
-
-**Common incompatibilities:**
-- `@llamaindex/readers` - May not work in serverless environments
-- `@llamaindex/huggingface` - Limited browser/edge compatibility
-- File system readers - Don't work in browser/edge environments
-
-**Solution:** Use environment-specific alternatives:
-
-```typescript
-// Instead of file system readers in serverless
-// Use remote data sources
-async function loadDocumentsFromAPI() {
-  const response = await fetch('https://api.example.com/documents');
-  const data = await response.json();
-  return data.map(doc => new Document(doc.content));
-}
-```
-
-## Runtime Issues
-
-### Memory Errors
-
-**Problem:** Out of memory errors during index creation or querying
-
-**Solution:** Optimize memory usage:
-
-```typescript
-// Batch process large document sets
-async function batchProcessDocuments(documents: Document[], batchSize = 10) {
-  const results = [];
-  
-  for (let i = 0; i < documents.length; i += batchSize) {
-    const batch = documents.slice(i, i + batchSize);
-    const batchIndex = await VectorStoreIndex.fromDocuments(batch);
-    results.push(batchIndex);
-    
-    // Optional: Add delay between batches
-    await new Promise(resolve => setTimeout(resolve, 100));
-  }
-  
-  return results;
-}
-```
-
-**For serverless environments:**
-
-```typescript
-// Use external vector stores instead of in-memory
-// TODO: Example with Pinecone, Weaviate, etc.
-// const vectorStore = new PineconeVectorStore(/* config */);
-// const index = await VectorStoreIndex.fromVectorStore(vectorStore);
-```
-
-### API Rate Limiting
-
-**Problem:** Rate limiting errors from LLM providers
-
-**Solution:** Implement retry logic with exponential backoff:
-
-```typescript
-async function queryWithRetry(queryEngine: any, question: string, maxRetries = 3) {
-  for (let i = 0; i < maxRetries; i++) {
-    try {
-      return await queryEngine.query(question);
-    } catch (error) {
-      if (error.message.includes('rate limit') && i < maxRetries - 1) {
-        const delay = Math.pow(2, i) * 1000; // Exponential backoff
-        await new Promise(resolve => setTimeout(resolve, delay));
-        continue;
-      }
-      throw error;
-    }
-  }
-}
-```
-
-### Tokenization Performance
-
-**Problem:** Slow tokenization affecting performance
-
-**Solution:** Install faster tokenizer (Node.js only):
-
-```bash
-npm install gpt-tokenizer
-```
-
-LlamaIndex will automatically use this for 60x faster tokenization.
-
-## Bundling Issues
-
-### Bundle Size Too Large
-
-**Problem:** Large bundle sizes affecting performance
-
-**Solution:** Use dynamic imports and code splitting:
-
-```typescript
-// Lazy load LlamaIndex components
-const initializeLlamaIndex = async () => {
-  const { VectorStoreIndex, SimpleDirectoryReader } = await import("llamaindex");
-  return { VectorStoreIndex, SimpleDirectoryReader };
-};
-
-// In your API route
-export async function POST(request: NextRequest) {
-  const { VectorStoreIndex, SimpleDirectoryReader } = await initializeLlamaIndex();
-  // Use the imported modules
-}
-```
-
-### Webpack/Vite Bundling Issues
-
-**Problem:** Bundler compatibility issues
-
-**Solution for Next.js:**
-
-```javascript
-// next.config.mjs
-import withLlamaIndex from "llamaindex/next";
-
-const nextConfig = {
-  webpack: (config, { isServer }) => {
-    // Custom webpack configuration if needed
-    if (!isServer) {
-      config.resolve.fallback = {
-        ...config.resolve.fallback,
-        fs: false,
-        net: false,
-        tls: false,
-      };
-    }
-    return config;
-  },
-};
-
-export default withLlamaIndex(nextConfig);
-```
-
-**Solution for Vite:**
-
-```typescript
-// vite.config.ts
-import { defineConfig } from 'vite';
-
-export default defineConfig({
-  define: {
-    global: 'globalThis',
-  },
-  resolve: {
-    alias: {
-      // Add aliases for problematic modules
-    },
-  },
-  optimizeDeps: {
-    include: ['llamaindex'],
-  },
-});
-```
-
-## Environment-Specific Issues
-
-### Node.js Version Compatibility
-
-**Problem:** Node.js version compatibility issues
-
-**Solution:** Use supported Node.js versions:
-
-```json
-{
-  "engines": {
-    "node": ">=18.0.0"
-  }
-}
-```
-
-**Check your Node.js version:**
-
-```bash
-node --version
-```
-
-### Cloudflare Workers Issues
-
-**Problem:** Module not available in Cloudflare Workers
-
-**Solution:** Use `@llamaindex/env` for environment compatibility:
-
-```typescript
-export default {
-  async fetch(request: Request, env: Env): Promise<Response> {
-    const { setEnvs } = await import("@llamaindex/env");
-    setEnvs(env);
-    
-    // Your LlamaIndex code here
-  },
-};
-```
-
-### Vercel Edge Runtime Issues
-
-**Problem:** Limited Node.js API access in Edge Runtime
-
-**Solution:** Use standard runtime or adapt code:
-
-```typescript
-// Force standard runtime
-export const runtime = "nodejs";
-
-// Or adapt for edge
-export const runtime = "edge";
-
-export async function POST(request: NextRequest) {
-  // Use edge-compatible code only
-  const { setEnvs } = await import("@llamaindex/env");
-  setEnvs(process.env);
-  
-  // Avoid file system operations
-  // Use remote data sources
-}
-```
-
-## Performance Issues
-
-### Slow Query Responses
-
-**Problem:** Slow query performance
-
-**Solution:** Implement caching and optimization:
-
-```typescript
-import { LRUCache } from 'lru-cache';
-
-const queryCache = new LRUCache<string, string>({
-  max: 100,
-  ttl: 1000 * 60 * 10, // 10 minutes
-});
-
-export async function optimizedQuery(question: string, queryEngine: any) {
-  // Check cache first
-  const cached = queryCache.get(question);
-  if (cached) return cached;
-  
-  // Query and cache result
-  const result = await queryEngine.query(question);
-  queryCache.set(question, result);
-  
-  return result;
-}
-```
-
-### Cold Start Issues
-
-**Problem:** Slow cold starts in serverless environments
-
-**Solution:** Pre-warm your functions:
-
-```typescript
-// Pre-initialize outside handler
-let cachedQueryEngine: any = null;
-
-export async function handler(event: any) {
-  if (!cachedQueryEngine) {
-    cachedQueryEngine = await initializeQueryEngine();
-  }
-  
-  // Use cached engine
-  return await cachedQueryEngine.query(question);
-}
-```
-
-## Environment Variable Issues
-
-### Missing API Keys
-
-**Problem:** API key not found or invalid
-
-**Solution:** Verify environment variable setup:
-
-```typescript
-// Check if API key is available
-if (!process.env.OPENAI_API_KEY) {
-  throw new Error('OPENAI_API_KEY environment variable is required');
-}
-
-// For debugging (remove in production)
-console.log('API Key present:', !!process.env.OPENAI_API_KEY);
-```
-
-### Environment Variable Loading
-
-**Problem:** Environment variables not loading correctly
-
-**Solution:** Use proper loading mechanisms:
-
-```typescript
-// For Node.js
-import 'dotenv/config';
-
-// For Next.js - use .env.local
-// Variables are automatically loaded
-
-// For Cloudflare Workers
-export default {
-  async fetch(request: Request, env: Env): Promise<Response> {
-    // Use env parameter, not process.env
-    const apiKey = env.OPENAI_API_KEY;
-    // ...
-  },
-};
-```
-
-## Common Error Messages
-
-### "Cannot find module 'llamaindex'"
-
-**Cause:** Package not installed or module resolution issue
-
-**Solution:**
-```bash
-npm install llamaindex
-```
-
-### "Module not found: Can't resolve 'fs'"
-
-**Cause:** File system modules used in browser/edge environment
-
-**Solution:**
-```typescript
-// Use dynamic imports with fallbacks
-const loadDocuments = async () => {
-  if (typeof window !== 'undefined') {
-    // Browser environment - use alternative
-    return await loadDocumentsFromAPI();
-  } else {
-    // Node.js environment - use file system
-    const { SimpleDirectoryReader } = await import('llamaindex');
-    return await new SimpleDirectoryReader('data').loadData();
-  }
-};
-```
-
-### "ReferenceError: global is not defined"
-
-**Cause:** Global polyfill missing in browser environments
-
-**Solution:**
-```typescript
-// Add to your app entry point
-if (typeof global === 'undefined') {
-  global = globalThis;
-}
-```
-
-### "Cannot read properties of undefined (reading 'query')"
-
-**Cause:** Query engine not properly initialized
-
-**Solution:**
-```typescript
-// Always check initialization
-if (!queryEngine) {
-  throw new Error('Query engine not initialized');
-}
-
-// Or use optional chaining
-const response = await queryEngine?.query(question);
-```
-
-## Debugging Tips
-
-### Enable Debug Logging
-
-```typescript
-// Enable debug logging
-process.env.DEBUG = "llamaindex:*";
-
-// Or specific modules
-process.env.DEBUG = "llamaindex:vector-store";
-```
-
-### Check Package Versions
-
-```bash
-npm list llamaindex
-npm list @llamaindex/openai
-```
-
-### Test in Isolation
-
-```typescript
-// Create minimal test case
-import { VectorStoreIndex } from 'llamaindex';
-
-async function testBasic() {
-  try {
-    console.log('Testing basic import...');
-    const index = new VectorStoreIndex();
-    console.log('Success!');
-  } catch (error) {
-    console.error('Error:', error);
-  }
-}
-
-testBasic();
-```
-
-## Getting Help
-
-### Before Asking for Help
-
-1. **Check this troubleshooting guide**
-2. **Search existing GitHub issues**
-3. **Try minimal reproduction**
-4. **Check your environment configuration**
-
-### When Reporting Issues
-
-Include:
-- Node.js version (`node --version`)
-- Package versions (`npm list llamaindex`)
-- Environment (Node.js, Cloudflare Workers, Vercel, etc.)
-- Minimal code reproduction
-- Full error message and stack trace
-
-### Useful Resources
-
-- [GitHub Issues](https://github.com/run-llama/LlamaIndexTS/issues)
-- [Discord Community](https://discord.gg/dGcwcsnxhU)
-- [Documentation](https://docs.llamaindex.ai/)
-
-## Next Steps
-
-If you're still experiencing issues:
-
-1. **Check specific deployment guides:**
-   - [Server APIs](/docs/llamaindex/getting_started/installation/server-apis)
-   - [Serverless Functions](/docs/llamaindex/getting_started/installation/serverless)
-   - [Next.js Applications](/docs/llamaindex/getting_started/installation/nextjs)
-
-2. **Open an issue** on GitHub with a minimal reproduction
-
-3. **Join our Discord** for community support 

apps/next/src/content/docs/llamaindex/getting_started/installation/typescript.mdx

@@ -0,0 +1,99 @@
+---
+title: With TypeScript
+description: In this guide, you'll learn how to use LlamaIndex with TypeScript
+---
+
+LlamaIndex.TS is written in TypeScript and designed to be used in TypeScript projects.
+
+We put a lot of work on strong typing to make sure you have a great typing experience with code completion such as:
+
+```ts twoslash
+import { PromptTemplate } from 'llamaindex'
+const promptTemplate = new PromptTemplate({
+  template: `Context information from multiple sources is below.
+---------------------
+{context}
+---------------------
+Given the information from multiple sources and not prior knowledge.
+Answer the query in the style of a Shakespeare play"
+Query: {query}
+Answer:`,
+	templateVars: ["context", "query"],
+});
+// @noErrors
+promptTemplate.format({
+	c
+//^|
+})
+```
+
+## Enable TypeScript
+
+Make sure to set [moduleResolution](https://www.typescriptlang.org/docs/handbook/modules/theory.html#module-resolution) in your `tsconfig.json` file:
+
+```json5
+{
+  compilerOptions: {
+    // ⬇️ add this line to your tsconfig.json
+    moduleResolution: "bundler", // or "nodenext" | "node16" | "node"
+  },
+}
+```
+
+We recommend using `bundler` or `nodenext`, but due to popularity of `node`, we still added support for it.
+
+## Enable AsyncIterable for `Web Stream` API
+
+Some modules uses `Web Stream` API like `ReadableStream` and `WritableStream`, you need to enable `DOM.AsyncIterable` in your `tsconfig.json`.
+
+```json5
+{
+  compilerOptions: {
+    // ⬇️ add this lib to your tsconfig.json
+    lib: ["DOM.AsyncIterable"],
+  },
+}
+```
+
+```typescript
+import { tool } from 'llamaindex'
+import { agent } from "@llamaindex/workflow";
+import { openai } from "@llamaindex/openai";
+
+Settings.llm = openai({
+  model: "gpt-4o-mini",
+});
+
+const addTool = tool({
+  name: "add", 
+  description: "Adds two numbers",
+  parameters: z.object({x: z.number(), y: z.number()}),
+  execute: ({ x, y }) => x + y,
+});
+
+const myAgent = agent({
+  tools: [addTool],
+});
+
+// Chat with the agent
+const context = myAgent.run("Hello, how are you?");
+
+for await (const event of context) {
+  if (event instanceof AgentStream) {
+    for (const chunk of event.data.delta) {
+      process.stdout.write(chunk); // stream response
+    }
+  } else {
+    console.log(event); // other events
+  }
+}
+
+```
+
+## Run TypeScript Script in Node.js
+
+We recommend to use [tsx](https://www.npmjs.com/package/tsx) to run TypeScript script in Node.js.
+
+```shell
+node --import tsx ./my-script.ts
+```

apps/next/src/content/docs/llamaindex/getting_started/installation/vite.mdx

@@ -0,0 +1,23 @@
+---
+title: With Vite
+description: In this guide, you'll learn how to use LlamaIndex with Vite
+---
+
+Before you start, make sure you have try LlamaIndex.TS in Node.js to make sure you understand the basics.
+
+<Card
+  title="Getting Started with LlamaIndex.TS in Node.js"
+  href="/docs/llamaindex/getting_started/installation/node"
+/>
+
+Also, make sure you have a basic understanding of [Vite](https://vitejs.dev/).
+
+## Why mention Vite?
+
+Vite.js is widely used in building many web applications, like React.js, even for some native app like [Electron](https://www.electronjs.org/).
+
+However, it's not a ready-to-use solution for a Node.js-like application using Vite, as Vite is designed for web applications(run in browser).
+
+There's some plugin/framework based on Vite, like [Waku.gg](https://github.com/dai-shi/waku), or [Electron Vite](https://electron-vite.org/)
+
+For now, we have no clear solution for bundling LlamaIndex.TS with Vite, if you have any idea/solution, please let us know.

apps/next/src/content/docs/llamaindex/index.mdx

@@ -1,118 +1,21 @@
 ---
-title: Welcome to LlamaIndex.TS
+title: What is LlamaIndex.TS
-description: LlamaIndex.TS is the leading framework for utilizing context engineering to build LLM applications in JavaScript and TypeScript.
+description: LlamaIndex is the leading data framework for building LLM applications
 ---
 
-LlamaIndex.TS is a **framework for utilizing context engineering to build generative AI applications** with large language models. From rapid-prototyping RAG chatbots to deploying multi-agent workflows in production, LlamaIndex gives you everything you need — all in idiomatic TypeScript.
+LlamaIndex is a framework for building context-augmented generative AI applications with LLMs including agents and workflows.
 
-Built for modern JavaScript runtimes like <SiNodedotjs className="inline" color="#5FA04E" /> **Node.js**, <SiDeno className="inline" color="#70FFAF" /> **Deno**, <SiBun className="inline" /> **Bun**, <SiCloudflareworkers className="inline" color="#F38020" /> **Cloudflare Workers**, and more.
+The TypeScript implementation is designed for JavaScript server side applications using <SiNodedotjs className="inline" color="#5FA04E" /> Node.js, <SiDeno className="inline" color="#70FFAF" /> Deno, <SiBun className="inline" /> Bun, <SiCloudflareworkers className="inline" color="#F38020" /> Cloudflare Workers, and more.
 
-<div className="grid grid-cols-1 gap-4 sm:grid-cols-2 lg:grid-cols-3 my-6">
+LlamaIndex.TS provides tools for beginners, advanced users, and everyone in between.
-  <a href="#introduction" className="block rounded-lg border border-gray-600/40 p-4 hover:border-gray-400 hover:bg-gray-700/20 no-underline">
-    <h3 className="mb-1 text-lg font-semibold underline">Introduction</h3>
-    <p className="text-sm text-gray-400 no-underline">Context engineering, agents &amp; workflows — what do they mean?</p>
-  </a>
 
-  <a href="#use-cases" className="block rounded-lg border border-gray-600/40 p-4 hover:border-gray-400 hover:bg-gray-700/20 no-underline">
+Try it out with a starter example using StackBlitz:
-    <h3 className="mb-1 text-lg font-semibold underline">Use cases</h3>
-    <p className="text-sm text-gray-400 no-underline">See what you can build with LlamaIndex.TS.</p>
-  </a>
-
-  <a href="#getting-started" className="block rounded-lg border border-gray-600/40 p-4 hover:border-gray-400 hover:bg-gray-700/20 no-underline">
-    <h3 className="mb-1 text-lg font-semibold underline">Getting started</h3>
-    <p className="text-sm text-gray-400 no-underline">Your first app in 5 lines of code.</p>
-  </a>
-
-  <a href="https://docs.cloud.llamaindex.ai/" className="block rounded-lg border border-gray-600/40 p-4 hover:border-gray-400 hover:bg-gray-700/20 no-underline" target="_blank" rel="noopener noreferrer">
-    <h3 className="mb-1 text-lg font-semibold underline">LlamaCloud</h3>
-    <p className="text-sm text-gray-400 no-underline">Managed parsing, extraction &amp; retrieval pipelines.</p>
-  </a>
-
-  <a href="#community" className="block rounded-lg border border-gray-600/40 p-4 hover:border-gray-400 hover:bg-gray-700/20 no-underline">
-    <h3 className="mb-1 text-lg font-semibold underline">Community</h3>
-    <p className="text-sm text-gray-400 no-underline">Join thousands of builders on Discord, Twitter, and more.</p>
-  </a>
-
-  <a href="#related-projects" className="block rounded-lg border border-gray-600/40 p-4 hover:border-gray-400 hover:bg-gray-700/20 no-underline">
-    <h3 className="mb-1 text-lg font-semibold underline">Related projects</h3>
-    <p className="text-sm text-gray-400 no-underline">Connectors, demos &amp; starter kits.</p>
-  </a>
-</div>
-
-## Introduction
-
-### What are agents?
-
-[Agents](/docs/llamaindex/tutorials/agents/1_setup) are LLM-powered assistants that can reason, use external tools, and take actions to accomplish tasks such as research, data extraction, and automation. 
-LlamaIndex.TS provides foundational building blocks for creating and orchestrating these agents.
-
-### What are workflows?
-
-[Workflows](/docs/llamaindex/tutorials/workflows) are multi-step, event-driven processes that combine agents, data connectors, and other tools to solve complex problems. 
-With LlamaIndex.TS you can chain together retrieval, generation, and tool-calling steps and then deploy the entire pipeline as a microservice.
-
-### What is context engineering?
-
-LLMs come pre-trained on vast public corpora, but not on **your** private or domain-specific data. 
-Context engineering bridges that gap by injecting the right pieces of your data into the LLM prompt at the right time. 
-The most popular example is [Retrieval-Augmented Generation (RAG)](/docs/llamaindex/getting_started/concepts), but the same idea powers agent memory, evaluation, extraction, summarisation, and more.
-
-LlamaIndex.TS gives you:
-
-- **Data connectors** to ingest from APIs, files, SQL, and dozens more sources.
-- **Indexes & retrievers** to store and retrieve your data for LLM consumption.
-- **Agents and Engines** to query and use chat+reasoning interfaces over your data.
-- **Workflows** for fine-grained orchestration of your data and LLM-powered agents.
-- **Observability** integrations so you can iterate with confidence.
-
-You can learn more about these concepts in our [concepts guide](/docs/llamaindex/getting_started/concepts).
-
-## Use cases
-
-Popular scenarios include:
-
-- [LLM-Powered Agents](/docs/llamaindex/tutorials/agents/1_setup)
-- [Indexing and Retrieval](/docs/llamaindex/tutorials/rag)
-- [Extracting Structured Data](/docs/llamaindex/tutorials/structured_data_extraction)
-- [Custom Orchestration with Workflows](/docs/llamaindex/tutorials/workflows)
-
-## Getting started
-
-The fastest way to get started is in StackBlitz below — no local setup required:
 
 <iframe
   className="w-full h-[440px]"
   aria-label="LlamaIndex.TS Starter"
-  aria-description="Interactive starter for LlamaIndex.TS"
+  aria-description="This is a starter example for LlamaIndex.TS, it shows the basic usage of the library."
   src="https://stackblitz.com/github/run-llama/LlamaIndexTS/tree/main/examples?embed=1&file=starter.ts"
 />
 
-Want to learn more? We have several tutorials to get you started:
+You'll need an OpenAI API key to run this example. You can retrieve it from [OpenAI](https://platform.openai.com/api-keys).
-
-- [Installation + Runtime Guide](/docs/llamaindex/getting_started/installation)
-- [Create your first agent](/docs/llamaindex/tutorials/agents/1_setup)
-- [Learn how to index data and chat with it](/docs/llamaindex/tutorials/rag)
-- [Learn how to write your own workflows and agents](/docs/llamaindex/tutorials/workflows)
-
----
-
-## LlamaCloud
-
-Need an end-to-end managed pipeline? Check out **[LlamaCloud](https://cloud.llamaindex.ai/)**: best-in-class document parsing (LlamaParse), extraction (LlamaExtract), and indexing services with generous free tiers.
-
----
-
-## Community
-
-- [Twitter](https://twitter.com/llama_index)
-- [Discord](https://discord.gg/dGcwcsnxhU)
-- [LinkedIn](https://www.linkedin.com/company/llamaindex/)
-
-We 💜 contributors! View our [contributing guide](https://github.com/run-llama/LlamaIndexTS/blob/main/CONTRIBUTING.md) to get started.
-
-## Related projects
-
-- [Python framework GitHub](https://github.com/run-llama/llama_index)
-- [Python docs](https://docs.llamaindex.ai/)
-- [create-llama](https://www.npmjs.com/package/create-llama) — scaffold a new project in seconds!
-- [UI Components](https://ui.llamaindex.ai/) — build chat applications with our Next.js components.

apps/next/src/content/docs/llamaindex/integration/mcp-toolbox.mdx

@@ -1,85 +0,0 @@
----
-title: MCP Toolbox For Databases
-description: MCP Toolbox for Databases is an open source MCP server for databases.
----
-
-# MCP Toolbox for Databases
-
-[MCP Toolbox for Databases](https://github.com/googleapis/genai-toolbox) is an open source MCP server for databases. It was designed with enterprise-grade and production-quality in mind. It enables you to develop tools easier, faster, and more securely by handling the complexities such as connection pooling, authentication, and more.
-
-Toolbox Tools can be seemlessly integrated with LlamaIndex applications. For more
-information on [getting
-started](https://googleapis.github.io/genai-toolbox/getting-started/local_quickstart_js/) or
-[configuring](https://googleapis.github.io/genai-toolbox/getting-started/configure/)
-Toolbox, see the
-[documentation](https://googleapis.github.io/genai-toolbox/getting-started/introduction/).
-
-![architecture](/images/mcp_db_toolbox.png)
-
-### Configure and deploy
-
-Toolbox is an open source server that you deploy and manage yourself. For more
-instructions on deploying and configuring, see the official Toolbox
-documentation:
-
-* [Installing the Server](https://googleapis.github.io/genai-toolbox/getting-started/introduction/#installing-the-server)
-* [Configuring Toolbox](https://googleapis.github.io/genai-toolbox/getting-started/configure/)
-
-### Install client SDK
-
-LlamaIndex relies on the `@toolbox-sdk/core` node package to use Toolbox. Install the
-package before getting started:
-
-```shell
-npm install @toolbox-sdk/core
-```
-
-### Loading Toolbox Tools
-
-Once your Toolbox server is configured and up and running, you can load tools
-from your server using the SDK:
-
-```javascript
-import { gemini, GEMINI_MODEL } from "@llamaindex/google";
-import { agent } from "@llamaindex/workflow";
-import { tool } from "llamaindex";
-import { ToolboxClient } from "@toolbox-sdk/core";
-
-// Initialize LLM
-const llm = gemini({
-  model: GEMINI_MODEL.GEMINI_2_0_FLASH,
-  apiKey: process.env.GOOGLE_API_KEY,
-});
-
-// Replace with your Toolbox Server URL
-const URL = 'https://127.0.0.1:5000';
-
-const client = new ToolboxClient("http://127.0.0.1:5000");
-const toolboxTools = await client.loadToolset("my-toolset");
-
-const getTool = (toolboxTool) => tool({
-  name: toolboxTool.getName(),
-  description: toolboxTool.getDescription(),
-  parameters: toolboxTool.getParamSchema(),
-  execute: toolboxTool
-});
-const tools = toolboxTools.map(getTool);
-
-const myAgent = agent({
-  tools: tools,
-  llm,
-  memory,
-  systemPrompt: prompt,
-});
-const result = await myAgent.run(query);
-console.log(result);
-```
-
-### Advanced Toolbox Features
-
-Toolbox has a variety of features to make developing Gen AI tools for databases seamless.
-For more information, read more about the following:
-
-- [Authenticated Parameters](https://googleapis.github.io/genai-toolbox/resources/tools/#authenticated-parameters): bind tool inputs to values from OIDC tokens automatically, making it easy to run sensitive queries without potentially leaking data
-- [Authorized Invocations](https://googleapis.github.io/genai-toolbox/resources/tools/#authorized-invocations): restrict access to use a tool based on the users Auth token
-- [OpenTelemetry](https://googleapis.github.io/genai-toolbox/how-to/export_telemetry/): get metrics and tracing from Toolbox with [OpenTelemetry](https://opentelemetry.io/docs/)

apps/next/src/content/docs/llamaindex/integration/meta.json

@@ -1,5 +1,5 @@
 {
   "title": "Integration",
   "description": "See our integrations",
-  "pages": ["open-llm-metry", "lang-trace", "mcp-toolbox", "vercel"]
+  "pages": ["open-llm-metry", "lang-trace", "vercel"]
 }

apps/next/src/content/docs/llamaindex/modules/agents/agent_workflow.mdx

@@ -34,7 +34,6 @@ const jokeAgent = agent({
 // Run the workflow
 const result = await jokeAgent.run("Tell me something funny");
 console.log(result.data.result); // Baby Llama is called cria
-console.log(result.data.message); // { role: 'assistant', content: 'Baby Llama is called cria' }
 ```
 
 ### Event Streaming

apps/next/src/content/docs/llamaindex/modules/agents/low-level.mdx

@@ -1,164 +0,0 @@
----
-title: Low-Level LLM Execution
----
-
-Sometimes your need more control over LLM interactions than what high-level agents provide. The `llm.exec` method makes it simple for you to make a single LLM call with tools but hides the complexity of executing the tools and generating the tool messages.
-
-## When to Use `llm.exec`
-
-Use `llm.exec` when you need to:
-- Build custom agent logic in [workflow](/docs/llamaindex/modules/agents/workflows) steps
-- Have precise control over message handling and tool execution
-
-## Basic Usage
-
-The `llm.exec` method takes messages and tools as parameter and executes one LLM call.
-The LLM might either request to call one or more of the tools or generate an assistant message as result.
-For each tool call that is requested, `llm.exec` executes it and generates the two tool call messages (call and result). If no tool call is requested, just the assistant message is returned. 
-
-```ts
-import { openai } from "@llamaindex/openai";
-import { ChatMessage, tool } from "llamaindex";
-import z from "zod";
-
-const llm = openai({ model: "gpt-4.1-mini" });
-const messages = [
-  {
-    content: "What's the weather like in San Francisco?",
-    role: "user",
-  } as ChatMessage,
-];
-
-const { newMessages, toolCalls } = await llm.exec({
-  messages,
-  tools: [
-    tool({
-      name: "get_weather",
-      description: "Get the current weather for a location",
-      parameters: z.object({
-        address: z.string().describe("The address"),
-      }),
-      execute: ({ address }) => {
-        return `It's sunny in ${address}!`;
-      },
-    }),
-  ],
-});
-
-// Add the new messages (including tool calls and responses) to your conversation
-messages.push(...newMessages);
-```
-
-> `newMessages` is an array as each tool call generates two messages: a tool call message and the tool call result message.
-
-## Agent Loop Pattern
-
-A common pattern is to use `llm.exec` in a loop until the LLM stops making tool calls:
-
-```ts
-import { openai } from "@llamaindex/openai";
-import { ChatMessage, tool } from "llamaindex";
-import z from "zod";
-
-async function runAgentLoop() {
-  const llm = openai({ model: "gpt-4.1-mini" });
-  const messages = [
-    {
-      content: "What's the weather like in San Francisco?",
-      role: "user",
-    } as ChatMessage,
-  ];
-
-  let exit = false;
-  do {
-    const { newMessages, toolCalls } = await llm.exec({
-      messages,
-      tools: [
-        tool({
-          name: "get_weather",
-          description: "Get the current weather for a location",
-          parameters: z.object({
-            address: z.string().describe("The address"),
-          }),
-          execute: ({ address }) => {
-            return `It's sunny in ${address}!`;
-          },
-        }),
-      ],
-    });
-    
-    console.log(newMessages);
-    messages.push(...newMessages);
-    
-    // Exit when no more tool calls are made
-    exit = toolCalls.length === 0;
-  } while (!exit);
-}
-```
-
-## Streaming Support
-
-For real-time responses, use the `stream` option to get the assistant's response as streamed tokens:
-
-```ts
-import { openai } from "@llamaindex/openai";
-import { tool } from "llamaindex";
-import z from "zod";
-
-async function streamingAgentLoop() {
-  const llm = openai({ model: "gpt-4o-mini" });
-  const messages = [
-    {
-      content: "What's the weather like in San Francisco?",
-      role: "user",
-    } as ChatMessage,
-  ];
-
-  let exit = false;
-  do {
-    const { stream, newMessages, toolCalls } = await llm.exec({
-      messages,
-      tools: [
-        tool({
-          name: "get_weather",
-          description: "Get the current weather for a location",
-          parameters: z.object({
-            address: z.string().describe("The address"),
-          }),
-          execute: ({ address }) => {
-            return `It's sunny in ${address}!`;
-          },
-        }),
-      ],
-      stream: true,
-    });
-    
-    // Stream the response token by token
-    for await (const chunk of stream) {
-      process.stdout.write(chunk.delta);
-    }
-    
-    messages.push(...newMessages());
-    
-    exit = toolCalls.length === 0;
-  } while (!exit);
-}
-```
-
-> `newMessages` is a function when streaming. The reason is that the result only is available after streaming. Calling it before, will throw an error.
-
-## Return Values
-
-`llm.exec` returns an object with:
-
-- **`newMessages`**: Array of new chat messages including the LLM response and any tool call messages (call or result). This is a function return the array when streaming.
-- **`toolCalls`**: Array of tool calls made by the LLM
-- **`stream`**: Async iterable for streaming responses (only when `stream: true`)
-
-## Best Practices
-
-For using `llm.exec` in an agent loop, take care to:
-
-1. **Maintain message history**: Always add `newMessages` to your conversation history
-2. **Set exit conditions**: Implement proper logic to avoid infinite loops
-

apps/next/src/content/docs/llamaindex/modules/agents/meta.json

@@ -1,10 +1,4 @@
 {
   "title": "Agents",
-  "pages": [
+  "pages": ["tool", "agent_workflow", "workflows", "natural_language_workflow"]
-    "tool",
-    "agent_workflow",
-    "workflows",
-    "low-level",
-    "natural_language_workflow"
-  ]
 }

apps/next/src/content/docs/llamaindex/modules/agents/tool/index.mdx

@@ -101,9 +101,6 @@ const agent = agent({
 });
 ```
 
-You can also use [MCP Toolbox for
-Databases](/docs/llamaindex/integration/mcp-toolbox) to interact with MCP tools.
-
 
 ## Function tool
 

apps/next/src/content/docs/llamaindex/modules/data/memory/index.mdx

@@ -106,40 +106,34 @@ const memory = createMemory({
 
 Long-term memory is represented as `Memory Block` objects. These objects contain information that are from previous user sessions or from the beginning of the current conversation. When memory is retrieved (by calling `getLLM`), the short-term and long-term memories are merged together within the given `tokenLimit`. 
 
