Starlight-compatible docs

.changeset/chatty-numbers-attack.md

@@ -0,0 +1,6 @@
+---
+"@llamaindex/workflow": patch
+"@llamaindex/core": patch
+---
+
+Remove requireContext from tools - better use binding to pass context

.changeset/red-clocks-attack.md

@@ -0,0 +1,5 @@
+---
+"@llamaindex/qdrant": patch
+---
+
+Update implementation to use query instead of search which is being deprecated

.changeset/six-dryers-rescue.md

@@ -0,0 +1,6 @@
+---
+"llamaindex": minor
+"@llamaindex/core": patch
+---
+
+Remove old workflows - use @llamaindex/workflow package

.changeset/wild-parents-look.md

@@ -0,0 +1,6 @@
+---
+"@llamaindex/azure": patch
+"@llamaindex/openai": minor
+---
+
+Move Azure models to azure package

CLAUDE.md

@@ -1,92 +0,0 @@
-# CLAUDE.md
-
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
-
-## Development Commands
-
-This project uses pnpm as the package manager and Turbo for build orchestration:
-
-- `pnpm install` - Install all dependencies
-- `pnpm build` - Build all packages using Turbo
-- `pnpm dev` - Start development mode for all packages
-- `pnpm test` - Run all unit tests
-- `pnpm e2e` - Run end-to-end tests
-- `pnpm lint` - Run ESLint across all packages
-- `pnpm type-check` - Run TypeScript type checking across workspace
-- `pnpm format` - Check code formatting with Prettier
-- `pnpm format:write` - Auto-fix formatting issues
-- `pnpm circular-check` - Check for circular dependencies using madge
-
-For individual package development:
-
-- `turbo run build --filter="@llamaindex/core"` - Build specific package
-- `turbo run test --filter="@llamaindex/core"` - Test specific package
-- Navigate to specific package directory and run `pnpm test` for focused testing
-- `pnpm clean` - Remove all build artifacts and node_modules across workspace
-
-## Architecture Overview
-
-LlamaIndex.TS is a TypeScript data framework for LLM applications organized as a pnpm monorepo with multiple runtime environment support (Node.js, Deno, Bun, Vercel Edge, Cloudflare Workers).
-
-### Package Structure
-
-**Core Packages:**
-
-- `packages/core/` - Abstract base classes and interfaces for all runtime environments
-- `packages/llamaindex/` - Main package that aggregates core functionality
-- `packages/env/` - Environment-specific compatibility layers for different JS runtimes
-
-**Provider Packages (`packages/providers/`):**
-
-- LLM providers: `openai/`, `anthropic/`, `ollama/`, `google/`, `groq/`, etc.
-- Vector stores: `storage/pinecone/`, `storage/chroma/`, `storage/qdrant/`, etc.
-- Embeddings: Various embedding providers integrated within LLM packages
-- Readers: `assemblyai/`, `discord/`, `notion/` for data ingestion
-
-**Specialized Packages:**
-
-- `packages/cloud/` - LlamaCloud integration for managed services
-- `packages/tools/` - Function calling tools and utilities
-- `packages/workflow/` - Agent workflow orchestration
-- `packages/readers/` - File format readers (PDF, DOCX, etc.)
-
-### Key Architectural Patterns
-
-**Runtime Abstraction:** Core functionality is runtime-agnostic, with environment-specific implementations in separate entry points (`index.ts`, `index.edge.ts`, `index.workerd.ts`).
-
-**Provider Pattern:** LLMs, embeddings, and vector stores implement common interfaces from `@llamaindex/core`, allowing easy swapping between providers.
-
-**Modular Design:** Each provider is a separate package to minimize bundle size - users install only what they need.
-
-**Data Flow:** Document → NodeParser → Embedding → VectorStore → Retriever → QueryEngine → Response
-
-### Core Components
-
-- **Agents and Workflows:** Abstractions for building agentic workflows and agents in `packages/workflow`
-- **Chat Engines:** Conversational interfaces in `core/chat-engine/`
-- **Query Engines:** Document querying with retrieval in `core/query-engine/`
-- **Indices:** VectorStoreIndex, SummaryIndex, KeywordTable in `llamaindex/indices/`
-- **Node Parsers:** Text splitting and chunking in `core/node-parser/`
-- **Ingestion Pipeline:** Document processing workflows in `llamaindex/ingestion/`
-- **Storage:** Chat stores, document stores, index stores, and KV stores in `core/storage/`
-
-### Deprecated Components
-
-- **Agents:** ReAct and function calling agents in `core/agent/` and `llamaindex/agent/`
-
-### Testing Structure
-
-- Unit tests in each package's `tests/` directory
-- E2E tests in `e2e/` directory with runtime-specific examples
-- Tests depend on build artifacts, so always run `pnpm build` before testing
-
-### Multi-Runtime Support
-
-The codebase supports multiple JavaScript runtimes through conditional exports and separate entry points. When making changes, consider compatibility across Node.js, Deno, Bun, and edge runtimes.
-
-### Development Notes
-
-- The project uses Husky for git hooks with lint-staged for pre-commit formatting and linting
-- All packages use bunchee for building with dual CJS/ESM support
-- Core package exports are organized as sub-modules (e.g., `@llamaindex/core/llms`, `@llamaindex/core/embeddings`)
-- Always run `pnpm build` before running tests, as tests depend on build artifacts

CONTRIBUTING.md

@@ -25,7 +25,7 @@ Make sure you have Node.js LTS (Long-term Support) installed. You can check your
 
 ```shell
 node -v
-# v22.x.x
+# v20.x.x
 ```
 
 ### Use pnpm
@@ -38,7 +38,6 @@ npm install -g pnpm
 
 ```shell
 pnpm install
-pnpm install -g tsx
 ```
 
 ### Build the packages
@@ -49,56 +48,6 @@ To build all packages, run:
 pnpm build
 ```
 
-### Start Developing
-
-You can launch the package in dev-mode by running:
-
-```shell
-pnpm dev
-```
-
-This will use turbo to run all packages in watch-mode. This means you can make changes and have them automatically built.
-
-If you want to customize what packages are built/watched, you can run turbo directly and adjust the filter:
-
-```shell
-pnpm turbo run dev --filter="./packages/core" --concurrency=100
-```
-
-In another terminal, you can write and run any script needed to quickly test your changes. For example:
-
-```typescript
-import { createMemory, staticBlock } from "@llamaindex/core/memory";
-
-// Create memory with predefined context
-const memory = createMemory({
-  memoryBlocks: [
-    staticBlock({
-      content:
-        "The user is a software engineer who loves TypeScript and LlamaIndex.",
-      messageRole: "system",
-    }),
-  ],
-});
-
-async function main() {
-  const result = await memory.getLLM();
-  console.log(result);
-}
-
-void main().catch(console.error);
-```
-
-And run it with:
-
-```shell
-pnpm exec tsx my_script.ts
-```
-
-This flow allows you to easily test your changes without having to build the entire project.
-
-Once you are happy with your changes, be sure to add tests (and confirm existing tests are passing!).
-
 ### Run tests
 
 #### Unit tests
@@ -143,7 +92,7 @@ Before sending a PR, make sure of the following:
 3. If you have a new feature, add a new example in the `examples` folder.
 4. You have a descriptive changeset for each PR:
 
-### Bumping the versions of packages you've modified
+### Changesets
 
 We use [changesets](https://github.com/changesets/changesets) for managing versions and changelogs. To create a new
 changeset, run in the root folder:
@@ -152,8 +101,6 @@ changeset, run in the root folder:
 pnpm changeset
 ```
 
-You will be prompted to choose what packages need their versions bumped, and what kind of bump (major, minor or patch) is needed. Once you carry out this operation, the bumping will be automatic after the PR is merged.
-
 ## Publishing (maintainers only)
 
 The [Release Github Action](.github/workflows/release.yml) is automatically generating and updating a

apps/next/CHANGELOG.md

@@ -1,208 +1,5 @@
 # @llamaindex/doc
 
-## 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
-
-- 39758ab: Add title to homepage header
-
-## 0.2.33
-
-### Patch Changes
-
-- Updated dependencies [47a7555]
-  - @llamaindex/cloud@4.0.18
-  - llamaindex@0.11.13
-
-## 0.2.32
-
-### Patch Changes
-
-- Updated dependencies [d578889]
-- Updated dependencies [0fcc92f]
-- Updated dependencies [515a8b9]
-  - @llamaindex/core@0.6.13
-  - llamaindex@0.11.12
-  - @llamaindex/cloud@4.0.17
-  - @llamaindex/node-parser@2.0.13
-  - @llamaindex/openai@0.4.7
-  - @llamaindex/readers@3.1.12
-  - @llamaindex/workflow@1.1.13
-
-## 0.2.31
-
-### Patch Changes
-
-- Updated dependencies [7039e1a]
-- Updated dependencies [7039e1a]
-  - llamaindex@0.11.11
-  - @llamaindex/core@0.6.12
-  - @llamaindex/cloud@4.0.16
-  - @llamaindex/node-parser@2.0.12
-  - @llamaindex/openai@0.4.6
-  - @llamaindex/readers@3.1.11
-  - @llamaindex/workflow@1.1.12
-
-## 0.2.30
-
-### Patch Changes
-
-- Updated dependencies [f7ec293]
-  - @llamaindex/workflow@1.1.11
-  - llamaindex@0.11.10
-
-## 0.2.29
-
-### Patch Changes
-
-- Updated dependencies [c5846bd]
-  - @llamaindex/readers@3.1.10
-
-## 0.2.28
-
-### Patch Changes
-
-- Updated dependencies [a89e187]
-- Updated dependencies [62699b7]
-- Updated dependencies [c5b2691]
-- Updated dependencies [d8ac8d3]
-  - @llamaindex/core@0.6.11
-  - @llamaindex/openai@0.4.5
-  - @llamaindex/cloud@4.0.15
-  - llamaindex@0.11.9
-  - @llamaindex/node-parser@2.0.11
-  - @llamaindex/readers@3.1.9
-  - @llamaindex/workflow@1.1.10
-
-## 0.2.27
-
-### Patch Changes
-
-- 8a51c16: Add natural language agent page
-- Updated dependencies [8a51c16]
-- Updated dependencies [1b5af14]
-  - @llamaindex/workflow@1.1.9
-  - @llamaindex/core@0.6.10
-  - llamaindex@0.11.8
-  - @llamaindex/cloud@4.0.14
-  - @llamaindex/node-parser@2.0.10
-  - @llamaindex/openai@0.4.4
-  - @llamaindex/readers@3.1.8
-
-## 0.2.26
-
-### Patch Changes
-
-- a4d394f: fix: correct SimpleDirectoryReader import path in documentation example
-- Updated dependencies [dbd857f]
-- Updated dependencies [3c857f4]
-  - @llamaindex/workflow@1.1.8
-  - llamaindex@0.11.7
-
-## 0.2.25
-
-### Patch Changes
-
-- Updated dependencies [40161fe]
-  - @llamaindex/workflow@1.1.7
-  - llamaindex@0.11.6
-
-## 0.2.24
-
-### Patch Changes
-
-- Updated dependencies [766054b]
-- Updated dependencies [71598f8]
-  - @llamaindex/workflow@1.1.6
-  - @llamaindex/core@0.6.9
-  - llamaindex@0.11.5
-  - @llamaindex/cloud@4.0.13
-  - @llamaindex/node-parser@2.0.9
-  - @llamaindex/openai@0.4.3
-  - @llamaindex/readers@3.1.7
-
-## 0.2.23
-
-### Patch Changes
-
-- Updated dependencies [c927457]
-  - @llamaindex/openai@0.4.2
-  - @llamaindex/core@0.6.8
-  - @llamaindex/cloud@4.0.12
-  - llamaindex@0.11.4
-  - @llamaindex/node-parser@2.0.8
-  - @llamaindex/readers@3.1.6
-  - @llamaindex/workflow@1.1.5
-
-## 0.2.22
-
-### Patch Changes
-
-- Updated dependencies [76ff23d]
-  - @llamaindex/cloud@4.0.11
-  - llamaindex@0.11.3
-
-## 0.2.21
-
-### Patch Changes
-
-- Updated dependencies [59601dd]
-  - @llamaindex/openai@0.4.1
-  - @llamaindex/core@0.6.7
-  - @llamaindex/cloud@4.0.10
-  - llamaindex@0.11.2
-  - @llamaindex/node-parser@2.0.7
-  - @llamaindex/readers@3.1.5
-  - @llamaindex/workflow@1.1.4
-
-## 0.2.20
-
-### Patch Changes
-
-- Updated dependencies [3703f90]
-  - @llamaindex/cloud@4.0.9
-  - llamaindex@0.11.1
-
-## 0.2.19
-
-### Patch Changes
-
-- Updated dependencies [680b529]
-- Updated dependencies [b0cd530]
-- Updated dependencies [361a685]
-- Updated dependencies [3e66ddc]
-  - @llamaindex/workflow@1.1.3
-  - @llamaindex/core@0.6.6
-  - llamaindex@0.11.0
-  - @llamaindex/openai@0.4.0
-  - @llamaindex/cloud@4.0.8
-  - @llamaindex/node-parser@2.0.6
-  - @llamaindex/readers@3.1.4
-
 ## 0.2.18
 
 ### Patch Changes

apps/next/CLAUDE.md

@@ -1,143 +0,0 @@
-# CLAUDE.md
-
-This file provides guidance to Claude Code (claude.ai/code) when working with the LlamaIndex.TS documentation site.
-
-## Application Overview
-
-This is a Next.js documentation site (`@llamaindex/doc`) that serves as the official documentation for LlamaIndex.TS. It's built using Fumadocs, a modern documentation framework, and includes interactive features, API documentation generation, and AI-powered chat functionality.
-
-## Development Commands
-
-From this directory (`apps/next/`):
-
-- `pnpm dev` - Start development server with Turbo
-- `pnpm build` - Build the documentation site (includes `prebuild` step)
-- `pnpm start` - Start production server
-- `pnpm build:docs` - Generate API documentation from TypeScript source
-- `pnpm validate-links` - Validate all internal and external links
-
-Key build process:
-
-1. `prebuild` runs `build:docs` to generate API documentation using TypeDoc
-2. `build` runs Next.js build process
-3. `postbuild` runs post-processing scripts and link validation
-
-## Architecture
-
-### Framework Stack
-
-- **Next.js 15.3** - React framework with App Router
-- **Fumadocs** - Documentation framework with MDX support
-- **React Server Components** - AI chat functionality with server actions
-- **Tailwind CSS** - Styling with custom design system
-- **TypeScript** - Full type safety
-
-### Key Dependencies
-
-- **Fumadocs ecosystem**: `fumadocs-ui`, `fumadocs-mdx`, `fumadocs-core`, `fumadocs-openapi`
-- **AI features**: `ai` package for React Server Components chat
-- **Code features**: Monaco Editor, Shiki syntax highlighting, Twoslash TypeScript integration
-- **UI components**: Radix UI primitives, Framer Motion animations
-- **Content processing**: MDX, remark/rehype plugins, TypeDoc for API generation
-
-### Directory Structure
-
-**Content Management:**
-
-- `src/content/docs/` - MDX documentation files organized by topic
-- `src/content/docs/api/` - Auto-generated API documentation from TypeScript
-- `scripts/` - Build-time documentation generation and validation
-
-**Application Code:**
-
-- `src/app/` - Next.js App Router pages and API routes
-- `src/components/` - Reusable React components including UI library
-- `src/lib/` - Utilities, constants, and configuration
-
-**Configuration:**
-
-- `source.config.ts` - Fumadocs MDX configuration with plugins
-- `next.config.mjs` - Next.js configuration with MDX integration
-- `tailwind.config.mjs` - Tailwind CSS customization
-
-### Key Features
-
-**Documentation Features:**
-
-- MDX-based content with TypeScript code highlighting
-- Auto-generated API documentation from TypeScript source
-- Interactive code examples with Monaco Editor
-- Math equation support with KaTeX
-- Link validation and build-time checks
-
-**Interactive Features:**
-
-- AI-powered chat interface using React Server Components
-- Code demos with live TypeScript execution
-- Interactive UI components and animations
-- Search functionality across all documentation
-
-**Build Process:**
-
-- TypeDoc generates API documentation from workspace packages
-- Custom scripts transform and validate generated content
-- Link checking ensures all internal/external links work
-- Static site generation with 10-minute timeout for large documentation set
-
-### Configuration Files
-
-**source.config.ts**: Defines MDX processing pipeline with:
-
-- Code highlighting themes (Catppuccin)
-- Twoslash TypeScript integration
-- Remark/rehype plugins for enhanced Markdown
-- Content directories including external docs
-
-**next.config.mjs**: Next.js configuration with:
-
-- Extended static generation timeout (10 minutes)
-- Monaco Editor transpilation
-- Server external packages for build optimization
-- Webpack/Turbopack aliases for browser compatibility
-
-### Content Organization
-
-**Documentation Structure:**
-
-- `/docs/llamaindex/` - Core LlamaIndex.TS documentation
-- `/docs/cloud/` - LlamaCloud integration guides
-- `/docs/api/` - Auto-generated TypeScript API reference
-
-**Content Sources:**
-
-- Local MDX files in `src/content/docs/`
-- External docs from `@llamaindex/workflow-docs` package
-- Generated API docs from TypeScript source
-
-### Development Notes
-
-- Documentation content is sourced from multiple locations including external packages
-- API documentation is regenerated on each build from TypeScript source
-- The site uses advanced MDX features including custom transformers and plugins
-- Build process includes comprehensive link validation
-- Large memory allocation needed for TypeDoc generation (`--max-old-space-size=8192`)
-- Chat functionality uses React Server Components with streaming responses
-
-### AI Chat Integration
-
-The documentation includes an AI chat feature that:
-
-- Uses React Server Components for server-side AI processing
-- Integrates with LlamaIndex.TS packages for demonstrations
-- Provides interactive examples and code generation
-- Streams responses for better user experience
-
-### Content Authoring
-
-When adding new documentation:
-
-- Create MDX files in appropriate `src/content/docs/` subdirectories
-- Follow existing content structure and frontmatter conventions
-- Use Fumadocs MDX features like code blocks, callouts, and tabs
-- API documentation is auto-generated - edit TypeScript source comments instead
-- Run `pnpm validate-links` to check all links before publishing

apps/next/README.md

@@ -3,8 +3,6 @@
 This is a Next.js application generated with
 [Create Fumadocs](https://github.com/fuma-nama/fumadocs).
 