-Currently, there are three predefined memory blocks:
+Currently, there are two predefined memory blocks:
 
 - `staticBlock`: A memory block that stores a static piece of information.
 - `factExtractionBlock`: A memory block that extracts facts from the chat history.
-- `vectorBlock`: A memory block that stores and retrieves chat messages from a vector database using semantic similarity search. Messages are stored individually and retrieved based on their relevance to recent conversation context. Here we've passed in the `vectorStore` to use to store and retrieve the chat messages.
 
 This sounds a bit complicated, but it's actually quite simple. Let's look at an example:
 
 ```ts
-import { createMemory, factExtractionBlock, staticBlock, vectorBlock } from "llamaindex";
+import { createMemory, factExtractionBlock, staticBlock } from "llamaindex";
-import { QdrantVectorStore } from "@llamaindex/qdrant";
-import { OpenAIEmbedding } from "@llamaindex/openai";
 
 const memoryBlocks= [
   staticBlock({
+    id: "core_info",
     content: "My name is Logan, and I live in Saskatoon. I work at LlamaIndex.",
   }),
   factExtractionBlock({
+    id: "user-extracted_info",
     priority: 1,
     llm: llm,
     maxFacts: 50,
   }),
-  vectorBlock({
-    vectorStore: new QdrantVectorStore({ url: "http://localhost:6333" }),
-    priority: 2,
-  }),
 ];
 ```
 
-Here, we've setup three memory blocks:
+Here, we've setup two memory blocks:
 
-- `staticBlock`: A static memory block that stores some core information about the user. This information will always be inserted into the memory. The type used is `MessageContent` to support multi-modal content.
+- `core_info`: A static memory block that stores some core information about the user. This information will always be inserted into the memory. The type used is `MessageContent` to support multi-modal content.
-- `factExtractionBlock`: An extracted memory block that will extract information from the chat history. Here we've passed in the `llm` to use to extract facts from the chat history, and set the `maxFacts` to 50. If the number of extracted facts exceeds this limit, the `maxFacts` will be automatically summarized and reduced to leave room for new information.
+- `extracted_info`: An extracted memory block that will extract information from the chat history. Here we've passed in the `llm` to use to extract facts from the chat history, and set the `maxFacts` to 50. If the number of extracted facts exceeds this limit, the `maxFacts` will be automatically summarized and reduced to leave room for new information.
-- `vectorBlock`: A vector memory block that will store in a vector database and retrieve them from there. Messages are stored individually and retrieved based on their relevance to recent conversation context. Here we've passed in the `vectorStore` to use to store and retrieve the chat messages.
 
 You'll also notice that we've set the `priority` for the `factExtractionBlock` block. This is used to determine the handling when the memory blocks content (i.e. long-term memory) + short-term memory exceeds the token limit on the `Memory` object.
 
@@ -164,46 +158,6 @@ When memory is retrieved (using `getLLM`), the short-term and long-term memories
 
 The amount of short-term memory included is specified by the `shortTermTokenLimitRatio`. If it's set to `0.7`, 70% of the `tokenLimit` is used for short-term memory (not including the static memory block).
 
-
-#### VectorBlock Configuration Options
-
-The `vectorBlock` offers several configuration options to customize its behavior:
-
-```ts
-vectorBlock({
-  vectorStore: new QdrantVectorStore({ url: "http://localhost:6333" }),
-  priority: 2,
-  retrievalContextWindow: 5, // Number of recent messages to use for context when retrieving
-  formatTemplate: new PromptTemplate({ template: "Context: {{ context }}" }), // Custom formatting template
-  nodePostprocessors: [/* custom postprocessors */], // Apply processing to retrieved nodes
-  queryOptions: {
-    similarityTopK: 3, // Number of top similar results to return (default: 2)
-    mode: VectorStoreQueryMode.DEFAULT, // Query mode for the vector store
-    sessionFilterKey: "session_id", // Metadata key for session filtering (default: "session_id")
-    // Custom filters can be added here - session filter is automatically included
-    filters: {
-      filters: [
-        { key: "custom_field", value: "custom_value", operator: "==" }
-      ],
-      condition: "and"
-    }
-  }
-})
-```
-
-**Key Configuration Options:**
-
-- **`retrievalContextWindow`**: Number of recent messages to consider when creating the retrieval query (default: 5). A larger window provides more context but may be less precise.
-- **`formatTemplate`**: Template for formatting retrieved information before adding to memory. Defaults to a simple context template.
-- **`nodePostprocessors`**: Array of postprocessors to apply to retrieved nodes, useful for filtering or transforming results.
-- **`queryOptions.similarityTopK`**: Number of most similar messages to retrieve from the vector store (default: 2).
-- **`queryOptions.sessionFilterKey`**: Metadata key used to isolate memory between different sessions (default: "session_id").
-- **`queryOptions.filters`**: Additional metadata filters for retrieval. The session filter is automatically added to ensure memory isolation.
-
-**Session Isolation:**
-
-The vectorBlock automatically adds a session filter using the block's ID to ensure that memories from different sessions don't interfere with each other. This filter uses the `sessionFilterKey` (default: "session_id") and can be customized if needed.
-
 ## Persistence with Snapshots
 
 Save and restore memory state:

apps/next/src/content/docs/llamaindex/modules/models/llms/bedrock.mdx

@@ -5,13 +5,13 @@ title: Bedrock
 ## Installation
 
 ```package-install
-npm i llamaindex @llamaindex/aws
+npm i llamaindex @llamaindex/community
 ```
 
 ## Usage
 
 ```ts
-import { BEDROCK_MODELS, Bedrock } from "@llamaindex/aws";
+import { BEDROCK_MODELS, Bedrock } from "@llamaindex/community";
 
 Settings.llm = new Bedrock({
   model: BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
@@ -23,19 +23,9 @@ Settings.llm = new Bedrock({
 });
 ```
 
-Supported models are listed below (accessible by BEDROCK_MODELS).
+Currently only supports Anthropic and Meta models:
 
 ```ts
-AMAZON_TITAN_TG1_LARGE = "amazon.titan-tg1-large";
-AMAZON_TITAN_TEXT_EXPRESS_V1 = "amazon.titan-text-express-v1";
-AI21_J2_GRANDE_INSTRUCT = "ai21.j2-grande-instruct";
-AI21_J2_JUMBO_INSTRUCT = "ai21.j2-jumbo-instruct";
-AI21_J2_MID = "ai21.j2-mid";
-AI21_J2_MID_V1 = "ai21.j2-mid-v1";
-AI21_J2_ULTRA = "ai21.j2-ultra";
-AI21_J2_ULTRA_V1 = "ai21.j2-ultra-v1";
-COHERE_COMMAND_TEXT_V14 = "cohere.command-text-v14";
-
 ANTHROPIC_CLAUDE_INSTANT_1 = "anthropic.claude-instant-v1";
 ANTHROPIC_CLAUDE_2 = "anthropic.claude-v2";
 ANTHROPIC_CLAUDE_2_1 = "anthropic.claude-v2:1";
@@ -43,12 +33,7 @@ ANTHROPIC_CLAUDE_3_SONNET = "anthropic.claude-3-sonnet-20240229-v1:0";
 ANTHROPIC_CLAUDE_3_HAIKU = "anthropic.claude-3-haiku-20240307-v1:0";
 ANTHROPIC_CLAUDE_3_OPUS = "anthropic.claude-3-opus-20240229-v1:0"; // available on us-west-2
 ANTHROPIC_CLAUDE_3_5_SONNET = "anthropic.claude-3-5-sonnet-20240620-v1:0";
-ANTHROPIC_CLAUDE_3_5_SONNET_V2 = "anthropic.claude-3-5-sonnet-20241022-v2:0";
 ANTHROPIC_CLAUDE_3_5_HAIKU = "anthropic.claude-3-5-haiku-20241022-v1:0";
-ANTHROPIC_CLAUDE_3_7_SONNET = "anthropic.claude-3-7-sonnet-20250219-v1:0";
-ANTHROPIC_CLAUDE_4_SONNET = "anthropic.claude-sonnet-4-20250514-v1:0";
-ANTHROPIC_CLAUDE_4_OPUS = "anthropic.claude-opus-4-20250514-v1:0";
-
 META_LLAMA2_13B_CHAT = "meta.llama2-13b-chat-v1";
 META_LLAMA2_70B_CHAT = "meta.llama2-70b-chat-v1";
 META_LLAMA3_8B_INSTRUCT = "meta.llama3-8b-instruct-v1:0";
@@ -60,66 +45,41 @@ META_LLAMA3_2_1B_INSTRUCT = "meta.llama3-2-1b-instruct-v1:0"; // only available
 META_LLAMA3_2_3B_INSTRUCT = "meta.llama3-2-3b-instruct-v1:0"; // only available via inference endpoints (see below)
 META_LLAMA3_2_11B_INSTRUCT = "meta.llama3-2-11b-instruct-v1:0"; // only available via inference endpoints (see below), multimodal and function call supported
 META_LLAMA3_2_90B_INSTRUCT = "meta.llama3-2-90b-instruct-v1:0"; // only available via inference endpoints (see below), multimodal and function call supported
-META_LLAMA3_3_70B_INSTRUCT = "meta.llama3-3-70b-instruct-v1:0";
-
-MISTRAL_7B_INSTRUCT = "mistral.mistral-7b-instruct-v0:2";
-MISTRAL_MIXTRAL_7B_INSTRUCT = "mistral.mixtral-8x7b-instruct-v0:1";
-MISTRAL_MIXTRAL_LARGE_2402 = "mistral.mistral-large-2402-v1:0";
-
 AMAZON_NOVA_PREMIER_1 = "amazon.nova-premier-v1:0";
 AMAZON_NOVA_PRO_1 = "amazon.nova-pro-v1:0";
 AMAZON_NOVA_LITE_1 = "amazon.nova-lite-v1:0";
 AMAZON_NOVA_MICRO_1 = "amazon.nova-micro-v1:0";
 ```
 
-You can also use Bedrock's Inference endpoints by using the model names (accessible by INFERENCE_BEDROCK_MODELS).
+You can also use Bedrock's Inference endpoints by using the model names:
-Note that the region must be set correctly.
 
 ```ts
-//US
+// US
 US_ANTHROPIC_CLAUDE_3_HAIKU = "us.anthropic.claude-3-haiku-20240307-v1:0";
-US_ANTHROPIC_CLAUDE_3_5_HAIKU = "us.anthropic.claude-3-5-haiku-20241022-v1:0";
 US_ANTHROPIC_CLAUDE_3_OPUS = "us.anthropic.claude-3-opus-20240229-v1:0";
 US_ANTHROPIC_CLAUDE_3_SONNET = "us.anthropic.claude-3-sonnet-20240229-v1:0";
 US_ANTHROPIC_CLAUDE_3_5_SONNET = "us.anthropic.claude-3-5-sonnet-20240620-v1:0";
-US_ANTHROPIC_CLAUDE_3_5_SONNET_V2 = "us.anthropic.claude-3-5-sonnet-20241022-v2:0";
+US_ANTHROPIC_CLAUDE_3_5_SONNET_V2 =
-US_ANTHROPIC_CLAUDE_3_7_SONNET = "us.anthropic.claude-3-7-sonnet-20250219-v1:0";
+  "us.anthropic.claude-3-5-sonnet-20241022-v2:0";
-US_ANTHROPIC_CLAUDE_4_SONNET = "us.anthropic.claude-sonnet-4-20250514-v1:0";
-US_ANTHROPIC_CLAUDE_4_OPUS = "us.anthropic.claude-opus-4-20250514-v1:0";
 US_META_LLAMA_3_2_1B_INSTRUCT = "us.meta.llama3-2-1b-instruct-v1:0";
 US_META_LLAMA_3_2_3B_INSTRUCT = "us.meta.llama3-2-3b-instruct-v1:0";
 US_META_LLAMA_3_2_11B_INSTRUCT = "us.meta.llama3-2-11b-instruct-v1:0";
 US_META_LLAMA_3_2_90B_INSTRUCT = "us.meta.llama3-2-90b-instruct-v1:0";
-US_META_LLAMA_3_3_70B_INSTRUCT = "us.meta.llama3-3-70b-instruct-v1:0";
+US_AMAZON_NOVA_PRO_1 = "us.amazon.nova-premier-v1:0";
-US_AMAZON_NOVA_PREMIER_1 = "us.amazon.nova-premier-v1:0";
 US_AMAZON_NOVA_PRO_1 = "us.amazon.nova-pro-v1:0";
 US_AMAZON_NOVA_LITE_1 = "us.amazon.nova-lite-v1:0";
 US_AMAZON_NOVA_MICRO_1 = "us.amazon.nova-micro-v1:0";
 
-//EU
+// EU
 EU_ANTHROPIC_CLAUDE_3_HAIKU = "eu.anthropic.claude-3-haiku-20240307-v1:0";
-EU_ANTHROPIC_CLAUDE_3_5_HAIKU = "eu.anthropic.claude-3-5-haiku-20240307-v1:0";
 EU_ANTHROPIC_CLAUDE_3_SONNET = "eu.anthropic.claude-3-sonnet-20240229-v1:0";
 EU_ANTHROPIC_CLAUDE_3_5_SONNET = "eu.anthropic.claude-3-5-sonnet-20240620-v1:0";
-EU_ANTHROPIC_CLAUDE_3_7_SONNET = "eu.anthropic.claude-3-7-sonnet-20250219-v1:0";
-EU_ANTHROPIC_CLAUDE_4_SONNET = "eu.anthropic.claude-sonnet-4-20250514-v1:0";
-EU_ANTHROPIC_CLAUDE_4_OPUS = "eu.anthropic.claude-opus-4-20250514-v1:0";
 EU_META_LLAMA_3_2_1B_INSTRUCT = "eu.meta.llama3-2-1b-instruct-v1:0";
 EU_META_LLAMA_3_2_3B_INSTRUCT = "eu.meta.llama3-2-3b-instruct-v1:0";
-EU_AMAZON_NOVA_PREMIER_1 = "eu.amazon.nova-premier-v1:0";
+EU_AMAZON_NOVA_PRO_1 = "eu.amazon.nova-premier-v1:0";
 EU_AMAZON_NOVA_PRO_1 = "eu.amazon.nova-pro-v1:0";
 EU_AMAZON_NOVA_LITE_1 = "eu.amazon.nova-lite-v1:0";
 EU_AMAZON_NOVA_MICRO_1 = "eu.amazon.nova-micro-v1:0";
-
-//APAC
-APAC_ANTHROPIC_CLAUDE_3_5_SONNET = "apac.anthropic.claude-3-5-sonnet-20240620-v1:0";
-APAC_ANTHROPIC_CLAUDE_3_5_SONNET_V2 = "apac.anthropic.claude-3-5-sonnet-20241022-v2:0";
-APAC_ANTHROPIC_CLAUDE_3_7_SONNET = "apac.anthropic.claude-3-7-sonnet-20250219-v1:0";
-APAC_ANTHROPIC_CLAUDE_3_HAIKU = "apac.anthropic.claude-3-haiku-20240307-v1:0";
-APAC_ANTHROPIC_CLAUDE_3_SONNET = "apac.anthropic.claude-3-sonnet-20240229-v1:0";
-APAC_AMAZON_NOVA_PRO_1 = "apac.amazon.nova-pro-v1:0";
-APAC_AMAZON_NOVA_LITE_1 = "apac.amazon.nova-lite-v1:0";
-APAC_AMAZON_NOVA_MICRO_1 = "apac.amazon.nova-micro-v1:0";
 ```
 
 Sonnet, Haiku and Opus are multimodal, image_url only supports base64 data url format, e.g. `data:image/jpeg;base64,SGVsbG8sIFdvcmxkIQ==`
@@ -127,11 +87,10 @@ Sonnet, Haiku and Opus are multimodal, image_url only supports base64 data url f
 ## Full Example
 
 ```ts
-import { INFERENCE_BEDROCK_MODELS, Bedrock } from "@llamaindex/aws";
+import { BEDROCK_MODELS, Bedrock } from "llamaindex";
 
 Settings.llm = new Bedrock({
-  model: INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_SONNET,
+  model: BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
-  region: "us-east-1",
 });
 
 async function main() {
@@ -160,7 +119,7 @@ async function main() {
 ## Agent Example
 
 ```ts
-import { BEDROCK_MODELS, Bedrock } from "@llamaindex/aws";
+import { BEDROCK_MODELS, Bedrock } from "@llamaindex/community";
 import { tool } from "llamaindex";
 import { agent } from "@llamaindex/workflow";
 import { z } from "zod";

apps/next/src/content/docs/llamaindex/tutorials/basic_agent.mdx

@@ -38,13 +38,10 @@ You should expect output something like:
 {
   result: '5 + 5 is 10. Then, 10 divided by 2 is 5.',
   state: {
-    memory: Memory {
+    memory: ChatMemoryBuffer {
-      messages: [Array],
+      chatStore: SimpleChatStore {},
-      tokenLimit: 30000,
+      chatStoreKey: 'chat_history',
-      shortTermTokenLimitRatio: 0.7,
+      tokenLimit: 750000
-      memoryBlocks: [],
-      memoryCursor: 0,
-      adapters: [Object]
     },
     scratchpad: [],
     currentAgentName: 'Agent',

e2e/examples/cloudflare-worker-agent/CHANGELOG.md

@@ -1,71 +1,5 @@
 # @llamaindex/cloudflare-worker-agent-test
 
-## 0.0.185
-
-### Patch Changes
-
-- llamaindex@0.11.24
-
-## 0.0.184
-
-### Patch Changes
-
-- llamaindex@0.11.23
-
-## 0.0.183
-
-### Patch Changes
-
-- llamaindex@0.11.22
-
-## 0.0.182
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
-## 0.0.181
-
-### Patch Changes
-
-- llamaindex@0.11.20
-
-## 0.0.180
-
-### Patch Changes
-
-- llamaindex@0.11.19
-
-## 0.0.179
-
-### Patch Changes
-
-- llamaindex@0.11.18
-
-## 0.0.178
-
-### Patch Changes
-
-- llamaindex@0.11.17
-
-## 0.0.177
-
-### Patch Changes
-
-- llamaindex@0.11.16
-
-## 0.0.176
-
-### Patch Changes
-
-- llamaindex@0.11.15
-
-## 0.0.175
-
-### Patch Changes
-
-- llamaindex@0.11.14
-
 ## 0.0.174
 
 ### Patch Changes

e2e/examples/cloudflare-worker-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.185",
+  "version": "0.0.174",
   "type": "module",
   "private": true,
   "scripts": {

e2e/examples/llama-parse-browser/CHANGELOG.md

@@ -1,74 +1,5 @@
 # @llamaindex/llama-parse-browser-test
 
-## 0.0.83
-
-### Patch Changes
-
-- Updated dependencies [c3bf3c7]
-  - @llamaindex/cloud@4.0.28
-
-## 0.0.82
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.27
-
-## 0.0.81
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.26
-
-## 0.0.80
-
-### Patch Changes
-
-- Updated dependencies [2967d57]
-  - @llamaindex/cloud@4.0.25
-
-## 0.0.79
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.24
-
-## 0.0.78
-
-### Patch Changes
-
-- Updated dependencies [a1b1598]
-  - @llamaindex/cloud@4.0.23
-
-## 0.0.77
-
-### Patch Changes
-
-- Updated dependencies [d2be868]
-  - @llamaindex/cloud@4.0.22
-
-## 0.0.76
-
-### Patch Changes
-
-- Updated dependencies [579ca0c]
-  - @llamaindex/cloud@4.0.21
-
-## 0.0.75
-
-### Patch Changes
-
-- Updated dependencies [48b0d88]
-- Updated dependencies [f185772]
-  - @llamaindex/cloud@4.0.20
-
-## 0.0.74
-
-### Patch Changes
-
-- Updated dependencies [5a0ed1f]
-- Updated dependencies [5a0ed1f]
-  - @llamaindex/cloud@4.0.19
-
 ## 0.0.73
 
 ### Patch Changes

e2e/examples/llama-parse-browser/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llama-parse-browser-test",
   "private": true,
-  "version": "0.0.83",
+  "version": "0.0.73",
   "type": "module",
   "scripts": {
     "dev": "vite",

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,71 +1,5 @@
 # @llamaindex/next-agent-test
 
-## 0.1.185
-
-### Patch Changes
-
-- llamaindex@0.11.24
-
-## 0.1.184
-
-### Patch Changes
-
-- llamaindex@0.11.23
-
-## 0.1.183
-
-### Patch Changes
-
-- llamaindex@0.11.22
-
-## 0.1.182
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
-## 0.1.181
-
-### Patch Changes
-
-- llamaindex@0.11.20
-
-## 0.1.180
-
-### Patch Changes
-
-- llamaindex@0.11.19
-
-## 0.1.179
-
-### Patch Changes
-
-- llamaindex@0.11.18
-
-## 0.1.178
-
-### Patch Changes
-
-- llamaindex@0.11.17
-
-## 0.1.177
-
-### Patch Changes
-
-- llamaindex@0.11.16
-
-## 0.1.176
-
-### Patch Changes
-
-- llamaindex@0.11.15
-
-## 0.1.175
-
-### Patch Changes
-
-- llamaindex@0.11.14
-
 ## 0.1.174
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.185",
+  "version": "0.1.174",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -15,11 +15,11 @@
     "react-dom": "19.0.0"
   },
   "devDependencies": {
-    "@types/node": "^24.0.13",
+    "@types/node": "^22.9.0",
-    "@types/react": "^19.1.8",
+    "@types/react": "^19.0.10",
-    "@types/react-dom": "^19.1.6",
+    "@types/react-dom": "^19.0.4",
-    "eslint": "9.30.1",
+    "eslint": "9.16.0",
-    "eslint-config-next": "15.3.5",
+    "eslint-config-next": "15.1.0",
     "typescript": "^5.8.3"
   }
 }

e2e/examples/nextjs-edge-runtime/CHANGELOG.md

@@ -1,71 +1,5 @@
 # test-edge-runtime
 
-## 0.1.184
-
-### Patch Changes
-
-- llamaindex@0.11.24
-
-## 0.1.183
-
-### Patch Changes
-
-- llamaindex@0.11.23
-
-## 0.1.182
-
-### Patch Changes
-
-- llamaindex@0.11.22
-
-## 0.1.181
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
-## 0.1.180
-
-### Patch Changes
-
-- llamaindex@0.11.20
-
-## 0.1.179
-
-### Patch Changes
-
-- llamaindex@0.11.19
-
-## 0.1.178
-
-### Patch Changes
-
-- llamaindex@0.11.18
-
-## 0.1.177
-
-### Patch Changes
-
-- llamaindex@0.11.17
-
-## 0.1.176
-
-### Patch Changes
-
-- llamaindex@0.11.16
-
-## 0.1.175
-
-### Patch Changes
-
-- llamaindex@0.11.15
-
-## 0.1.174
-
-### Patch Changes
-
-- llamaindex@0.11.14
-
 ## 0.1.173
 
 ### Patch Changes

e2e/examples/nextjs-edge-runtime/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.184",
+  "version": "0.1.173",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -14,9 +14,9 @@
     "react-dom": "^19.1.0"
   },
   "devDependencies": {
-    "@types/node": "^24.0.13",
+    "@types/node": "^22.9.0",
-    "@types/react": "^19.1.8",
+    "@types/react": "^19.0.10",
-    "@types/react-dom": "^19.1.6",
+    "@types/react-dom": "^19.0.4",
     "typescript": "^5.8.3"
   }
 }

e2e/examples/nextjs-node-runtime/CHANGELOG.md

@@ -1,89 +1,5 @@
 # @llamaindex/next-node-runtime
 
-## 0.1.54
-
-### Patch Changes
-
-- llamaindex@0.11.24
-- @llamaindex/huggingface@0.1.24
-- @llamaindex/readers@3.1.18
-
-## 0.1.53
-
-### Patch Changes
-
-- llamaindex@0.11.23
-- @llamaindex/huggingface@0.1.23
-- @llamaindex/readers@3.1.17
-
-## 0.1.52
-
-### Patch Changes
-
-- llamaindex@0.11.22
-
-## 0.1.51
-
-### Patch Changes
-
-- llamaindex@0.11.21
-- @llamaindex/huggingface@0.1.22
-- @llamaindex/readers@3.1.16
-
-## 0.1.50
-
-### Patch Changes
-
-- llamaindex@0.11.20
-- @llamaindex/huggingface@0.1.21
-- @llamaindex/readers@3.1.15
-
-## 0.1.49
-
-### Patch Changes
-
-- @llamaindex/huggingface@0.1.20
-
-## 0.1.48
-
-### Patch Changes
-
-- llamaindex@0.11.19
-- @llamaindex/huggingface@0.1.19
-- @llamaindex/readers@3.1.14
-
-## 0.1.47
-
-### Patch Changes
-
-- llamaindex@0.11.18
-
-## 0.1.46
-
-### Patch Changes
-
-- llamaindex@0.11.17
-
-## 0.1.45
-
-### Patch Changes
-
-- llamaindex@0.11.16
-
-## 0.1.44
-
-### Patch Changes
-
-- llamaindex@0.11.15
-
-## 0.1.43
-
-### Patch Changes
-
-- llamaindex@0.11.14
-- @llamaindex/huggingface@0.1.18
-- @llamaindex/readers@3.1.13
-
 ## 0.1.42
 
 ### Patch Changes

e2e/examples/nextjs-node-runtime/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.54",
+  "version": "0.1.42",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -16,11 +16,11 @@
     "react-dom": "19.0.0"
   },
   "devDependencies": {
-    "@types/node": "^24.0.13",
+    "@types/node": "^22.9.0",
-    "@types/react": "^19.1.8",
+    "@types/react": "^19.0.10",
-    "@types/react-dom": "^19.1.6",
+    "@types/react-dom": "^19.0.4",
-    "eslint": "9.30.1",
+    "eslint": "9.16.0",
-    "eslint-config-next": "15.3.5",
+    "eslint-config-next": "15.1.0",
     "typescript": "^5.8.3"
   }
 }

e2e/examples/vite-import-llamaindex/CHANGELOG.md

@@ -1,71 +1,5 @@
 # vite-import-llamaindex
 
-## 0.0.51
-
-### Patch Changes
-
-- llamaindex@0.11.24
-
-## 0.0.50
-
-### Patch Changes
-
-- llamaindex@0.11.23
-
-## 0.0.49
-
-### Patch Changes
-
-- llamaindex@0.11.22
-
-## 0.0.48
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
-## 0.0.47
-
-### Patch Changes
-
-- llamaindex@0.11.20
-
-## 0.0.46
-
-### Patch Changes
-
-- llamaindex@0.11.19
-
-## 0.0.45
-
-### Patch Changes
-
-- llamaindex@0.11.18
-
-## 0.0.44
-
-### Patch Changes
-
-- llamaindex@0.11.17
-
-## 0.0.43
-
-### Patch Changes
-
-- llamaindex@0.11.16
-
-## 0.0.42
-
-### Patch Changes
-
-- llamaindex@0.11.15
-
-## 0.0.41
-
-### Patch Changes
-
-- llamaindex@0.11.14
-
 ## 0.0.40
 
 ### Patch Changes

e2e/examples/vite-import-llamaindex/package.json

@@ -1,7 +1,7 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.51",
+  "version": "0.0.40",
   "type": "module",
   "scripts": {
     "build": "vite build",

e2e/examples/waku-query-engine/CHANGELOG.md

@@ -1,71 +1,5 @@
 # @llamaindex/waku-query-engine-test
 
-## 0.0.185
-
-### Patch Changes
-
-- llamaindex@0.11.24
-
-## 0.0.184
-
-### Patch Changes
-
-- llamaindex@0.11.23
-
-## 0.0.183
-
-### Patch Changes
-
-- llamaindex@0.11.22
-
-## 0.0.182
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
-## 0.0.181
-
-### Patch Changes
-
-- llamaindex@0.11.20
-
-## 0.0.180
-
-### Patch Changes
-
-- llamaindex@0.11.19
-
-## 0.0.179
-
-### Patch Changes
-
-- llamaindex@0.11.18
-
-## 0.0.178
-
-### Patch Changes
-
-- llamaindex@0.11.17
-
-## 0.0.177
-
-### Patch Changes
-
-- llamaindex@0.11.16
-
-## 0.0.176
-
-### Patch Changes
-
-- llamaindex@0.11.15
-
-## 0.0.175
-
-### Patch Changes
-
-- llamaindex@0.11.14
-
 ## 0.0.174
 
 ### Patch Changes

e2e/examples/waku-query-engine/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.185",
+  "version": "0.0.174",
   "type": "module",
   "private": true,
   "scripts": {
@@ -18,10 +18,10 @@
   },
   "devDependencies": {
     "@tailwindcss/postcss": "^4.1.4",
-    "@types/react": "19.1.8",
+    "@types/react": "19.0.10",
-    "@types/react-dom": "19.1.6",
+    "@types/react-dom": "19.0.4",
     "rollup": "4.38.0",
-    "tailwindcss": "^4.1.11",
+    "tailwindcss": "^4.1.4",
     "typescript": "5.8.3"
   }
 }

e2e/node/vector-store/pinecone.e2e.ts

@@ -23,7 +23,7 @@ await test("pinecone", async (t) => {
   });
 
   const vectorStore = new PineconeVectorStore({
-    embedModel: openaiEmbedding,
+    embeddingModel: openaiEmbedding,
   });
 
   t.after(async () => {

e2e/package.json

@@ -19,14 +19,14 @@
     "@llamaindex/openai": "workspace:*",
     "@llamaindex/pinecone": "workspace:*",
     "@llamaindex/postgres": "workspace:*",
-    "@types/node": "^24.0.13",
+    "@types/node": "^22.9.0",
     "@types/pg": "^8.11.8",
     "consola": "^3.2.3",
-    "dotenv": "^17.2.0",
+    "dotenv": "^16.4.5",
     "llamaindex": "workspace:*",
     "pg": "^8.12.0",
     "pgvector": "0.2.0",
-    "tsx": "^4.20.3",
+    "tsx": "^4.19.3",
     "zod": "^3.25.76"
   }
 }

examples/CHANGELOG.md

@@ -1,356 +1,5 @@
 # examples
 
-## 0.3.35
-
-### Patch Changes
-
-- Updated dependencies [c3bf3c7]
-- Updated dependencies [f9f1de9]
-  - @llamaindex/cloud@4.0.28
-  - @llamaindex/core@0.6.19
-  - llamaindex@0.11.24
-  - @llamaindex/node-parser@2.0.19
-  - @llamaindex/anthropic@0.3.21
-  - @llamaindex/assemblyai@0.1.18
-  - @llamaindex/clip@0.0.70
-  - @llamaindex/cohere@0.0.33
-  - @llamaindex/deepinfra@0.0.70
-  - @llamaindex/discord@0.1.18
-  - @llamaindex/google@0.3.18
-  - @llamaindex/huggingface@0.1.24
-  - @llamaindex/jinaai@0.0.30
-  - @llamaindex/mistral@0.1.19
-  - @llamaindex/mixedbread@0.0.33
-  - @llamaindex/notion@0.1.18
-  - @llamaindex/ollama@0.1.19
-  - @llamaindex/openai@0.4.14
-  - @llamaindex/perplexity@0.0.27
-  - @llamaindex/portkey-ai@0.0.61
-  - @llamaindex/replicate@0.0.61
-  - @llamaindex/bm25-retriever@0.0.8
-  - @llamaindex/astra@0.0.33
-  - @llamaindex/azure@0.1.31
-  - @llamaindex/chroma@0.0.33
-  - @llamaindex/elastic-search@0.1.19
-  - @llamaindex/firestore@1.0.26
-  - @llamaindex/milvus@0.1.28
-  - @llamaindex/mongodb@0.0.34
-  - @llamaindex/pinecone@0.1.19
-  - @llamaindex/postgres@0.0.62
-  - @llamaindex/qdrant@0.1.29
-  - @llamaindex/supabase@0.1.20
-  - @llamaindex/upstash@0.0.33
-  - @llamaindex/weaviate@0.0.34
-  - @llamaindex/vercel@0.1.19
-  - @llamaindex/voyage-ai@1.0.25
-  - @llamaindex/readers@3.1.18
-  - @llamaindex/tools@0.1.9
-  - @llamaindex/workflow@1.1.20
-  - @llamaindex/deepseek@0.0.31
-  - @llamaindex/fireworks@0.0.30
-  - @llamaindex/groq@0.0.86
-  - @llamaindex/together@0.0.30
-  - @llamaindex/vllm@0.0.56
-  - @llamaindex/xai@0.0.17
-
-## 0.3.34
-
-### Patch Changes
-
-- Updated dependencies [f29799e]
-- Updated dependencies [7224c06]
-  - @llamaindex/workflow@1.1.19
-  - @llamaindex/core@0.6.18
-  - llamaindex@0.11.23
-  - @llamaindex/cloud@4.0.27
-  - @llamaindex/node-parser@2.0.18
-  - @llamaindex/anthropic@0.3.20
-  - @llamaindex/assemblyai@0.1.17
-  - @llamaindex/clip@0.0.69
-  - @llamaindex/cohere@0.0.32
-  - @llamaindex/deepinfra@0.0.69
-  - @llamaindex/discord@0.1.17
-  - @llamaindex/google@0.3.17
-  - @llamaindex/huggingface@0.1.23
-  - @llamaindex/jinaai@0.0.29
-  - @llamaindex/mistral@0.1.18
-  - @llamaindex/mixedbread@0.0.32
-  - @llamaindex/notion@0.1.17
-  - @llamaindex/ollama@0.1.18
-  - @llamaindex/openai@0.4.13
-  - @llamaindex/perplexity@0.0.26
-  - @llamaindex/portkey-ai@0.0.60
-  - @llamaindex/replicate@0.0.60
-  - @llamaindex/bm25-retriever@0.0.7
-  - @llamaindex/astra@0.0.32
-  - @llamaindex/azure@0.1.30
-  - @llamaindex/chroma@0.0.32
-  - @llamaindex/elastic-search@0.1.18
-  - @llamaindex/firestore@1.0.25
-  - @llamaindex/milvus@0.1.27
-  - @llamaindex/mongodb@0.0.33
-  - @llamaindex/pinecone@0.1.18
-  - @llamaindex/postgres@0.0.61
-  - @llamaindex/qdrant@0.1.28
-  - @llamaindex/supabase@0.1.19
-  - @llamaindex/upstash@0.0.32
-  - @llamaindex/weaviate@0.0.33
-  - @llamaindex/vercel@0.1.18
-  - @llamaindex/voyage-ai@1.0.24
-  - @llamaindex/readers@3.1.17
-  - @llamaindex/tools@0.1.8
-  - @llamaindex/deepseek@0.0.30
-  - @llamaindex/fireworks@0.0.29
-  - @llamaindex/groq@0.0.85
-  - @llamaindex/together@0.0.29
-  - @llamaindex/vllm@0.0.55
-  - @llamaindex/xai@0.0.16
-
-## 0.3.33
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-  - @llamaindex/cloud@4.0.26
-  - llamaindex@0.11.21
-  - @llamaindex/node-parser@2.0.17
-  - @llamaindex/anthropic@0.3.19
-  - @llamaindex/assemblyai@0.1.16
-  - @llamaindex/clip@0.0.68
-  - @llamaindex/cohere@0.0.31
-  - @llamaindex/deepinfra@0.0.68
-  - @llamaindex/discord@0.1.16
-  - @llamaindex/google@0.3.16
-  - @llamaindex/huggingface@0.1.22
-  - @llamaindex/jinaai@0.0.28
-  - @llamaindex/mistral@0.1.17
-  - @llamaindex/mixedbread@0.0.31
-  - @llamaindex/notion@0.1.16
-  - @llamaindex/ollama@0.1.17
-  - @llamaindex/openai@0.4.12
-  - @llamaindex/perplexity@0.0.25
-  - @llamaindex/portkey-ai@0.0.59
-  - @llamaindex/replicate@0.0.59
-  - @llamaindex/bm25-retriever@0.0.6
-  - @llamaindex/astra@0.0.31
-  - @llamaindex/azure@0.1.29
-  - @llamaindex/chroma@0.0.31
-  - @llamaindex/elastic-search@0.1.17
-  - @llamaindex/firestore@1.0.24
-  - @llamaindex/milvus@0.1.26
-  - @llamaindex/mongodb@0.0.32
-  - @llamaindex/pinecone@0.1.17
-  - @llamaindex/postgres@0.0.60
-  - @llamaindex/qdrant@0.1.27
-  - @llamaindex/supabase@0.1.18
-  - @llamaindex/upstash@0.0.31
-  - @llamaindex/weaviate@0.0.32
-  - @llamaindex/vercel@0.1.17
-  - @llamaindex/voyage-ai@1.0.23
-  - @llamaindex/readers@3.1.16
-  - @llamaindex/tools@0.1.7
-  - @llamaindex/workflow@1.1.17
-  - @llamaindex/deepseek@0.0.29
-  - @llamaindex/fireworks@0.0.28
-  - @llamaindex/groq@0.0.84
-  - @llamaindex/together@0.0.28
-  - @llamaindex/vllm@0.0.54
-  - @llamaindex/xai@0.0.15
-
-## 0.3.32
-
-### Patch Changes
-
-- Updated dependencies [650eeb1]
-- Updated dependencies [a8ec08c]
-- Updated dependencies [2967d57]
-  - @llamaindex/google@0.3.15
-  - @llamaindex/core@0.6.16
-  - @llamaindex/workflow@1.1.16
-  - @llamaindex/cloud@4.0.25
-  - llamaindex@0.11.20
-  - @llamaindex/node-parser@2.0.16
-  - @llamaindex/anthropic@0.3.18
-  - @llamaindex/assemblyai@0.1.15
-  - @llamaindex/clip@0.0.67
-  - @llamaindex/cohere@0.0.30
-  - @llamaindex/deepinfra@0.0.67
-  - @llamaindex/discord@0.1.15
-  - @llamaindex/huggingface@0.1.21
-  - @llamaindex/jinaai@0.0.27
-  - @llamaindex/mistral@0.1.16
-  - @llamaindex/mixedbread@0.0.30
-  - @llamaindex/notion@0.1.15
-  - @llamaindex/ollama@0.1.16
-  - @llamaindex/openai@0.4.11
-  - @llamaindex/perplexity@0.0.24
-  - @llamaindex/portkey-ai@0.0.58
-  - @llamaindex/replicate@0.0.58
-  - @llamaindex/bm25-retriever@0.0.5
-  - @llamaindex/astra@0.0.30
-  - @llamaindex/azure@0.1.28
-  - @llamaindex/chroma@0.0.30
-  - @llamaindex/elastic-search@0.1.16
-  - @llamaindex/firestore@1.0.23
-  - @llamaindex/milvus@0.1.25
-  - @llamaindex/mongodb@0.0.31
-  - @llamaindex/pinecone@0.1.16
-  - @llamaindex/postgres@0.0.59
-  - @llamaindex/qdrant@0.1.26
-  - @llamaindex/supabase@0.1.17
-  - @llamaindex/upstash@0.0.30
-  - @llamaindex/weaviate@0.0.31
-  - @llamaindex/vercel@0.1.16
-  - @llamaindex/voyage-ai@1.0.22
-  - @llamaindex/readers@3.1.15
-  - @llamaindex/tools@0.1.6
-  - @llamaindex/deepseek@0.0.28
-  - @llamaindex/fireworks@0.0.27
-  - @llamaindex/groq@0.0.83
-  - @llamaindex/together@0.0.27
-  - @llamaindex/vllm@0.0.53
-  - @llamaindex/xai@0.0.14
-
-## 0.3.31
-
-### Patch Changes
-
-- Updated dependencies [d8f4f6a]
-- Updated dependencies [856dd8c]
-  - @llamaindex/supabase@0.1.16
-  - @llamaindex/openai@0.4.10
-  - @llamaindex/clip@0.0.66
-  - @llamaindex/deepinfra@0.0.66
-  - @llamaindex/deepseek@0.0.27
-  - @llamaindex/fireworks@0.0.26
-  - @llamaindex/groq@0.0.82
-  - @llamaindex/huggingface@0.1.20
-  - @llamaindex/jinaai@0.0.26
-  - @llamaindex/perplexity@0.0.23
-  - @llamaindex/azure@0.1.27
-  - @llamaindex/together@0.0.26
-  - @llamaindex/vllm@0.0.52
-  - @llamaindex/xai@0.0.13
-
-## 0.3.30
-
-### Patch Changes
-
-- Updated dependencies [7ad3411]
-- Updated dependencies [5da5b3c]
-- Updated dependencies [a1fdb07]
-- Updated dependencies [ddc0eaf]
-  - @llamaindex/core@0.6.15
-  - @llamaindex/tools@0.1.5
-  - @llamaindex/workflow@1.1.15
-  - @llamaindex/openai@0.4.9
-  - @llamaindex/anthropic@0.3.17
-  - @llamaindex/cloud@4.0.24
-  - llamaindex@0.11.19
-  - @llamaindex/node-parser@2.0.15
-  - @llamaindex/assemblyai@0.1.14
-  - @llamaindex/clip@0.0.65
-  - @llamaindex/cohere@0.0.29
-  - @llamaindex/deepinfra@0.0.65
-  - @llamaindex/discord@0.1.14
-  - @llamaindex/google@0.3.14
-  - @llamaindex/huggingface@0.1.19
-  - @llamaindex/jinaai@0.0.25
-  - @llamaindex/mistral@0.1.15
-  - @llamaindex/mixedbread@0.0.29
-  - @llamaindex/notion@0.1.14
-  - @llamaindex/ollama@0.1.15
-  - @llamaindex/perplexity@0.0.22
-  - @llamaindex/portkey-ai@0.0.57
-  - @llamaindex/replicate@0.0.57
-  - @llamaindex/bm25-retriever@0.0.4
-  - @llamaindex/astra@0.0.29
-  - @llamaindex/azure@0.1.26
-  - @llamaindex/chroma@0.0.29
-  - @llamaindex/elastic-search@0.1.15
-  - @llamaindex/firestore@1.0.22
-  - @llamaindex/milvus@0.1.24
-  - @llamaindex/mongodb@0.0.30
-  - @llamaindex/pinecone@0.1.15
-  - @llamaindex/postgres@0.0.58
-  - @llamaindex/qdrant@0.1.25
-  - @llamaindex/supabase@0.1.15
-  - @llamaindex/upstash@0.0.29
-  - @llamaindex/weaviate@0.0.30
-  - @llamaindex/vercel@0.1.15
-  - @llamaindex/voyage-ai@1.0.21
-  - @llamaindex/readers@3.1.14
-  - @llamaindex/deepseek@0.0.26
-  - @llamaindex/fireworks@0.0.25
-  - @llamaindex/groq@0.0.81
-  - @llamaindex/together@0.0.25
-  - @llamaindex/vllm@0.0.51
-  - @llamaindex/xai@0.0.12
-
-## 0.3.29
-
-### Patch Changes
-
-- Updated dependencies [af3f866]
-  - @llamaindex/deepseek@0.0.25
-
-## 0.3.28
-
-### Patch Changes
-
-- 36773a8: Fixed start script, reverted some changes to imports
-- 891562d: Fix xai dependency in the examples
-- Updated dependencies [5a0ed1f]
-- Updated dependencies [5a0ed1f]
-- Updated dependencies [8eeac33]
-  - @llamaindex/cloud@4.0.19
-  - @llamaindex/core@0.6.14
-  - llamaindex@0.11.14
-  - @llamaindex/node-parser@2.0.14
-  - @llamaindex/anthropic@0.3.16
-  - @llamaindex/assemblyai@0.1.13
-  - @llamaindex/clip@0.0.64
-  - @llamaindex/cohere@0.0.28
-  - @llamaindex/deepinfra@0.0.64
-  - @llamaindex/discord@0.1.13
-  - @llamaindex/google@0.3.13
-  - @llamaindex/huggingface@0.1.18
-  - @llamaindex/jinaai@0.0.24
-  - @llamaindex/mistral@0.1.14
-  - @llamaindex/mixedbread@0.0.28
-  - @llamaindex/notion@0.1.13
-  - @llamaindex/ollama@0.1.14
-  - @llamaindex/openai@0.4.8
-  - @llamaindex/perplexity@0.0.21
-  - @llamaindex/portkey-ai@0.0.56
-  - @llamaindex/replicate@0.0.56
-  - @llamaindex/bm25-retriever@0.0.3
-  - @llamaindex/astra@0.0.28
-  - @llamaindex/azure@0.1.25
-  - @llamaindex/chroma@0.0.28
-  - @llamaindex/elastic-search@0.1.14
-  - @llamaindex/firestore@1.0.21
-  - @llamaindex/milvus@0.1.23
-  - @llamaindex/mongodb@0.0.29
-  - @llamaindex/pinecone@0.1.14
-  - @llamaindex/postgres@0.0.57
-  - @llamaindex/qdrant@0.1.24
-  - @llamaindex/supabase@0.1.14
-  - @llamaindex/upstash@0.0.28
-  - @llamaindex/weaviate@0.0.29
-  - @llamaindex/vercel@0.1.14
-  - @llamaindex/voyage-ai@1.0.20
-  - @llamaindex/readers@3.1.13
-  - @llamaindex/tools@0.1.4
-  - @llamaindex/workflow@1.1.14
-  - @llamaindex/deepseek@0.0.24
-  - @llamaindex/fireworks@0.0.24
-  - @llamaindex/groq@0.0.80
-  - @llamaindex/together@0.0.24
-  - @llamaindex/vllm@0.0.50
-  - @llamaindex/xai@0.0.11
-
 ## 0.3.27
 
 ### Patch Changes

examples/README.md

@@ -1,10 +1,9 @@
 # LlamaIndexTS Examples
 
-This package contains several examples of how to use LlamaIndexTS.
+Before running any of the code examples,
+make sure you have basic knowledge of the [LlamaIndexTS](https://ts.llamaindex.ai/).
 
-Most examples will use OpenAI by default, so be sure to set your API key.
+## Usage
-
-## Running Examples
 
 ```shell
 # export your API key
@@ -13,31 +12,8 @@ export OPENAI_API_KEY="sk-..."
 npx tsx ./rag/chatEngine.ts
 ```
 
-## Recommended Starter Examples
+## Build your own RAG app
 
-Agents:
+```shell
-
+npx create llama
-- [Basic OpenAI Agent with Tools](./agents/agent/openai.ts)
+```
-- [Agent with MCP Tools](./agents/agent/mcp-tools.ts)
-- [Customizing Memory](./agents/memory/agent-memory.ts)
-
-Workflows:
-
-- [Workflow basics](./agents/workflow/joke.ts)
-- [Find more workflow examples in the `workflows-ts` repo!](https://github.com/run-llama/workflows-ts)
-
-Indexing, Retrieval, and Querying:
-
-- [Basic Vector Indexing + Query Engine](./index/vectorIndex.ts)
-- [Agent + Query Engine Tool](./agents/agent/query-tool.ts)
-
-Multimodal:
-
-- [Multimodal RAG](./multimodal/rag.ts)
-- [Multimodal Chat](./multimodal/context.ts)
-
-Some more general folders that might be useful to explore:
-
-- [storage](./storage/): Examples with various vector stores
-- [readers](./readers/): Examples of how to use the various readers
-- [models](./models/): Examples of how to use the various LLMs and embedding models from many providers

examples/agents/agent/single-agent.ts

@@ -3,7 +3,7 @@
  */
 import { openai } from "@llamaindex/openai";
 import { agent } from "@llamaindex/workflow";
-import { getWeatherTool } from "../tools/tools";
+import { getWeatherTool } from "../../deprecated/agents/utils/tools";
 
 async function main() {
   const weatherAgent = agent({
@@ -24,7 +24,6 @@ async function main() {
     state: result.data.state,
   });
   console.log(`${JSON.stringify(caResult, null, 2)}`);
-  console.log("assistant message:", result.data.message);
 }
 
 main().catch((error) => {

examples/agents/agent/with-ollama.ts

@@ -1,6 +1,6 @@
 import { ollama } from "@llamaindex/ollama";
 import { agent } from "@llamaindex/workflow";
-import { getWeatherTool } from "../tools/tools";
+import { getWeatherTool } from "../../deprecated/agents/utils/tools";
 
 async function main() {
   const myAgent = agent({

examples/agents/memory/vector-block.ts

@@ -1,150 +0,0 @@
-/**
- * Example: Vector Memory Block
- *
- * This example demonstrates how to use the VectorMemoryBlock to store and retrieve
- * conversation history using vector similarity search. The vector memory block
- * stores messages in a vector store and can retrieve relevant context based on
- * semantic similarity to recent messages.
- */
-
-import { OpenAI, OpenAIEmbedding } from "@llamaindex/openai";
-import { QdrantVectorStore } from "@llamaindex/qdrant";
-import { createMemory, vectorBlock } from "llamaindex";
-
-// Set up the LLM and embedding model
-const llm = new OpenAI({ model: "gpt-4.1-mini" });
-const embedModel = new OpenAIEmbedding({ model: "text-embedding-3-small" });
-
-// Simulate a conversation with some context
-// This conversation has 8 messages, which is more than the token limit of 100 tokens (set below)
-// The last 4 messages are kept in to short term memory block (as their tokens are in the limit)
-// Whereas the first 5 messages are added to long term memory block (in here we will use the vector memory block with Qdrant)
-const CONVERSATION_TURNS = [
-  //// This is the first 5 messages that are added to long term memory block (vector memory block)
-  {
-    role: "user",
-    content: "Hi, I'm Sarah and I work as a data scientist at Google.",
-  },
-  {
-    role: "assistant",
-    content:
-      "Hello Sarah! It's great to meet you. Data science at Google must be exciting!",
-  },
-  {
-    role: "user",
-    content:
-      "Yes, I specialize in machine learning and natural language processing.",
-  },
-  {
-    role: "assistant",
-    content: "That's impressive! ML and NLP are fascinating fields.",
-  },
-  {
-    role: "user",
-    content:
-      "I have a PhD in Computer Science from Stanford, and I love hiking on weekends.",
-  },
-
-  //// This is the last 4 messages that are added to short term memory block
-  {
-    role: "assistant",
-    content:
-      "Wow, Stanford PhD! And hiking is a great way to unwind from tech work.",
-  },
-  {
-    role: "user",
-    content: "I also have two cats named Whiskers and Mittens.",
-  },
-  {
-    role: "assistant",
-    content:
-      "Cats make wonderful companions! Whiskers and Mittens are cute names.",
-  },
-  {
-    role: "user",
-    content: "Summary information about Sarah and her cats",
-  },
-];
-
-async function main() {
-  console.log("=== Vector Memory Block Example ===\n");
-
-  /**
-   * Create a vector store. You can quickly get a local instance of Qdrant running with Docker:
-   * ```bash
-   * docker pull qdrant/qdrant
-   * docker run -p 6333:6333 qdrant/qdrant
-   * ```
-   *
-   * Go to http://localhost:6333/dashboard#/collections to see your data
-   */
-  const vectorStore = new QdrantVectorStore({
-    url: "http://localhost:6333",
-    embedModel,
-  });
-
-  // Create a vector memory block using the factory function
-  const vectorMemoryBlock = vectorBlock({
-    vectorStore,
-    priority: 5,
-  });
-
-  // Create a memory store with the vector memory block
-  const memory = createMemory([], {
-    llm,
-    memoryBlocks: [vectorMemoryBlock],
-    tokenLimit: 100,
-    shortTermTokenLimitRatio: 0.7,
-  });
-
-  // Store the conversation history in the vector memory
-  console.log(`Adding ${CONVERSATION_TURNS.length} messages to the memory...`);
-  for (const message of CONVERSATION_TURNS) {
-    await memory.add(message);
-  }
-
-  // Retrieve relevant context for the current user request
-  console.log("Retrieving relevant context...");
-  const chatHistory = await memory.getLLM();
-
-  // You will see there's 1 generated context message from vector memory block, and 4 messages from short term memory block
-  console.log("Chat memory:", chatHistory);
-
-  // Now simulate the assistant responding with context
-  console.log("\nAssistant response with context:");
-  const response = await llm.chat({
-    messages: chatHistory,
-  });
-  console.log(response.message.content);
-
-  // Try adding more messages to the memory
-  const newMessages = [
-    {
-      role: "user",
-      content: "Write a long paragraph about weather in Tokyo",
-    },
-    {
-      role: "assistant",
-      content:
-        "The weather in Tokyo is sunny and warm. The temperature is around 20 degrees Celsius. The weather is very nice and the people are friendly.",
-    },
-    {
-      role: "user",
-      content: "What is the weather in Tokyo?",
-    },
-  ];
-  // Add the new messages to the memory
-  for (const message of newMessages) {
-    await memory.add(message);
-  }
-
-  // Try retrieving the new messages
-  const newChatHistory = await memory.getLLM();
-  // You can see now that new chat history will contain the nodes (separated by `\n`) in the
-  // context message that is generated by the vector memory block
-  // The number of retrieved nodes is set by `similarityTopK` in `queryOptions` of `vectorBlock`
-  // (default `similarityTopK` is 2)
-  console.log("New chat history:", newChatHistory);
-}
-
-main().catch(console.error);

examples/agents/tools/exec-stream.ts

@@ -1,46 +0,0 @@
-import { openai } from "@llamaindex/openai";
-import { tool } from "llamaindex";
-import z from "zod";
-
-import { ChatMessage } from "llamaindex";
-
-async function main() {
-  const llm = openai({ model: "gpt-4.1-mini" });
-  const messages = [
-    {
-      content: `What's the weather like in San Francisco?`,
-      role: "user",
-    } as ChatMessage,
-  ];
-
-  let exit = false;
-  do {
-    const { stream, newMessages, toolCalls } = await llm.exec({
-      messages,
-      tools: [
-        tool({
-          name: "get_weather",
-          description: "Get the current weather for a location",
-          parameters: z.object({
-            address: z.string().describe("The address"),
-          }),
-          execute: ({ address }) => {
-            return `It's sunny in ${address}!`;
-          },
-        }),
-      ],
-      stream: true,
-    });
-    for await (const chunk of stream) {
-      process.stdout.write(chunk.delta);
-    }
-    messages.push(...newMessages());
-    // exit condition to stop the agent loop
-    // here we can also check for specific tool calls or limit the number of llm.exec calls
-    exit = toolCalls.length === 0;
-  } while (!exit);
-}
-
-(async function () {
-  await main();
-})();

examples/agents/tools/exec.ts

@@ -1,43 +0,0 @@
-import { openai } from "@llamaindex/openai";
-import { ChatMessage, tool } from "llamaindex";
-import z from "zod";
-
-async function main() {
-  const llm = openai({ model: "gpt-4.1-mini" });
-  const messages = [
-    {
-      content: `What's the weather like in San Francisco?`,
-      role: "user",
-    } as ChatMessage,
-  ];
-
-  let exit = false;
-  do {
-    const { newMessages, toolCalls } = await llm.exec({
-      messages,
-      tools: [
-        tool({
-          name: "get_weather",
-          description: "Get the current weather for a location",
-          parameters: z.object({
-            address: z.string().describe("The address"),
-          }),
-          execute: ({ address }) => {
-            return `It's sunny in ${address}!`;
-          },
-        }),
-      ],
-    });
-    console.log(newMessages);
-    messages.push(...newMessages);
-    // exit condition to stop the agent loop
-    // here we can also check for specific tool calls or limit the number of llm.exec calls
-    exit = toolCalls.length === 0;
-  } while (!exit);
-}
-
-(async function () {
-  console.log("Starting...");
-  await main();
-  console.log("Done");
-})();

examples/agents/toolsStream.ts

@@ -1,7 +1,7 @@
-import { openai } from "@llamaindex/openai";
+import { OpenAI } from "@llamaindex/openai";
 
 async function main() {
-  const llm = openai({ model: "gpt-4.1-mini" });
+  const llm = new OpenAI({ model: "gpt-4-turbo" });
   const args: Parameters<typeof llm.chat>[0] = {
     additionalChatOptions: {
       tool_choice: "auto",

examples/deprecated/agents/openai-task.ts

@@ -4,7 +4,7 @@ import {
   getCurrentIDTool,
   getUserInfoTool,
   getWeatherTool,
-} from "../../agents/tools/tools";
+} from "./utils/tools";
 
 async function main() {
   // Create an OpenAIAgent with the function tools

examples/deprecated/agents/react-task.ts

@@ -3,7 +3,7 @@ import {
   getCurrentIDTool,
   getUserInfoTool,
   getWeatherTool,
-} from "../../agents/tools/tools";
+} from "./utils/tools";
 