-> Note: Before running the development server, make sure to build the whole project first, see [CONTRIBUTING.md](../../CONTRIBUTING.md) for more details.
-
 Run development server:
 
 ```bash

apps/next/components.json

@@ -12,9 +12,9 @@
   },
   "aliases": {
     "components": "@/components",
-    "utils": "@/libs/utils",
+    "utils": "@/lib/utils",
     "ui": "@/components/ui",
-    "lib": "@/libs",
+    "lib": "@/lib",
     "hooks": "@/hooks"
   }
 }

apps/next/next.config.mjs

@@ -15,20 +15,6 @@ const config = {
     "twoslash",
     "typescript",
   ],
-  async redirects() {
-    return [
-      {
-        source: "/docs/chat-ui/:path*.mdx",
-        destination: "/docs/chat-ui/:path*",
-        permanent: true,
-      },
-      {
-        source: "/docs/workflows/:path*.mdx",
-        destination: "/docs/workflows/:path*",
-        permanent: true,
-      },
-    ];
-  },
   turbopack: {
     resolveAlias: {
       fs: { browser: "./fallback.js" },

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.36",
+  "version": "0.2.18",
   "private": true,
   "scripts": {
     "postinstall": "fumadocs-mdx",
@@ -15,17 +15,16 @@
   "dependencies": {
     "@huggingface/transformers": "^3.5.0",
     "@icons-pack/react-simple-icons": "^10.1.0",
-    "@llamaindex/chat-ui-docs": "^0.0.5",
+    "@llama-flow/docs": "0.0.8",
+    "@llamaindex/chat-ui": "0.2.0",
     "@llamaindex/cloud": "workspace:*",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/node-parser": "workspace:*",
     "@llamaindex/openai": "workspace:*",
     "@llamaindex/readers": "workspace:*",
     "@llamaindex/workflow": "workspace:*",
-    "@llamaindex/workflow-docs": "0.1.1",
     "@mdx-js/mdx": "^3.1.0",
     "@monaco-editor/react": "^4.7.0",
-    "@next/third-parties": "^15.3.4",
     "@number-flow/react": "^0.3.4",
     "@radix-ui/react-dialog": "^1.1.2",
     "@radix-ui/react-icons": "^1.3.2",
@@ -35,22 +34,22 @@
     "@radix-ui/react-tooltip": "^1.1.4",
     "@scalar/api-client-react": "^1.1.25",
     "@vercel/functions": "^1.5.0",
-    "ai": "^4.3.17",
+    "ai": "^3.4.33",
     "class-variance-authority": "^0.7.0",
     "clsx": "2.1.1",
     "foxact": "^0.2.41",
     "framer-motion": "^11.11.17",
-    "fumadocs-core": "^15.5.0",
+    "fumadocs-core": "^15.2.7",
     "fumadocs-docgen": "^2.0.0",
-    "fumadocs-mdx": "^11.6.6",
-    "fumadocs-openapi": "^9.0.5",
-    "fumadocs-twoslash": "^3.1.3",
-    "fumadocs-typescript": "^4.0.5",
-    "fumadocs-ui": "^15.5.0",
+    "fumadocs-mdx": "^11.6.0",
+    "fumadocs-openapi": "^8.0.1",
+    "fumadocs-twoslash": "^3.1.1",
+    "fumadocs-typescript": "^4.0.2",
+    "fumadocs-ui": "^15.2.7",
     "hast-util-to-jsx-runtime": "^2.3.2",
     "llamaindex": "workspace:*",
     "lucide-react": "^0.460.0",
-    "next": "^15.3.3",
+    "next": "^15.3.0",
     "next-themes": "^0.4.3",
     "react": "^19.1.0",
     "react-dom": "^19.1.0",
@@ -70,30 +69,30 @@
     "twoslash": "^0.3.1",
     "use-stick-to-bottom": "^1.0.42",
     "web-tree-sitter": "^0.24.4",
-    "zod": "^3.25.76"
+    "zod": "^3.23.8"
   },
   "devDependencies": {
     "@next/env": "^15.3.0",
     "@tailwindcss/postcss": "^4.0.9",
     "@types/mdx": "^2.0.13",
-    "@types/node": "24.0.13",
-    "@types/react": "^19.1.8",
-    "@types/react-dom": "^19.1.6",
+    "@types/node": "22.9.0",
+    "@types/react": "^19.0.10",
+    "@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",
-    "tsx": "^4.20.3",
+    "tailwindcss": "^4.0.9",
+    "tsx": "^4.19.3",
     "typedoc": "0.28.3",
     "typedoc-plugin-markdown": "^4.6.2",
     "typedoc-plugin-merge-modules": " ^7.0.0",
-    "typescript": "^5.8.3"
+    "typescript": "^5.7.3"
   }
 }

apps/next/scripts/validate-links.mts

@@ -13,7 +13,7 @@ const INTERNAL_LINK_REGEX = /(?:(?:\]\(|\bhref=["'])\/docs\/([^")]+))/g;
 // This captures relative links like [text](./path) or ![alt](../images/image.png)
 const RELATIVE_LINK_REGEX = /(?:\]\()(?:\s*)(?:\.\.?)\//g;
 
-const ALLOWED_LINKS = ["/docs/workflows", "/docs/chat-ui"];
+const ALLOWED_LINKS = ["/docs/llamaflow"];
 
 interface LinkValidationResult {
   file: string;

apps/next/source.config.ts

@@ -9,16 +9,7 @@ import rehypeKatex from "rehype-katex";
 import remarkMath from "remark-math";
 
 export const docs = defineDocs({
-  dir: [
-    "./src/content/docs",
-    "./node_modules/@llamaindex/workflow-docs",
-    "./node_modules/@llamaindex/chat-ui-docs",
-    // NOTE: When adding external docs (like chat-ui or workflow-docs above),
-    // make sure to also update:
-    // 1. scripts/validate-links.mts - add to ALLOWED_LINKS array
-    // 2. next.config.mjs - add redirect for .mdx files
-    // 3. src/content/docs/meta.json - add to pages array
-  ],
+  dir: ["./src/content/docs", "./node_modules/@llama-flow/docs"],
   docs: {
     async: true,
   },

apps/next/src/app/(home)/page.tsx

@@ -10,7 +10,7 @@ import { MagicMove } from "@/components/magic-move";
 import { NpmInstall } from "@/components/npm-install";
 import { Supports } from "@/components/supports";
 import { Button } from "@/components/ui/button";
-import { DOCUMENT_URL } from "@/libs/const";
+import { DOCUMENT_URL } from "@/lib/const";
 import { SiStackblitz } from "@icons-pack/react-simple-icons";
 import { Blocks, Bot, Footprints, Terminal } from "lucide-react";
 import Link from "next/link";
@@ -113,8 +113,7 @@ export default function HomePage() {
           description="Truly powerful retrieval-augmented generation applications use agentic techniques, and LlamaIndex.TS makes it easy to build them."
         >
           <CodeBlock
-            code={`import { VectorStoreIndex } from "llamaindex";
-import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
+            code={`import { SimpleDirectoryReader, VectorStoreIndex } from "llamaindex";
 import { openai } from "@llamaindex/openai";
 import { agent } from "@llamaindex/workflow";
 

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

@@ -1,4 +1,4 @@
-import { source } from "@/libs/source";
+import { source } from "@/lib/source";
 import { structure } from "fumadocs-core/mdx-plugins";
 import { createFromSource } from "fumadocs-core/search/server";
 

apps/next/src/app/docs/[[...slug]]/page.tsx

@@ -1,6 +1,7 @@
+import { ChatDemoRSC } from "@/components/demo/chat/rsc/demo";
 import * as demos from "@/components/demo/lazy";
-import { createMetadata, metadataImage } from "@/libs/metadata";
-import { openapi, source } from "@/libs/source";
+import { createMetadata, metadataImage } from "@/lib/metadata";
+import { openapi, source } from "@/lib/source";
 import * as Icons from "@icons-pack/react-simple-icons";
 import { APIPage } from "fumadocs-openapi/ui";
 import { Popup, PopupContent, PopupTrigger } from "fumadocs-twoslash/ui";
@@ -50,6 +51,7 @@ export default async function Page(props: {
             ...Icons,
             ...defaultMdxComponents,
             ...demos,
+            ChatDemoRSC,
             Accordion,
             Accordions,
             APIPage: (props) => <APIPage {...openapi.getAPIPageProps(props)} />,

apps/next/src/app/docs/layout.tsx

@@ -1,5 +1,5 @@
 import { baseOptions } from "@/app/layout.config";
-import { source } from "@/libs/source";
+import { source } from "@/lib/source";
 import "fumadocs-twoslash/twoslash.css";
 import { DocsLayout } from "fumadocs-ui/layouts/docs";
 import type { ReactNode } from "react";

apps/next/src/app/layout.config.tsx

@@ -1,4 +1,4 @@
-import { DOCUMENT_URL } from "@/libs/const";
+import { DOCUMENT_URL } from "@/lib/const";
 import type { BaseLayoutProps } from "fumadocs-ui/layouts/shared";
 import Image from "next/image";
 

apps/next/src/app/layout.tsx

@@ -1,6 +1,5 @@
 import { AIProvider } from "@/actions";
 import { TooltipProvider } from "@/components/ui/tooltip";
-import { GoogleAnalytics } from "@next/third-parties/google";
 import { RootProvider } from "fumadocs-ui/provider";
 import { Inter } from "next/font/google";
 import type { ReactNode } from "react";
@@ -32,9 +31,6 @@ export default function Layout({ children }: { children: ReactNode }) {
           sizes="16x16"
           href="/favicon-16x16.png"
         />
-        <title>
-          LlamaIndex.TS - Build LLM-powered document agents and workflows
-        </title>
       </head>
       <body className="flex min-h-screen flex-col">
         <TooltipProvider>
@@ -43,7 +39,6 @@ export default function Layout({ children }: { children: ReactNode }) {
           </AIProvider>
         </TooltipProvider>
       </body>
-      <GoogleAnalytics gaId="G-NB9B8LW9W5" />
     </html>
   );
 }

apps/next/src/app/og/[...slug]/route.tsx

@@ -1,5 +1,5 @@
 import { generateOGImage } from "@/app/og/[...slug]/og";
-import { metadataImage } from "@/libs/metadata";
+import { metadataImage } from "@/lib/metadata";
 import { type ImageResponse } from "next/og";
 import { readFileSync } from "node:fs";
 

apps/next/src/components/contribution.tsx

@@ -1,6 +1,6 @@
 import ContributorCounter from "@/components/contributor-count";
 import { buttonVariants } from "@/components/ui/button";
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 import { Heart } from "lucide-react";
 import { ReactElement } from "react";
 

apps/next/src/components/contributor-count.tsx

@@ -1,5 +1,5 @@
-import { fetchContributors } from "@/libs/get-contributors";
-import { cn } from "@/libs/utils";
+import { fetchContributors } from "@/lib/get-contributors";
+import { cn } from "@/lib/utils";
 import Image from "next/image";
 import type { HTMLAttributes, ReactElement } from "react";
 

apps/next/src/components/create-app-animation.tsx

@@ -1,5 +1,5 @@
 "use client";
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 import { TerminalIcon } from "lucide-react";
 import {
   Fragment,

apps/next/src/components/demo/chat/api/demo.tsx

@@ -0,0 +1,21 @@
+"use client";
+import {
+  ChatHandler,
+  ChatInput,
+  ChatMessages,
+  ChatSection,
+} from "@llamaindex/chat-ui";
+import { useChat } from "ai/react";
+
+export const ChatDemo = () => {
+  const handler = useChat();
+  return (
+    <ChatSection handler={handler as ChatHandler}>
+      <ChatMessages>
+        <ChatMessages.List className="h-auto max-h-[400px]" />
+        <ChatMessages.Actions />
+      </ChatMessages>
+      <ChatInput />
+    </ChatSection>
+  );
+};

apps/next/src/components/demo/chat/rsc/ai-action.tsx

@@ -0,0 +1,57 @@
+import { Markdown } from "@llamaindex/chat-ui/widgets";
+import { MockLLM } from "@llamaindex/core/utils";
+import { generateId, Message } from "ai";
+import { createAI, createStreamableUI, getMutableAIState } from "ai/rsc";
+import { type ChatMessage, Settings, SimpleChatEngine } from "llamaindex";
+import { ReactNode } from "react";
+
+type ServerState = Message[];
+type FrontendState = Array<Message & { display: ReactNode }>;
+type Actions = {
+  chat: (message: Message) => Promise<Message & { display: ReactNode }>;
+};
+
+Settings.llm = new MockLLM(); // config your LLM here
+
+export const AI = createAI<ServerState, FrontendState, Actions>({
+  initialAIState: [],
+  initialUIState: [],
+  actions: {
+    chat: async (message: Message) => {
+      "use server";
+
+      const aiState = getMutableAIState<typeof AI>();
+      aiState.update((prev) => [...prev, message]);
+
+      const uiStream = createStreamableUI();
+      const chatEngine = new SimpleChatEngine();
+      const assistantMessage: Message = {
+        id: generateId(),
+        role: "assistant",
+        content: "",
+      };
+
+      // run the async function without blocking
+      (async () => {
+        const chatResponse = await chatEngine.chat({
+          stream: true,
+          message: message.content,
+          chatHistory: aiState.get() as ChatMessage[],
+        });
+
+        for await (const chunk of chatResponse) {
+          assistantMessage.content += chunk.delta;
+          uiStream.update(<Markdown content={assistantMessage.content} />);
+        }
+
+        aiState.done([...aiState.get(), assistantMessage]);
+        uiStream.done();
+      })();
+
+      return {
+        ...assistantMessage,
+        display: uiStream.value,
+      };
+    },
+  },
+});

apps/next/src/components/demo/chat/rsc/chat-section.tsx

@@ -0,0 +1,35 @@
+"use client";
+
+import {
+  ChatHandler,
+  ChatInput,
+  ChatMessage,
+  ChatMessages,
+  ChatSection as ChatSectionUI,
+  Message,
+} from "@llamaindex/chat-ui";
+import { useChatRSC } from "./use-chat-rsc";
+
+export const ChatSectionRSC = () => {
+  const handler = useChatRSC();
+  return (
+    <ChatSectionUI handler={handler as ChatHandler}>
+      <ChatMessages>
+        <ChatMessages.List className="h-auto max-h-[400px]">
+          {handler.messages.map((message, index) => (
+            <ChatMessage
+              key={index}
+              message={message as Message}
+              isLast={index === handler.messages.length - 1}
+            >
+              <ChatMessage.Avatar />
+              <ChatMessage.Content>{message.display}</ChatMessage.Content>
+            </ChatMessage>
+          ))}
+          <ChatMessages.Loading />
+        </ChatMessages.List>
+      </ChatMessages>
+      <ChatInput />
+    </ChatSectionUI>
+  );
+};

apps/next/src/components/demo/chat/rsc/demo.tsx

@@ -0,0 +1,8 @@
+import { AI } from "./ai-action";
+import { ChatSectionRSC } from "./chat-section";
+
+export const ChatDemoRSC = () => (
+  <AI>
+    <ChatSectionRSC />
+  </AI>
+);

apps/next/src/components/demo/chat/rsc/use-chat-rsc.tsx

@@ -0,0 +1,41 @@
+"use client";
+
+import { useActions } from "ai/rsc";
+
+import { generateId, Message } from "ai";
+import { useUIState } from "ai/rsc";
+import { useState } from "react";
+import { AI } from "./ai-action";
+
+export function useChatRSC() {
+  const [input, setInput] = useState<string>("");
+  const [isLoading, setIsLoading] = useState<boolean>(false);
+  const [messages, setMessages] = useUIState<typeof AI>();
+  const { chat } = useActions<typeof AI>();
+
+  const append = async (message: Omit<Message, "id">) => {
+    const newMsg: Message = { ...message, id: generateId() };
+
+    setIsLoading(true);
+    try {
+      setMessages((prev) => [...prev, { ...newMsg, display: message.content }]);
+      const assistantMsg = await chat(newMsg);
+      setMessages((prev) => [...prev, assistantMsg]);
+    } catch (error) {
+      console.error(error);
+    }
+    setIsLoading(false);
+    setInput("");
+
+    return message.content;
+  };
+
+  return {
+    input,
+    setInput,
+    isLoading,
+    messages,
+    setMessages,
+    append,
+  };
+}

apps/next/src/components/demo/lazy.ts

@@ -1,6 +1,11 @@
 "use client";
 import dynamic from "next/dynamic";
 
+// lazy load client components
+export const ChatDemo = dynamic(() =>
+  import("@/components/demo/chat/api/demo").then((mod) => mod.ChatDemo),
+);
+
 export const CodeNodeParserDemo = dynamic(() =>
   import("@/components/demo/code-node-parser").then(
     (mod) => mod.CodeNodeParserDemo,

apps/next/src/components/feature.tsx

@@ -1,4 +1,4 @@
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 import { LucideIcon } from "lucide-react";
 import { HTMLAttributes, ReactElement, ReactNode } from "react";
 

apps/next/src/components/magic-move.tsx

@@ -1,6 +1,6 @@
 "use client";
 import { Button } from "@/components/ui/button";
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 import { CodeBlock } from "fumadocs-ui/components/codeblock";
 import { RotateCcw } from "lucide-react";
 import { useTheme } from "next-themes";

apps/next/src/components/message.tsx

@@ -1,6 +1,6 @@
 "use client";
 
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 import Image from "next/image";
 import { ReactNode } from "react";
 import { IconAI, IconUser } from "./ui/icons";

apps/next/src/components/reactbits/rotating-text.tsx

@@ -1,4 +1,4 @@
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 import {
   AnimatePresence,
   motion,

apps/next/src/components/ui/alert.tsx

@@ -1,7 +1,7 @@
 import { cva, type VariantProps } from "class-variance-authority";
 import * as React from "react";
 
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 
 const alertVariants = cva(
   "relative w-full rounded-lg border px-4 py-3 text-sm [&>svg+div]:translate-y-[-3px] [&>svg]:absolute [&>svg]:left-4 [&>svg]:top-4 [&>svg]:text-foreground [&>svg~*]:pl-7",

apps/next/src/components/ui/badge.tsx

@@ -1,7 +1,7 @@
 import { cva, type VariantProps } from "class-variance-authority";
 import * as React from "react";
 
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 
 const badgeVariants = cva(
   "inline-flex items-center rounded-md border px-2.5 py-0.5 text-xs font-semibold transition-colors focus:outline-none focus:ring-2 focus:ring-ring focus:ring-offset-2",

apps/next/src/components/ui/button.tsx

@@ -2,7 +2,7 @@ import { Slot } from "@radix-ui/react-slot";
 import { cva, type VariantProps } from "class-variance-authority";
 import * as React from "react";
 
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 
 const buttonVariants = cva(
   "inline-flex items-center justify-center gap-2 whitespace-nowrap rounded-md text-sm font-medium transition-colors focus-visible:outline-none focus-visible:ring-1 focus-visible:ring-ring disabled:pointer-events-none disabled:opacity-50 [&_svg]:pointer-events-none [&_svg]:size-4 [&_svg]:shrink-0",

apps/next/src/components/ui/dialog.tsx

@@ -4,7 +4,7 @@ import * as DialogPrimitive from "@radix-ui/react-dialog";
 import { Cross2Icon } from "@radix-ui/react-icons";
 import * as React from "react";
 
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 
 const Dialog = DialogPrimitive.Root;
 

apps/next/src/components/ui/icons.tsx

@@ -1,4 +1,4 @@
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 
 export function IconAI({ className, ...props }: React.ComponentProps<"svg">) {
   return (

apps/next/src/components/ui/infinite-slider.tsx

@@ -1,5 +1,5 @@
 "use client";
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 import { animate, motion, useMotionValue } from "framer-motion";
 import { useEffect, useState } from "react";
 import useMeasure from "react-use-measure";

apps/next/src/components/ui/input.tsx

@@ -1,6 +1,6 @@
 import * as React from "react";
 
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 
 export type InputProps = React.InputHTMLAttributes<HTMLInputElement>;
 

apps/next/src/components/ui/label.tsx

@@ -4,7 +4,7 @@ import * as LabelPrimitive from "@radix-ui/react-label";
 import { cva, type VariantProps } from "class-variance-authority";
 import * as React from "react";
 
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 
 const labelVariants = cva(
   "text-sm font-medium leading-none peer-disabled:cursor-not-allowed peer-disabled:opacity-70",

apps/next/src/components/ui/skeleton.tsx

@@ -1,4 +1,4 @@
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 
 function Skeleton({
   className,

apps/next/src/components/ui/slider.tsx

@@ -3,7 +3,7 @@
 import * as SliderPrimitive from "@radix-ui/react-slider";
 import * as React from "react";
 
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 
 const Slider = React.forwardRef<
   React.ElementRef<typeof SliderPrimitive.Root>,

apps/next/src/components/ui/textarea.tsx

@@ -1,6 +1,6 @@
 import * as React from "react";
 
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 
 export type TextareaProps = React.TextareaHTMLAttributes<HTMLTextAreaElement>;
 

apps/next/src/components/ui/tooltip.tsx

@@ -3,7 +3,7 @@
 import * as TooltipPrimitive from "@radix-ui/react-tooltip";
 import * as React from "react";
 
-import { cn } from "@/libs/utils";
+import { cn } from "@/lib/utils";
 
 const TooltipProvider = TooltipPrimitive.Provider;
 

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

@@ -33,7 +33,7 @@ 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); // Baby Llama is called cria
 ```
 
 ### Event Streaming
@@ -44,7 +44,7 @@ Agent Workflows provide a unified interface for event streaming, making it easy
 import { agentToolCallEvent, agentStreamEvent } from "@llamaindex/workflow";
 
 // Get the workflow execution context
-const events = jokeAgent.runStream("Tell me something funny");
+const events = workflow.runStream("Tell me something funny");
 
 // Stream and handle events
 for await (const event of events) {
@@ -112,7 +112,6 @@ const agents = multiAgent({
 const result = await agents.run(
   "Give me a morning greeting with a joke and the weather in San Francisco"
 );
-console.log(result.data.result);
 ```
 
 The workflow will coordinate between agents, allowing them to handle different aspects of the request and hand off tasks when appropriate.

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

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

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

@@ -1,103 +0,0 @@
----
-title: Define workflows using natural language  
----
-
-When working with Workflows, you have to write code to handle an event in the workflow. 
-Often, the logic of the handler is not too complex so that it can be expressed using natural language and executed by an LLM.  
-Besides the instructions, we just need the expected result event of the step, possible tool calls and optionally other events that can be emitted.  
-
-## Usage
-
-Let's take an example of a workflow that generates a joke, gets a critique for it, and then improves it.
-
-### Define the events
-
-First, we define the events for our workflow. We need one for writing the joke, one for critiquing it, and one for the final result:
-
-```typescript
-import { z } from "zod";
-import { zodEvent } from "@llamaindex/workflow";
-
-const writeJokeSchema = z.object({
-  description: z
-    .string()
-    .describe("The topic to write a joke or describe the joke to improve."),
-  writtenJoke: z.optional(z.string()).describe("The written joke."),
-  retriedTimes: z
-    .number()
-    .default(0)
-    .describe(
-      "The retried times for writing the joke. Always increase this from the input retriedTimes.",
-    ),
-});
-
-const critiqueSchema = z.object({
-  joke: z.string().describe("The joke to critique"),
-  retriedTimes: z.number().describe("The retried times for writing the joke."),
-});
-
-const finalResultSchema = z.object({
-  joke: z.string().describe("The joke to critique"),
-  critique: z.string().describe("The critique of the joke"),
-});
-
-const writeJokeEvent = zodEvent(writeJokeSchema, {
-  debugLabel: "writeJokeEvent",
-}); 
-const critiqueEvent = zodEvent(critiqueSchema, {
-  debugLabel: "critiqueEvent",
-}); 
-const finalResultEvent = zodEvent(finalResultSchema, {
-  debugLabel: "finalResultEvent",
-}); 
-```
-
-Note that your natural language workflows the events need to be created by the `zodEvent` function passing the zod schema as an argument. The agent needs the schema of the event data to correctly generate events.  
-Also, we need a `debugLabel` so the LLM can identify the event to emit in the workflow.
-
-### Define the workflow
-
-As usual you first create the workflow:
-
-```typescript
-import { agentHandler, createWorkflow } from "@llamaindex/workflow";
-
-const jokeFlow = createWorkflow();
-```
-
-Then you need to handle the events. For the handlers, instead of code, you're now going to use natural language by calling the `agentHandler` function.
-
-It only requires two parameters:
-- `instructions`: A prompt to guide the agent how to handle the steps.
-- `results`: The output events that the agent should return after handling the step.
-
-Then you will have a simple code to handle the step:
-
-```typescript
-jokeFlow.handle(
-  [writeJokeEvent],
-  agentHandler({
-    instructions: `You are a joke writer. You are given a topic and you need to write a joke about it.`,
-    results: [critiqueEvent],
-  }),
-);
-
-jokeFlow.handle(
-  [critiqueEvent],
-  agentHandler({
-    instructions: `
-You are given a joke and you need to critique it. Follow the following guidelines:
-1. You have maximum 3 times to improve the joke.
-2. If the joke is not good, increase the retriedTimes, describe how to improve the joke and send a writeJokeEvent.
-3. If the joke is good, trigger the finalResultEvent event.
-`,
-    results: [writeJokeEvent, finalResultEvent],
-  }),
-);
-```
-
-For advanced usage, you can add more functionality to `agentHandler` by using these parameters:
-- `events`: A list of additional events that the agent can emit to the workflow. E.g., your agent can emit a `uiEvent` to update the UI during the execution.
-- `tools`: A list of tools that the agent can use to handle the step. E.g., your agent can use a `search` tool to search the web.
-
-You can find more code examples in the [examples](https://github.com/run-llama/LlamaIndexTS/tree/main/examples/agents/natural) folder.

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

@@ -74,21 +74,12 @@ const server = mcp({
   args: ["-y", "@modelcontextprotocol/server-filesystem", "."],
   verbose: true,
 });
-// or by StreamableHTTP transport
+// or by SSE
 const server = mcp({
   url: "http://localhost:8000/mcp",
   verbose: true,
 });
 
-// if your MCP server is not using StreamableHTTP transport, you can also use SSE transport
-// by setting useSSETransport to true.
-// See: https://modelcontextprotocol.io/docs/concepts/transports#server-sent-events-sse-deprecated
-const server = mcp({
-  url: "http://localhost:8000/mcp",
-  useSSETransport: true,
-  verbose: true,
-});
-
 // 3. Get tools from MCP server
 const tools = await server.tools();
 

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

@@ -8,14 +8,11 @@ Workflows are designed to be flexible and can be used to build agents, RAG flows
 
 To use workflows install this package:
 
-```package-install
-npm i @llamaindex/workflow-core
-```
-
-This contains the core functionality for the workflow system. You can read more about the core concepts in the [workflow-core](/docs/workflows) section.
-
-In contrast, the `@llamaindex/workflow` package contains more utiltities, such as prebuilt agents.
-
 ```package-install
 npm i @llamaindex/workflow
 ```
+
+This package is a stable, production-ready version of our [llama-flow](/docs/llamaflow) project. 
+
+While you can still reference the llama-flow documentation for detailed information about the underlying concepts, we recommend using the `@llamaindex/workflow` package for all new projects to ensure stability and long-term availability.
+

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

@@ -1,182 +0,0 @@
----
-title: Memory
-description: Manage conversation history and context with agents
----
-
-## Concept
-
-Memory is a core component of agentic systems. It allows you to store and retrieve information from the past.
-
-In LlamaIndexTS, you can create memory by using the `createMemory` function. This function will return a `Memory` object, which you can then use to store and retrieve information.
-
-As the agent runs, it will make calls to `add()` to store information, and `get()` to retrieve information. 
-
-## Usage
-
-A `Memory` object has both short-term memory (i.e. a FIFO queue of messages) and optionally long-term memory (i.e. extracting information over time).
-
-`get()` always returns all messages stored in the memory. The longer the agent runs, this will exceed the context window of the agent. To avoid this, the agent is using the `getLLM` method to get the last X messages that fit into the context window.
-
-### Configuring Memory for an Agent
-
-Here we're creating a memory with a static block (read more about [memory blocks](#long-term-memory)) that contains some information about the user.
-
-```ts twoslash
-import { openai } from "@llamaindex/openai";
-import { agent } from "@llamaindex/workflow";
-import { createMemory, staticBlock } from "llamaindex";
-
-const llm = openai({ model: "gpt-4.1-mini" });
-
-// Create memory with predefined context
-const memory = createMemory({
-  memoryBlocks: [
-    staticBlock({
-      content:
-        "The user is a software engineer who loves TypeScript and LlamaIndex.",
-    }),
-  ],
-});
-
-// Create an agent with the memory
-const workflow = agent({
-  name: "assistant",
-  llm,
-  memory,
-});
-
-const result = await workflow.run("What is my name?");
-console.log("Response:", result.data.result);
-```
-
-### Using Vercel format
-
-You can also put messages in Vercel format directly to the memory:
-
-```ts
-await memory.add({
-  id: "1",
-  createdAt: new Date(),
-  role: "user",
-  content: "Hello!",
-  options: {
-    parts: [
-      {
-        type: "file",
-        data: "base64...",
-        mimeType: "image/png",
-      },
-    ],
-  },
-});
-```
-
-If you call `get`, messages are usually retrieved in the LlamaIndexTS format (type `ChatMessage`). If you specify the `type` parameter using `get`, you can return the messages in different formats. E.g.: using `type: "vercel"`, you can return the messages in Vercel format:
-
-```ts
-const messages = await memory.get({ type: "vercel" });
-console.log(messages);
-```
-
-## Customizing Memory
-
-### Short-Term Memory
-
-The `Memory` object will store all the messages that are added to the `Memory` object. Unless you call `clear()`, no messages are removed from the memory. This is the short-term memory (usually you will store the memory of one user session there) which is augmented by the long-term memory.
-
-Calling `getLLM` will retrieve messages from long-term memory and ensure that the given `tokenLimit` is not reached. These are the messages that you will sent to the LLM.
-
-For initialization, you call `createMemory` with the following options:
-
-- `tokenLimit`: Maximum tokens for memory retrieval using `getLLM` (default: 30000).
-- `shortTermTokenLimitRatio`: Ratio of tokens for short-term vs long-term memory (default: 0.7)
-- `customAdapters`: Custom message adapters for different message formats. LlamaIndex (`ChatMessageAdapter`) and Vercel (`VercelMessageAdapter`) are built-in adapters.
-- `memoryBlocks`: Memory blocks for long-term storage, see [Long-Term Memory](#long-term-memory)
-
-Example:
-
-```ts
-const memory = createMemory({
-    tokenLimit=40000,
-    shortTermTokenLimitRatio=0.5,
-});
-```
-
-### Long-Term Memory
-
-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 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.
-
-This sounds a bit complicated, but it's actually quite simple. Let's look at an example:
-
-```ts
-import { createMemory, factExtractionBlock, staticBlock } from "llamaindex";
-
-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,
-  }),
-];
-```
-
-Here, we've setup two memory blocks:
-
-- `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.
-- `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.
-
-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.
-
-- `priority=0`: This block will always be kept in memory (`staticBlocks` always have priority 0.)
-- `priority=1, 2, 3, etc`: This determines the order in which memory blocks are truncated when the memory exceeds the token limit, to help the overall short-term memory + long-term memory content be less than or equal to the `tokenLimit`.
-
-Now, let's pass these blocks into the `createMemory` function:
-
-```ts
-const memory = createMemory({
-  tokenLimit: 40000,
-  memoryBlocks: memoryBlocks,
-)
-```
-
-When memory is retrieved (using `getLLM`), the short-term and long-term memories are merged together. The `Memory` object will ensure that the short-term memory + long-term memory content is less than or equal to the `tokenLimit`. If it is longer, messages are retrieved in the following order:
-
-1. StaticMemoryBlock (information always included)
-2. LongTermMemoryBlock (depending on priority)
-3. ShortTermMemoryBlock 
-4. Transient messages
-
-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).
-
-## Persistence with Snapshots
-
-Save and restore memory state:
-
-```ts twoslash
-import { createMemory, loadMemory } from "llamaindex";
-
-const memory = createMemory();
-
-// Add some messages
-await memory.add({ role: "user", content: "Hello!" });
-
-// Create snapshot
-const snapshot = memory.snapshot();
-
-// Later, restore from the snapshot
-const restoredMemory = loadMemory(snapshot);
-```
-
-## Examples
-
-Want to learn more about the Memory class? Check out our example codes in [Github](https://github.com/run-llama/LlamaIndexTS/tree/main/examples/agents/memory).

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

@@ -1,11 +1,4 @@
 {
   "title": "Data",
-  "pages": [
-    "index",
-    "memory",
-    "readers",
-    "data_index",
-    "ingestion_pipeline",
-    "stores"
-  ]
+  "pages": ["index", "readers", "data_index", "ingestion_pipeline", "stores"]
 }

apps/next/src/content/docs/llamaindex/modules/data/stores/vector_stores/supabase.mdx

@@ -28,12 +28,11 @@ embedding vector(1536)
 );
 ```
 
--- Create a function for similarity search with filtering support
+-- Create a function for similarity search
 ```sql
 create function match_documents (
 query_embedding vector(1536),
-match_count int,
-filter jsonb DEFAULT '{}'
+match_count int
 ) returns table (
 id uuid,
 content text,
@@ -43,7 +42,6 @@ similarity float
 )
 language plpgsql
 as $$
-#variable_conflict use_column
 begin
 return query
 select
@@ -53,7 +51,6 @@ metadata,
 embedding,
 1 - (embedding <=> query_embedding) as similarity
 from documents
-where metadata @> filter
 order by embedding <=> query_embedding
 limit match_count;
 end;
@@ -98,7 +95,6 @@ const index = await VectorStoreIndex.fromDocuments(documents, {
 ```ts
 const queryEngine = index.asQueryEngine();
 
-// Basic query without filters
 const response = await queryEngine.query({
   query: "What is in the document?",
 });
@@ -107,32 +103,6 @@ const response = await queryEngine.query({
 console.log(response.toString());
 ```
 
-## Query with filters
-
-You can filter documents based on metadata when querying:
-
-```ts
-import { FilterOperator, MetadataFilters } from "llamaindex";
-
-// Create a filter for documents with author = "Jane Smith"
-const filters: MetadataFilters = {
-  filters: [
-    {
-      key: "author",
-      value: "Jane Smith",
-      operator: FilterOperator.EQ,
-    },
-  ],
-};
-
-// Query with filters
-const filteredResponse = await vectorStore.query({
-  queryEmbedding: embedModel.getQueryEmbedding("What is vector search?"),
-  similarityTopK: 5,
-  filters,
-});
-```
-
 ## Full code
 
 ```ts

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

@@ -2,43 +2,89 @@
 title: Azure OpenAI
 ---
 
-To use Azure OpenAI, you only need to install the `@llamaindex/azure` package:
+To use Azure OpenAI, you only need to set a few environment variables together with the `OpenAI` class.
+
+For example:
+
+## Environment Variables
+
+```
+export AZURE_OPENAI_KEY="<YOUR KEY HERE>"
+export AZURE_OPENAI_ENDPOINT="<YOUR ENDPOINT, see https://learn.microsoft.com/en-us/azure/ai-services/openai/quickstart?tabs=command-line%2Cpython&pivots=rest-api>"
+export AZURE_OPENAI_DEPLOYMENT="gpt-4" # or some other deployment name
+```
 
 ## Installation
 
 ```package-install
-npm i llamaindex @llamaindex/azure
+npm i llamaindex @llamaindex/openai
 ```
 
 ## Usage
 
-The class `AzureOpenAI` is used for setting the LLM and `AzureOpenAIEmbedding` is used for setting the embedding model, e.g.:
-
 ```ts
 import { Settings } from "llamaindex";
-import { AzureOpenAI, AzureOpenAIEmbedding } from "@llamaindex/azure";
+import { OpenAI } from "@llamaindex/openai";
 
-Settings.llm = new AzureOpenAI({ 
-  apiKey: '[key]',
-  deployment: '[model]',
-  apiVersion: '[version]',
-  endpoint: `https://[deployment].openai.azure.com/`, 
-});
-Settings.embedModel = new AzureOpenAIEmbedding({
-  apiKey: '[key]',
-  deployment: '[embedding-model]',
-  apiVersion: '[version]',
-  endpoint: `https://[deployment].openai.azure.com/`, 
+Settings.llm = new OpenAI({ model: "gpt-4", temperature: 0 });
+```
+
+## Load and index documents
+
+For this example, we will use a single document. In a real-world scenario, you would have multiple documents to index.
+
+```ts
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
 });
 ```
 
-Instead of explicitly setting the API key, deployment, version, and endpoint in the constructor, you can use the following environment variables: `AZURE_OPENAI_DEPLOYMENT` for the model deployment name, `AZURE_OPENAI_KEY` for your API key, `AZURE_OPENAI_ENDPOINT` for your Azure endpoint URL, and `AZURE_OPENAI_API_VERSION` for the API version.
+## Full Example
 
-## Examples
+```ts
+import { Document, VectorStoreIndex, Settings } from "llamaindex";
+import { OpenAI } from "@llamaindex/openai";
 
-See the [Azure examples](https://github.com/run-llama/LlamaIndexTS/tree/main/examples/storage/azure) for more examples of how to use Azure OpenAI.
+Settings.llm = new OpenAI({ model: "gpt-4", temperature: 0 });
+
+async function main() {
+  const document = new Document({ text: essay, id_: "essay" });
+
+  // Load and index documents
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // get retriever
+  const retriever = index.asRetriever();
+
+  // Create a query engine
+  const queryEngine = index.asQueryEngine({
+    retriever,
+  });
+
+  const query = "What is the meaning of life?";
+
+  // Query
+  const response = await queryEngine.query({
+    query,
+  });
+
+  // Log the response
+  console.log(response.response);
+}
+```
 
 ## API Reference
 
-- [AzureOpenAI](/docs/api/classes/AzureOpenAI)
-- [AzureOpenAIEmbedding](/docs/api/classes/AzureOpenAIEmbedding)
+- [OpenAI](/docs/api/classes/OpenAI)

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

@@ -11,130 +11,58 @@ npm i llamaindex @llamaindex/google
 ## Usage
 
 ```ts
-import { gemini, GEMINI_MODEL } from "@llamaindex/google";
+import { Gemini, GEMINI_MODEL } from "@llamaindex/google";
 import { Settings } from "llamaindex";
 
-Settings.llm = gemini({
-  model: GEMINI_MODEL.GEMINI_2_0_FLASH,
+Settings.llm = new Gemini({
+  model: GEMINI_MODEL.GEMINI_PRO,
+});
+```
+
+## Usage with Proxy
+
+```ts
+import { Gemini, GEMINI_MODEL } from "@llamaindex/google";
+import { Settings } from "llamaindex";
+
+Settings.llm = new Gemini({
+  model: GEMINI_MODEL.GEMINI_PRO,
+  requestOptions: {
+    baseUrl: <YOUR_PROXY_URL>   // optional, but useful for custom endpoints
+  }
 });
 ```
 
 ### Usage with Vertex AI
 
-To use Gemini via Vertex AI, you can specify the vertex configuration:
+To use Gemini via Vertex AI you can use `GeminiVertexSession`.
+
+GeminiVertexSession accepts the env variables: `GOOGLE_VERTEX_LOCATION` and `GOOGLE_VERTEX_PROJECT`
 
 ```ts
-import { gemini, GEMINI_MODEL } from "@llamaindex/google";
+import { Gemini, GEMINI_MODEL, GeminiVertexSession } from "@llamaindex/google";
 
-const llm = gemini({
-  model: GEMINI_MODEL.GEMINI_2_0_FLASH,
-  vertex: {
-    project: "your-cloud-project",    // required for Vertex AI
-    location: "us-central1",          // required for Vertex AI
-  },
+const gemini = new Gemini({
+  model: GEMINI_MODEL.GEMINI_PRO,
+  session: new GeminiVertexSession({
+    location: "us-central1",      // optional if provided by GOOGLE_VERTEX_LOCATION env variable
+    project: "project1",          // optional if provided by GOOGLE_VERTEX_PROJECT env variable
+    googleAuthOptions: {...},     // optional, but useful for production. It accepts all values from `GoogleAuthOptions`
+  }),
 });
 ```
 
+[GoogleAuthOptions](https://github.com/googleapis/google-auth-library-nodejs/blob/main/src/auth/googleauth.ts)
+
 To authenticate for local development:
 
 ```bash
+npm i @google-cloud/vertexai
 gcloud auth application-default login
 ```
 
 To authenticate for production you'll have to use a [service account](https://cloud.google.com/docs/authentication/). `googleAuthOptions` has `credentials` which might be useful for you.
 