 async function main() {
   // Create an OpenAIAgent with the function tools

examples/models/openai/live/browser/open-ai-realtime/package.json

@@ -15,15 +15,15 @@
   },
   "devDependencies": {
     "@eslint/js": "^9.25.0",
-    "@types/react": "^19.1.8",
+    "@types/react": "^19.1.2",
-    "@types/react-dom": "^19.1.6",
+    "@types/react-dom": "^19.1.2",
     "@vitejs/plugin-react": "^4.5.2",
-    "eslint": "^9.30.1",
+    "eslint": "^9.25.0",
     "eslint-plugin-react-hooks": "^5.2.0",
     "eslint-plugin-react-refresh": "^0.4.19",
     "globals": "^16.0.0",
     "typescript": "~5.8.3",
-    "typescript-eslint": "^8.36.0",
+    "typescript-eslint": "^8.30.1",
     "vite": "^6.3.5"
   }
 }

examples/models/openai/responses/image-gen.ts

@@ -30,12 +30,6 @@ async function main() {
   );
   // and print out the text part
   console.log(textPart?.text);
-
-  const imageId = response.message.options?.image_id;
-  if (imageId) {
-    console.log("Image ID for multi-turn generation:", imageId);
-    console.log("Use this image_id in subsequent requests to modify the image");
-  }
 }
 
 main().catch(console.error);

examples/models/openai/responses/multi-turn-image-gen.ts

@@ -1,89 +0,0 @@
-import { openaiResponses } from "@llamaindex/openai";
-import fs from "fs";
-import { MessageContentDetail } from "llamaindex";
-
-async function main() {
-  const llm = openaiResponses({
-    model: "gpt-4.1-mini",
-    builtInTools: [{ type: "image_generation" }],
-  });
-
-  // First turn: Generate initial image
-  console.log("=== First Turn: Generate initial image ===");
-  const firstResponse = await llm.chat({
-    messages: [
-      {
-        role: "user",
-        content:
-          "Generate an image of a cute tiny llama wearing a hat playing with a cat on a meadow",
-      },
-    ],
-  });
-
-  const firstContent = firstResponse.message.content as MessageContentDetail[];
-  const firstImagePart = firstContent.find((part) => part.type === "image");
-  const firstTextPart = firstContent.find((part) => part.type === "text");
-
-  // Save the first image
-  if (firstImagePart?.data) {
-    fs.writeFileSync(
-      "llama-initial.png",
-      Buffer.from(firstImagePart.data as string, "base64"),
-    );
-    console.log("First image saved as 'llama-initial.png'");
-  }
-
-  if (firstTextPart?.text) {
-    console.log("First response:", firstTextPart.text);
-  }
-
-  // Get the image_id from the response options for multi-turn
-  const imageId = firstResponse.message.options?.image_id;
-  console.log("Image ID for multi-turn:", imageId);
-
-  if (imageId) {
-    // Second turn: Modify the image using the image_id
-    console.log("\n=== Second Turn: Modify the image ===");
-    const secondResponse = await llm.chat({
-      messages: [
-        {
-          role: "user",
-          content:
-            "Generate an image of a cute tiny llama wearing a hat playing with a cat on a meadow",
-        },
-        {
-          role: "assistant",
-          content: firstContent,
-          options: { image_id: imageId },
-        },
-        {
-          role: "user",
-          content:
-            "Now add a rainbow in the background and make the llama's hat blue",
-        },
-      ],
-    });
-
-    const secondContent = secondResponse.message
-      .content as MessageContentDetail[];
-    const secondImagePart = secondContent.find((part) => part.type === "image");
-    const secondTextPart = secondContent.find((part) => part.type === "text");
-
-    // Save the modified image
-    if (secondImagePart?.data) {
-      fs.writeFileSync(
-        "llama-modified.png",
-        Buffer.from(secondImagePart.data as string, "base64"),
-      );
-      console.log("Modified image saved as 'llama-modified.png'");
-    }
-
-    if (secondTextPart?.text) {
-      console.log("Second response:", secondTextPart.text);
-    }
-  } else {
-    console.log("No image_id received, cannot perform multi-turn generation");
-  }
-}
-
-main().catch(console.error);

examples/package.json

@@ -1,79 +1,79 @@
 {
   "name": "@llamaindex/examples",
-  "version": "0.3.35",
+  "version": "0.3.27",
   "private": true,
   "scripts": {
     "lint": "eslint .",
-    "start": "echo 'To get started, run `npx tsx <path to example>`'"
+    "start": "tsx ./starter.ts"
   },
   "dependencies": {
     "@ai-sdk/openai": "^1.0.5",
     "@azure/cosmos": "^4.1.1",
     "@azure/identity": "^4.4.1",
     "@azure/search-documents": "^12.1.0",
-    "@llamaindex/anthropic": "^0.3.21",
+    "@llamaindex/anthropic": "^0.3.15",
-    "@llamaindex/assemblyai": "^0.1.18",
+    "@llamaindex/assemblyai": "^0.1.12",
-    "@llamaindex/astra": "^0.0.33",
+    "@llamaindex/astra": "^0.0.27",
-    "@llamaindex/azure": "^0.1.31",
+    "@llamaindex/azure": "^0.1.24",
-    "@llamaindex/bm25-retriever": "^0.0.8",
+    "@llamaindex/bm25-retriever": "^0.0.2",
-    "@llamaindex/chroma": "^0.0.33",
+    "@llamaindex/chroma": "^0.0.27",
-    "@llamaindex/clip": "^0.0.70",
+    "@llamaindex/clip": "^0.0.63",
-    "@llamaindex/cloud": "^4.0.28",
+    "@llamaindex/cloud": "^4.0.18",
-    "@llamaindex/cohere": "^0.0.33",
+    "@llamaindex/cohere": "^0.0.27",
-    "@llamaindex/core": "^0.6.19",
+    "@llamaindex/core": "^0.6.13",
-    "@llamaindex/deepinfra": "^0.0.70",
+    "@llamaindex/deepinfra": "^0.0.63",
-    "@llamaindex/deepseek": "^0.0.31",
+    "@llamaindex/deepseek": "^0.0.23",
-    "@llamaindex/discord": "^0.1.18",
+    "@llamaindex/discord": "^0.1.12",
-    "@llamaindex/elastic-search": "^0.1.19",
+    "@llamaindex/elastic-search": "^0.1.13",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/firestore": "^1.0.26",
+    "@llamaindex/firestore": "^1.0.20",
-    "@llamaindex/fireworks": "^0.0.30",
+    "@llamaindex/fireworks": "^0.0.23",
-    "@llamaindex/google": "^0.3.18",
+    "@llamaindex/google": "^0.3.12",
-    "@llamaindex/groq": "^0.0.86",
+    "@llamaindex/groq": "^0.0.79",
-    "@llamaindex/huggingface": "^0.1.24",
+    "@llamaindex/huggingface": "^0.1.17",
-    "@llamaindex/jinaai": "^0.0.30",
+    "@llamaindex/jinaai": "^0.0.23",
-    "@llamaindex/milvus": "^0.1.28",
+    "@llamaindex/milvus": "^0.1.22",
-    "@llamaindex/mistral": "^0.1.19",
+    "@llamaindex/mistral": "^0.1.13",
-    "@llamaindex/mixedbread": "^0.0.33",
+    "@llamaindex/mixedbread": "^0.0.27",
-    "@llamaindex/mongodb": "^0.0.34",
+    "@llamaindex/mongodb": "^0.0.28",
-    "@llamaindex/node-parser": "^2.0.19",
+    "@llamaindex/node-parser": "^2.0.13",
-    "@llamaindex/notion": "^0.1.18",
+    "@llamaindex/notion": "^0.1.12",
-    "@llamaindex/ollama": "^0.1.19",
+    "@llamaindex/ollama": "^0.1.13",
-    "@llamaindex/openai": "^0.4.14",
+    "@llamaindex/openai": "^0.4.7",
-    "@llamaindex/perplexity": "^0.0.27",
+    "@llamaindex/perplexity": "^0.0.20",
-    "@llamaindex/pinecone": "^0.1.19",
+    "@llamaindex/pinecone": "^0.1.13",
-    "@llamaindex/portkey-ai": "^0.0.61",
+    "@llamaindex/portkey-ai": "^0.0.55",
-    "@llamaindex/postgres": "^0.0.62",
+    "@llamaindex/postgres": "^0.0.56",
-    "@llamaindex/qdrant": "^0.1.29",
+    "@llamaindex/qdrant": "^0.1.23",
-    "@llamaindex/readers": "^3.1.18",
+    "@llamaindex/readers": "^3.1.12",
-    "@llamaindex/replicate": "^0.0.61",
+    "@llamaindex/replicate": "^0.0.55",
-    "@llamaindex/supabase": "^0.1.20",
+    "@llamaindex/supabase": "^0.1.13",
-    "@llamaindex/together": "^0.0.30",
+    "@llamaindex/together": "^0.0.23",
-    "@llamaindex/tools": "^0.1.9",
+    "@llamaindex/tools": "^0.1.3",
-    "@llamaindex/upstash": "^0.0.33",
+    "@llamaindex/upstash": "^0.0.27",
-    "@llamaindex/vercel": "^0.1.19",
+    "@llamaindex/vercel": "^0.1.13",
-    "@llamaindex/vllm": "^0.0.56",
+    "@llamaindex/vllm": "^0.0.49",
-    "@llamaindex/voyage-ai": "^1.0.25",
+    "@llamaindex/voyage-ai": "^1.0.19",
-    "@llamaindex/weaviate": "^0.0.34",
+    "@llamaindex/weaviate": "^0.0.28",
-    "@llamaindex/workflow": "^1.1.20",
+    "@llamaindex/workflow": "^1.1.13",
-    "@llamaindex/xai": "^0.0.17",
+    "@llamaindex/xai": "workspace:^0.0.10",
-    "@notionhq/client": "^4.0.0",
+    "@notionhq/client": "^2.2.15",
     "@pinecone-database/pinecone": "^4.0.0",
     "@vercel/postgres": "^0.10.0",
     "ai": "^4.3.17",
     "ajv": "^8.17.1",
     "commander": "^12.1.0",
-    "dotenv": "^17.2.0",
+    "dotenv": "^16.4.5",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.11.24",
+    "llamaindex": "^0.11.13",
     "mongodb": "6.7.0",
     "postgres": "^3.4.4",
     "wikipedia": "^2.1.2",
     "zod": "^3.25.76"
   },
   "devDependencies": {
-    "@types/node": "^24.0.13",
+    "@types/node": "^22.9.0",
-    "tsx": "^4.20.3",
+    "tsx": "^4.19.3",
     "typescript": "^5.8.3"
   },
   "stackblitz": {

examples/pnpm-workspace.yaml

@@ -1,2 +0,0 @@
-packages:
-  - "**"

examples/readers/package.json

@@ -23,12 +23,11 @@
     "@llamaindex/cloud": "workspace:* || ^2.0.24",
     "@llamaindex/excel": "workspace:*",
     "@llamaindex/readers": "workspace:* || ^1.0.25",
-    "@notionhq/client": "^4.0.0",
     "llamaindex": "workspace:* || ^0.8.37"
   },
   "devDependencies": {
-    "@types/node": "^24.0.13",
+    "@types/node": "^22.9.0",
-    "tsx": "^4.20.3",
+    "tsx": "^4.19.3",
     "typescript": "^5.8.3"
   }
 }

examples/storage/qdrantdb/with-gemini.ts

@@ -15,7 +15,7 @@ async function main() {
   const vectorStore = new QdrantVectorStore({
     url: process.env.QDRANT_URL,
     apiKey: process.env.QDRANT_API_KEY,
-    embedModel: embedding,
+    embeddingModel: embedding,
     collectionName: "gemini_test",
   });
   const storageContext = await storageContextFromDefaults({ vectorStore });

examples/storage/qdrantdb/with-jina.ts

@@ -16,7 +16,7 @@ async function main() {
   const vectorStore = new QdrantVectorStore({
     url: process.env.QDRANT_URL,
     apiKey: process.env.QDRANT_API_KEY,
-    embedModel: embedding,
+    embeddingModel: embedding,
     collectionName: "jina_test",
   });
   const storageContext = await storageContextFromDefaults({ vectorStore });

package.json

@@ -17,19 +17,18 @@
     "release-snapshot": "pnpm run build && changeset publish --tag snapshot",
     "new-version": "changeset version && pnpm format:write && pnpm run build",
     "new-snapshot": "pnpm run build && changeset version --snapshot",
-    "lint-staged": "lint-staged",
+    "lint-staged": "lint-staged"
-    "preinstall": "npx only-allow pnpm"
   },
   "devDependencies": {
     "@changesets/cli": "^2.27.5",
     "@eslint/js": "^9.25.0",
     "bunchee": "6.4.0",
-    "eslint": "9.30.1",
+    "eslint": "9.22.0",
-    "eslint-config-next": "^15.3.5",
+    "eslint-config-next": "^15.1.0",
-    "eslint-config-prettier": "^10.1.5",
+    "eslint-config-prettier": "^9.1.0",
-    "eslint-config-turbo": "^2.5.4",
+    "eslint-config-turbo": "^2.3.3",
-    "eslint-plugin-react": "7.37.5",
+    "eslint-plugin-react": "7.37.2",
-    "eslint-plugin-turbo": "^2.5.4",
+    "eslint-plugin-turbo": "^2.5.0",
     "globals": "^15.12.0",
     "husky": "^9.1.7",
     "lint-staged": "^15.2.11",
@@ -39,15 +38,10 @@
     "prettier-plugin-tailwindcss": "^0.6.11",
     "turbo": "^2.4.4",
     "typescript": "^5.8.3",
-    "typescript-eslint": "^8.36.0",
+    "typescript-eslint": "^8.18.0",
     "vitest": "^3.1.1"
   },
   "packageManager": "pnpm@10.8.1",
-  "pnpm": {
-    "overrides": {
-      "@notionhq/client": "4.0.0"
-    }
-  },
   "lint-staged": {
     "*.{js,jsx,ts,tsx}": [
       "eslint --fix",

packages/autotool/CHANGELOG.md

@@ -1,71 +1,5 @@
 # @llamaindex/autotool
 
-## 8.0.24
-
-### Patch Changes
-
-- llamaindex@0.11.24
-
-## 8.0.23
-
-### Patch Changes
-
-- llamaindex@0.11.23
-
-## 8.0.22
-
-### Patch Changes
-
-- llamaindex@0.11.22
-
-## 8.0.21
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
-## 8.0.20
-
-### Patch Changes
-
-- llamaindex@0.11.20
-
-## 8.0.19
-
-### Patch Changes
-
-- llamaindex@0.11.19
-
-## 8.0.18
-
-### Patch Changes
-
-- llamaindex@0.11.18
-
-## 8.0.17
-
-### Patch Changes
-
-- llamaindex@0.11.17
-
-## 8.0.16
-
-### Patch Changes
-
-- llamaindex@0.11.16
-
-## 8.0.15
-
-### Patch Changes
-
-- llamaindex@0.11.15
-
-## 8.0.14
-
-### Patch Changes
-
-- llamaindex@0.11.14
-
 ## 8.0.13
 
 ### Patch Changes

packages/autotool/examples/01_node/CHANGELOG.md

@@ -1,82 +1,5 @@
 # @llamaindex/autotool-01-node-example
 
-## 0.0.132
-
-### Patch Changes
-
-- llamaindex@0.11.24
-- @llamaindex/autotool@8.0.24
-
-## 0.0.131
-
-### Patch Changes
-
-- llamaindex@0.11.23
-- @llamaindex/autotool@8.0.23
-
-## 0.0.130
-
-### Patch Changes
-
-- llamaindex@0.11.22
-- @llamaindex/autotool@8.0.22
-
-## 0.0.129
-
-### Patch Changes
-
-- llamaindex@0.11.21
-- @llamaindex/autotool@8.0.21
-
-## 0.0.128
-
-### Patch Changes
-
-- llamaindex@0.11.20
-- @llamaindex/autotool@8.0.20
-
-## 0.0.127
-
-### Patch Changes
-
-- llamaindex@0.11.19
-- @llamaindex/autotool@8.0.19
-
-## 0.0.126
-
-### Patch Changes
-
-- llamaindex@0.11.18
-- @llamaindex/autotool@8.0.18
-
-## 0.0.125
-
-### Patch Changes
-
-- llamaindex@0.11.17
-- @llamaindex/autotool@8.0.17
-
-## 0.0.124
-
-### Patch Changes
-
-- llamaindex@0.11.16
-- @llamaindex/autotool@8.0.16
-
-## 0.0.123
-
-### Patch Changes
-
-- llamaindex@0.11.15
-- @llamaindex/autotool@8.0.15
-
-## 0.0.122
-
-### Patch Changes
-
-- llamaindex@0.11.14
-- @llamaindex/autotool@8.0.14
-
 ## 0.0.121
 
 ### Patch Changes

packages/autotool/examples/01_node/package.json

@@ -8,10 +8,10 @@
     "openai": "^4.73.1"
   },
   "devDependencies": {
-    "tsx": "^4.20.3"
+    "tsx": "^4.19.3"
   },
   "scripts": {
     "start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
   },
-  "version": "0.0.132"
+  "version": "0.0.121"
 }

packages/autotool/package.json

@@ -6,7 +6,7 @@
     "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
     "directory": "packages/autotool"
   },
-  "version": "8.0.24",
+  "version": "8.0.13",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",
@@ -74,11 +74,11 @@
   "devDependencies": {
     "@swc/types": "^0.1.12",
     "@types/json-schema": "^7.0.15",
-    "@types/node": "^24.0.13",
+    "@types/node": "^22.9.0",
     "llamaindex": "workspace:*",
     "next": "^15.3.3",
     "rollup": "^4.28.1",
-    "tsx": "^4.20.3",
+    "tsx": "^4.19.3",
     "typescript": "^5.8.3",
     "vitest": "^2.1.5",
     "webpack": "^5.97.1"

packages/cloud/CHANGELOG.md

@@ -1,78 +1,5 @@
 # @llamaindex/cloud
 
-## 4.0.28
-
-### Patch Changes
-
-- c3bf3c7: Adding support for citations to beta agent data schema
-- Updated dependencies [f9f1de9]
-  - @llamaindex/core@0.6.19
-
-## 4.0.27
-
-### Patch Changes
-
-- Updated dependencies [f29799e]
-- Updated dependencies [7224c06]
-  - @llamaindex/core@0.6.18
-
-## 4.0.26
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
-## 4.0.25
-
-### Patch Changes
-
-- 2967d57: Default to \_public agent url id
-- Updated dependencies [a8ec08c]
-  - @llamaindex/core@0.6.16
-
-## 4.0.24
-
-### Patch Changes
-
-- Updated dependencies [7ad3411]
-- Updated dependencies [5da5b3c]
-  - @llamaindex/core@0.6.15
-
-## 4.0.23
-
-### Patch Changes
-
-- a1b1598: fix: add generic types into agent data responses
-
-## 4.0.22
-
-### Patch Changes
-
-- d2be868: Bug fixes for new beta agent-data cloud API
-
-## 4.0.21
-
-### Patch Changes
-
-- 579ca0c: chore: bump sdk version
-
-## 4.0.20
-
-### Patch Changes
-
-- 48b0d88: fix: exports in `api` submodule
-- f185772: fix(cloud): missing file
-
-## 4.0.19
-
-### Patch Changes
-
-- 5a0ed1f: feat: init agent api on cloud sdk
-- 5a0ed1f: feat: init agent api on cloud sdk
-- Updated dependencies [8eeac33]
-  - @llamaindex/core@0.6.14
-
 ## 4.0.18
 
 ### Patch Changes

packages/cloud/beta/agent/package.json

@@ -1,8 +0,0 @@
-{
-  "type": "module",
-  "main": "./dist/index.cjs",
-  "module": "./dist/index.js",
-  "types": "./dist/index.d.ts",
-  "exports": "./dist/index.js",
-  "private": true
-}

packages/cloud/openapi.json

@@ -2519,7 +2519,7 @@
       "get": {
         "tags": ["Organizations"],
         "summary": "Get Organization Usage",
-        "description": "Get usage for a specific organization.",
+        "description": "Get usage for a project",
         "operationId": "get_organization_usage_api_v1_organizations__organization_id__usage_get",
         "security": [
           {
@@ -2535,8 +2535,15 @@
             "in": "path",
             "required": true,
             "schema": {
-              "type": "string",
+              "anyOf": [
-              "format": "uuid",
+                {
+                  "type": "string",
+                  "format": "uuid"
+                },
+                {
+                  "type": "null"
+                }
+              ],
               "title": "Organization Id"
             }
           },
@@ -11643,7 +11650,7 @@
     },
     "/api/v1/projects/{project_id}/agents": {
       "get": {
-        "tags": ["Agent Deployments"],
+        "tags": ["Llama Apps"],
         "summary": "List Deployments",
         "description": "List all deployments for a project.",
         "operationId": "list_deployments_api_v1_projects__project_id__agents_get",
@@ -11709,7 +11716,7 @@
     },
     "/api/v1/projects/{project_id}/agents:sync": {
       "post": {
-        "tags": ["Agent Deployments"],
+        "tags": ["Llama Apps"],
         "summary": "Sync Deployments",
         "description": "Sync deployments for a project.",
         "operationId": "sync_deployments_api_v1_projects__project_id__agents_sync_post",
@@ -11773,12 +11780,12 @@
         }
       }
     },
-    "/api/v1/classifier/classify": {
+    "/api/v1/billing/checkout-session": {
       "post": {
-        "tags": ["Classifier", "Beta", "Classifier"],
+        "tags": ["Billing"],
-        "summary": "Classify Documents",
+        "summary": "Create Checkout Session",
-        "description": "**[BETA]** Classify documents based on provided rules - simplified classification system.\n\n**This is a Beta feature** - API may change based on user feedback.\n\nThis endpoint supports:\n- Classifying new uploaded files\n- Classifying existing files by ID\n- Both new files and existing file IDs in one request\n\n## v0 Features:\n- **Simplified Rules**: Only `type` and `description` fields needed\n- **Matching Threshold**: Confidence-based classification with configurable threshold\n- **Smart Classification**: Filename heuristics + LLM content analysis\n- **Document Type Filtering**: Automatically filters out non-document file types\n- **Fast Processing**: Uses LlamaParse fast mode + GPT-4.1-nano\n- **Optimized Performance**: Parses each file only once for all rules\n\n## Simplified Scoring Logic:\n1. **Evaluate All Rules**: Compare document against all classification rules\n2. **Best Match Selection**: Return the highest scoring rule above matching_threshold\n3. **Unknown Classification**: Return as \"unknown\" if no rules score above threshold\n\nThis ensures optimal classification by:\n- Finding the best possible match among all rules\n- Avoiding false positives with confidence thresholds\n- Maximizing performance with single-pass file parsing\n\n## Rule Format:\n```json\n[\n  {\n    \"type\": \"invoice\",\n    \"description\": \"contains invoice number, line items, and total amount\"\n  },\n  {\n    \"type\": \"receipt\",\n    \"description\": \"purchase receipt with transaction details and payment info\"\n  }\n]\n```\n\n## Classification Process:\n1. **Metadata Heuristics** (configurable via API):\n   - **Document Type Filter**: Only process document file types (PDF, DOC, DOCX, RTF, TXT, ODT, Pages, HTML, XML, Markdown)\n   - **Filename Heuristics**: Check if rule type appears in filename\n   - **Content Analysis**: Parse document content once and use LLM for semantic matching against all rules\n2. **Result**: Returns type, confidence score, and matched rule information\n\n## API Parameters:\n- `matching_threshold` (0.1-0.99, default: 0.6): Minimum confidence threshold for acceptable matches\n- `enable_metadata_heuristic` (boolean, default: true): Enable metadata-based features\n\n## Supported Document Types:\n**Text Documents**: pdf, doc, docx, rtf, txt, odt, pages\n**Web Documents**: html, htm, xml\n**Markup**: md, markdown\n\n## Limits (Beta):\n- Maximum 100 files per request\n- Maximum 10 rules per request\n- Rule descriptions: 10-500 characters\n- Document types: 1-50 characters (alphanumeric, hyphens, underscores)\n\n**Beta Notice**: This API is subject to change. Please provide feedback!",
+        "description": "Create a new checkout session.",
-        "operationId": "classify_documents_api_v1_classifier_classify_post",
+        "operationId": "create_checkout_session_api_v1_billing_checkout_session_post",
         "security": [
           {
             "HTTPBearer": []
@@ -11788,23 +11795,6 @@
           }
         ],
         "parameters": [
-          {
-            "name": "project_id",
-            "in": "query",
-            "required": false,
-            "schema": {
-              "anyOf": [
-                {
-                  "type": "string",
-                  "format": "uuid"
-                },
-                {
-                  "type": "null"
-                }
-              ],
-              "title": "Project Id"
-            }
-          },
           {
             "name": "organization_id",
             "in": "query",
@@ -11842,9 +11832,9 @@
         "requestBody": {
           "required": true,
           "content": {
-            "multipart/form-data": {
+            "application/json": {
               "schema": {
-                "$ref": "#/components/schemas/Body_classify_documents_api_v1_classifier_classify_post"
+                "$ref": "#/components/schemas/CheckoutSessionCreatePayload"
               }
             }
           }
@@ -11855,7 +11845,8 @@
             "content": {
               "application/json": {
                 "schema": {
-                  "$ref": "#/components/schemas/ClassifyResponse"
+                  "type": "string",
+                  "title": "Response Create Checkout Session Api V1 Billing Checkout Session Post"
                 }
               }
             }
@@ -11957,6 +11948,55 @@
         }
       }
     },
+    "/api/v1/billing/webhook": {
+      "post": {
+        "tags": ["Billing"],
+        "summary": "Stripe Webhook",
+        "description": "Stripe webhook endpoint.",
+        "operationId": "stripe_webhook_api_v1_billing_webhook_post",
+        "parameters": [
+          {
+            "name": "stripe-signature",
+            "in": "header",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "title": "Stripe-Signature"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "additionalProperties": {
+                    "const": "success",
+                    "type": "string"
+                  },
+                  "propertyNames": {
+                    "const": "status"
+                  },
+                  "title": "Response Stripe Webhook Api V1 Billing Webhook Post"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
     "/api/v1/billing/downgrade-plan": {
       "post": {
         "tags": ["Billing"],
@@ -12125,6 +12165,64 @@
         }
       }
     },
+    "/api/v1/billing/metronome-webhook": {
+      "post": {
+        "tags": ["Billing"],
+        "summary": "Metronome Webhook",
+        "description": "Metronome webhook endpoint.",
+        "operationId": "metronome_webhook_api_v1_billing_metronome_webhook_post",
+        "parameters": [
+          {
+            "name": "Metronome-Webhook-Signature",
+            "in": "header",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "title": "Metronome-Webhook-Signature"
+            }
+          },
+          {
+            "name": "Date",
+            "in": "header",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "title": "Date"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "additionalProperties": {
+                    "const": "success",
+                    "type": "string"
+                  },
+                  "propertyNames": {
+                    "const": "status"
+                  },
+                  "title": "Response Metronome Webhook Api V1 Billing Metronome Webhook Post"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
     "/api/v1/billing/metronome/dashboard": {
       "get": {
         "tags": ["Billing"],
@@ -15670,12 +15768,12 @@
         }
       }
     },
-    "/api/v1/beta/agent-data": {
+    "/api/v1/beta/agent-data/": {
       "post": {
         "tags": ["Beta", "Agent Data"],
         "summary": "Create Agent Data",
         "description": "Create new agent data.",
-        "operationId": "create_agent_data_api_v1_beta_agent_data_post",
+        "operationId": "create_agent_data_api_v1_beta_agent_data__post",
         "security": [
           {
             "HTTPBearer": []
@@ -18785,73 +18883,6 @@
         "required": ["start_date", "end_date"],
         "title": "BillingPeriod"
       },
-      "Body_classify_documents_api_v1_classifier_classify_post": {
-        "properties": {
-          "rules_json": {
-            "type": "string",
-            "title": "Rules Json",
-            "description": "JSON string containing classifier rules"
-          },
-          "files": {
-            "anyOf": [
-              {
-                "items": {
-                  "type": "string",
-                  "format": "binary"
-                },
-                "type": "array"
-              },
-              {
-                "type": "null"
-              }
-            ],
-            "title": "Files"
-          },
-          "file_ids": {
-            "anyOf": [
-              {
-                "type": "string"
-              },
-              {
-                "type": "null"
-              }
-            ],
-            "title": "File Ids",
-            "description": "Comma-separated list of existing file IDs"
-          },
-          "matching_threshold": {
-            "anyOf": [
-              {
-                "type": "number",
-                "maximum": 0.99,
-                "minimum": 0.1
-              },
-              {
-                "type": "null"
-              }
-            ],
-            "title": "Matching Threshold",
-            "description": "Minimum confidence threshold for acceptable matches (0.1-0.99, default: 0.6)",
-            "default": 0.6
-          },
-          "enable_metadata_heuristic": {
-            "anyOf": [
-              {
-                "type": "boolean"
-              },
-              {
-                "type": "null"
-              }
-            ],
-            "title": "Enable Metadata Heuristic",
-            "description": "Enable metadata-based features (document filtering + content classification, default: true)",
-            "default": true
-          }
-        },
-        "type": "object",
-        "required": ["rules_json"],
-        "title": "Body_classify_documents_api_v1_classifier_classify_post"
-      },
       "Body_create_report_api_v1_reports__post": {
         "properties": {
           "name": {
@@ -19345,11 +19376,6 @@
             ],
             "title": "Max Pages"
           },
-          "merge_tables_across_pages_in_markdown": {
-            "type": "boolean",
-            "title": "Merge Tables Across Pages In Markdown",
-            "default": false
-          },
           "outlined_table_extraction": {
             "type": "boolean",
             "title": "Outlined Table Extraction",
@@ -19831,11 +19857,6 @@
             ],
             "title": "Max Pages"
           },
-          "merge_tables_across_pages_in_markdown": {
-            "type": "boolean",
-            "title": "Merge Tables Across Pages In Markdown",
-            "default": false
-          },
           "outlined_table_extraction": {
             "type": "boolean",
             "title": "Outlined Table Extraction",
@@ -20409,101 +20430,30 @@
         "type": "object",
         "title": "ChatInputParams"
       },
+      "CheckoutSessionCreatePayload": {
+        "properties": {
+          "success_url": {
+            "type": "string",
+            "minLength": 1,
+            "format": "uri",
+            "title": "Success Url"
+          },
+          "cancel_url": {
+            "type": "string",
+            "minLength": 1,
+            "format": "uri",
+            "title": "Cancel Url"
+          }
+        },
+        "type": "object",
+        "required": ["success_url", "cancel_url"],
+        "title": "CheckoutSessionCreatePayload"
+      },
       "ChunkMode": {
         "type": "string",
         "enum": ["PAGE", "DOCUMENT", "SECTION", "GROUPED_PAGES"],
         "title": "ChunkMode"
       },
-      "ClassificationResult": {
-        "properties": {
-          "file_id": {
-            "type": "string",
-            "format": "uuid",
-            "title": "File Id",
-            "description": "The ID of the classified file"
-          },
-          "type": {
-            "type": "string",
-            "title": "Type",
-            "description": "The assigned document type ('unknown' if no rules matched)",
-            "examples": ["invoice", "receipt", "contract", "unknown"]
-          },
-          "confidence": {
-            "type": "number",
-            "maximum": 1.0,
-            "minimum": 0.0,
-            "title": "Confidence",
-            "description": "Confidence score of the classification (0.0-1.0)"
-          },
-          "matched_rule": {
-            "anyOf": [
-              {
-                "type": "string"
-              },
-              {
-                "type": "null"
-              }
-            ],
-            "title": "Matched Rule",
-            "description": "Description of the rule that matched, or method used (e.g., 'auto: filename contains invoice')",
-            "examples": [
-              "contains invoice number, line items, and total",
-              "auto: filename contains 'invoice'",
-              null
-            ]
-          }
-        },
-        "type": "object",
-        "required": ["file_id", "type", "confidence", "matched_rule"],
-        "title": "ClassificationResult",
-        "description": "Result of classifying a single file.\n\nContains the classification outcome with confidence score and matched rule info."
-      },
-      "ClassifyResponse": {
-        "properties": {
-          "items": {
-            "items": {
-              "$ref": "#/components/schemas/ClassificationResult"
-            },
-            "type": "array",
-            "title": "Items",
-            "description": "The list of items."
-          },
-          "next_page_token": {
-            "anyOf": [
-              {
-                "type": "string"
-              },
-              {
-                "type": "null"
-              }
-            ],
-            "title": "Next Page Token",
-            "description": "A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages."
-          },
-          "total_size": {
-            "anyOf": [
-              {
-                "type": "integer"
-              },
-              {
-                "type": "null"
-              }
-            ],
-            "title": "Total Size",
-            "description": "The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only."
-          },
-          "unknown_count": {
-            "type": "integer",
-            "minimum": 0.0,
-            "title": "Unknown Count",
-            "description": "Number of files that couldn't be classified"
-          }
-        },
-        "type": "object",
-        "required": ["items", "unknown_count"],
-        "title": "ClassifyResponse",
-        "description": "Response model for the classify endpoint following AIP-132 pagination standard.\n\nContains classification results with pagination support and summary statistics."
-      },
       "CloudAzStorageBlobDataSource": {
         "properties": {
           "supports_access_control": {
@@ -21991,7 +21941,6 @@
           },
           "query": {
             "type": "string",
-            "minLength": 1,
             "title": "Query",
             "description": "The query to retrieve against."
           }
@@ -22508,12 +22457,14 @@
           "version_metadata": {
             "anyOf": [
               {
-                "$ref": "#/components/schemas/DataSourceReaderVersionMetadata"
+                "additionalProperties": true,
+                "type": "object"
               },
               {
                 "type": "null"
               }
             ],
+            "title": "Version Metadata",
             "description": "Version metadata for the data source"
           },
           "project_id": {
@@ -22619,24 +22570,6 @@
         "title": "DataSourceCreate",
         "description": "Schema for creating a data source."
       },
-      "DataSourceReaderVersionMetadata": {
-        "properties": {
-          "reader_version": {
-            "anyOf": [
-              {
-                "type": "string"
-              },
-              {
-                "type": "null"
-              }
-            ],
-            "title": "Reader Version",
-            "description": "The version of the reader to use for this data source."
-          }
-        },
-        "type": "object",
-        "title": "DataSourceReaderVersionMetadata"
-      },
       "DataSourceUpdate": {
         "properties": {
           "name": {
@@ -22908,7 +22841,6 @@
           },
           "query": {
             "type": "string",
-            "minLength": 1,
             "title": "Query",
             "description": "The query to retrieve against."
           },
@@ -23867,7 +23799,7 @@
       },
       "ExtractMode": {
         "type": "string",
-        "enum": ["FAST", "BALANCED", "PREMIUM", "MULTIMODAL"],
+        "enum": ["FAST", "BALANCED", "PREMIUM", "MULTIMODAL", "ACCURATE"],
         "title": "ExtractMode"
       },
       "ExtractModels": {
@@ -26278,19 +26210,6 @@
             "description": "Whether to try to extract outlined tables",
             "default": false
           },
-          "mergeTablesAcrossPagesInMarkdown": {
-            "anyOf": [
-              {
-                "type": "boolean"
-              },
-              {
-                "type": "null"
-              }
-            ],
-            "title": "Mergetablesacrosspagesinmarkdown",
-            "description": "Whether to merge tables across pages in markdown",
-            "default": false
-          },
           "saveImages": {
             "anyOf": [
               {
@@ -27151,7 +27070,6 @@
               "disable_image_extraction": false,
               "invalidate_cache": false,
               "outlined_table_extraction": false,
-              "merge_tables_across_pages_in_markdown": false,
               "output_pdf_of_document": false,
               "do_not_cache": false,
               "fast_mode": false,
@@ -27328,18 +27246,6 @@
             "title": "Outlined Table Extraction",
             "default": false
           },
-          "merge_tables_across_pages_in_markdown": {
-            "anyOf": [
-              {
-                "type": "boolean"
-              },
-              {
-                "type": "null"
-              }
-            ],
-            "title": "Merge Tables Across Pages In Markdown",
-            "default": false
-          },
           "output_pdf_of_document": {
             "anyOf": [
               {
@@ -29500,18 +29406,6 @@
             "title": "Outlined Table Extraction",
             "default": false
           },
-          "merge_tables_across_pages_in_markdown": {
-            "anyOf": [
-              {
-                "type": "boolean"
-              },
-              {
-                "type": "null"
-              }
-            ],
-            "title": "Merge Tables Across Pages In Markdown",
-            "default": false
-          },
           "output_pdf_of_document": {
             "anyOf": [
               {
@@ -31440,12 +31334,14 @@
           "version_metadata": {
             "anyOf": [
               {
-                "$ref": "#/components/schemas/DataSourceReaderVersionMetadata"
+                "additionalProperties": true,
+                "type": "object"
               },
               {
                 "type": "null"
               }
             ],
+            "title": "Version Metadata",
             "description": "Version metadata for the data source"
           },
           "project_id": {
@@ -32233,6 +32129,12 @@
             "title": "Data Source Project File Changed",
             "description": "Whether the data source project file has changed",
             "default": false
+          },
+          "should_migrate_pipeline_file_to_external_file_id": {
+            "type": "boolean",
+            "title": "Should Migrate Pipeline File To External File Id",
+            "description": "Whether to migrate the pipeline file to the external file id",
+            "default": false
           }
         },
         "type": "object",
@@ -34337,6 +34239,19 @@
             "title": "Name",
             "description": "A name for the role."
           },
+          "organization_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "format": "uuid"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "title": "Organization Id",
+            "description": "The organization's ID."
+          },
           "permissions": {
             "items": {
               "$ref": "#/components/schemas/Permission"
@@ -34347,7 +34262,7 @@
           }
         },
         "type": "object",
-        "required": ["id", "name", "permissions"],
+        "required": ["id", "name", "organization_id", "permissions"],
         "title": "Role",
         "description": "Schema for a role."
       },
@@ -35219,13 +35134,19 @@
             "title": "Project Ids",
             "description": "The project ID scope."
           },
+          "role_id": {
+            "type": "string",
+            "format": "uuid",
+            "title": "Role Id",
+            "description": "The role's ID."
+          },
           "role": {
             "$ref": "#/components/schemas/Role",
             "description": "The role."
           }
         },
         "type": "object",
-        "required": ["id", "user_id", "organization_id", "role"],
+        "required": ["id", "user_id", "organization_id", "role_id", "role"],
         "title": "UserOrganizationRole",
         "description": "Schema for a user's role in an organization."
       },