-## Multimodal Usage
-
-Gemini supports multimodal inputs including text, images, audio, and video:
-
-```ts
-import { gemini, GEMINI_MODEL } from "@llamaindex/google";
-import fs from "fs";
-
-const llm = gemini({ model: GEMINI_MODEL.GEMINI_2_0_FLASH });
-
-const result = await llm.chat({
-  messages: [
-    {
-      role: "user",
-      content: [
-        {
-          type: "text",
-          text: "What's in this image?",
-        },
-        {
-          type: "image",
-          data: fs.readFileSync("./image.jpg").toString("base64"),
-          mimeType: "image/jpeg",
-        },
-      ],
-    },
-  ],
-});
-```
-
-## Tool Calling
-
-Gemini supports function calling with tools:
-
-```ts
-import { gemini, GEMINI_MODEL } from "@llamaindex/google";
-import { tool } from "llamaindex";
-import { z } from "zod";
-
-const llm = gemini({ model: GEMINI_MODEL.GEMINI_2_0_FLASH });
-
-const result = await llm.chat({
-  messages: [
-    {
-      content: "What's the weather in Tokyo?",
-      role: "user",
-    },
-  ],
-  tools: [
-    tool({
-      name: "weather",
-      description: "Get the weather",
-      parameters: z.object({
-        location: z.string().describe("The location to get the weather for"),
-      }),
-      execute: ({ location }) => {
-        return `The weather in ${location} is sunny and hot`;
-      },
-    }),
-  ],
-});
-```
-
-## Live API (Real-time Conversations)
-
-For real-time audio/video conversations using [Gemini Live API](https://ai.google.dev/gemini-api/docs/live). 
-
-The Live API is running directly in the frontend. That's why you have to generate an ephemeral key first on the server side and pass it to the frontend.
-
-To use the Live API, make sure to pass `apiVersion: "v1alpha"` to the `httpOptions`.
-
-```ts
-import { gemini, GEMINI_MODEL } from "@llamaindex/google";
-
-// Server-side: Generate ephemeral key
-const serverLlm = gemini({
-  model: GEMINI_MODEL.GEMINI_2_0_FLASH_LIVE,
-  httpOptions: { apiVersion: "v1alpha" },
-});
-const ephemeralKey = await serverLlm.live.getEphemeralKey();
-
-// Client-side: Use ephemeral key for Live API
-const llm = gemini({
-  apiKey: ephemeralKey,
-  model: GEMINI_MODEL.GEMINI_2_0_FLASH_LIVE,
-  voiceName: "Zephyr",
-  httpOptions: { apiVersion: "v1alpha" },
-});
-
-const session = await llm.live.connect();
-```
-
 ## Load and index documents
 
 For this example, we will use a single document. In a real-world scenario, you would have multiple documents to index.
@@ -162,11 +90,11 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import { gemini, GEMINI_MODEL } from "@llamaindex/google";
+import { Gemini, GEMINI_MODEL } from "@llamaindex/google";
 import { Document, VectorStoreIndex, Settings } from "llamaindex";
 
-Settings.llm = gemini({
-  model: GEMINI_MODEL.GEMINI_2_0_FLASH,
+Settings.llm = new Gemini({
+  model: GEMINI_MODEL.GEMINI_PRO,
 });
 
 async function main() {
@@ -176,7 +104,9 @@ async function main() {
   const index = await VectorStoreIndex.fromDocuments([document]);
 
   // Create a query engine
-  const queryEngine = index.asQueryEngine();
+  const queryEngine = index.asQueryEngine({
+    retriever,
+  });
 
   const query = "What is the meaning of life?";
 

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

@@ -378,186 +378,3 @@ async function main() {
 ## API Reference
 
 - [OpenAI](/docs/api/classes/OpenAI)
-
-
-# OpenAI Live LLM
-
-The OpenAI Live LLM integration in LlamaIndex provides real-time chat capabilities with support for audio streaming and tool calling.
-
-## Basic Usage
-
-```typescript
-import { openai } from "@llamaindex/openai";
-import { tool, ModalityType } from "llamaindex";
-
-// Get the ephimeral key on the server 
-const serverllm = openai({
-  apiKey: "your-api-key", 
-  model: "gpt-4o-realtime-preview-2025-06-03",
-});
-
-// Get an ephemeral key 
-// Usually this code is run on the server and the ephemeral key is passed to the
-// client - the ephemeral key can be securely used on the client side
-const ephemeralKey = await serverllm.live.getEphemeralKey();
-
-// Create a client-side LLM instance with the ephemeral key
-const llm = openai({
-  apiKey: ephemeralKey,
-  model: "gpt-4o-realtime-preview-2025-06-03"
-});
-
-// Create a live sessionimport { tool } from "llamaindex";
-const session = await llm.live.connect({
-  systemInstruction: "You are a helpful assistant.",
-});
-
-// Send a message
-session.sendMessage({
-  content: "Hello!",
-  role: "user",
-});
-```
-
-## Tool Integration
-
-Tools are handled server-side, making it simple to pass them to the live session:
-
-```typescript
-// Define your tools
-const weatherTool = tool({
-  name: "weather",
-  description: "Get the weather for a location",
-  parameters: z.object({
-    location: z.string().describe("The location to get weather for"),
-  }),
-  execute: async ({ location }) => {
-    return `The weather in ${location} is sunny`;
-  },
-});
-
-// Create session with tools
-const session = await llm.live.connect({
-  systemInstruction: "You are a helpful assistant.",
-  tools: [weatherTool],
-});
-```
-
-## Audio Support
-
-For audio capabilities:
-
-```typescript
-// Get microphone access
-const userStream = await navigator.mediaDevices.getUserMedia({
-  audio: true,
-});
-
-// Create session with audio
-const session = await llm.live.connect({
-  audioConfig: {
-    stream: userStream,
-    onTrack: (remoteStream) => {
-      // Handle incoming audio
-      audioElement.srcObject = remoteStream;
-    },
-  },
-});
-```
-
-## Event Handling
-
-Listen to events from the session:
-
-```typescript
-for await (const event of session.streamEvents()) {
-  if (liveEvents.open.include(event)) {
-    // Connection established
-    console.log("Connected!");
-  } else if (liveEvents.text.include(event)) {
-    // Received text response
-    console.log("Assistant:", event.text);
-  }
-}
-```
-
-## Capabilities
-
-The OpenAI Live LLM supports:
-
-- Real-time text chat
-- Audio streaming (if configured)
-- Tool calling (server-side execution)
-- Ephemeral key generation for secure sessions
-
-## API Reference
-
-### LiveLLM Methods
-// Get an ephemeral key 
-// Usually this code is run on the server and the ephemeral key is passed to the
-// client - the ephemeral key can be securely used on the client side
-
-#### `connect(config?: LiveConnectConfig)`
-
-Creates a new live session.
-
-```typescript
-interface LiveConnectConfig {
-  systemInstruction?: string;
-  tools?: BaseTool[];
-  audioConfig?: AudioConfig;
-  responseModality?: ModalityType[];
-}
-```
-
-#### `getEphemeralKey()`
-
-Gets a temporary key for the session.
-
-### LiveLLMSession Methods
-
-#### `sendMessage(message: ChatMessage)`
-
-Sends a message to the assistant.
-
-```typescript
-interface ChatMessage {
-  content: string | MessageContentDetail[];
-  role: "user" | "assistant";
-}
-```
-
-#### `disconnect()`
-
-Closes the session and cleans up resources.
-
-## Error Handling
-
-```typescript
-try {
-  const session = await llm.live.connect();
-} catch (error) {
-  if (error instanceof Error) {
-    console.error("Connection failed:", error.message);
-  }
-}
-```
-
-## Best Practices
-
-1. **Tool Definition**
-
-   - Keep tool implementations server-side
-   - Use clear descriptions for tools
-   - Handle tool errors gracefully
-
-2. **Session Management**
-
-   - Always disconnect sessions when done
-   - Clean up audio resources
-   - Handle reconnection scenarios
-
-3. **Security**
-   - Use ephemeral keys for sessions
-   - Validate tool inputs
-   - Secure API key handling

apps/next/src/content/docs/llamaindex/modules/rag/retriever.mdx

@@ -11,7 +11,6 @@ A retriever in LlamaIndex is what is used to fetch `Node`s from an index using a
 - [KeywordTableLLMRetriever](/docs/api/classes/KeywordTableLLMRetriever) uses an LLM to extract keywords from the query and retrieve relevant nodes based on keyword matches.
 - [KeywordTableSimpleRetriever](/docs/api/classes/KeywordTableSimpleRetriever) uses a basic frequency-based approach to extract keywords and retrieve nodes.
 - [KeywordTableRAKERetriever](/docs/api/classes/KeywordTableRAKERetriever) uses the RAKE (Rapid Automatic Keyword Extraction) algorithm to extract keywords from the query, focusing on co-occurrence and context for keyword-based retrieval.
-- [Bm25Retriever](/docs/api/classes/Bm25Retriever) uses the BM25 algorithm to extract keywords from the query and retrieve relevant nodes based on keyword matches.
 
 ```typescript
 const retriever = vectorIndex.asRetriever({

apps/next/src/content/docs/llamaindex/modules/ui/chat.mdx

@@ -0,0 +1,44 @@
+---
+title: Using API Route
+description: Chat interface for your LlamaIndexTS application using API Route
+---
+
+Using [chat-ui](https://github.com/run-llama/chat-ui), it's easy to add a chat interface to your LlamaIndexTS application.
+You just need to create an API route that provides an `api/chat` endpoint and a chat component to consume the API.
+
+## API route
+
+As an example, this is an API route for the Next.js App Router. Copy the following code into your `app/api/chat/route.ts` file to get started:
+
+```json doc-gen:file
+{
+  "file": "./src/app/api/chat/route.ts",
+	"codeblock": true
+}
+```
+
+## Chat UI
+
+This is the simplest way to add a chat interface to your application. Copy the following code into your application to consume the API:
+
+```json doc-gen:file
+{
+  "file": "./src/components/demo/chat/api/demo.tsx",
+	"codeblock": true
+}
+```
+
+## Try it out ⬇️
+
+Combining both, you're getting a fully functional chat interface:
+
+<ChatDemo />
+
+
+## Next Steps
+
+The steps above are the bare minimum to get a chat interface working. From here, you can go two ways:
+
+1. Use [create-llama](https://github.com/run-llama/create-llama) to scaffold a new LlamaIndexTS project including complex API routes and chat interfaces or
+2. Learn more about [chat-ui](https://github.com/run-llama/chat-ui) and [LlamaIndexTS](https://github.com/run-llama/llamaindex-ts) to customize the chat interface and API routes to your needs.
+

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

@@ -1,8 +0,0 @@
----
-title: Using @llamaindex/chat-ui
-description: Chat UI components for your LlamaIndexTS application
----
-
-@llamaindex/chat-ui is a library that provides a set of components for building chat user interfaces. It is built on top of [Shadcn UI](https://ui.shadcn.com).
-
-Check out our [chat-ui](/docs/chat-ui) documentation or try running examples on the [ui.llamaindex.ai](https://ui.llamaindex.ai) website.

apps/next/src/content/docs/llamaindex/modules/ui/install.mdx

@@ -0,0 +1,22 @@
+---
+title: Install @llamaindex/chat
+description: Chat interface for your LlamaIndexTS application
+---
+
+## Quick Start
+
+You can quickly add a chatbot to your project by using Shadcn CLI command:
+
+```sh
+npx shadcn@latest add https://ui.llamaindex.ai/r/chat.json
+```
+
+## Manual Installation
+
+To install the package, run the following command in your project directory:
+
+```sh
+npm i @llamaindex/chat-ui
+```
+
+For more information, check out the [github.comrun-llama/chat-ui](https://github.com/run-llama/chat-ui)

apps/next/src/content/docs/llamaindex/modules/ui/llamaindex-server.mdx

@@ -9,11 +9,161 @@ LlamaIndexServer is a Next.js-based application that allows you to quickly launc
 
 ## Features
 
-- Add a sophisticated chatbot UI to your LlamaIndex workflow
-- Edit code and document artifacts in an OpenAI Canvas-style UI
-- Extendable UI components for events and headers
+- Serving a workflow as a chatbot
 - Built on Next.js for high performance and easy API development
+- Optional built-in chat UI with extendable UI components
+- Prebuilt development code
+
+## Installation
+
+```package-install
+npm i @llamaindex/server
+```
 
 ## Quick Start
 
-Check the latest information on the NPM package page: https://www.npmjs.com/package/@llamaindex/server
+Create an `index.ts` file and add the following code:
+
+```ts
+import { LlamaIndexServer } from "@llamaindex/server";
+import { wiki } from "@llamaindex/tools"; // or any other tool
+
+const createWorkflow = () => agent({ tools: [wiki()] })
+
+new LlamaIndexServer({
+  workflow: createWorkflow,
+  uiConfig: {
+    appTitle: "LlamaIndex App",
+    starterQuestions: ["Who is the first president of the United States?"],
+  },
+}).start();
+```
+
+## Running the Server
+
+In the same directory as `index.ts`, run the following command to start the server:
+
+```bash
+tsx index.ts
+```
+The server will start at `http://localhost:3000`
+
+You can also make a request to the server:
+
+```bash
+curl -X POST "http://localhost:3000/api/chat" -H "Content-Type: application/json" -d '{"message": "Who is the first president of the United States?"}'
+```
+
+## Configuration Options
+
+The `LlamaIndexServer` accepts the following configuration options:
+
+- `workflow`: A callable function that creates a workflow instance for each request
+- `uiConfig`: An object to configure the chat UI containing the following properties:
+  - `appTitle`: The title of the application (default: `"LlamaIndex App"`)
+  - `starterQuestions`: List of starter questions for the chat UI (default: `[]`)
+  - `componentsDir`: The directory for custom UI components rendering events emitted by the workflow. The default is undefined, which does not render custom UI components.
+  - `llamaCloudIndexSelector`: Whether to show the LlamaCloud index selector in the chat UI (requires `LLAMA_CLOUD_API_KEY` to be set in the environment variables) (default: `false`)
+
+LlamaIndexServer accepts all the configuration options from Nextjs Custom Server such as `port`, `hostname`, `dev`, etc.
+See all Nextjs Custom Server options [here](https://nextjs.org/docs/app/building-your-application/configuring/custom-server).
+
+## AI-generated UI Components
+
+The LlamaIndex server provides support for rendering workflow events using custom UI components, allowing you to extend and customize the chat interface. 
+These components can be auto-generated using an LLM by providing a JSON schema of the workflow event. 
+
+### UI Event Schema 
+
+To display custom UI components, your workflow needs to emit UI events that have an event type for identification and a data object:
+
+```typescript
+class UIEvent extends WorkflowEvent<{
+  type: "ui_event";
+  data: UIEventData;
+}> {}
+```
+
+The `data` object can be any JSON object. To enable AI generation of the UI component, you need to provide a schema for that data (here we're using Zod):
+
+```typescript
+const MyEventDataSchema = z.object({
+  stage: z.enum(["retrieve", "analyze", "answer"]).describe("The current stage the workflow process is in."),
+  progress: z.number().min(0).max(1).describe("The progress in percent of the current stage"),
+}).describe("WorkflowStageProgress");
+
+type UIEventData = z.infer<typeof MyEventDataSchema>;
+```
+
+### Generate UI Components
+
+The `generateEventComponent` function uses an LLM to generate a custom UI component based on the JSON schema of a workflow event. The schema should contain accurate descriptions of each field so that the LLM can generate matching components for your use case. We've done this for you in the example above using the `describe` function from Zod:
+
+```typescript
+import { OpenAI } from "llamaindex";
+import { generateEventComponent } from "@llamaindex/server";
+import { MyEventDataSchema } from "./your-workflow";
+
+// Also works well with Claude 3.5 Sonnet and Google Gemini 2.5 Pro
+const llm = new OpenAI({ model: "gpt-4.1" });
+const code = generateEventComponent(MyEventDataSchema, llm);
+```
+
+After generating the code, we need to save it to a file. The file name must match the event type from your workflow (e.g., `ui_event.jsx` for handling events with `ui_event` type):
+
+```ts
+fs.writeFileSync("components/ui_event.jsx", code);
+```
+
+Feel free to modify the generated code to match your needs. If you're not satisfied with the generated code, we suggest improving the provided JSON schema first or trying another LLM.
+
+> Note that `generateEventComponent` is generating JSX code, but you can also provide a TSX file.
+
+
+### Server Setup
+
+To use the generated UI components, you need to initialize the LlamaIndex server with the `componentsDir` that contains your custom UI components:
+
+```ts
+new LlamaIndexServer({
+  workflow: createWorkflow,
+  uiConfig: {
+    appTitle: "LlamaIndex App",
+    componentsDir: "components",
+  },
+}).start();
+```
+
+## Default Endpoints and Features
+
+### Chat Endpoint
+
+The server includes a default chat endpoint at `/api/chat` for handling chat interactions.
+
+### Chat UI
+
+The server always provides a chat interface at the root path (`/`) with:
+
+- Configurable starter questions
+- Real-time chat interface
+- API endpoint integration
+
+### Static File Serving
+
+- The server automatically mounts the `data` and `output` folders at `{server_url}{api_prefix}/files/data` (default: `/api/files/data`) and `{server_url}{api_prefix}/files/output` (default: `/api/files/output`) respectively.
+- Your workflows can use both folders to store and access files. By convention, the `data` folder is used for documents that are ingested, and the `output` folder is used for documents generated by the workflow.
+
+
+## Best Practices
+
+1. Always provide a workflow factory that creates a fresh workflow instance for each request.
+2. Use environment variables for sensitive configuration (e.g., API keys).
+3. Use starter questions to guide users in the chat UI.
+
+## Getting Started with a New Project
+
+Want to start a new project with LlamaIndexServer? Check out our [create-llama](https://github.com/run-llama/create-llama) tool to quickly generate a new project with LlamaIndexServer.
+
+## API Reference
+
+- [LlamaIndexServer](https://github.com/run-llama/create-llama/blob/main/packages/server)

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

@@ -2,5 +2,5 @@
   "title": "Chat UI",
   "description": "Use chat-ui to add a chat interface to your LlamaIndexTS application.",
   "defaultOpen": false,
-  "pages": ["index", "llamaindex-server"]
+  "pages": ["install", "chat", "rsc", "llamaindex-server"]
 }

apps/next/src/content/docs/llamaindex/modules/ui/rsc.mdx

@@ -0,0 +1,65 @@
+---
+title: Using Next.js RSC
+description: Chat interface for your LlamaIndexTS application using Next.js RSC
+---
+
+Using [chat-ui](https://github.com/run-llama/chat-ui), it's easy to add a chat interface to your LlamaIndexTS application using [Next.js RSC](https://nextjs.org/docs/app/building-your-application/rendering/server-components) and [Vercel AI RSC](https://sdk.vercel.ai/docs/ai-sdk-rsc/overview).
+
+With RSC, the chat messages are not returned as JSON from the server (like when using an [API route](/docs/llamaindex/modules/ui/chat)), instead the chat message components are rendered on the server side.
+This is for example useful for rendering a whole chat history on the server before sending it to the client. [Check here](https://sdk.vercel.ai/docs/getting-started/navigating-the-library#when-to-use-ai-sdk-rsc), for a discussion of when to use use RSC.
+
+For implementing a chat interface with RSC, you need to create an AI action and then connect the chat interface to use it.
+
+## Create an AI action
+
+First, define an [AI context provider](https://sdk.vercel.ai/examples/rsc/state-management/ai-ui-states) with a chat server action:
+
+```json doc-gen:file
+{
+  "file": "./src/components/demo/chat/rsc/ai-action.tsx",
+	"codeblock": true
+}
+```
+
+The chat server action is using LlamaIndexTS to generate a response based on the chat history and the user input.
+
+## Create the chat UI
+
+The entrypoint of our application initializes the AI provider for the application and adds a `ChatSection` component:
+
+```json doc-gen:file
+{
+  "file": "./src/components/demo/chat/rsc/demo.tsx",
+	"codeblock": true
+}
+```
+
+The `ChatSection` component is created by using chat components from @llamaindex/chat-ui:
+
+```json doc-gen:file
+{
+  "file": "./src/components/demo/chat/rsc/chat-section.tsx",
+	"codeblock": true
+}
+```
+
+It is using a `useChatRSC` hook to conntect the chat interface to the `chat` AI action that we defined earlier:
+
+```json doc-gen:file
+{
+  "file": "./src/components/demo/chat/rsc/use-chat-rsc.tsx",
+	"codeblock": true
+}
+```
+
+## Try RSC Chat ⬇️
+
+<ChatDemoRSC />
+
+## Next Steps
+
+The steps above are the bare minimum to get a chat interface working with RSC. From here, you can go two ways:
+
+1. Use our [full-stack RSC example](https://github.com/run-llama/nextjs-rsc) based on [create-llama](https://github.com/run-llama/create-llama) to get started quickly with a fully working chat interface or
+2. Learn more about [AI RSC](https://sdk.vercel.ai/examples/rsc), [chat-ui](https://github.com/run-llama/chat-ui) and [LlamaIndexTS](https://github.com/run-llama/llamaindex-ts) to customize the chat interface and AI actions to your needs.
+

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

@@ -1,3 +1,3 @@
 {
-  "pages": ["llamaindex", "api", "workflows", "chat-ui"]
+  "pages": ["llamaindex", "api", "llamaflow"]
 }

apps/next/src/lib/const.ts

@@ -1,2 +1,2 @@
 // when we are ready, change to /docs/llamaindex
-export const DOCUMENT_URL = "/docs/llamaindex";
+export const DOCUMENT_URL = '/docs/llamaindex'

apps/next/src/lib/get-contributors.ts

@@ -10,7 +10,7 @@ export async function fetchContributors(
 ): Promise<Contributor[]> {
   const headers = new Headers();
   if (process.env.GITHUB_TOKEN)
-    headers.set("Authorization", `Bearer ${process.env.GITHUB_TOKEN}`);
+    headers.set('Authorization', `Bearer ${process.env.GITHUB_TOKEN}`);
 
   const response = await fetch(
     `https://api.github.com/repos/${repoOwner}/${repoName}/contributors?per_page=50`,
@@ -26,6 +26,6 @@ export async function fetchContributors(
 
   const contributors = (await response.json()) as Contributor[];
   return contributors
-    .filter((contributor) => !contributor.login.endsWith("[bot]"))
+    .filter((contributor) => !contributor.login.endsWith('[bot]'))
     .sort((a, b) => b.contributions - a.contributions);
 }

apps/next/src/lib/metadata.ts

@@ -0,0 +1,30 @@
+import { createMetadataImage } from 'fumadocs-core/server';
+import { source } from '@/lib/source';
+import { Metadata } from 'next';
+
+export const metadataImage = createMetadataImage({
+	source,
+	imageRoute: 'og',
+});
+
+export function createMetadata(override: Metadata): Metadata {
+	return {
+		...override,
+		openGraph: {
+			title: override.title ?? undefined,
+			description: override.description ?? undefined,
+			url: 'https://ts.llamaindex.ai/',
+			images: '/og.png',
+			siteName: 'LlamaIndex.TS',
+			...override.openGraph,
+		},
+		twitter: {
+			card: 'summary_large_image',
+			creator: '@llama_index',
+			title: override.title ?? undefined,
+			description: override.description ?? undefined,
+			images: '/og.png',
+			...override.twitter,
+		},
+	};
+}

apps/next/src/lib/source.ts

@@ -1,9 +1,9 @@
-import { docs } from "@/.source";
-import { loader } from "fumadocs-core/source";
+import { docs } from '@/.source';
+import { loader } from 'fumadocs-core/source';
 import { createOpenAPI } from "fumadocs-openapi/server";
 
 export const source = loader({
-  baseUrl: "/docs",
+  baseUrl: '/docs',
   source: docs.toFumadocsSource(),
 });
 

apps/next/src/lib/utils.ts

@@ -0,0 +1,6 @@
+import { clsx, type ClassValue } from "clsx"
+import { twMerge } from "tailwind-merge"
+
+export function cn(...inputs: ClassValue[]) {
+  return twMerge(clsx(inputs))
+}

apps/next/src/libs/metadata.ts

@@ -1,30 +0,0 @@
-import { source } from "@/libs/source";
-import { createMetadataImage } from "fumadocs-core/server";
-import { Metadata } from "next";
-
-export const metadataImage = createMetadataImage({
-  source,
-  imageRoute: "og",
-});
-
-export function createMetadata(override: Metadata): Metadata {
-  return {
-    ...override,
-    openGraph: {
-      title: override.title ?? undefined,