packages/cloud/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloud",
-  "version": "4.0.28",
+  "version": "4.0.18",
   "type": "module",
   "license": "MIT",
   "scripts": {
@@ -11,22 +11,20 @@
   "files": [
     "openapi.json",
     "./api",
-    "./reader",
+    "./reader"
-    "./parse",
-    "./beta/agent"
   ],
   "exports": {
     "./openapi.json": "./openapi.json",
-    "./beta/agent": {
+    "./agent": {
       "require": {
-        "types": "./beta/agent/dist/index.d.cts",
+        "types": "./agent/dist/index.d.cts",
-        "default": "./beta/agent/dist/index.cjs"
+        "default": "./agent/dist/index.cjs"
       },
       "import": {
-        "types": "./beta/agent/dist/index.d.ts",
+        "types": "./agent/dist/index.d.ts",
-        "default": "./beta/agent/dist/index.js"
+        "default": "./agent/dist/index.js"
       },
-      "default": "./beta/agent/dist/index.js"
+      "default": "./agent/dist/index.js"
     },
     "./api": {
       "require": {

packages/cloud/src/agent/client.ts

@@ -0,0 +1,291 @@
+import { createClient, createConfig } from "@hey-api/client-fetch";
+import { getEnv } from "@llamaindex/env";
+import pRetry from "p-retry";
+import {
+  createAgentDataApiV1BetaAgentDataPost,
+  deleteAgentDataApiV1BetaAgentDataItemIdDelete,
+  getAgentDataApiV1BetaAgentDataItemIdGet,
+  searchAgentDataApiV1BetaAgentDataSearchPost,
+  updateAgentDataApiV1BetaAgentDataItemIdPut,
+  type AgentData,
+} from "../client";
+import type {
+  CreateAgentDataOptions,
+  ExtractedData,
+  ExtractOptions,
+  ListAgentDataOptions,
+  TypedAgentData,
+  TypedAgentDataItems,
+  UpdateAgentDataOptions,
+} from "./types";
+
+/**
+ * Async client for agent data operations
+ */
+export class AgentClient {
+  private client: ReturnType<typeof createClient>;
+  private baseUrl: string;
+  private headers: Record<string, string>;
+
+  constructor(options?: { apiKey?: string; baseUrl?: string }) {
+    const apiKey = options?.apiKey || getEnv("LLAMA_CLOUD_API_KEY");
+    this.baseUrl = options?.baseUrl || "https://api.cloud.llamaindex.ai/";
+
+    this.headers = {
+      "X-SDK-Name": "llamaindex-ts",
+      ...(apiKey && { Authorization: `Bearer ${apiKey}` }),
+    };
+
+    this.client = createClient(
+      createConfig({
+        baseUrl: this.baseUrl,
+        headers: this.headers,
+      }),
+    );
+  }
+
+  /**
+   * Create new agent data
+   */
+  async create<T = unknown>(
+    options: CreateAgentDataOptions<T>,
+  ): Promise<TypedAgentData<T>> {
+    const response = await createAgentDataApiV1BetaAgentDataPost({
+      throwOnError: true,
+      body: {
+        agent_slug: options.agentSlug,
+        ...(options.collection !== undefined && {
+          collection: options.collection,
+        }),
+        data: options.data as Record<string, unknown>,
+      },
+      client: this.client,
+    });
+
+    return this.transformResponse(response.data);
+  }
+
+  /**
+   * Get agent data by ID
+   */
+  async get<T = unknown>(id: string): Promise<TypedAgentData<T> | null> {
+    try {
+      const response = await getAgentDataApiV1BetaAgentDataItemIdGet({
+        throwOnError: true,
+        path: { item_id: id },
+        client: this.client,
+      });
+
+      return this.transformResponse(response.data);
+    } catch (error) {
+      if (
+        error instanceof Error &&
+        "response" in error &&
+        (error as { response?: { status?: number } }).response?.status === 404
+      ) {
+        return null;
+      }
+      throw error;
+    }
+  }
+
+  /**
+   * Update agent data
+   */
+  async update<T = unknown>(
+    id: string,
+    options: UpdateAgentDataOptions<T>,
+  ): Promise<TypedAgentData<T>> {
+    const response = await updateAgentDataApiV1BetaAgentDataItemIdPut({
+      throwOnError: true,
+      path: { item_id: id },
+      body: {
+        data: options.data as Record<string, unknown>,
+      },
+      client: this.client,
+    });
+
+    return this.transformResponse(response.data);
+  }
+
+  /**
+   * Delete agent data
+   */
+  async delete(id: string): Promise<void> {
+    await deleteAgentDataApiV1BetaAgentDataItemIdDelete({
+      throwOnError: true,
+      path: { item_id: id },
+      client: this.client,
+    });
+  }
+
+  /**
+   * List agent data
+   */
+  async list<T = unknown>(
+    options: ListAgentDataOptions,
+  ): Promise<TypedAgentDataItems<T>> {
+    const response = await searchAgentDataApiV1BetaAgentDataSearchPost({
+      throwOnError: true,
+      body: {
+        agent_slug: options.agentSlug,
+        ...(options.collection !== undefined && {
+          collection: options.collection,
+        }),
+        ...(options.filter !== undefined && { filter: options.filter }),
+        ...(options.orderBy !== undefined && { order_by: options.orderBy }),
+        ...(options.pageSize !== undefined && { page_size: options.pageSize }),
+        ...(options.pageToken !== undefined && {
+          page_token: options.pageToken,
+        }),
+        ...(options.offset !== undefined && { offset: options.offset }),
+      },
+      client: this.client,
+    });
+
+    const result: TypedAgentDataItems<T> = {
+      items: response.data.items.map((item: AgentData) =>
+        this.transformResponse(item),
+      ),
+    };
+
+    if (
+      response.data.total_size !== null &&
+      response.data.total_size !== undefined
+    ) {
+      result.totalSize = response.data.total_size;
+    }
+
+    if (
+      response.data.next_page_token !== null &&
+      response.data.next_page_token !== undefined
+    ) {
+      result.nextPageToken = response.data.next_page_token;
+    }
+
+    return result;
+  }
+
+  /**
+   * Extract data from agent with retry logic
+   */
+  async extract<T = unknown>(
+    agentId: string,
+    input: unknown,
+    options?: ExtractOptions,
+  ): Promise<ExtractedData<T>> {
+    const extractOptions = {
+      retries: options?.retryCount || 3,
+      onFailedAttempt: (error: {
+        attemptNumber: number;
+        retriesLeft: number;
+      }) => {
+        console.log(
+          `Extraction attempt ${error.attemptNumber} failed. ${error.retriesLeft} retries left.`,
+        );
+      },
+      minTimeout: options?.retryDelay || 1000,
+      maxTimeout: options?.timeout || 30000,
+    };
+
+    return pRetry(async () => {
+      // Note: The extract endpoint might not be in the generated client yet
+      // Using the native fetch API for this endpoint
+      const response = await fetch(
+        `${this.baseUrl}/api/v1/beta/agent-data/${agentId}/extract`,
+        {
+          method: "POST",
+          body: JSON.stringify({ input }),
+          headers: {
+            "Content-Type": "application/json",
+            ...this.headers,
+          },
+        },
+      );
+
+      if (!response.ok) {
+        throw new Error(`Failed to extract data: ${response.statusText}`);
+      }
+
+      const extractedData = (await response.json()) as ExtractedData<T>;
+
+      // If status is still pending or in progress, poll for completion
+      if (
+        extractedData.status === "pending" ||
+        extractedData.status === "in_progress"
+      ) {
+        return this.pollExtraction<T>(extractedData.id, options);
+      }
+
+      return extractedData;
+    }, extractOptions);
+  }
+
+  /**
+   * Poll for extraction completion
+   */
+  private async pollExtraction<T = unknown>(
+    extractionId: string,
+    options?: ExtractOptions,
+  ): Promise<ExtractedData<T>> {
+    const pollInterval = 2000; // 2 seconds
+    const maxAttempts = Math.floor((options?.timeout || 30000) / pollInterval);
+
+    for (let i = 0; i < maxAttempts; i++) {
+      await new Promise((resolve) => setTimeout(resolve, pollInterval));
+
+      const response = await fetch(
+        `${this.baseUrl}/api/v1/extractions/${extractionId}`,
+        {
+          headers: this.headers,
+        },
+      );
+
+      if (!response.ok) {
+        throw new Error(
+          `Failed to get extraction status: ${response.statusText}`,
+        );
+      }
+
+      const extractedData = (await response.json()) as ExtractedData<T>;
+
+      if (
+        extractedData.status === "completed" ||
+        extractedData.status === "failed"
+      ) {
+        return extractedData;
+      }
+    }
+
+    throw new Error("Extraction timeout exceeded");
+  }
+
+  /**
+   * Transform API response to typed data
+   */
+  private transformResponse<T = unknown>(data: AgentData): TypedAgentData<T> {
+    const result: TypedAgentData<T> = {
+      id: data.id!,
+      agentSlug: data.agent_slug,
+      data: data.data as T,
+      createdAt: new Date(data.created_at!),
+      updatedAt: new Date(data.updated_at!),
+    };
+
+    if (data.collection !== undefined) {
+      result.collection = data.collection;
+    }
+
+    return result;
+  }
+}
+
+/**
+ * Create a new AsyncAgentDataClient instance
+ */
+export function createAgentDataClient(options?: {
+  apiKey?: string;
+  baseUrl?: string;
+}): AgentClient {
+  return new AgentClient(options);
+}

packages/cloud/src/agent/index.ts

@@ -1,16 +1,18 @@
 export { AgentClient, createAgentDataClient } from "./client";
 
 export type {
-  AggregateAgentDataOptions,
+  AgentDataT,
-  ComparisonOperator,
+  CreateAgentDataOptions,
+  ExtractOptions,
   ExtractedData,
+  ExtractedT,
   FilterOperation,
-  SearchAgentDataOptions,
+  ListAgentDataOptions,
+  SortOptions,
   StatusType,
   TypedAgentData,
   TypedAgentDataItems,
-  TypedAggregateGroup,
+  UpdateAgentDataOptions,
-  TypedAggregateGroupItems,
 } from "./types";
 
 export { StatusType as StatusTypeEnum } from "./types";

packages/cloud/src/agent/types.ts

@@ -0,0 +1,98 @@
+/**
+ * Status types for agent data processing
+ */
+export enum StatusType {
+  PENDING = "pending",
+  IN_PROGRESS = "in_progress",
+  COMPLETED = "completed",
+  FAILED = "failed",
+}
+
+/**
+ * Filter operation for searching/filtering agent data
+ */
+export interface FilterOperation {
+  [key: string]: unknown;
+}
+
+/**
+ * Base extracted data interface
+ */
+export interface ExtractedData<T = unknown> {
+  id: string;
+  status: StatusType;
+  data?: T;
+  error?: string;
+  createdAt: Date;
+  updatedAt: Date;
+}
+
+/**
+ * TypedAgentData interface for typed agent data
+ */
+export interface TypedAgentData<T = unknown> {
+  id: string;
+  agentSlug: string;
+  collection?: string;
+  data: T;
+  createdAt: Date;
+  updatedAt: Date;
+}
+
+/**
+ * Collection of typed agent data items
+ */
+export interface TypedAgentDataItems<T = unknown> {
+  items: TypedAgentData<T>[];
+  totalSize?: number;
+  nextPageToken?: string;
+}
+
+/**
+ * Options for creating agent data
+ */
+export interface CreateAgentDataOptions<T = unknown> {
+  agentSlug: string;
+  collection?: string;
+  data: T;
+}
+
+/**
+ * Options for updating agent data
+ */
+export interface UpdateAgentDataOptions<T = unknown> {
+  data: T;
+}
+
+/**
+ * Sort options for listing
+ */
+export interface SortOptions {
+  field: string;
+  order: "asc" | "desc";
+}
+
+/**
+ * Options for listing agent data
+ */
+export interface ListAgentDataOptions {
+  agentSlug: string;
+  collection?: string;
+  filter?: Record<string, FilterOperation>;
+  orderBy?: string;
+  pageSize?: number;
+  pageToken?: string;
+  offset?: number;
+}
+
+/**
+ * Options for extraction
+ */
+export interface ExtractOptions {
+  timeout?: number;
+  retryCount?: number;
+  retryDelay?: number;
+}
+
+export type ExtractedT<T> = T;
+export type AgentDataT<T> = T;

packages/cloud/src/api.ts

@@ -7,5 +7,21 @@ client.setConfig({
   },
 });
 
+export {
+  AgentClient,
+  createAgentDataClient,
+  StatusTypeEnum,
+  type AgentDataT,
+  type CreateAgentDataOptions,
+  type ExtractedData,
+  type ExtractedT,
+  type ExtractOptions,
+  type ListAgentDataOptions,
+  type SortOptions,
+  type StatusType,
+  type TypedAgentData,
+  type TypedAgentDataItems,
+  type UpdateAgentDataOptions,
+} from "./agent";
 export * from "./client";
 export { client };

packages/cloud/src/beta/agent/client.ts

@@ -1,329 +0,0 @@
-import { createClient, createConfig } from "@hey-api/client-fetch";
-import { getEnv } from "@llamaindex/env";
-import {
-  aggregateAgentDataApiV1BetaAgentDataAggregatePost,
-  createAgentDataApiV1BetaAgentDataPost,
-  deleteAgentDataApiV1BetaAgentDataItemIdDelete,
-  getAgentDataApiV1BetaAgentDataItemIdGet,
-  searchAgentDataApiV1BetaAgentDataSearchPost,
-  updateAgentDataApiV1BetaAgentDataItemIdPut,
-  type AgentData,
-  type AggregateGroup,
-} from "../../client";
-import type {
-  AggregateAgentDataOptions,
-  SearchAgentDataOptions,
-  TypedAgentData,
-  TypedAgentDataItems,
-  TypedAggregateGroup,
-  TypedAggregateGroupItems,
-} from "./types";
-
-/**
- * Async client for agent data operations
- */
-export class AgentClient<T = unknown> {
-  private client: ReturnType<typeof createClient>;
-  private baseUrl: string;
-  private headers: Record<string, string>;
-  private collection: string;
-  private agentUrlId: string;
-
-  constructor({
-    apiKey = getEnv("LLAMA_CLOUD_API_KEY"),
-    baseUrl = "https://api.cloud.llamaindex.ai/",
-    collection = "default",
-    agentUrlId = "_public",
-  }: {
-    apiKey?: string;
-    baseUrl?: string;
-    collection?: string;
-    agentUrlId?: string;
-  }) {
-    this.baseUrl = baseUrl;
-
-    this.headers = {
-      "X-SDK-Name": "llamaindex-ts",
-      ...(apiKey && { Authorization: `Bearer ${apiKey}` }),
-    };
-
-    this.client = createClient(
-      createConfig({
-        baseUrl: this.baseUrl,
-        headers: this.headers,
-      }),
-    );
-
-    this.collection = collection;
-    this.agentUrlId = agentUrlId;
-  }
-
-  /**
-   * Create new agent data
-   */
-  async createItem(data: T): Promise<TypedAgentData<T>> {
-    const response = await createAgentDataApiV1BetaAgentDataPost({
-      throwOnError: true,
-      body: {
-        agent_slug: this.agentUrlId,
-        collection: this.collection,
-        data: data as Record<string, unknown>,
-      },
-      client: this.client,
-    });
-
-    return this.transformResponse(response.data);
-  }
-
-  /**
-   * Get agent data by ID
-   */
-  async getItem(id: string): Promise<TypedAgentData<T> | null> {
-    try {
-      const response = await getAgentDataApiV1BetaAgentDataItemIdGet({
-        throwOnError: true,
-        path: { item_id: id },
-        client: this.client,
-      });
-
-      return this.transformResponse(response.data);
-    } catch (error) {
-      if (
-        error instanceof Error &&
-        "response" in error &&
-        (error as { response?: { status?: number } }).response?.status === 404
-      ) {
-        return null;
-      }
-      throw error;
-    }
-  }
-
-  /**
-   * Update agent data
-   */
-  async updateItem(id: string, data: T): Promise<TypedAgentData<T>> {
-    const response = await updateAgentDataApiV1BetaAgentDataItemIdPut({
-      throwOnError: true,
-      path: { item_id: id },
-      body: {
-        data: data as Record<string, unknown>,
-      },
-      client: this.client,
-    });
-
-    return this.transformResponse(response.data);
-  }
-
-  /**
-   * Delete agent data
-   */
-  async deleteItem(id: string): Promise<void> {
-    await deleteAgentDataApiV1BetaAgentDataItemIdDelete({
-      throwOnError: true,
-      path: { item_id: id },
-      client: this.client,
-    });
-  }
-
-  /**
-   * Search agent data
-   */
-  async search(
-    options: SearchAgentDataOptions,
-  ): Promise<TypedAgentDataItems<T>> {
-    const response = await searchAgentDataApiV1BetaAgentDataSearchPost({
-      throwOnError: true,
-      body: {
-        agent_slug: this.agentUrlId,
-        ...(this.collection !== undefined && {
-          collection: this.collection,
-        }),
-        ...(options.filter !== undefined && { filter: options.filter }),
-        ...(options.orderBy !== undefined && { order_by: options.orderBy }),
-        ...(options.pageSize !== undefined && { page_size: options.pageSize }),
-        ...(options.offset !== undefined && { offset: options.offset }),
-        ...(options.includeTotal !== undefined && {
-          include_total: options.includeTotal,
-        }),
-      },
-      client: this.client,
-    });
-
-    const result: TypedAgentDataItems<T> = {
-      items: response.data.items.map((item: AgentData) =>
-        this.transformResponse(item),
-      ),
-    };
-
-    if (
-      response.data.total_size !== null &&
-      response.data.total_size !== undefined
-    ) {
-      result.totalSize = response.data.total_size;
-    }
-
-    if (
-      response.data.next_page_token !== null &&
-      response.data.next_page_token !== undefined
-    ) {
-      result.nextPageToken = response.data.next_page_token;
-    }
-
-    return result;
-  }
-
-  /**
-   * Aggregate agent data into groups
-   */
-  async aggregate(
-    options: AggregateAgentDataOptions,
-  ): Promise<TypedAggregateGroupItems<T>> {
-    const response = await aggregateAgentDataApiV1BetaAgentDataAggregatePost({
-      throwOnError: true,
-      body: {
-        agent_slug: this.agentUrlId,
-        ...(this.collection !== undefined && {
-          collection: this.collection,
-        }),
-        ...(options.filter !== undefined && { filter: options.filter }),
-        ...(options.groupBy !== undefined && { group_by: options.groupBy }),
-        ...(options.count !== undefined && { count: options.count }),
-        ...(options.first !== undefined && { first: options.first }),
-        ...(options.orderBy !== undefined && { order_by: options.orderBy }),
-        ...(options.offset !== undefined && { offset: options.offset }),
-        ...(options.pageSize !== undefined && { page_size: options.pageSize }),
-      },
-      client: this.client,
-    });
-
-    const result: TypedAggregateGroupItems<T> = {
-      items: response.data.items.map((item) =>
-        this.transformAggregateResponse(item),
-      ),
-    };
-
-    if (
-      response.data.total_size !== null &&
-      response.data.total_size !== undefined
-    ) {
-      result.totalSize = response.data.total_size;
-    }
-
-    if (
-      response.data.next_page_token !== null &&
-      response.data.next_page_token !== undefined
-    ) {
-      result.nextPageToken = response.data.next_page_token;
-    }
-
-    return result;
-  }
-
-  /**
-   * Transform API response to typed data
-   */
-  private transformResponse(data: AgentData): TypedAgentData<T> {
-    const result: TypedAgentData<T> = {
-      id: data.id!,
-      agentUrlId: data.agent_slug,
-      data: data.data as T,
-      createdAt: new Date(data.created_at!),
-      updatedAt: new Date(data.updated_at!),
-    };
-
-    if (data.collection !== undefined) {
-      result.collection = data.collection;
-    }
-
-    return result;
-  }
-
-  /**
-   * Transform API aggregate response to typed data
-   */
-  private transformAggregateResponse(
-    data: AggregateGroup,
-  ): TypedAggregateGroup<T> {
-    const result: TypedAggregateGroup<T> = {
-      groupKey: data.group_key,
-    };
-
-    if (data.count !== null && data.count !== undefined) {
-      result.count = data.count;
-    }
-
-    if (data.first_item !== null && data.first_item !== undefined) {
-      result.firstItem = data.first_item as T;
-    }
-
-    return result;
-  }
-}
-
-export interface AgentDataClientOptions<T = unknown> {
-  /** API key for the client */
-  apiKey?: string;
-  /** Base URL for the client */
-  /** Base URL of the llama cloud api */
-  baseUrl?: string;
-  /** If running in an agent runtime, optionally provide the window url to infer the agent url id */
-  windowUrl?: string;
-  /** Agent URL ID for the client, if not provided, it will be inferred from the window url, or fall back to "default" */
-  agentUrlId?: string;
-  /** Collection name for the client, defaults to "default" */
-  collection?: string;
-}
-/**
- * Create a new AsyncAgentDataClient instance. Does it's best to infer an agent url id from environment.
- * Pass in the window url and/or env to infer the agent url id from them.
- * @param options - The options for the client
- * @returns A new AgentClient instance
- */
-export function createAgentDataClient<T = unknown>({
-  apiKey,
-  baseUrl,
-  windowUrl,
-  env,
-  agentUrlId,
-  collection = "default",
-}: {
-  apiKey?: string;
-  baseUrl?: string;
-  windowUrl?: string;
-  env?: Record<string, string>;
-  agentUrlId?: string;
-  collection?: string;
-} = {}): AgentClient<T> {
-  if (env && !agentUrlId) {
-    agentUrlId =
-      env.LLAMA_DEPLOY_DEPLOYMENT_NAME ||
-      env.NEXT_PUBLIC_LLAMA_DEPLOY_DEPLOYMENT_NAME ||
-      env.VITE_LLAMA_DEPLOY_DEPLOYMENT_NAME;
-  }
-  if (windowUrl && !agentUrlId) {
-    try {
-      const url = new URL(windowUrl);
-      const path = url.pathname;
-      const isLocalhost = // local agents should default to _public, otherwise a full deployment is required
-        url.hostname.includes("localhost") ||
-        url.hostname.includes("127.0.0.1");
-      if (path.startsWith("/deployments/") && !isLocalhost) {
-        // /deployments/<agent-url-id>/ui/ -> ["", "deployments", "<agent-url-id>", "ui"]
-        agentUrlId = path.split("/")[2];
-      }
-    } catch (error) {
-      console.warn(
-        "Failed to infer agent url id from window url, falling back to default",
-        error,
-      );
-    }
-  }
-
-  return new AgentClient({
-    ...(apiKey && { apiKey }),
-    ...(baseUrl && { baseUrl }),
-    ...(agentUrlId && { agentUrlId }),
-    collection,
-  });
-}

packages/cloud/src/beta/agent/types.ts

@@ -1,163 +0,0 @@
-import type { FilterOperation as RawFilterOperation } from "../../client/types.gen";
-/**
- * Status types for agent data processing
- */
-export const StatusType = {
-  ERROR: "error",
-  ACCEPTED: "accepted",
-  REJECTED: "rejected",
-  PENDING_REVIEW: "pending_review",
-} as const;
-
-export type StatusType = (typeof StatusType)[keyof typeof StatusType];
-
-export const ComparisonOperator = {
-  GT: "gt",
-  GTE: "gte",
-  LT: "lt",
-  LTE: "lte",
-  EQ: "eq",
-  INCLUDES: "includes",
-} as const;
-
-export type ComparisonOperator =
-  (typeof ComparisonOperator)[keyof typeof ComparisonOperator];
-
-/**
- * Filter operation for searching/filtering agent data
- */
-export type FilterOperation = RawFilterOperation;
-
-/**
- * Metadata for an extracted field, including confidence and citation information
- */
-export interface ExtractedFieldMetadata {
-  /** The confidence score for the field, combined with parsing confidence if applicable */
-  confidence?: number;
-  /** The confidence score for the field based on the extracted text only */
-  extracted_confidence?: number;
-  /** The page number that the field occurred on */
-  page_number?: number;
-  /** The original text this field's value was derived from */
-  matching_text?: string;
-}
-
-/**
- * Dictionary mapping field names to their metadata
- * Values can be ExtractedFieldMetadata objects, nested dictionaries, or arrays
- */
-export type ExtractedFieldMetadataDict = Record<
-  string,
-  ExtractedFieldMetadata | Record<string, unknown> | unknown[]
->;
-
-/**
- * Base extracted data interface
- */
-export interface ExtractedData<T = unknown> {
-  /** The original data that was extracted from the document. For tracking changes. Should not be updated. */
-  original_data: T;
-  /** The latest state of the data. Will differ if data has been updated. */
-  data: T;
-  /** The status of the extracted data. Prefer to use the StatusType values, but any string is allowed. */
-  status: StatusType | string;
-  /** The overall confidence score for the extracted data. */
-  overall_confidence?: number;
-  /** Page links, and perhaps eventually bounding boxes, for individual fields in the extracted data. */
-  field_metadata?: ExtractedFieldMetadataDict;
-  /** The ID of the file that was used to extract the data. */
-  file_id?: string;
-  /** The name of the file that was used to extract the data. */
-  file_name?: string;
-  /** The hash of the file that was used to extract the data. */
-  file_hash?: string;
-  /** Additional metadata about the extracted data, such as errors, tokens, etc. */
-  metadata?: Record<string, unknown>;
-}
-
-/**
- * TypedAgentData interface for typed agent data
- */
-export interface TypedAgentData<T = unknown> {
-  /** The unique ID of the agent data record. */
-  id: string;
-  /** The ID of the agent that created the data. */
-  agentUrlId: string;
-  /** The collection of the agent data. */
-  collection?: string;
-  /** The data of the agent data. Usually an ExtractedData&lt;SomeOtherType&gt; */
-  data: T;
-  /** The date and time the data was created. */
-  createdAt: Date;
-  /** The date and time the data was last updated. */
-  updatedAt: Date;
-}
-
-/**
- * Paginated response of typed agent data items
- */
-export interface TypedAgentDataItems<T = unknown> {
-  items: TypedAgentData<T>[];
-  totalSize?: number;
-  nextPageToken?: string;
-}
-
-/**
- * Options for listing agent data
- */
-export interface SearchAgentDataOptions {
-  /** Filter options for the list. */
-  filter?: Record<string, FilterOperation>;
-  /** Order by options for the list. */
-  orderBy?: string;
-  /** Page size for the list. */
-  pageSize?: number;
-  /** Offset for the list. */
-  offset?: number;
-  /**
-   * Whether to include the total number of items in the response.
-   * Should use only for first request to build total pagination, and not subsequent requests.
-   */
-  includeTotal?: boolean;
-}
-
-/**
- * Options for aggregating agent data
- */
-export interface AggregateAgentDataOptions {
-  /** Filter options for the aggregation. */
-  filter?: Record<string, FilterOperation>;
-  /** Fields to group by. */
-  groupBy?: string[];
-  /** Whether to count the number of items in each group. */
-  count?: boolean;
-  /** Whether to return the first item in each group. */
-  first?: boolean;
-  /** Order by options for the aggregation. */
-  orderBy?: string;
-  /** Offset for the aggregation. */
-  offset?: number;
-  /** Page size for the aggregation. */
-  pageSize?: number;
-}
-
-/**
- * Single aggregation group result
- */
-export interface TypedAggregateGroup<T = unknown> {
-  /** The group key values */
-  groupKey: Record<string, unknown>;
-  /** Count of items in the group */
-  count?: number;
-  /** First item in the group */
-  firstItem?: T;
-}
-
-/**
- * Paginated response of aggregated agent data
- */
-export interface TypedAggregateGroupItems<T = unknown> {
-  items: TypedAggregateGroup<T>[];
-  totalSize?: number;
-  nextPageToken?: string;
-}

packages/cloud/src/reader.ts

@@ -179,7 +179,6 @@ export class LlamaParseReader extends FileReader {
   page_header_suffix?: string | undefined;
   page_footer_prefix?: string | undefined;
   page_footer_suffix?: string | undefined;
-  merge_tables_across_pages_in_markdown?: boolean | undefined;
 
   constructor(
     params: Partial<Omit<LlamaParseReader, "language" | "apiKey">> & {
@@ -369,8 +368,6 @@ export class LlamaParseReader extends FileReader {
       page_header_suffix: this.page_header_suffix,
       page_footer_prefix: this.page_footer_prefix,
       page_footer_suffix: this.page_footer_suffix,
-      merge_tables_across_pages_in_markdown:
-        this.merge_tables_across_pages_in_markdown,
     } satisfies {
       [Key in keyof BodyUploadFileApiParsingUploadPost]-?:
         | BodyUploadFileApiParsingUploadPost[Key]

packages/community/CHANGELOG.md

@@ -1,777 +0,0 @@
-# @llamaindex/community
-
-## 0.0.101
-
-### Patch Changes
-
-- Updated dependencies [f9f1de9]
-  - @llamaindex/core@0.6.19
-
-## 0.0.100
-
-### Patch Changes
-
-- Updated dependencies [f29799e]
-- Updated dependencies [7224c06]
-  - @llamaindex/core@0.6.18
-
-## 0.0.99
-
-### Patch Changes
-
-- c65a2dc: Deprecate community package and link to AWS package
-
-## 0.0.98
-
-### Patch Changes
-
-- Updated dependencies [9b2e25a]
-  - @llamaindex/core@0.6.4
-  - @llamaindex/env@0.1.30
-
-## 0.0.97
-
-### Patch Changes
-
-- Updated dependencies [3ee8c83]
-  - @llamaindex/core@0.6.3
-
-## 0.0.96
-
-### Patch Changes
-
-- e9bf442: fix: update the tool call schema for nova
-
-## 0.0.95
-
-### Patch Changes
-
-- 411dcea: Add Nova Premier to AWS Nova models. Add EU endpoints
-
-## 0.0.94
-
-### Patch Changes
-
-- Updated dependencies [9c63f3f]
-  - @llamaindex/core@0.6.2
-
-## 0.0.93
-
-### Patch Changes
-
-- Updated dependencies [1b6f368]
-- Updated dependencies [eaf326e]
-  - @llamaindex/core@0.6.1
-
-## 0.0.92
-
-### Patch Changes
-
-- 1325178: fix: stringify all tool results for anthropic on bedrock
-
-## 0.0.91
-
-### Patch Changes
-
-- 5189b44: fix: add retry handling logic to parser reader and fix lint issues
-- 3fd4cc3: feat: use google's new gen ai library to support multimodal output
-- Updated dependencies [21bebfc]
-- Updated dependencies [93bc0ff]
-- Updated dependencies [91a18e7]
-- Updated dependencies [5189b44]
-  - @llamaindex/core@0.6.0
-
-## 0.0.90
-
-### Patch Changes
-
-- Updated dependencies [40ee761]
-  - @llamaindex/core@0.5.8
-
-## 0.0.89
-
-### Patch Changes
-
-- Updated dependencies [4bac71d]
-  - @llamaindex/core@0.5.7
-
-## 0.0.88
-
-### Patch Changes
-
-- e28c29d: Added Llama 3.3 70B Instruct support
-- Updated dependencies [beb922b]
-  - @llamaindex/env@0.1.29
-  - @llamaindex/core@0.5.6
-
-## 0.0.87
-
-### Patch Changes
-
-- Updated dependencies [5668970]
-  - @llamaindex/core@0.5.5
-
-## 0.0.86
-
-### Patch Changes
-
-- Updated dependencies [ad3c7f1]
-  - @llamaindex/core@0.5.4
-
-## 0.0.85
-
-### Patch Changes
-
-- 1914b52: Added Claude 3.7 Sonnet support
-- Updated dependencies [cb021e7]
-  - @llamaindex/core@0.5.3
-
-## 0.0.84
-
-### Patch Changes
-
-- Updated dependencies [d952e68]
-  - @llamaindex/core@0.5.2
-
-## 0.0.83
-
-### Patch Changes
-
-- Updated dependencies [cc50c9c]
-  - @llamaindex/env@0.1.28
-  - @llamaindex/core@0.5.1
-
-## 0.0.82
-
-### Patch Changes
-
-- Updated dependencies [6a4a737]
-- Updated dependencies [d924c63]
-  - @llamaindex/core@0.5.0
-
-## 0.0.81
-
-### Patch Changes
-
-- 1c908fd: Revert previous release (not working with CJS)
-- Updated dependencies [1c908fd]
-  - @llamaindex/core@0.4.23
-  - @llamaindex/env@0.1.27
-
-## 0.0.80
-
-### Patch Changes
-
-- cb608b5: fix: bundle output incorrect
-- Updated dependencies [cb608b5]
-  - @llamaindex/core@0.4.22
-  - @llamaindex/env@0.1.26
-
-## 0.0.79
-
-### Patch Changes
-
-- Updated dependencies [9456616]
-- Updated dependencies [1931bbc]
-  - @llamaindex/core@0.4.21
-
-## 0.0.78
-
-### Patch Changes
-
-- Updated dependencies [d211b7a]
-  - @llamaindex/core@0.4.20
-
-## 0.0.77
-
-### Patch Changes
-
-- 24caf93: fix: added inference profile mapping for nova models"
-- Updated dependencies [a9b5b99]
-  - @llamaindex/core@0.4.19
-
-## 0.0.76
-
-### Patch Changes
-
-- c1850ee: feat: Amazon Nova support via Bedrock
-- Updated dependencies [b504303]
-- Updated dependencies [e0f6cc3]
-  - @llamaindex/env@0.1.25
-  - @llamaindex/core@0.4.18
-
-## 0.0.75
-
-### Patch Changes
-
-- Updated dependencies [3d1808b]
-  - @llamaindex/core@0.4.17
-
-## 0.0.74
-
-### Patch Changes
-
-- 8be4589: chore: bump version
-- Updated dependencies [8be4589]
-  - @llamaindex/core@0.4.16
-  - @llamaindex/env@0.1.24
-
-## 0.0.73
-
-### Patch Changes
-
-- Updated dependencies [d2b2722]
-  - @llamaindex/env@0.1.23
-  - @llamaindex/core@0.4.15
-
-## 0.0.72
-
-### Patch Changes
-
-- Updated dependencies [969365c]
-  - @llamaindex/env@0.1.22
-  - @llamaindex/core@0.4.14
-
-## 0.0.71
-
-### Patch Changes
-
-- 90d265c: chore: bump version
-- Updated dependencies [90d265c]
-  - @llamaindex/core@0.4.13
-  - @llamaindex/env@0.1.21
-
-## 0.0.70
-
-### Patch Changes
-
-- Updated dependencies [ef4f63d]
-  - @llamaindex/core@0.4.12
-
-## 0.0.69
-
-### Patch Changes
-
-- Updated dependencies [6d22fa2]
-  - @llamaindex/core@0.4.11
-
-## 0.0.68
-
-### Patch Changes
-
-- Updated dependencies [a7b0ac3]
-- Updated dependencies [c69605f]
-  - @llamaindex/core@0.4.10
-
-## 0.0.67
-
-### Patch Changes
-
-- Updated dependencies [7ae6eaa]
-  - @llamaindex/core@0.4.9
-
-## 0.0.66
-
-### Patch Changes
-
-- Updated dependencies [f865c98]
-  - @llamaindex/core@0.4.8
-
-## 0.0.65
-
-### Patch Changes
-
-- Updated dependencies [d89ebe0]
-- Updated dependencies [fd8c882]
-  - @llamaindex/core@0.4.7
-
-## 0.0.64
-
-### Patch Changes
-
-- Updated dependencies [4fc001c]
-  - @llamaindex/env@0.1.20
-  - @llamaindex/core@0.4.6
-
-## 0.0.63
-
-### Patch Changes
-
-- Updated dependencies [ad85bd0]
-  - @llamaindex/core@0.4.5
-  - @llamaindex/env@0.1.19
-
-## 0.0.62
-
-### Patch Changes
-
-- Updated dependencies [a8d3fa6]
-  - @llamaindex/env@0.1.18
-  - @llamaindex/core@0.4.4
-
-## 0.0.61
-
-### Patch Changes
-
-- 487782c: Add missing inference endpoints for Haiku 3.5
-- Updated dependencies [95a5cc6]
-  - @llamaindex/core@0.4.3
-
-## 0.0.60
-
-### Patch Changes
-
-- Updated dependencies [14cc9eb]
-  - @llamaindex/env@0.1.17
-  - @llamaindex/core@0.4.2
-
-## 0.0.59
-
-### Patch Changes
-
-- 47a7c3e: feat: added support for Haiku 3.5 via Bedrock
-
-## 0.0.58
-
-### Patch Changes
-
-- Updated dependencies [9c73f0a]
-  - @llamaindex/core@0.4.1
-
-## 0.0.57
-
-### Patch Changes
-
-- Updated dependencies [359fd33]
-- Updated dependencies [efb7e1b]
-- Updated dependencies [98ba1e7]
-- Updated dependencies [620c63c]
-  - @llamaindex/core@0.4.0
-
-## 0.0.56
-
-### Patch Changes
-
-- Updated dependencies [60b185f]
-  - @llamaindex/core@0.3.7
-
-## 0.0.55
-
-### Patch Changes
-
-- Updated dependencies [691c5bc]
-  - @llamaindex/core@0.3.6
-
-## 0.0.54
-
-### Patch Changes
-
-- Updated dependencies [fa60fc6]
-  - @llamaindex/env@0.1.16
-  - @llamaindex/core@0.3.5
-
-## 0.0.53
-
-### Patch Changes
-
-- Updated dependencies [e2a0876]
-  - @llamaindex/core@0.3.4
-
-## 0.0.52
-
-### Patch Changes
-
-- a5a75f6: feat: added sonnet 3.5 v2
-
-## 0.0.51
-
-### Patch Changes
-
-- Updated dependencies [0493f67]
-  - @llamaindex/core@0.3.3
-
-## 0.0.50
-
-### Patch Changes
-
-- Updated dependencies [4ba2cfe]
-  - @llamaindex/env@0.1.15
-  - @llamaindex/core@0.3.2
-
-## 0.0.49
-
-### Patch Changes
-
-- a75af83: refactor: move some llm and embedding to single package
-- Updated dependencies [ae49ff4]
-- Updated dependencies [a75af83]
-  - @llamaindex/env@0.1.14
-  - @llamaindex/core@0.3.1
-
-## 0.0.48
-
-### Patch Changes
-
-- Updated dependencies [1364e8e]
-- Updated dependencies [96fc69c]
-  - @llamaindex/core@0.3.0
-
-## 0.0.47
-
-### Patch Changes
-
-- Updated dependencies [5f67820]
-  - @llamaindex/core@0.2.12
-
-## 0.0.46
-
-### Patch Changes
-
-- Updated dependencies [ee697fb]
-  - @llamaindex/core@0.2.11
-
-## 0.0.45
-
-### Patch Changes
-
-- Updated dependencies [3489e7d]
-- Updated dependencies [468bda5]
-  - @llamaindex/core@0.2.10
-
-## 0.0.44
-
-### Patch Changes
-
-- Updated dependencies [b17d439]
-  - @llamaindex/core@0.2.9
-
-## 0.0.43
-
-### Patch Changes
-
-- 2774e80: feat: added meta3.2 support via Bedrock including vision, tool call and inference region support
-
-## 0.0.42
-
-### Patch Changes
-
-- df441e2: fix: consoleLogger is missing from `@llamaindex/env`
-- Updated dependencies [df441e2]
-  - @llamaindex/core@0.2.8
-  - @llamaindex/env@0.1.13
-
-## 0.0.41
-
-### Patch Changes
-
-- Updated dependencies [6cce3b1]
-  - @llamaindex/core@0.2.7
-
-## 0.0.40
-
-### Patch Changes
-
-- 50e6b57: feat: add Amazon Bedrock Retriever
-- Updated dependencies [8b7fdba]
-  - @llamaindex/core@0.2.6
-
-## 0.0.39
-
-### Patch Changes
-
-- Updated dependencies [d902cc3]
-  - @llamaindex/core@0.2.5
-
-## 0.0.38
-
-### Patch Changes
-
-- Updated dependencies [b48bcc3]
-  - @llamaindex/core@0.2.4
-  - @llamaindex/env@0.1.12
-
-## 0.0.37
-
-### Patch Changes
-
-- Updated dependencies [2cd1383]
-  - @llamaindex/core@0.2.3
-
-## 0.0.36
-
-### Patch Changes
-
-- Updated dependencies [749b43a]
-  - @llamaindex/core@0.2.2
-
-## 0.0.35
-
-### Patch Changes
-
-- Updated dependencies [ac07e3c]
-- Updated dependencies [70ccb4a]
-- Updated dependencies [1a6137b]
-- Updated dependencies [ac07e3c]
-  - @llamaindex/core@0.2.1
-  - @llamaindex/env@0.1.11
-
-## 0.0.34
-
-### Patch Changes
-
-- Updated dependencies [11feef8]
-  - @llamaindex/core@0.2.0
-
-## 0.0.33
-
-### Patch Changes
-
-- Updated dependencies [711c814]
-  - @llamaindex/core@0.1.12
-
-## 0.0.32
-
-### Patch Changes
-
-- Updated dependencies [4648da6]
-  - @llamaindex/env@0.1.10
-  - @llamaindex/core@0.1.11
-
-## 0.0.31
-
-### Patch Changes
-
-- Updated dependencies [0148354]
-  - @llamaindex/core@0.1.10
-
-## 0.0.30
-
-### Patch Changes
-
-- Updated dependencies [e27e7dd]
-  - @llamaindex/core@0.1.9
-
-## 0.0.29
-
-### Patch Changes
-
-- 58abc57: fix: align version
-- Updated dependencies [58abc57]
-  - @llamaindex/core@0.1.8
-  - @llamaindex/env@0.1.9
-
-## 0.0.28
-
-### Patch Changes
-
-- Updated dependencies [04b2f8e]
-  - @llamaindex/core@0.1.7
-
-## 0.0.27
-
-### Patch Changes
-
-- Updated dependencies [0452af9]
-  - @llamaindex/core@0.1.6
-
-## 0.0.26
-
-### Patch Changes
-
-- 224d507: fix: prevent tool calling getting mixed with conversation
-- 376d29a: feat: added tool calling and agent support for llama3.1 504B
-
-## 0.0.25
-
-### Patch Changes
-
-- Updated dependencies [91d02a4]
-  - @llamaindex/core@0.1.5
-
-## 0.0.24
-
-### Patch Changes
-
-- 3d9a802: feat: added llama 3.1
-- Updated dependencies [15962b3]
-  - @llamaindex/core@0.1.4
-
-## 0.0.23
-
-### Patch Changes
-
-- Updated dependencies [6cf6ae6]
-  - @llamaindex/core@0.1.3
-
-## 0.0.22
-
-### Patch Changes
-
-- Updated dependencies [b974eea]
-  - @llamaindex/core@0.1.2
-
-## 0.0.21
-
-### Patch Changes
-
-- Updated dependencies [b3681bf]
-  - @llamaindex/core@0.1.1
-
-## 0.0.20
-
-### Patch Changes
-
-- 56746c2: fix: llama3 patched to handle empty content (can happen with system) and added max tokens export
-
-## 0.0.19
-
-### Patch Changes
-
-- 16ef5dd: refactor: depends on core pacakge instead of llamaindex
-- Updated dependencies [16ef5dd]
-- Updated dependencies [16ef5dd]
-  - @llamaindex/core@0.1.0
-
-## 0.0.18
-
-### Patch Changes
-
-- llamaindex@0.4.14
-
-## 0.0.17
-
-### Patch Changes
-
-- Updated dependencies [e8f8bea]
-- Updated dependencies [304484b]
-  - llamaindex@0.4.13
-
-## 0.0.16
-
-### Patch Changes
-
-- f326ab8: chore: bump version
-- Updated dependencies [f326ab8]
-  - llamaindex@0.4.12
-
-## 0.0.15
-
-### Patch Changes
-
-- Updated dependencies [8bf5b4a]
-  - llamaindex@0.4.11
-
-## 0.0.14
-
-### Patch Changes
-
-- Updated dependencies [7dce3d2]
-  - llamaindex@0.4.10
-
-## 0.0.13
-
-### Patch Changes
-
-- Updated dependencies [3a96a48]
-  - llamaindex@0.4.9
-
-## 0.0.12
-
-### Patch Changes
-
-- Updated dependencies [83ebdfb]
-  - llamaindex@0.4.8
-
-## 0.0.11
-
-### Patch Changes
-
-- Updated dependencies [41fe871]
-- Updated dependencies [321c39d]
-- Updated dependencies [f7f1af0]
-  - llamaindex@0.4.7
-
-## 0.0.10
-
-### Patch Changes
-
-- Updated dependencies [1feb23b]
-- Updated dependencies [08c55ec]
-  - llamaindex@0.4.6
-
-## 0.0.9
-
-### Patch Changes
-
-- Updated dependencies [6c3e5d0]
-  - llamaindex@0.4.5
-
-## 0.0.8
-
-### Patch Changes
-
-- Updated dependencies [42eb73a]
-  - llamaindex@0.4.4
-
-## 0.0.7
-
-### Patch Changes
-
-- Updated dependencies [2ef62a9]
-  - llamaindex@0.4.3
-
-## 0.0.6
-
-### Patch Changes
-
-- a87a4d1: feat: added tool support calling for Bedrock's Calude and general llm support for agents
-- Updated dependencies [a87a4d1]
-- Updated dependencies [0730140]
-  - llamaindex@0.4.2
-
-## 0.0.5
-
-### Patch Changes
-
-- ed467a9: Add model ids for Anthropic Claude 3.5 Sonnet model on Anthropic and Bedrock
-- Updated dependencies [3c47910]
-- Updated dependencies [ed467a9]
-- Updated dependencies [cba5406]
-  - llamaindex@0.4.1
-
-## 0.0.4
-
-### Patch Changes
-
-- b1a4a74: docs: updated Bedrock Opus region and added a basic README
-- Updated dependencies [436bc41]
-- Updated dependencies [a44e54f]
-- Updated dependencies [a51ed8d]
-- Updated dependencies [d3b635b]
-  - llamaindex@0.4.0
-
-## 0.0.3
-
-### Patch Changes
-
-- Updated dependencies [6bc5bdd]
-- Updated dependencies [bf25ff6]
-- Updated dependencies [e6d6576]
-  - llamaindex@0.3.17
-
-## 0.0.2
-
-### Patch Changes
-
-- 8832669: Community bedrock support added
-- Updated dependencies [11ae926]
-- Updated dependencies [631f000]
-- Updated dependencies [1378ec4]
-- Updated dependencies [6b1ded4]
-- Updated dependencies [4d4bd85]
-- Updated dependencies [24a9d1e]
-- Updated dependencies [45952de]
-- Updated dependencies [54230f0]
-- Updated dependencies [a29d835]
-- Updated dependencies [73819bf]
-  - llamaindex@0.3.16

packages/community/README.md

@@ -1,17 +0,0 @@
-# @llamaindex/community
-
-AWS package for LlamaIndexTS, deprecated, use [@llamaindex/aws](https://www.npmjs.com/package/@llamaindex/aws) instead.
-
-## Current Features:
-
-- Bedrock support for Amazon Nova models Pro, Lite and Micro
-- Bedrock support for the Anthropic Claude Models [usage](https://ts.llamaindex.ai/docs/llamaindex/modules/llms/bedrock) including the latest Sonnet 3.5 v2 and Haiku 3.5
-- Bedrock support for the Meta LLama 2, 3, 3.1 and 3.2 Models [usage](https://ts.llamaindex.ai/docs/llamaindex/modules/llms/bedrock)
-- Meta LLama3.1 405b and Llama3.2 tool call support
-- Meta 3.2 11B and 90B vision support
-- Bedrock support for querying Knowledge Base
-- Bedrock: [Supported Regions and models for cross-region inference](https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html)
-
-## LICENSE
-
-MIT

packages/community/package.json

@@ -1,53 +0,0 @@
-{
-  "name": "@llamaindex/community",
-  "description": "Community package for LlamaIndexTS",
-  "version": "0.0.101",
-  "type": "module",
-  "types": "dist/type/index.d.ts",
-  "main": "dist/cjs/index.js",
-  "exports": {
-    ".": {
-      "import": {
-        "types": "./dist/type/index.d.ts",
-        "default": "./dist/index.js"
-      },
-      "require": {
-        "types": "./dist/type/index.d.ts",
-        "default": "./dist/index.cjs"
-      }
-    },
-    "./llm/bedrock": {
-      "import": {
-        "types": "./dist/type/llm/bedrock.d.ts",
-        "default": "./dist/llm/bedrock/index.js"
-      },
-      "require": {
-        "types": "./dist/type/llm/bedrock.d.ts",
-        "default": "./dist/llm/bedrock/index.cjs"
-      }
-    }
-  },
-  "files": [
-    "dist",
-    "CHANGELOG.md",
-    "!**/*.tsbuildinfo"
-  ],
-  "repository": {
-    "type": "git",
-    "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
-    "directory": "packages/community"
-  },
-  "scripts": {
-    "build": "bunchee",
-    "dev": "bunchee --watch"
-  },
-  "devDependencies": {
-    "@types/node": "^22.9.0"
-  },
-  "dependencies": {
-    "@aws-sdk/client-bedrock-agent-runtime": "^3.706.0",
-    "@aws-sdk/client-bedrock-runtime": "^3.706.0",
-    "@llamaindex/core": "workspace:*",
-    "@llamaindex/env": "workspace:*"
-  }
-}

packages/community/src/index.ts

@@ -1,8 +0,0 @@
-export {
-  BEDROCK_MODELS,
-  BEDROCK_MODEL_MAX_TOKENS,
-  Bedrock,
-  INFERENCE_BEDROCK_MODELS,
-  INFERENCE_TO_BEDROCK_MAP,
-} from "./llm/bedrock/index.js";
-export { AmazonKnowledgeBaseRetriever } from "./retrievers/bedrock.js";