-      description: override.description ?? undefined,
-      url: "https://ts.llamaindex.ai/",
-      images: "/og.png",
-      siteName: "LlamaIndex.TS",
-      ...override.openGraph,
-    },
-    twitter: {
-      card: "summary_large_image",
-      creator: "@llama_index",
-      title: override.title ?? undefined,
-      description: override.description ?? undefined,
-      images: "/og.png",
-      ...override.twitter,
-    },
-  };
-}

apps/next/src/libs/utils.ts

@@ -1,6 +0,0 @@
-import { clsx, type ClassValue } from "clsx";
-import { twMerge } from "tailwind-merge";
-
-export function cn(...inputs: ClassValue[]) {
-  return twMerge(clsx(inputs));
-}

apps/next/turbo.json

@@ -4,8 +4,7 @@
   "tasks": {
     "build": {
       "inputs": [
-        "node_modules/@llamaindex/workflow-docs/**",
-        "node_modules/@llamaindex/chat-ui-docs/**",
+        "node_modules/@llama-flow/docs/**",
         "src/**/*.ts",
         "src/**/*.tsx",
         "src/**/*.mdx",

docs/llamaindexTS/getting_started/concepts.mdx

@@ -0,0 +1,60 @@
+---
+title: High-Level Concepts
+---
+
+This is a quick guide to the high-level concepts you'll encounter frequently when building LLM applications.
+
+## Large Language Models (LLMs)
+
+LLMs are the fundamental innovation that launched LlamaIndex. They are an artificial intelligence (AI) computer system that can understand, generate, and manipulate natural language, including answering questions based on their training data or data provided to them at query time. 
+
+## Agentic Applications
+
+When an LLM is used within an application, it is often used to make decisions, take actions, and/or interact with the world. This is the core definition of an **agentic application**.
+
+While the definition of an agentic application is broad, there are several key characteristics that define an agentic application:
+
+- **LLM Augmentation**: The LLM is augmented with tools (i.e. arbitrary callable functions in code), memory, and/or dynamic prompts.
+- **Prompt Chaining**: Several LLM calls are used that build on each other, with the output of one LLM call being used as the input to the next.
+- **Routing**: The LLM is used to route the application to the next appropriate step or state in the application.
+- **Parallelism**: The application can perform multiple steps or actions in parallel.
+- **Orchestration**: A hierarchical structure of LLMs is used to orchestrate lower-level actions and LLMs.
+- **Reflection**: The LLM is used to reflect and validate outputs of previous steps or LLM calls, which can be used to guide the application to the next appropriate step or state.
+
+In LlamaIndex, you can build agentic applications by using the workflows to orchestrate a sequence of steps and LLMs. You can [learn more about workflows](/docs/llamaindex/tutorials/workflows).
+
+## Agents
+
+We define an agent as a specific instance of an "agentic application". An agent is a piece of software that semi-autonomously performs tasks by combining LLMs with other tools and memory, orchestrated in a reasoning loop that decides which tool to use next (if any).
+
+What this means in practice, is something like:
+- An agent receives a user message
+- The agent uses an LLM to determine the next appropriate action to take using the previous chat history, tools, and the latest user message
+- The agent may invoke one or more tools to assist in the users request
+- If tools are used, the agent will then interpret the tool outputs and use them to inform the next action
+- Once the agent stops taking actions, it returns the final output to the user
+
+You can [learn more about agents](/docs/llamaindex/tutorials/basic_agent).
+
+## Retrieval Augmented Generation (RAG)
+
+Retrieval-Augmented Generation (RAG) is a core technique for building data-backed LLM applications with LlamaIndex. It allows LLMs to answer questions about your private data by providing it to the LLM at query time, rather than training the LLM on your data. To avoid sending **all** of your data to the LLM every time, RAG indexes your data and selectively sends only the relevant parts along with your query. You can [learn more about RAG](/docs/llamaindex/tutorials/rag).
+
+## Use cases
+
+There are endless use cases for data-backed LLM applications but they can be roughly grouped into four categories:
+
+[**Agents**](/docs/llamaindex/tutorials/basic_agent):
+An agent is an automated decision-maker powered by an LLM that interacts with the world via a set of [tools](/docs/llamaindex/modules/agents/tool). Agents can take an arbitrary number of steps to complete a given task, dynamically deciding on the best course of action rather than following pre-determined steps. This gives it additional flexibility to tackle more complex tasks.
+
+[**Workflows**](/docs/llamaindex/tutorials/workflows):
+A Workflow in LlamaIndex is a specific event-driven abstraction that allows you to orchestrate a sequence of steps and LLMs calls. Workflows can be used to implement any agentic application, and are a core component of LlamaIndex.
+
+[**Structured Data Extraction**](/docs/llamaindex/tutorials/structured_data_extraction):
+Pydantic extractors allow you to specify a precise data structure to extract from your data and use LLMs to fill in the missing pieces in a type-safe way. This is useful for extracting structured data from unstructured sources like PDFs, websites, and more, and is key to automating workflows.
+
+[**Query Engines**](/docs/llamaindex/modules/rag/query_engines):
+A query engine is an end-to-end flow that allows you to ask questions over your data. It takes in a natural language query, and returns a response, along with reference context retrieved and passed to the LLM.
+
+[**Chat Engines**](/docs/llamaindex/modules/rag/chat_engine):
+A chat engine is an end-to-end flow for having a conversation with your data (multiple back-and-forth instead of a single question-and-answer).

docs/llamaindexTS/getting_started/create_llama.mdx

@@ -0,0 +1,21 @@
+---
+title: Create-Llama
+---
+
+`create-llama` is a powerful but easy to use command-line tool that generates a working, full-stack web application that allows you to chat with your data. You can learn more about it on [the `create-llama` README page](https://www.npmjs.com/package/create-llama).
+
+Run it once and it will ask you a series of questions about the kind of application you want to generate. Then you can customize your application to suit your use-case. To get started, run:
+
+```bash npm2yarn
+npx create-llama@latest
+```
+
+Once your app is generated, `cd` into your app directory and run
+
+```bash npm2yarn
+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)

docs/llamaindexTS/getting_started/examples.mdx

@@ -0,0 +1,32 @@
+---
+title: Code examples
+---
+
+Our GitHub repository has a wealth of examples to explore and try out. You can check out our [examples folder](https://github.com/run-llama/LlamaIndexTS/tree/main/examples) to see them all at once, or browse the pages in this section for some selected highlights.
+
+## Use examples locally
+
+It may be useful to check out all the examples at once so you can try them out locally. To do this into a folder called `my-new-project`, run these commands:
+
+```bash npm2yarn
+npx degit run-llama/LlamaIndexTS/examples my-new-project
+cd my-new-project
+npm i
+```
+
+Then you can run any example in the folder with `tsx`, e.g.:
+
+```bash npm2yarn
+npx tsx ./vectorIndex.ts
+```
+
+## Try examples online
+
+You can also try the examples online using StackBlitz:
+
+<iframe
+  style={{ width: '100%', height: '440px' }}
+  aria-label="LlamaIndex.TS Examples"
+  aria-description="This is a list of examples for LlamaIndex.TS."
+  src="https://stackblitz.com/github/run-llama/LlamaIndexTS/tree/main/examples?file=README.md"
+/>

docs/llamaindexTS/getting_started/installation/cloudflare.mdx

@@ -0,0 +1,72 @@
+---
+title: With Cloudflare Worker
+description: In this guide, you'll learn how to use LlamaIndex with CloudFlare Worker
+---
+import { SiCloudflareworkers } from '@icons-pack/react-simple-icons';
+import { LinkCard, Aside } from '@astrojs/starlight/components';
+
+Before you start, make sure you have try LlamaIndex.TS in Node.js to make sure you understand the basics.
+
+<LinkCard
+  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.
+
+<Aside type="caution">Do not commit the api key to git repository.</Aside>
+
+## 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.
+
+

docs/llamaindexTS/getting_started/installation/index.mdx

@@ -0,0 +1,63 @@
+---
+title: Installation
+description: How to install llamaindex packages.
+---
+import { Card, CardGrid, LinkCard, Icon } from '@astrojs/starlight/components';
+import { SiTypescript, SiVite, SiCloudflareworkers, SiNodedotjs, SiNextdotjs } from '@icons-pack/react-simple-icons';
+
+To install llamaindex, run the following command:
+
+```package-install
+npm i llamaindex
+```
+
+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
+```
+
+Go to [LLM APIs](/docs/llamaindex/modules/models/llms) to find out how to use other LLMs.
+
+
+## Frameworks
+
+LlamaIndex supports a wide range of frameworks and runtimes. Click on the card below to learn more.
+
+<CardGrid>
+	<LinkCard
+		title="Node.js"
+		href="/docs/llamaindex/getting_started/installation/node"
+	/>
+	<LinkCard
+		title="TypeScript"
+		href="/docs/llamaindex/getting_started/installation/typescript"
+	/>
+	<LinkCard
+		title="Vite"
+		href="/docs/llamaindex/getting_started/installation/vite"
+	/>
+	<LinkCard
+		title="Next.js"
+		href="/docs/llamaindex/getting_started/installation/next"
+	/>
+	<LinkCard
+		title="Cloudflare Workers"
+		href="/docs/llamaindex/getting_started/installation/cloudflare"
+	/>
+</CardGrid>
+
+## What's next?
+
+<CardGrid>
+	<LinkCard
+		title="Learn LlamaIndex.TS"
+		description="Learn how to use LlamaIndex.TS by starting with one of our tutorials."
+		href="/docs/llamaindex/tutorials/rag"
+	/>
+	<LinkCard
+		title="Show me code examples"
+		description="Explore code examples using LlamaIndex.TS."
+		href="/docs/llamaindex/getting_started/examples"
+	/>
+</CardGrid>

docs/llamaindexTS/getting_started/installation/meta.json

@@ -0,0 +1,4 @@
+{
+  "title": "Installation",
+  "pages": ["node", "typescript", "next", "vite", "cloudflare"]
+}

docs/llamaindexTS/getting_started/installation/next.mdx

@@ -0,0 +1,42 @@
+---
+title: With Next.js
+description: In this guide, you'll learn how to use LlamaIndex with Next.js.
+---
+import { Card, CardGrid, LinkCard, Icon } from '@astrojs/starlight/components';
+
+Before you start, make sure you have try LlamaIndex.TS in Node.js to make sure you understand the basics.
+
+<LinkCard
+  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.

docs/llamaindexTS/getting_started/installation/node.mdx

@@ -0,0 +1,41 @@
+---
+title: With Node.js/Bun/Deno
+description: In this guide, you'll learn how to use LlamaIndex with Node.js, Bun, and Deno.
+---
+import { Card, CardGrid, LinkCard, Icon, Aside } from '@astrojs/starlight/components';
+
+## 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
+```
+
+<Aside type="caution">Do not commit the api key to git repository.</Aside>
+
+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
+
+<LinkCard
+	title="Getting Started with LlamaIndex.TS in TypeScript"
+	href="/docs/llamaindex/getting_started/installation/typescript"
+/>

docs/llamaindexTS/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
+```

docs/llamaindexTS/getting_started/installation/vite.mdx

@@ -0,0 +1,24 @@
+---
+title: With Vite
+description: In this guide, you'll learn how to use LlamaIndex with Vite
+---
+import { Card, CardGrid, LinkCard, Icon, Aside } from '@astrojs/starlight/components';
+
+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.

docs/llamaindexTS/getting_started/meta.json

@@ -0,0 +1,4 @@
+{
+  "title": "Getting Started",
+  "pages": ["concepts", "installation", "create_llama", "examples"]
+}

docs/llamaindexTS/index.mdx

@@ -0,0 +1,22 @@
+---
+title: What is LlamaIndex.TS
+description: LlamaIndex is the leading data framework for building LLM applications
+---
+import { SiBun, SiCloudflareworkers, SiDeno, SiNodedotjs } from '@icons-pack/react-simple-icons';
+
+LlamaIndex is a framework for building context-augmented generative AI applications with LLMs including agents and workflows.
+
+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.
+
+LlamaIndex.TS provides tools for beginners, advanced users, and everyone in between.
+
+Try it out with a starter example using StackBlitz:
+
+<iframe
+  style={{ width: '100%', height: '440px' }}
+  aria-label="LlamaIndex.TS Starter"
+  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"
+/>
+
+You'll need an OpenAI API key to run this example. You can retrieve it from [OpenAI](https://platform.openai.com/api-keys).

docs/llamaindexTS/integration/lang-trace.mdx

@@ -0,0 +1,28 @@
+---
+title: Langtrace
+description: Learn how to integrate LlamaIndex.TS with Langtrace.
+---
+
+Enhance your observability with Langtrace, a robust open-source tool supports OpenTelemetry and is designed to trace, evaluate, and manage LLM applications seamlessly. Langtrace integrates directly with LlamaIndex, offering detailed, real-time insights into performance metrics such as accuracy, evaluations, and latency.
+
+## Install
+
+- Self-host or sign-up and generate an API key using [Langtrace](https://www.langtrace.ai) Cloud
+
+```package-install
+npm i @langtrase/typescript-sdk
+```
+
+## Initialize
+
+```js
+import * as Langtrace from "@langtrase/typescript-sdk";
+Langtrace.init({ api_key: "<YOUR_API_KEY>" });
+```
+
+Features:
+
+- OpenTelemetry compliant, ensuring broad compatibility with observability platforms.
+- Provides comprehensive logs and detailed traces of all components.
+- Real-time monitoring of accuracy, evaluations, usage, costs, and latency.
+- For more configuration options and details, visit [Langtrace Docs](https://docs.langtrace.ai/introduction).

docs/llamaindexTS/integration/meta.json

@@ -0,0 +1,5 @@
+{
+  "title": "Integration",
+  "description": "See our integrations",
+  "pages": ["open-llm-metry", "lang-trace", "vercel"]
+}

docs/llamaindexTS/integration/open-llm-metry.mdx

@@ -0,0 +1,22 @@
+---
+title: OpenLLMetry
+description: Learn how to integrate LlamaIndex.TS with OpenLLMetry.
+---
+
+[OpenLLMetry](https://github.com/traceloop/openllmetry-js) is an open-source project based on OpenTelemetry for tracing and monitoring
+LLM applications. It connects to [all major observability platforms](https://www.traceloop.com/docs/openllmetry/integrations/introduction) and installs in minutes.
+
+### Usage Pattern
+
+```package-install
+npm i @traceloop/node-server-sdk
+```
+
+```js
+import * as traceloop from "@traceloop/node-server-sdk";
+
+traceloop.initialize({
+  apiKey: process.env.TRACELOOP_API_KEY,
+  disableBatch: true
+});
+```

docs/llamaindexTS/integration/vercel.mdx

@@ -0,0 +1,102 @@
+---
+title: Vercel
+description: Integrate LlamaIndex with Vercel's AI SDK
+---
+
+LlamaIndex provides integration with Vercel's AI SDK, allowing you to create powerful search and retrieval applications. You can:
+- Use any of Vercel AI's [model providers](https://sdk.vercel.ai/docs/foundations/providers-and-models) as LLMs in LlamaIndex
+- Use indexes (e.g. VectorStoreIndex, LlamaCloudIndex) from LlamaIndexTS in your Vercel AI applications
+
+## Setup
+
+First, install the required dependencies:
+
+```package-install
+npm i @llamaindex/vercel ai
+```
+
+## Using Vercel AI's Model Providers 
+
+Using the `VercelLLM` adapter, it's easy to use any of Vercel AI's [model providers](https://sdk.vercel.ai/docs/foundations/providers-and-models) as LLMs in LlamaIndex. Here's an example of how to use OpenAI's GPT-4o model:
+
+```typescript
+const llm = new VercelLLM({ model: openai("gpt-4o") });
+const result = await llm.complete({
+  prompt: "What is the capital of France?",
+  stream: false, // Set to true if you want streaming responses
+});
+console.log(result.text);
+```
+
+## Use Indexes
+
+### Using VectorStoreIndex
+
+Here's how to create a simple vector store index and query it using Vercel's AI SDK:
+
+```typescript
+import { openai } from "@ai-sdk/openai";
+import { llamaindex } from "@llamaindex/vercel";
+import { streamText } from "ai";
+import { Document, VectorStoreIndex } from "llamaindex";
+
+// Create an index from your documents
+const document = new Document({ text: yourText, id_: "unique-id" });