packages/community/src/llm/bedrock/amazon/provider.ts

@@ -1,134 +0,0 @@
-import type {
-  ContentBlockDelta,
-  ConverseOutput,
-  ConverseRequest,
-  ConverseResponse,
-  ConverseStreamOutput,
-  InvokeModelCommandInput,
-  InvokeModelWithResponseStreamCommandInput,
-  ResponseStream,
-} from "@aws-sdk/client-bedrock-runtime";
-import type {
-  BaseTool,
-  ChatMessage,
-  LLMMetadata,
-  ToolCall,
-  ToolCallLLMMessageOptions,
-} from "@llamaindex/core/llms";
-import { toUtf8 } from "../utils";
-
-import { Provider, type BedrockChatStreamResponse } from "../provider";
-import {
-  mapBaseToolsToAmazonTools,
-  mapChatMessagesToAmazonMessages,
-} from "./utils";
-
-export class AmazonProvider extends Provider<ConverseStreamOutput> {
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
-  getResultFromResponse(response: Record<string, any>): ConverseResponse {
-    return JSON.parse(toUtf8(response.body));
-  }
-
-  getToolsFromResponse<ToolContent>(response: ConverseOutput): ToolContent[] {
-    return (
-      response.message?.content
-        ?.filter((item) => item.toolUse)
-        .map(
-          (item) =>
-            ({
-              id: item.toolUse!.toolUseId,
-              name: item.toolUse!.name,
-              input: item.toolUse!.input
-                ? JSON.parse(item.toolUse!.input as string)
-                : "",
-            }) as ToolContent,
-        ) ?? []
-    );
-  }
-
-  getTextFromResponse(response: ConverseResponse): string {
-    const result = this.getResultFromResponse(response);
-    const content = result.output?.message?.content ?? [];
-    return content.map((item) => item.text).join(" ");
-  }
-
-  getTextFromStreamResponse(response: ResponseStream): string {
-    const event: ConverseStreamOutput | undefined =
-      this.getStreamingEventResponse(response);
-    if (!event || !event.contentBlockDelta) return "";
-    const delta: ContentBlockDelta | undefined = event.contentBlockDelta.delta;
-    return delta?.text || "";
-  }
-
-  async *reduceStream(
-    stream: AsyncIterable<ResponseStream>,
-  ): BedrockChatStreamResponse {
-    let toolId: string | undefined = undefined;
-    let toolName: string | undefined = undefined;
-    for await (const response of stream) {
-      const event = this.getStreamingEventResponse(response);
-      const delta = this.getTextFromStreamResponse(response);
-
-      let options: undefined | ToolCallLLMMessageOptions = undefined;
-      if (event?.contentBlockStart && event.contentBlockStart.start?.toolUse) {
-        toolId = event.contentBlockStart.start?.toolUse.toolUseId;
-        toolName = event.contentBlockStart.start?.toolUse.name;
-        continue;
-      }
-      if (
-        toolId &&
-        toolName &&
-        event?.contentBlockDelta?.delta?.toolUse?.input
-      ) {
-        options = {
-          toolCall: [
-            {
-              id: toolId,
-              name: toolName,
-              input: JSON.parse(event?.contentBlockDelta?.delta?.toolUse.input),
-            } as ToolCall,
-          ],
-        };
-        toolId = undefined;
-        toolName = undefined;
-      }
-
-      if (!delta && !options) continue;
-
-      yield {
-        delta: options ? "" : delta,
-        options,
-        raw: response,
-      };
-    }
-  }
-
-  getRequestBody<T extends ChatMessage>(
-    metadata: LLMMetadata,
-    messages: T[],
-    tools: BaseTool[] = [],
-    options: Omit<ConverseRequest, "modelId" | "messages" | "inferenceConfig">,
-  ): InvokeModelCommandInput | InvokeModelWithResponseStreamCommandInput {
-    const request: Omit<ConverseRequest, "modelId"> = {
-      ...options,
-      messages: mapChatMessagesToAmazonMessages(messages),
-      inferenceConfig: {
-        maxTokens: metadata.maxTokens,
-        temperature: metadata.temperature,
-        topP: metadata.topP,
-      },
-    };
-    if (tools.length) {
-      request.toolConfig = {
-        tools: mapBaseToolsToAmazonTools(tools),
-      };
-    }
-
-    return {
-      modelId: metadata.model,
-      contentType: "application/json",
-      accept: "application/json",
-      body: JSON.stringify(request),
-    };
-  }
-}

packages/community/src/llm/bedrock/amazon/types.ts

@@ -1,5 +0,0 @@
-import type { ConverseRequest, Message } from "@aws-sdk/client-bedrock-runtime";
-
-export type AmazonMessages = ConverseRequest["messages"];
-
-export type AmazonMessage = Message;

packages/community/src/llm/bedrock/amazon/utils.ts

@@ -1,141 +0,0 @@
-import type {
-  ImageBlock,
-  ImageFormat,
-  Message,
-  Tool,
-} from "@aws-sdk/client-bedrock-runtime";
-import type {
-  BaseTool,
-  ChatMessage,
-  MessageContentDetail,
-  ToolCallLLMMessageOptions,
-} from "@llamaindex/core/llms";
-import { extractDataUrlComponents } from "../utils";
-
-import type { JSONObject } from "@llamaindex/core/global";
-import { mapMessageContentToMessageContentDetails } from "../../utils";
-import type { AmazonMessage, AmazonMessages } from "./types";
-
-const ACCEPTED_IMAGE_MIME_TYPES = [
-  "image/jpeg",
-  "image/png",
-  "image/webp",
-  "image/gif",
-] as const;
-
-const ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP: Record<
-  (typeof ACCEPTED_IMAGE_MIME_TYPES)[number],
-  ImageFormat
-> = {
-  "image/jpeg": "jpeg",
-  "image/png": "png",
-  "image/webp": "webp",
-  "image/gif": "gif",
-};
-
-export const mapImageContent = (imageUrl: string): ImageBlock => {
-  if (!imageUrl.startsWith("data:"))
-    throw new Error(
-      "For Amazon please only use base64 data url, e.g.: data:image/jpeg;base64,SGVsbG8sIFdvcmxkIQ==",
-    );
-  const { mimeType, base64: data } = extractDataUrlComponents(imageUrl);
-  if (
-    !ACCEPTED_IMAGE_MIME_TYPES.includes(
-      mimeType as keyof typeof ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP,
-    )
-  )
-    throw new Error(
-      `Amazon only accepts the following mimeTypes: ${ACCEPTED_IMAGE_MIME_TYPES.join("\n")}`,
-    );
-
-  return {
-    format:
-      ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP[
-        mimeType as keyof typeof ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP
-      ],
-
-    // @ts-expect-error: there's a mistake in the "@aws-sdk/client-bedrock-runtime" compared to the actual api
-    source: { bytes: data },
-  };
-};
-
-export const mapMessageContentDetailToAmazonContent = <
-  T extends MessageContentDetail,
->(
-  detail: T,
-): Message["content"] => {
-  let content: Message["content"] = [];
-
-  if (detail.type === "text") {
-    content = [{ text: detail.text }];
-  } else if (detail.type === "image_url") {
-    content = [{ image: mapImageContent(detail.image_url.url) }];
-  } else {
-    throw new Error("Unsupported content detail type");
-  }
-  return content;
-};
-
-export const mapChatMessagesToAmazonMessages = <
-  T extends ChatMessage<ToolCallLLMMessageOptions>,
->(
-  messages: T[],
-): AmazonMessages => {
-  return messages.flatMap((msg: T): AmazonMessage[] => {
-    return mapMessageContentToMessageContentDetails(msg.content).map(
-      (detail: MessageContentDetail): AmazonMessage => {
-        if (msg.options && "toolCall" in msg.options) {
-          return {
-            role: "assistant",
-            content: msg.options.toolCall.map((call) => ({
-              toolUse: {
-                toolUseId: call.id,
-                name: call.name,
-                input: call.input as JSONObject,
-              },
-            })),
-          };
-        }
-        if (msg.options && "toolResult" in msg.options) {
-          return {
-            role: "user",
-            content: [
-              {
-                toolResult: {
-                  toolUseId: msg.options.toolResult.id,
-                  content: [
-                    {
-                      text: msg.options.toolResult.result,
-                    },
-                  ],
-                },
-              },
-            ],
-          };
-        }
-
-        return {
-          role: msg.role === "assistant" ? "assistant" : "user",
-          content: mapMessageContentDetailToAmazonContent(detail),
-        };
-      },
-    );
-  });
-};
-
-export const mapBaseToolsToAmazonTools = (tools?: BaseTool[]): Tool[] => {
-  if (!tools) return [];
-  return tools.map((tool: BaseTool) => {
-    const {
-      metadata: { parameters, ...options },
-    } = tool;
-    return {
-      toolSpec: {
-        ...options,
-        inputSchema: {
-          json: parameters,
-        },
-      },
-    } as Tool;
-  });
-};

packages/community/src/llm/bedrock/anthropic/provider.ts

@@ -1,156 +0,0 @@
-import {
-  type InvokeModelCommandInput,
-  type InvokeModelWithResponseStreamCommandInput,
-  ResponseStream,
-} from "@aws-sdk/client-bedrock-runtime";
-import type {
-  BaseTool,
-  ChatMessage,
-  LLMMetadata,
-  PartialToolCall,
-  ToolCall,
-  ToolCallLLMMessageOptions,
-} from "@llamaindex/core/llms";
-import { type BedrockChatStreamResponse, Provider } from "../provider";
-import { toUtf8 } from "../utils";
-import type {
-  AnthropicAdditionalChatOptions,
-  AnthropicNoneStreamingResponse,
-  AnthropicStreamEvent,
-  AnthropicTextContent,
-  ToolBlock,
-} from "./types";
-
-import {
-  mapBaseToolsToAnthropicTools,
-  mapChatMessagesToAnthropicMessages,
-} from "./utils";
-
-export class AnthropicProvider extends Provider<AnthropicStreamEvent> {
-  getResultFromResponse(
-    // eslint-disable-next-line @typescript-eslint/no-explicit-any
-    response: Record<string, any>,
-  ): AnthropicNoneStreamingResponse {
-    return JSON.parse(toUtf8(response.body));
-  }
-
-  getToolsFromResponse<AnthropicToolContent>(
-    // eslint-disable-next-line @typescript-eslint/no-explicit-any
-    response: Record<string, any>,
-  ): AnthropicToolContent[] {
-    const result = this.getResultFromResponse(response);
-    return result.content
-      .filter((item) => item.type === "tool_use")
-      .map((item) => item as AnthropicToolContent);
-  }
-
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
-  getTextFromResponse(response: Record<string, any>): string {
-    const result = this.getResultFromResponse(response);
-    return result.content
-      .filter((item) => item.type === "text")
-      .map((item) => (item as AnthropicTextContent).text)
-      .join(" ");
-  }
-
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
-  getTextFromStreamResponse(response: Record<string, any>): string {
-    const event = this.getStreamingEventResponse(response);
-    if (event?.type === "content_block_delta") {
-      if (event.delta.type === "text_delta") return event.delta.text;
-      if (event.delta.type === "input_json_delta")
-        return event.delta.partial_json;
-    }
-    return "";
-  }
-
-  async *reduceStream(
-    stream: AsyncIterable<ResponseStream>,
-  ): BedrockChatStreamResponse {
-    let collecting = [];
-    let tool: ToolBlock | undefined = undefined;
-    // #TODO this should be broken down into a separate consumer
-    for await (const response of stream) {
-      const delta = this.getTextFromStreamResponse(response);
-      const event = this.getStreamingEventResponse(response);
-      if (
-        event?.type === "content_block_start" &&
-        event.content_block.type === "tool_use"
-      ) {
-        tool = event.content_block;
-        continue;
-      }
-
-      if (
-        event?.type === "content_block_delta" &&
-        event.delta.type === "input_json_delta"
-      ) {
-        collecting.push(event.delta.partial_json);
-      }
-
-      let options: undefined | ToolCallLLMMessageOptions = undefined;
-      if (tool && collecting.length) {
-        const input = collecting.filter((item) => item).join("");
-        // We have all we need to parse the tool_use json
-        if (event?.type === "content_block_stop") {
-          options = {
-            toolCall: [
-              {
-                id: tool.id,
-                name: tool.name,
-                input: JSON.parse(input),
-              } as ToolCall,
-            ],
-          };
-          // reset the collection/tool
-          collecting = [];
-          tool = undefined;
-        } else {
-          options = {
-            toolCall: [
-              {
-                id: tool.id,
-                name: tool.name,
-                input,
-              } as PartialToolCall,
-            ],
-          };
-        }
-      }
-      if (!delta && !options) continue;
-
-      yield {
-        delta: options ? "" : delta,
-        options,
-        raw: response,
-      };
-    }
-  }
-
-  getRequestBody<T extends ChatMessage<ToolCallLLMMessageOptions>>(
-    metadata: LLMMetadata,
-    messages: T[],
-    tools?: BaseTool[],
-    options?: AnthropicAdditionalChatOptions,
-  ): InvokeModelCommandInput | InvokeModelWithResponseStreamCommandInput {
-    const extra: Record<string, unknown> = {};
-    if (options?.toolChoice) {
-      extra["tool_choice"] = options?.toolChoice;
-    }
-    const mapped = mapChatMessagesToAnthropicMessages(messages);
-    return {
-      modelId: metadata.model,
-      contentType: "application/json",
-      accept: "application/json",
-      body: JSON.stringify({
-        anthropic_version: "bedrock-2023-05-31",
-        messages: mapped,
-        tools: mapBaseToolsToAnthropicTools(tools),
-        max_tokens: metadata.maxTokens,
-        temperature: metadata.temperature,
-        top_p: metadata.topP,
-        ...extra,
-      }),
-    };
-  }
-}

packages/community/src/llm/bedrock/anthropic/types.ts

@@ -1,161 +0,0 @@
-import type { ToolMetadata } from "@llamaindex/core/llms";
-import type { InvocationMetrics } from "../types";
-
-export type ToolChoice =
-  | { type: "any" }
-  | { type: "auto" }
-  | { type: "tool"; name: string };
-
-export interface ThinkingConfigDisabled {
-  type: "disabled";
-}
-
-export interface ThinkingConfigEnabled {
-  budget_tokens: number;
-  type: "enabled";
-}
-
-export type AnthropicAdditionalChatOptions = {
-  toolChoice: ToolChoice;
-  thinking?: ThinkingConfigDisabled | ThinkingConfigEnabled;
-};
-
-type Usage = {
-  input_tokens: number;
-  output_tokens: number;
-};
-
-type Message = {
-  id: string;
-  type: string;
-  role: string;
-  content: string[];
-  model: string;
-  stop_reason: string | null;
-  stop_sequence: string | null;
-  usage: Usage;
-};
-
-export type ToolBlock = {
-  id: string;
-  input: unknown;
-  name: string;
-  type: "tool_use";
-};
-
-export type TextBlock = {
-  type: "text";
-  text: string;
-};
-
-type ContentBlockStart = {
-  type: "content_block_start";
-  index: number;
-  content_block: ToolBlock | TextBlock;
-};
-
-type Delta =
-  | {
-      type: "text_delta";
-      text: string;
-    }
-  | {
-      type: "input_json_delta";
-      partial_json: string;
-    };
-
-type ContentBlockDelta = {
-  type: "content_block_delta";
-  index: number;
-  delta: Delta;
-};
-
-type ContentBlockStop = {
-  type: "content_block_stop";
-  index: number;
-};
-
-type MessageDelta = {
-  type: "message_delta";
-  delta: {
-    stop_reason: string;
-    stop_sequence: string | null;
-  };
-  usage: Usage;
-};
-
-export type MessageStop = {
-  type: "message_stop";
-  "amazon-bedrock-invocationMetrics": InvocationMetrics;
-};
-
-export type AnthropicStreamEvent =
-  | { type: "message_start"; message: Message }
-  | ContentBlockStart
-  | ContentBlockDelta
-  | ContentBlockStop
-  | MessageDelta
-  | MessageStop;
-
-export type AnthropicContent =
-  | AnthropicTextContent
-  | AnthropicImageContent
-  | AnthropicToolContent
-  | AnthropicToolResultContent;
-
-export type AnthropicTextContent = {
-  type: "text";
-  text: string;
-};
-
-export type AnthropicToolContent = {
-  type: "tool_use";
-  id: string;
-  name: string;
-  input: Record<string, unknown>;
-};
-
-export type AnthropicToolResultContent = {
-  type: "tool_result";
-  tool_use_id: string;
-  content: string;
-};
-
-export type AnthropicMediaTypes =
-  | "image/jpeg"
-  | "image/png"
-  | "image/webp"
-  | "image/gif";
-
-export type AnthropicImageSource = {
-  type: "base64";
-  media_type: AnthropicMediaTypes;
-  data: string; // base64 encoded image bytes
-};
-
-export type AnthropicImageContent = {
-  type: "image";
-  source: AnthropicImageSource;
-};
-
-export type AnthropicMessage = {
-  role: "user" | "assistant";
-  content: AnthropicContent[];
-};
-
-export type AnthropicNoneStreamingResponse = {
-  id: string;
-  type: "message";
-  role: "assistant";
-  content: AnthropicContent[];
-  model: string;
-  stop_reason: "end_turn" | "max_tokens" | "stop_sequence";
-  stop_sequence?: string;
-  usage: { input_tokens: number; output_tokens: number };
-};
-
-export type AnthropicTool = {
-  name: string;
-  description: string;
-  input_schema: ToolMetadata["parameters"];
-};

packages/community/src/llm/bedrock/anthropic/utils.ts

@@ -1,166 +0,0 @@
-import type { JSONObject } from "@llamaindex/core/global";
-import type {
-  BaseTool,
-  ChatMessage,
-  MessageContent,
-  MessageContentDetail,
-  ToolCallLLMMessageOptions,
-} from "@llamaindex/core/llms";
-import { mapMessageContentToMessageContentDetails } from "../../utils";
-import { extractDataUrlComponents } from "../utils";
-import type {
-  AnthropicContent,
-  AnthropicImageContent,
-  AnthropicMediaTypes,
-  AnthropicMessage,
-  AnthropicTextContent,
-  AnthropicTool,
-} from "./types.js";
-
-const ACCEPTED_IMAGE_MIME_TYPES = [
-  "image/jpeg",
-  "image/png",
-  "image/webp",
-  "image/gif",
-];
-
-export const mergeNeighboringSameRoleMessages = (
-  messages: AnthropicMessage[],
-): AnthropicMessage[] => {
-  return messages.reduce(
-    (result: AnthropicMessage[], current: AnthropicMessage, index: number) => {
-      if (index > 0 && messages[index - 1]!.role === current.role) {
-        result[result.length - 1]!.content = [
-          ...result[result.length - 1]!.content,
-          ...current.content,
-        ];
-      } else {
-        result.push(current);
-      }
-      return result;
-    },
-    [],
-  );
-};
-
-export const mapMessageContentDetailToAnthropicContent = <
-  T extends MessageContentDetail,
->(
-  detail: T,
-): AnthropicContent => {
-  let content: AnthropicContent;
-
-  if (detail.type === "text") {
-    content = mapTextContent(detail.text);
-  } else if (detail.type === "image_url") {
-    content = mapImageContent(detail.image_url.url);
-  } else {
-    throw new Error("Unsupported content detail type");
-  }
-  return content;
-};
-
-export const mapMessageContentToAnthropicContent = <T extends MessageContent>(
-  content: T,
-): AnthropicContent[] => {
-  return mapMessageContentToMessageContentDetails(content).map(
-    mapMessageContentDetailToAnthropicContent,
-  );
-};
-
-export const mapBaseToolsToAnthropicTools = (
-  tools?: BaseTool[],
-): AnthropicTool[] => {
-  if (!tools) return [];
-  return tools.map((tool: BaseTool) => {
-    const {
-      metadata: { parameters, ...options },
-    } = tool;
-    return {
-      ...options,
-      input_schema: parameters,
-    };
-  });
-};
-
-export const mapChatMessagesToAnthropicMessages = <
-  T extends ChatMessage<ToolCallLLMMessageOptions>,
->(
-  messages: T[],
-): AnthropicMessage[] => {
-  const mapped = messages
-    .flatMap((msg: T): AnthropicMessage[] => {
-      if (msg.options && "toolCall" in msg.options) {
-        return [
-          {
-            role: "assistant",
-            content: msg.options.toolCall.map((call) => ({
-              type: "tool_use",
-              id: call.id,
-              name: call.name,
-              input: call.input as JSONObject,
-            })),
-          },
-        ];
-      }
-      if (msg.options && "toolResult" in msg.options) {
-        return [
-          {
-            role: "user",
-            content: [
-              {
-                type: "tool_result",
-                tool_use_id: msg.options.toolResult.id,
-                content: JSON.stringify(msg.options.toolResult.result),
-              },
-            ],
-          },
-        ];
-      }
-      return mapMessageContentToMessageContentDetails(msg.content).map(
-        (detail: MessageContentDetail): AnthropicMessage => {
-          const content = mapMessageContentDetailToAnthropicContent(detail);
-
-          return {
-            role: msg.role === "assistant" ? "assistant" : "user",
-            content: [content],
-          };
-        },
-      );
-    })
-    .filter((message: AnthropicMessage) => {
-      const content = message.content[0]!;
-      if (content.type === "text" && !content.text) return false;
-      if (content.type === "image" && !content.source.data) return false;
-      if (content.type === "image" && message.role === "assistant")
-        return false;
-      return true;
-    });
-
-  return mergeNeighboringSameRoleMessages(mapped);
-};
-
-export const mapTextContent = (text: string): AnthropicTextContent => {
-  return { type: "text", text };
-};
-
-export const mapImageContent = (imageUrl: string): AnthropicImageContent => {
-  if (!imageUrl.startsWith("data:"))
-    throw new Error(
-      "For Anthropic please only use base64 data url, e.g.: data:image/jpeg;base64,SGVsbG8sIFdvcmxkIQ==",
-    );
-  const { mimeType, base64: data } = extractDataUrlComponents(imageUrl);
-  if (!ACCEPTED_IMAGE_MIME_TYPES.includes(mimeType))
-    throw new Error(
-      `Anthropic only accepts the following mimeTypes: ${ACCEPTED_IMAGE_MIME_TYPES.join("\n")}`,
-    );
-
-  return {
-    type: "image",
-    source: {
-      type: "base64",
-      media_type: mimeType as AnthropicMediaTypes,
-      data,
-    },
-  };
-};

packages/community/src/llm/bedrock/index.ts

@@ -1,513 +0,0 @@
-import {
-  BedrockRuntimeClient,
-  type BedrockRuntimeClientConfig,
-  InvokeModelCommand,
-  InvokeModelWithResponseStreamCommand,
-} from "@aws-sdk/client-bedrock-runtime";
-import {
-  type ChatMessage,
-  type ChatResponse,
-  type CompletionResponse,
-  type LLMChatParamsNonStreaming,
-  type LLMChatParamsStreaming,
-  type LLMCompletionParamsNonStreaming,
-  type LLMCompletionParamsStreaming,
-  type LLMMetadata,
-  ToolCallLLM,
-  type ToolCallLLMMessageOptions,
-} from "@llamaindex/core/llms";
-import { streamConverter } from "@llamaindex/core/utils";
-import {
-  type BedrockAdditionalChatOptions,
-  type BedrockChatStreamResponse,
-  Provider,
-} from "./provider";
-
-import { wrapLLMEvent } from "@llamaindex/core/decorator";
-import { mapMessageContentToMessageContentDetails } from "../utils";
-import { AmazonProvider } from "./amazon/provider";
-import { AnthropicProvider } from "./anthropic/provider";
-import { MetaProvider } from "./meta/provider";
-
-// Other providers should go here
-export const PROVIDERS: { [key: string]: Provider } = {
-  anthropic: new AnthropicProvider(),
-  meta: new MetaProvider(),
-  amazon: new AmazonProvider(),
-};
-
-export type BedrockChatParamsStreaming = LLMChatParamsStreaming<
-  BedrockAdditionalChatOptions,
-  ToolCallLLMMessageOptions
->;
-
-export type BedrockChatParamsNonStreaming = LLMChatParamsNonStreaming<
-  BedrockAdditionalChatOptions,
-  ToolCallLLMMessageOptions
->;
-
-export type BedrockChatNonStreamResponse =
-  ChatResponse<ToolCallLLMMessageOptions>;
-
-export const BEDROCK_MODELS = {
-  AMAZON_TITAN_TG1_LARGE: "amazon.titan-tg1-large",
-  AMAZON_TITAN_TEXT_EXPRESS_V1: "amazon.titan-text-express-v1",
-  AI21_J2_GRANDE_INSTRUCT: "ai21.j2-grande-instruct",
-  AI21_J2_JUMBO_INSTRUCT: "ai21.j2-jumbo-instruct",
-  AI21_J2_MID: "ai21.j2-mid",
-  AI21_J2_MID_V1: "ai21.j2-mid-v1",
-  AI21_J2_ULTRA: "ai21.j2-ultra",
-  AI21_J2_ULTRA_V1: "ai21.j2-ultra-v1",
-  COHERE_COMMAND_TEXT_V14: "cohere.command-text-v14",
-  ANTHROPIC_CLAUDE_INSTANT_1: "anthropic.claude-instant-v1",
-  ANTHROPIC_CLAUDE_1: "anthropic.claude-v1", // EOF: No longer supported
-  ANTHROPIC_CLAUDE_2: "anthropic.claude-v2",
-  ANTHROPIC_CLAUDE_2_1: "anthropic.claude-v2:1",
-  ANTHROPIC_CLAUDE_3_SONNET: "anthropic.claude-3-sonnet-20240229-v1:0",
-  ANTHROPIC_CLAUDE_3_HAIKU: "anthropic.claude-3-haiku-20240307-v1:0",
-  ANTHROPIC_CLAUDE_3_OPUS: "anthropic.claude-3-opus-20240229-v1:0",
-  ANTHROPIC_CLAUDE_3_5_SONNET: "anthropic.claude-3-5-sonnet-20240620-v1:0",
-  ANTHROPIC_CLAUDE_3_5_SONNET_V2: "anthropic.claude-3-5-sonnet-20241022-v2:0",
-  ANTHROPIC_CLAUDE_3_5_HAIKU: "anthropic.claude-3-5-haiku-20241022-v1:0",
-  ANTHROPIC_CLAUDE_3_7_SONNET: "anthropic.claude-3-7-sonnet-20250219-v1:0",
-  META_LLAMA2_13B_CHAT: "meta.llama2-13b-chat-v1",
-  META_LLAMA2_70B_CHAT: "meta.llama2-70b-chat-v1",
-  META_LLAMA3_8B_INSTRUCT: "meta.llama3-8b-instruct-v1:0",
-  META_LLAMA3_70B_INSTRUCT: "meta.llama3-70b-instruct-v1:0",
-  META_LLAMA3_1_8B_INSTRUCT: "meta.llama3-1-8b-instruct-v1:0",
-  META_LLAMA3_1_70B_INSTRUCT: "meta.llama3-1-70b-instruct-v1:0",
-  META_LLAMA3_1_405B_INSTRUCT: "meta.llama3-1-405b-instruct-v1:0",
-  META_LLAMA3_2_1B_INSTRUCT: "meta.llama3-2-1b-instruct-v1:0",
-  META_LLAMA3_2_3B_INSTRUCT: "meta.llama3-2-3b-instruct-v1:0",
-  META_LLAMA3_2_11B_INSTRUCT: "meta.llama3-2-11b-instruct-v1:0",
-  META_LLAMA3_2_90B_INSTRUCT: "meta.llama3-2-90b-instruct-v1:0",
-  META_LLAMA3_3_70B_INSTRUCT: "meta.llama3-3-70b-instruct-v1:0",
-  MISTRAL_7B_INSTRUCT: "mistral.mistral-7b-instruct-v0:2",
-  MISTRAL_MIXTRAL_7B_INSTRUCT: "mistral.mixtral-8x7b-instruct-v0:1",
-  MISTRAL_MIXTRAL_LARGE_2402: "mistral.mistral-large-2402-v1:0",
-  AMAZON_NOVA_PREMIER_1: "amazon.nova-premier-v1:0",
-  AMAZON_NOVA_PRO_1: "amazon.nova-pro-v1:0",
-  AMAZON_NOVA_LITE_1: "amazon.nova-lite-v1:0",
-  AMAZON_NOVA_MICRO_1: "amazon.nova-micro-v1:0",
-};
-
-export type BEDROCK_MODELS =
-  (typeof BEDROCK_MODELS)[keyof typeof BEDROCK_MODELS];
-
-export const INFERENCE_BEDROCK_MODELS = {
-  US_ANTHROPIC_CLAUDE_3_HAIKU: "us.anthropic.claude-3-haiku-20240307-v1:0",
-  US_ANTHROPIC_CLAUDE_3_5_HAIKU: "us.anthropic.claude-3-5-haiku-20241022-v1:0",
-  US_ANTHROPIC_CLAUDE_3_OPUS: "us.anthropic.claude-3-opus-20240229-v1:0",
-  US_ANTHROPIC_CLAUDE_3_SONNET: "us.anthropic.claude-3-sonnet-20240229-v1:0",
-  US_ANTHROPIC_CLAUDE_3_5_SONNET:
-    "us.anthropic.claude-3-5-sonnet-20240620-v1:0",
-  US_ANTHROPIC_CLAUDE_3_5_SONNET_V2:
-    "us.anthropic.claude-3-5-sonnet-20241022-v2:0",
-  US_ANTHROPIC_CLAUDE_3_7_SONNET:
-    "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
-  US_META_LLAMA_3_2_1B_INSTRUCT: "us.meta.llama3-2-1b-instruct-v1:0",
-  US_META_LLAMA_3_2_3B_INSTRUCT: "us.meta.llama3-2-3b-instruct-v1:0",
-  US_META_LLAMA_3_2_11B_INSTRUCT: "us.meta.llama3-2-11b-instruct-v1:0",
-  US_META_LLAMA_3_2_90B_INSTRUCT: "us.meta.llama3-2-90b-instruct-v1:0",
-  US_META_LLAMA_3_3_70B_INSTRUCT: "us.meta.llama3-3-70b-instruct-v1:0",
-  US_AMAZON_NOVA_PREMIER_1: "us.amazon.nova-premier-v1:0",
-  US_AMAZON_NOVA_PRO_1: "us.amazon.nova-pro-v1:0",
-  US_AMAZON_NOVA_LITE_1: "us.amazon.nova-lite-v1:0",
-  US_AMAZON_NOVA_MICRO_1: "us.amazon.nova-micro-v1:0",
-
-  EU_ANTHROPIC_CLAUDE_3_HAIKU: "eu.anthropic.claude-3-haiku-20240307-v1:0",
-  EU_ANTHROPIC_CLAUDE_3_5_HAIKU: "eu.anthropic.claude-3-5-haiku-20240307-v1:0",
-  EU_ANTHROPIC_CLAUDE_3_SONNET: "eu.anthropic.claude-3-sonnet-20240229-v1:0",
-  EU_ANTHROPIC_CLAUDE_3_5_SONNET:
-    "eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
-  EU_ANTHROPIC_CLAUDE_3_7_SONNET:
-    "eu.anthropic.claude-3-7-sonnet-20250219-v1:0",
-  EU_META_LLAMA_3_2_1B_INSTRUCT: "eu.meta.llama3-2-1b-instruct-v1:0",
-  EU_META_LLAMA_3_2_3B_INSTRUCT: "eu.meta.llama3-2-3b-instruct-v1:0",
-  EU_AMAZON_NOVA_PREMIER_1: "eu.amazon.nova-premier-v1:0",
-  EU_AMAZON_NOVA_PRO_1: "eu.amazon.nova-pro-v1:0",
-  EU_AMAZON_NOVA_LITE_1: "eu.amazon.nova-lite-v1:0",
-  EU_AMAZON_NOVA_MICRO_1: "eu.amazon.nova-micro-v1:0",
-};
-
-export type INFERENCE_BEDROCK_MODELS =
-  (typeof INFERENCE_BEDROCK_MODELS)[keyof typeof INFERENCE_BEDROCK_MODELS];
-
-export const INFERENCE_TO_BEDROCK_MAP: Record<
-  INFERENCE_BEDROCK_MODELS,
-  BEDROCK_MODELS
-> = {
-  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_HAIKU]:
-    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
-  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_OPUS]:
-    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS,
-  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_SONNET]:
-    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET,
-  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_5_SONNET]:
-    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
-  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_7_SONNET]:
-    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
-  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_5_SONNET_V2]:
-    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
-  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_5_HAIKU]:
-    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU,
-  [INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_2_1B_INSTRUCT]:
-    BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT,
-  [INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_2_3B_INSTRUCT]:
-    BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT,
-  [INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_2_11B_INSTRUCT]:
-    BEDROCK_MODELS.META_LLAMA3_2_11B_INSTRUCT,
-  [INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_2_90B_INSTRUCT]:
-    BEDROCK_MODELS.META_LLAMA3_2_90B_INSTRUCT,
-  [INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_3_70B_INSTRUCT]:
-    BEDROCK_MODELS.META_LLAMA3_3_70B_INSTRUCT,
-
-  [INFERENCE_BEDROCK_MODELS.US_AMAZON_NOVA_PREMIER_1]:
-    BEDROCK_MODELS.AMAZON_NOVA_PREMIER_1,
-  [INFERENCE_BEDROCK_MODELS.US_AMAZON_NOVA_PRO_1]:
-    BEDROCK_MODELS.AMAZON_NOVA_PRO_1,
-  [INFERENCE_BEDROCK_MODELS.US_AMAZON_NOVA_LITE_1]:
-    BEDROCK_MODELS.AMAZON_NOVA_LITE_1,
-  [INFERENCE_BEDROCK_MODELS.US_AMAZON_NOVA_MICRO_1]:
-    BEDROCK_MODELS.AMAZON_NOVA_MICRO_1,
-
-  [INFERENCE_BEDROCK_MODELS.EU_ANTHROPIC_CLAUDE_3_HAIKU]:
-    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
-  [INFERENCE_BEDROCK_MODELS.EU_ANTHROPIC_CLAUDE_3_SONNET]:
-    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET,
-  [INFERENCE_BEDROCK_MODELS.EU_ANTHROPIC_CLAUDE_3_5_SONNET]:
-    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
-  [INFERENCE_BEDROCK_MODELS.EU_ANTHROPIC_CLAUDE_3_7_SONNET]:
-    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
-  [INFERENCE_BEDROCK_MODELS.EU_META_LLAMA_3_2_1B_INSTRUCT]:
-    BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT,
-  [INFERENCE_BEDROCK_MODELS.EU_META_LLAMA_3_2_3B_INSTRUCT]:
-    BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT,
-
-  [INFERENCE_BEDROCK_MODELS.EU_AMAZON_NOVA_PREMIER_1]:
-    BEDROCK_MODELS.AMAZON_NOVA_PREMIER_1,
-  [INFERENCE_BEDROCK_MODELS.EU_AMAZON_NOVA_PRO_1]:
-    BEDROCK_MODELS.AMAZON_NOVA_PRO_1,
-  [INFERENCE_BEDROCK_MODELS.EU_AMAZON_NOVA_LITE_1]:
-    BEDROCK_MODELS.AMAZON_NOVA_LITE_1,
-  [INFERENCE_BEDROCK_MODELS.EU_AMAZON_NOVA_MICRO_1]:
-    BEDROCK_MODELS.AMAZON_NOVA_MICRO_1,
-};
-
-/*
- * Values taken from https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html#model-parameters-claude
- */
-
-const COMPLETION_MODELS = {
-  [BEDROCK_MODELS.AMAZON_TITAN_TG1_LARGE]: 8000,
-  [BEDROCK_MODELS.AMAZON_TITAN_TEXT_EXPRESS_V1]: 8000,
-  [BEDROCK_MODELS.AI21_J2_GRANDE_INSTRUCT]: 8000,
-  [BEDROCK_MODELS.AI21_J2_JUMBO_INSTRUCT]: 8000,
-  [BEDROCK_MODELS.AI21_J2_MID]: 8000,
-  [BEDROCK_MODELS.AI21_J2_MID_V1]: 8000,
-  [BEDROCK_MODELS.AI21_J2_ULTRA]: 8000,
-  [BEDROCK_MODELS.AI21_J2_ULTRA_V1]: 8000,
-  [BEDROCK_MODELS.COHERE_COMMAND_TEXT_V14]: 4096,
-};
-
-const CHAT_ONLY_MODELS = {
-  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_INSTANT_1]: 100000,
-  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_1]: 100000,
-  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_2]: 100000,
-  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_2_1]: 200000,
-  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET]: 200000,
-  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU]: 200000,
-  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS]: 200000,
-  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET]: 200000,
-  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2]: 200000,
-  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU]: 200000,
-  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET]: 200000,
-  [BEDROCK_MODELS.META_LLAMA2_13B_CHAT]: 2048,
-  [BEDROCK_MODELS.META_LLAMA2_70B_CHAT]: 4096,
-  [BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT]: 8192,
-  [BEDROCK_MODELS.META_LLAMA3_70B_INSTRUCT]: 8192,
-  [BEDROCK_MODELS.META_LLAMA3_1_8B_INSTRUCT]: 128000,
-  [BEDROCK_MODELS.META_LLAMA3_1_70B_INSTRUCT]: 128000,
-  [BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT]: 128000,
-  [BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT]: 131000,
-  [BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT]: 131000,
-  [BEDROCK_MODELS.META_LLAMA3_2_11B_INSTRUCT]: 128000,
-  [BEDROCK_MODELS.META_LLAMA3_2_90B_INSTRUCT]: 128000,
-  [BEDROCK_MODELS.META_LLAMA3_3_70B_INSTRUCT]: 128000,
-  [BEDROCK_MODELS.MISTRAL_7B_INSTRUCT]: 32000,
-  [BEDROCK_MODELS.MISTRAL_MIXTRAL_7B_INSTRUCT]: 32000,
-  [BEDROCK_MODELS.MISTRAL_MIXTRAL_LARGE_2402]: 32000,
-  [BEDROCK_MODELS.AMAZON_NOVA_PREMIER_1]: 300000,
-  [BEDROCK_MODELS.AMAZON_NOVA_PRO_1]: 300000,
-  [BEDROCK_MODELS.AMAZON_NOVA_LITE_1]: 300000,
-  [BEDROCK_MODELS.AMAZON_NOVA_MICRO_1]: 130000,
-};
-
-const BEDROCK_FOUNDATION_LLMS = { ...COMPLETION_MODELS, ...CHAT_ONLY_MODELS };
-
-/*
- * Only the following models support streaming as
- * per result of Bedrock.Client.list_foundation_models
- * https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/bedrock/client/list_foundation_models.html
- */
-export const STREAMING_MODELS = new Set([
-  BEDROCK_MODELS.AMAZON_TITAN_TG1_LARGE,
-  BEDROCK_MODELS.AMAZON_TITAN_TEXT_EXPRESS_V1,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_INSTANT_1,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_1,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_2,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_2_1,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
-  BEDROCK_MODELS.META_LLAMA2_13B_CHAT,
-  BEDROCK_MODELS.META_LLAMA2_70B_CHAT,
-  BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_70B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_1_8B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_1_70B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_2_11B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_2_90B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_3_70B_INSTRUCT,
-  BEDROCK_MODELS.MISTRAL_7B_INSTRUCT,
-  BEDROCK_MODELS.MISTRAL_MIXTRAL_7B_INSTRUCT,
-  BEDROCK_MODELS.MISTRAL_MIXTRAL_LARGE_2402,
-  BEDROCK_MODELS.AMAZON_NOVA_PREMIER_1,
-  BEDROCK_MODELS.AMAZON_NOVA_PRO_1,
-  BEDROCK_MODELS.AMAZON_NOVA_LITE_1,
-  BEDROCK_MODELS.AMAZON_NOVA_MICRO_1,
-]);
-
-export const TOOL_CALL_MODELS: BEDROCK_MODELS[] = [
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU,
-  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
-  BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_2_11B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_2_90B_INSTRUCT,
-  BEDROCK_MODELS.META_LLAMA3_3_70B_INSTRUCT,
-  BEDROCK_MODELS.AMAZON_NOVA_PREMIER_1,
-  BEDROCK_MODELS.AMAZON_NOVA_PRO_1,
-  BEDROCK_MODELS.AMAZON_NOVA_LITE_1,
-  BEDROCK_MODELS.AMAZON_NOVA_MICRO_1,
-];
-
-const getProvider = (model: string): Provider => {
-  const providerName = model.split(".")[0];
-  if (!providerName) {
-    throw new Error(`Model ${model} is not supported`);
-  }
-  if (!(providerName in PROVIDERS)) {
-    throw new Error(
-      `Provider ${providerName} for model ${model} is not supported`,
-    );
-  }
-  return PROVIDERS[providerName]!;
-};
-
-export type BedrockModelParams = {
-  model: BEDROCK_MODELS | INFERENCE_BEDROCK_MODELS;
-  temperature?: number;
-  topP?: number;
-  maxTokens?: number;
-};
-
-export const BEDROCK_MODEL_MAX_TOKENS: Partial<Record<BEDROCK_MODELS, number>> =
-  {
-    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET]: 4096,
-    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU]: 4096,
-    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS]: 4096,
-    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET]: 4096,
-    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2]: 8192,
-    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU]: 8192,
-    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET]: 8192,
-    [BEDROCK_MODELS.META_LLAMA2_13B_CHAT]: 2048,
-    [BEDROCK_MODELS.META_LLAMA2_70B_CHAT]: 2048,
-    [BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT]: 2048,
-    [BEDROCK_MODELS.META_LLAMA3_70B_INSTRUCT]: 2048,
-    [BEDROCK_MODELS.META_LLAMA3_1_8B_INSTRUCT]: 2048,
-    [BEDROCK_MODELS.META_LLAMA3_1_70B_INSTRUCT]: 2048,
-    [BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT]: 2048,
-    [BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT]: 2048,
-    [BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT]: 2048,
-    [BEDROCK_MODELS.META_LLAMA3_2_11B_INSTRUCT]: 2048,
-    [BEDROCK_MODELS.META_LLAMA3_2_90B_INSTRUCT]: 2048,
-    [BEDROCK_MODELS.META_LLAMA3_3_70B_INSTRUCT]: 2048,
-  };
-
-const DEFAULT_BEDROCK_PARAMS = {
-  temperature: 0.1,
-  topP: 1,
-  maxTokens: 1024, // required by anthropic
-};
-
-export type BedrockParams = BedrockRuntimeClientConfig & BedrockModelParams;
-
-/**
- * ToolCallLLM for Bedrock
- */
-export class Bedrock extends ToolCallLLM<BedrockAdditionalChatOptions> {
-  private client: BedrockRuntimeClient;
-  protected actualModel: BEDROCK_MODELS | INFERENCE_BEDROCK_MODELS;
-  model: BEDROCK_MODELS;
-  temperature: number;
-  topP: number;
-  maxTokens?: number;
-  provider: Provider;
-  topK?: number;
-
-  // there should be no check for env variables. Bedrock can be authenticated in various ways
-  // AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY and AWS_REGION are the env variables used directly by the sdk
-  constructor({
-    temperature,
-    topP,
-    maxTokens,
-    model,
-    ...params
-  }: BedrockParams) {
-    super();
-    this.actualModel = model;
-    this.model = INFERENCE_TO_BEDROCK_MAP[model] ?? model;
-    this.provider = getProvider(this.model);
-    this.maxTokens = maxTokens ?? DEFAULT_BEDROCK_PARAMS.maxTokens;
-    this.temperature = temperature ?? DEFAULT_BEDROCK_PARAMS.temperature;
-    this.topP = topP ?? DEFAULT_BEDROCK_PARAMS.topP;
-    this.client = new BedrockRuntimeClient(params);
-  }
-
-  get supportToolCall(): boolean {
-    return TOOL_CALL_MODELS.includes(this.model);
-  }
-
-  get metadata(): LLMMetadata {
-    // NOTE, Anthropic supports top_k but LLMMetadata does not
-    return {
-      model: this.model,
-      temperature: this.temperature,
-      topP: this.topP,
-      maxTokens: this.maxTokens,
-      contextWindow: BEDROCK_FOUNDATION_LLMS[this.model] ?? 128000,
-      tokenizer: undefined,
-      structuredOutput: false,
-    };
-  }
-
-  protected async nonStreamChat(
-    params: BedrockChatParamsNonStreaming,
-  ): Promise<BedrockChatNonStreamResponse> {
-    if (!this.supportToolCall && params.tools?.length) {
-      console.warn(`The model "${this.model}" doesn't support ToolCall`);
-    }
-    const input = this.provider.getRequestBody(
-      this.metadata,
-      params.messages,
-      params.tools,
-      params.additionalChatOptions,
-    );
-    const command = new InvokeModelCommand(input);
-    command.input.modelId = this.actualModel;
-
-    const response = await this.client.send(command);
-    let options: ToolCallLLMMessageOptions = {};
-    if (this.supportToolCall) {
-      const tools = this.provider.getToolsFromResponse(response);
-      if (tools.length) {
-        options = { toolCall: tools };
-      }
-    }
-    return {
-      raw: response,
-      message: {
-        role: "assistant",
-        content: this.provider.getTextFromResponse(response),
-        options,
-      },
-    };
-  }
-
-  protected async *streamChat(
-    params: BedrockChatParamsStreaming,
-  ): BedrockChatStreamResponse {
-    if (!STREAMING_MODELS.has(this.model))
-      throw new Error(`The model: ${this.model} does not support streaming`);
-
-    if (!this.supportToolCall && params.tools?.length) {
-      console.warn(`The model "${this.model}" doesn't support ToolCall`);
-    }
-
-    const input = this.provider.getRequestBody(
-      this.metadata,
-      params.messages,
-      params.tools,
-      params.additionalChatOptions,
-    );
-    const command = new InvokeModelWithResponseStreamCommand(input);
-    command.input.modelId = this.actualModel;
-
-    const response = await this.client.send(command);
-    if (response.body) yield* this.provider.reduceStream(response.body);
-  }
-
-  chat(params: BedrockChatParamsStreaming): Promise<BedrockChatStreamResponse>;
-  chat(
-    params: BedrockChatParamsNonStreaming,
-  ): Promise<BedrockChatNonStreamResponse>;
-  @wrapLLMEvent
-  async chat(
-    params: BedrockChatParamsStreaming | BedrockChatParamsNonStreaming,
-  ): Promise<BedrockChatStreamResponse | BedrockChatNonStreamResponse> {
-    if (params.stream) {
-      return this.streamChat(params);
-    }
-    return this.nonStreamChat(params);
-  }
-
-  complete(
-    params: LLMCompletionParamsStreaming,
-  ): Promise<AsyncIterable<CompletionResponse>>;
-  complete(
-    params: LLMCompletionParamsNonStreaming,
-  ): Promise<CompletionResponse>;
-  async complete(
-    params: LLMCompletionParamsStreaming | LLMCompletionParamsNonStreaming,
-  ): Promise<CompletionResponse | AsyncIterable<CompletionResponse>> {
-    const message: ChatMessage = {
-      role: "user",
-      content: mapMessageContentToMessageContentDetails(params.prompt),
-    };
-
-    const input = this.provider.getRequestBody(this.metadata, [message]);
-
-    if (params.stream) {
-      const command = new InvokeModelWithResponseStreamCommand(input);
-      const response = await this.client.send(command);
-      if (response.body)
-        return streamConverter(response.body, (response) => {
-          return {
-            text: this.provider.getTextFromStreamResponse(response),
-            raw: response,
-          };
-        });
-    }
-
-    const command = new InvokeModelCommand(input);
-    const response = await this.client.send(command);
-    return {
-      text: this.provider.getTextFromResponse(response),
-      raw: response,
-    };
-  }
-}

packages/community/src/llm/bedrock/meta/constants.ts

@@ -1,3 +0,0 @@
-export const TOKENS = {
-  TOOL_CALL: "<|python_tag|>",
-};

packages/community/src/llm/bedrock/meta/provider.ts

@@ -1,153 +0,0 @@
-import type {
-  InvokeModelCommandInput,
-  InvokeModelWithResponseStreamCommandInput,
-  ResponseStream,
-} from "@aws-sdk/client-bedrock-runtime";
-import type {
-  BaseTool,
-  ChatMessage,
-  LLMMetadata,
-  ToolCall,
-  ToolCallLLMMessageOptions,
-} from "@llamaindex/core/llms";
-import { toUtf8 } from "../utils";
-import type { MetaNoneStreamingResponse, MetaStreamEvent } from "./types";
-
-import { randomUUID } from "@llamaindex/env";
-import { Provider, type BedrockChatStreamResponse } from "../provider";
-import { TOKENS } from "./constants";
-import {
-  mapChatMessagesToMetaLlama2Messages,
-  mapChatMessagesToMetaLlama3Messages,
-} from "./utils";
-
-export class MetaProvider extends Provider<MetaStreamEvent> {
-  getResultFromResponse(
-    // eslint-disable-next-line @typescript-eslint/no-explicit-any
-    response: Record<string, any>,
-  ): MetaNoneStreamingResponse {
-    return JSON.parse(toUtf8(response.body));
-  }
-
-  getToolsFromResponse<ToolContent>(
-    // eslint-disable-next-line @typescript-eslint/no-explicit-any
-    response: Record<string, any>,
-  ): ToolContent[] {
-    const result = this.getResultFromResponse(response);
-    if (!result.generation.trim().startsWith(TOKENS.TOOL_CALL)) return [];
-    const tool = JSON.parse(
-      result.generation.trim().split(TOKENS.TOOL_CALL)[1]!,
-    );
-    return [
-      {
-        id: randomUUID(),
-        name: tool.name,
-        input: tool.parameters,
-      } as ToolContent,
-    ];
-  }
-
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
-  getTextFromResponse(response: Record<string, any>): string {
-    const result = this.getResultFromResponse(response);
-    if (result.generation.trim().startsWith(TOKENS.TOOL_CALL)) return "";
-    return result.generation;
-  }
-
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
-  getTextFromStreamResponse(response: Record<string, any>): string {
-    const event = this.getStreamingEventResponse(response);
-    if (event?.generation) {
-      return event.generation;
-    }
-    return "";
-  }
-
-  async *reduceStream(
-    stream: AsyncIterable<ResponseStream>,
-  ): BedrockChatStreamResponse {
-    const collecting: string[] = [];
-    let toolId: string | undefined = undefined;
-    for await (const response of stream) {
-      const event = this.getStreamingEventResponse(response);
-      const delta = this.getTextFromStreamResponse(response);
-
-      // odd quirk of llama3.1, start token is \n\n
-      if (
-        !toolId &&
-        !event?.generation.trim() &&
-        event?.generation_token_count === 1 &&
-        event?.prompt_token_count !== null
-      )
-        continue;
-
-      if (delta.startsWith(TOKENS.TOOL_CALL)) {
-        toolId = randomUUID();
-        const parts = delta.split(TOKENS.TOOL_CALL).filter((part) => part);
-        collecting.push(...parts);
-        continue;
-      }
-
-      let options: undefined | ToolCallLLMMessageOptions = undefined;
-      if (toolId && event?.stop_reason === "stop") {
-        if (delta) collecting.push(delta);
-        const tool = JSON.parse(collecting.join(""));
-        options = {
-          toolCall: [
-            {
-              id: toolId,
-              name: tool.name,
-              input: tool.parameters,
-            } as ToolCall,
-          ],
-        };
-      } else if (toolId && !event?.stop_reason) {
-        collecting.push(delta);
-        continue;
-      }
-
-      if (!delta && !options) continue;
-
-      yield {
-        delta: options ? "" : delta,
-        options,
-        raw: response,
-      };
-    }
-  }
-
-  getRequestBody<T extends ChatMessage>(
-    metadata: LLMMetadata,
-    messages: T[],
-    tools: BaseTool[] = [],
-  ): InvokeModelCommandInput | InvokeModelWithResponseStreamCommandInput {
-    let prompt: string = "";
-    let images: string[] = [];
-    if (metadata.model.startsWith("meta.llama3")) {
-      const mapped = mapChatMessagesToMetaLlama3Messages({
-        messages,
-        tools,
-        model: metadata.model,
-      });
-      prompt = mapped.prompt;
-      images = mapped.images;
-    } else if (metadata.model.startsWith("meta.llama2")) {
-      prompt = mapChatMessagesToMetaLlama2Messages(messages);
-    } else {
-      throw new Error(`Meta model ${metadata.model} is not supported`);
-    }
-
-    return {
-      modelId: metadata.model,
-      contentType: "application/json",
-      accept: "application/json",
-      body: JSON.stringify({
-        prompt,
-        images: images.length ? images : undefined,
-        max_gen_len: metadata.maxTokens,
-        temperature: metadata.temperature,
-        top_p: metadata.topP,
-      }),
-    };
-  }
-}

packages/community/src/llm/bedrock/meta/types.ts

@@ -1,21 +0,0 @@
-import type { InvocationMetrics } from "../types";
-
-export type MetaTextContent = string;
-
-export type MetaMessage = {
-  role: "user" | "assistant" | "system" | "ipython";
-  content: MetaTextContent;
-};
-
-type MetaResponse = {
-  generation: string;
-  prompt_token_count: number;
-  generation_token_count: number;
-  stop_reason: "stop" | "length";
-};
-
-export type MetaStreamEvent = MetaResponse & {
-  "amazon-bedrock-invocationMetrics": InvocationMetrics;
-};
-
-export type MetaNoneStreamingResponse = MetaResponse;

packages/community/src/llm/bedrock/meta/utils.ts

@@ -1,273 +0,0 @@
-import type {
-  BaseTool,
-  ChatMessage,
-  LLMMetadata,
-  MessageContentTextDetail,
-  ToolCallLLMMessageOptions,
-} from "@llamaindex/core/llms";
-import { extractDataUrlComponents } from "../utils";
-import { TOKENS } from "./constants";
-import type { MetaMessage } from "./types";
-
-const getToolCallInstructionString = (tool: BaseTool): string => {
-  return `Use the function '${tool.metadata.name}' to '${tool.metadata.description}'`;
-};
-
-const getToolCallParametersString = (tool: BaseTool): string => {
-  return JSON.stringify({
-    name: tool.metadata.name,
-    description: tool.metadata.description,
-    parameters: tool.metadata.parameters
-      ? Object.entries(tool.metadata.parameters.properties).map(
-          ([name, definition]) => ({ [name]: definition }),
-        )
-      : {},
-  });
-};
-
-// ported from https://github.com/meta-llama/llama-agentic-system/blob/main/llama_agentic_system/system_prompt.py
-// NOTE: using json instead of the above xml style tool calling works more reliability
-export const getToolsPrompt_3_1 = (tools?: BaseTool[]) => {
-  if (!tools?.length) return "";
-
-  const customToolParams = tools.map((tool) => {
-    return [
-      getToolCallInstructionString(tool),
-      getToolCallParametersString(tool),
-    ].join("\n\n");
-  });
-
-  return `
-Environment: node
-
-# Tool Instructions
-- Never use ipython, always use javascript in node
-
-Cutting Knowledge Date: December 2023
-Today Date: ${new Date().toLocaleString("en-US", { year: "numeric", month: "long" })} 
-
-You have access to the following functions:
-
-${customToolParams}
-
-Think very carefully before calling functions.
-
-If a you choose to call a function ONLY reply in the following json format:
-{
-  "name": function_name,
-  "parameters": parameters,
-}
-where
-
-{
-  "name": function_name,
-  "parameters": parameters, => a JSON dict with the function argument name as key and function argument value as value.
-}
-
-Here is an example,
-
-{
-  "name": "example_function_name",
-  "parameters": {"example_name": "example_value"}
-}
-
-Reminder:
-- Function calls MUST follow the specified format
-- Required parameters MUST be specified
-- Only call one function at a time
-- Put the entire function call reply on one line
-- Always add your sources when using search results to answer the user query
-  `;
-};
-
-export const getToolsPrompt_3_2 = (tools?: BaseTool[]) => {
-  if (!tools?.length) return "";
-  return `
-You are an expert in composing functions. You are given a question and a set of possible functions.
-Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
-If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
-also point it out. You should only return the function call in tools call sections.
-
-If you decide to invoke any of the function(s), you MUST put it in the format of and start with the token: ${TOKENS.TOOL_CALL}:
-{
-  "name": function_name,
-  "parameters": parameters,
-}
-where
-
-{
-  "name": function_name,
-  "parameters": parameters, => a JSON dict with the function argument name as key and function argument value as value.
-}
-
-Here is an example,
-
-{
-  "name": "example_function_name",
-  "parameters": {"example_name": "example_value"}
-}
-
-Reminder:
-- Function calls MUST follow the specified format
-- Required parameters MUST be specified
-- Only call one function at a time
-- You SHOULD NOT include any other text in the response
-- Put the entire function call reply on one line
-
-Here is a list of functions in JSON format that you can invoke.
-
-${JSON.stringify(tools)}
-`;
-};
-
-export const mapChatRoleToMetaRole = (
-  role: ChatMessage["role"],
-): MetaMessage["role"] => {
-  if (role === "assistant") return "assistant";
-  if (role === "user") return "user";
-  return "system";
-};
-
-export const mapChatMessagesToMetaMessages = <
-  T extends ChatMessage<ToolCallLLMMessageOptions>,
->(
-  messages: T[],
-): MetaMessage[] => {
-  return messages.flatMap((msg) => {
-    if (msg.options && "toolCall" in msg.options) {
-      return msg.options.toolCall.map((call) => ({
-        role: "assistant",
-        content: JSON.stringify({
-          id: call.id,
-          name: call.name,
-          parameters: call.input,
-        }),
-      }));
-    }
-
-    if (msg.options && "toolResult" in msg.options) {
-      return {
-        role: "ipython",
-        content: JSON.stringify(msg.options.toolResult),
-      };
-    }
-
-    let content: string = "";
-    if (typeof msg.content === "string") {
-      content = msg.content;
-    } else if (msg.content.length) {
-      content = (msg.content[0] as MessageContentTextDetail).text;
-    }
-    return {
-      role: mapChatRoleToMetaRole(msg.role),
-      content,
-    };
-  });
-};
-
-/**
- * Documentation at https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3
- */
-export const mapChatMessagesToMetaLlama3Messages = <T extends ChatMessage>({
-  messages,
-  model,
-  tools,
-}: {
-  messages: T[];
-  model: LLMMetadata["model"];
-  tools?: BaseTool[];
-}): { prompt: string; images: string[] } => {
-  const images: string[] = [];
-  const textMessages: T[] = [];
-
-  messages.forEach((message) => {
-    if (Array.isArray(message.content)) {
-      message.content.forEach((content) => {
-        if (content.type === "image_url") {
-          const { base64 } = extractDataUrlComponents(content.image_url.url);
-          images.push(base64);
-        } else {
-          textMessages.push(message);
-        }
-      });
-    } else {
-      textMessages.push(message);
-    }
-  });
-
-  const parts: string[] = [];
-
-  let toolsPrompt = "";
-  if (model.startsWith("meta.llama3-2")) {
-    toolsPrompt = getToolsPrompt_3_2(tools);
-  } else if (model.startsWith("meta.llama3-1")) {
-    toolsPrompt = getToolsPrompt_3_1(tools);
-  }
-  if (toolsPrompt) {
-    parts.push(
-      "<|begin_of_text|>",
-      "<|start_header_id|>system<|end_header_id|>",
-      toolsPrompt,
-      "<|eot_id|>",
-    );
-  }
-
-  const mapped = mapChatMessagesToMetaMessages(messages).map((message) => {
-    return [
-      "<|start_header_id|>",
-      message.role,
-      "<|end_header_id|>",
-      message.content,
-      "<|eot_id|>",
-    ].join("\n");
-  });
-
-  parts.push(
-    "<|begin_of_text|>",
-    ...mapped,
-    "<|start_header_id|>assistant<|end_header_id|>",
-  );
-
-  const prompt = parts.join("\n");
-  return { prompt, images };
-};
-
-/**
- * Documentation at https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-2
- */
-export const mapChatMessagesToMetaLlama2Messages = <T extends ChatMessage>(
-  messages: T[],
-): string => {
-  const mapped = mapChatMessagesToMetaMessages(messages);
-  let output = "<s>";
-  let insideInst = false;
-  let needsStartAgain = false;
-  for (const message of mapped) {
-    if (needsStartAgain) {
-      output += "<s>";
-      needsStartAgain = false;
-    }
-    const text = message.content;
-    if (message.role === "system") {
-      if (!insideInst) {
-        output += "[INST] ";
-        insideInst = true;
-      }
-      output += `<<SYS>>\n${text}\n<</SYS>>\n`;
-    } else if (message.role === "user") {
-      output += text;
-      if (insideInst) {
-        output += " [/INST]";
-        insideInst = false;
-      }
-    } else if (message.role === "assistant") {
-      if (insideInst) {
-        output += " [/INST]";
-        insideInst = false;
-      }
-      output += ` ${text} </s>\n`;
-      needsStartAgain = true;
-    }
-  }
-  return output;
-};