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+// Create a query tool
+const queryTool = llamaindex({
+  model: openai("gpt-4"),
+  index,
+  description: "Search through the documents", // optional
+});
+
+// Use the tool with Vercel's AI SDK
+streamText({
+  model: openai("gpt-4"),
+  prompt: "Your question here",
+  tools: { queryTool },
+  onFinish({ response }) {
+    console.log("Response:", response.messages); // log the response
+  },
+}).toDataStream();
+```
+
+> Note: the Vercel AI model referenced in the `llamaindex` function is used by the response synthesizer to generate a response for the tool call.
+
+### Using LlamaCloud
+
+For production deployments, you can use LlamaCloud to store and manage your documents:
+
+```typescript
+import { LlamaCloudIndex } from "@llamaindex/cloud";
+
+// Create a LlamaCloud index
+const index = await LlamaCloudIndex.fromDocuments({
+  documents: [document],
+  name: "your-index-name",
+  projectName: "your-project",
+  apiKey: process.env.LLAMA_CLOUD_API_KEY,
+});
+
+// Use it the same way as VectorStoreIndex
+const queryTool = llamaindex({
+  model: openai("gpt-4"),
+  index,
+  description: "Search through the documents",
+  options: { fields: ["sourceNodes", "messages"]}
+});
+
+// Use the tool with Vercel's AI SDK
+streamText({
+  model: openai("gpt-4"),
+  prompt: "Your question here",
+  tools: { queryTool },
+}).toDataStream();
+```
+
+## Next Steps
+
+1. Explore [LlamaCloud](https://cloud.llamaindex.ai/) for managed document storage and retrieval
+2. Join our [Discord community](https://discord.gg/dGcwcsnxhU) for support and discussions
+

docs/llamaindexTS/meta.json

@@ -0,0 +1,14 @@
+{
+  "title": "LlamaIndex",
+  "description": "The Data framework for LLM",
+  "root": true,
+  "pages": [
+    "---Guide---",
+    "index",
+    "getting_started",
+    "tutorials",
+    "modules",
+    "integration",
+    "migration"
+  ]
+}

docs/llamaindexTS/migration/0.8-to-0.9.mdx

@@ -0,0 +1,85 @@
+---
+title: Migrating from v0.8 to v0.9
+---
+
+Version 0.9 of LlamaIndex.TS introduces significant architectural changes to improve package size and runtime compatibility. The main goals of this release are:
+
+1. Reduce the package size of the main `llamaindex` package by moving dependencies into provider packages, making it more suitable for serverless environments
+2. Enable consistent code across different environments by using unified imports (no separate imports for Node.js and Edge runtimes)
+
+## Major Changes
+
+### Installing Provider Packages
+
+In v0.9, you need to explicitly install the provider packages you want to use. The main `llamaindex` package no longer includes these dependencies by default.
+
+### Updating Imports
+
+You'll need to update your imports to get classes directly from their respective provider packages. Here's how to migrate different components:
+
+### 1. AI Model Providers
+
+Previously:
+```typescript
+import { OpenAI } from "llamaindex";
+```
+
+Now:
+```typescript
+import { OpenAI } from "@llamaindex/openai";
+```
+
+> Note: This examples requires installing the `@llamaindex/openai` package: 
+
+```package-install
+npm i @llamaindex/openai
+```
+
+For more details on available AI model providers and their configuration, see the [LLMs documentation](/docs/llamaindex/modules/models/llms) and the [Embedding Models documentation](/docs/llamaindex/modules/models/embeddings).
+
+### 2. Storage Providers
+
+Previously:
+```typescript
+import { PineconeVectorStore } from "llamaindex";
+```
+
+Now:
+```typescript
+import { PineconeVectorStore } from "@llamaindex/pinecone";
+```
+
+For more information about available storage options, refer to the [Data Stores documentation](/docs/llamaindex/modules/data/stores).
+
+### 3. Data Loaders
+
+Previously:
+```typescript
+import { SimpleDirectoryReader } from "llamaindex";
+```
+
+Now:
+```typescript
+import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
+```
+
+For more details about available data loaders and their usage, check the [Loading Data](/docs/llamaindex/modules/data/readers).
+
+### 4. Prefer using `llamaindex` instead of `@llamaindex/core`
+
+`llamaindex` is now re-exporting most of `@llamaindex/core`. To simplify imports, just use `import { ... } from "llamaindex"` instead of `import { ... } from "@llamaindex/core"`. This is possible because `llamaindex` is now a smaller package.
+
+We might change imports internally in `@llamaindex/core` in the future. Let us know if you're missing something. 
+
+## Benefits of the Changes
+
+- **Smaller Bundle Size**: By moving dependencies to separate packages, your application only includes the features you actually use
+- **Runtime Consistency**: The same code works across different environments without environment-specific imports
+- **Improved Serverless Support**: Reduced package size makes it easier to deploy to serverless environments with size limitations
+
+## Need Help?
+
+If you encounter any issues during migration, please:
+1. Check our [GitHub repository](https://github.com/run-llama/LlamaIndexTS) for the latest updates
+2. Join our [Discord community](https://discord.gg/dGcwcsnxhU) for support
+3. Open an issue on GitHub if you find a bug or have a feature request

docs/llamaindexTS/migration/deprecated/agent/index.mdx

@@ -0,0 +1,28 @@
+---
+title: Agents
+---
+
+**Note**: Agents are deprecated, use [Agent Workflows](/docs/llamaindex/modules/agents/agent_workflow) instead.
+
+An “agent” is an automated reasoning and decision engine. It takes in a user input/query and can make internal decisions for executing that query in order to return the correct result. The key agent components can include, but are not limited to:
+
+- Breaking down a complex question into smaller ones
+- Choosing an external Tool to use + coming up with parameters for calling the Tool
+- Planning out a set of tasks
+- Storing previously completed tasks in a memory module
+
+## Getting Started
+
+LlamaIndex.TS comes with a few built-in agents, but you can also create your own. The built-in agents include:
+
+- OpenAI Agent
+- Anthropic Agent both via Anthropic and Bedrock (in `@llamaIndex/community`)
+- Gemini Agent
+- ReACT Agent
+- Meta3.1 504B via Bedrock (in `@llamaIndex/community`)
+
+## Api References
+
+- [OpenAIAgent](/docs/api/classes/OpenAIAgent)
+- [AnthropicAgent](/docs/api/classes/AnthropicAgent)
+- [ReActAgent](/docs/api/classes/ReActAgent)

docs/llamaindexTS/migration/meta.json

@@ -0,0 +1,5 @@
+{
+  "title": "Migration",
+  "description": "Migration between different versions",
+  "pages": ["0.8-to-0.9", "deprecated"]
+}

docs/llamaindexTS/modules/agents/agent_workflow.mdx

@@ -0,0 +1,118 @@
+---
+title: Agent Workflows
+---
+
+
+Agent Workflows are a powerful system that enables you to create and orchestrate one or multiple agents with tools to perform specific tasks. It's built on top of the base [`Workflow`](/docs/llamaindex/modules/agents/workflows) system and provides a streamlined interface for agent interactions.
+
+## Usage
+
+### Single Agent Workflow
+
+The simplest use case is creating a single agent with specific tools. Here's an example of creating an assistant that tells jokes:
+
+```typescript
+import { tool } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
+import { openai } from "@llamaindex/openai";
+
+// Define a joke-telling tool
+const jokeTool = tool(
+  () => "Baby Llama is called cria",
+  {
+    name: "joke",
+    description: "Use this tool to get a joke",
+  }
+);
+
+// Create an single agent workflow with the tool
+const jokeAgent = agent({
+  tools: [jokeTool],
+  llm: openai({ model: "gpt-4o-mini" }),
+});
+
+// Run the workflow
+const result = await jokeAgent.run("Tell me something funny");
+console.log(result); // Baby Llama is called cria
+```
+
+### Event Streaming
+
+Agent Workflows provide a unified interface for event streaming, making it easy to track and respond to different events during execution:
+
+```typescript
+import { agentToolCallEvent, agentStreamEvent } from "@llamaindex/workflow";
+
+// Get the workflow execution context
+const events = workflow.runStream("Tell me something funny");
+
+// Stream and handle events
+for await (const event of events) {
+  if (agentToolCallEvent.include(event)) {
+    console.log(`Tool being called: ${event.data.toolName}`);
+  }
+  if (agentStreamEvent.include(event)) {
+    process.stdout.write(event.data.delta);
+  }
+}
+```
+
+### Multi-Agent Workflow
+
+An Agent Workflow can orchestrate multiple agents, enabling complex interactions and task handoffs. Each agent in a multi-agent workflow requires:
+
+- `name`: Unique identifier for the agent
+- `description`: Purpose description used for task routing
+- `tools`: Array of tools the agent can use
+- `canHandoffTo` (optional): Array of agent names or agent instances that this agent can delegate tasks to
+
+Here's an example of a multi-agent system that combines joke-telling and weather information:
+
+```typescript
+import { tool } from "llamaindex";
+import { multiAgent, agent } from "@llamaindex/workflow";
+import { openai } from "@llamaindex/openai";
+import { z } from "zod";
+
+// Create a weather agent
+const weatherAgent = agent({
+  name: "WeatherAgent",
+  description: "Provides weather information for any city",
+  tools: [
+    tool(
+      {
+        name: "fetchWeather",
+        description: "Get weather information for a city",
+        parameters: z.object({
+          city: z.string(),
+        }),
+        execute: ({ city }) => `The weather in ${city} is sunny`,
+      }
+    ),
+  ],
+  llm: openai({ model: "gpt-4o-mini" }),
+});
+
+// Create a joke-telling agent
+const jokeAgent = agent({
+  name: "JokeAgent",
+  description: "Tells jokes and funny stories",
+  tools: [jokeTool], // Using the joke tool defined earlier
+  llm: openai({ model: "gpt-4o-mini" }),
+  canHandoffTo: [weatherAgent], // Can hand off to the weather agent
+});
+
+// Create the multi-agent workflow
+const agents = multiAgent({
+  agents: [jokeAgent, weatherAgent],
+  rootAgent: jokeAgent, // Start with the joke agent
+});
+
+// Run the workflow
+const result = await agents.run(
+  "Give me a morning greeting with a joke and the weather in San Francisco"
+);
+```
+
+The workflow will coordinate between agents, allowing them to handle different aspects of the request and hand off tasks when appropriate.
+

docs/llamaindexTS/modules/agents/meta.json

@@ -0,0 +1,4 @@
+{
+  "title": "Agents",
+  "pages": ["tool", "agent_workflow", "workflows"]
+}

docs/llamaindexTS/modules/agents/tool/index.mdx

@@ -0,0 +1,144 @@
+---
+title: Tools
+---
+
+A "tool" is a utility that can be called by an agent on behalf of an LLM.
+A tool can be called to perform custom actions, or retrieve extra information based on the LLM-generated input.
+A result from a tool call can be used by subsequent steps in a workflow, or to compute a final answer.
+For example, a "weather tool" could fetch some live weather information from a geographical location.
+
+## Tool Function
+
+The `tool` function is a utility provided to define a tool that can be used by an agent. It takes a function and a configuration object as arguments. The configuration object includes the tool's name, description, and parameters.
+
+### Parameters with Zod
+
+The `parameters` field in the tool configuration is defined using `zod`, a TypeScript-first schema declaration and validation library. `zod` allows you to specify the expected structure and types of the input parameters, ensuring that the data passed to the tool is valid.
+
+Example:
+```ts
+import { tool } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
+import { z } from "zod";
+
+// first arg is LLM input, second is bound arg
+const queryKnowledgeBase = async ({ question }, { userToken }) => {
+  const response = await fetch(`https://knowledge-base.com?token=${userToken}&query=${question}`);
+  // ...
+};
+
+// define tool with zod validation
+const kbTool = tool(queryKnowledgeBase, {
+  name: 'queryKnowledgeBase',
+  description: 'Query knowledge base',
+  parameters: z.object({
+    question: z.string({
+      description: 'The user question',
+    }),
+  }),
+});
+
+```
+In this example, `z.object` is used to define a schema for the `parameters` where `question` is expected to be a string. This ensures that any input to the tool adheres to the specified structure, providing a layer of type safety and validation.
+
+
+## Built-in tools
+
+You can import built-in tools from the `@llamaindex/tools` package.
+
+```ts
+import { agent } from "@llamaindex/workflow";
+import { wiki } from "@llamaindex/tools";
+
+const researchAgent = agent({
+  name: "WikiAgent",
+  description: "Gathering information from the internet",
+  systemPrompt: `You are a research agent. Your role is to gather information from the internet using the provided tools.`,
+  tools: [wiki()],
+});
+```
+
+## MCP tools
+
+If you have a MCP server running, you can fetch tools from the server and use them in your agents.
+
+```ts
+// 1. Import MCP tools adapter
+import { mcp } from "@llamaindex/tools";
+import { agent } from "@llamaindex/workflow";
+
+// 2. Initialize a MCP client
+// by npx
+const server = mcp({
+  command: "npx",
+  args: ["-y", "@modelcontextprotocol/server-filesystem", "."],
+  verbose: true,
+});
+// or by SSE
+const server = mcp({
+  url: "http://localhost:8000/mcp",
+  verbose: true,
+});
+
+// 3. Get tools from MCP server
+const tools = await server.tools();
+
+// Now you can create an agent with the tools
+const agent = agent({
+  name: "My Agent",
+  systemPrompt: "You are a helpful assistant that can use the provided tools to answer questions.",
+  llm: openai({ model: "gpt-4o" }),
+  tools: tools,
+});
+```
+
+
+## Function tool
+
+You can still use the `FunctionTool` class to define a tool.
+A `FunctionTool` is constructed from a function with signature
+```ts
+(input: T, additionalArg?: AdditionalToolArgument) => R
+```
+where
+- `input` is generated by the LLM, `T` is the type defined by the tool `parameters`
+- `additionalArg` is an optional extra argument, see "Binding" below
+- `R` is the return type
+
+### Binding
+
+An additional argument can be bound to a tool, each tool call will be passed
+- the input provided by the LLM
+- the additional argument (extends object)
+
+Note: calling the `bind` method will return a new `FunctionTool` instance, without modifying the tool which `bind` is called on.
+
+Example to pass a `userToken` as additional argument:
+```ts
+import { tool } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
+
+// first arg is LLM input, second is bound arg
+const queryKnowledgeBase = async ({ question }, { userToken }) => {
+  const response = await fetch(`https://knowledge-base.com?token=${userToken}&query=${question}`);
+  // ...
+};
+
+// define tool as usual
+const kbTool = tool(queryKnowledgeBase, {
+  name: 'queryKnowledgeBase',
+  description: 'Query knowledge base',
+  parameters: z.object({
+    question: z.string({
+      description: 'The user question',
+    }),
+  }),
+});
+
+// create an agent
+const additionalArg = { userToken: 'abcd1234' };
+const workflow = agent({
+  tools: [kbTool.bind(additionalArg)],
+  // llm, systemPrompt etc
+})
+```

docs/llamaindexTS/modules/agents/workflows.mdx

@@ -0,0 +1,18 @@
+---
+title: Workflows
+---
+
+A `Workflow` in LlamaIndex is a lightweight, event-driven abstraction used to chain together several events. Workflows are made up of `handlers`, with each one responsible for processing specific event types and emitting new events.
+
+Workflows are designed to be flexible and can be used to build agents, RAG flows, extraction flows, or anything else you want to implement.
+
+To use workflows install this package:
+
+```package-install
+npm i @llamaindex/workflow
+```
+
+This package is a stable, production-ready version of our [llama-flow](/docs/llamaflow) project. 
+
+While you can still reference the llama-flow documentation for detailed information about the underlying concepts, we recommend using the `@llamaindex/workflow` package for all new projects to ensure stability and long-term availability.
+

docs/llamaindexTS/modules/data/data_index/index.mdx

@@ -0,0 +1,24 @@
+---
+title: Index
+---
+
+An index is the basic container for organizing your data. Besides managed indexes using [LlamaCloud](/docs/llamaindex/modules/data/data_index/managed), LlamaIndex.TS supports three indexes:
+
+
+- `VectorStoreIndex` - will send the top-k `Node`s to the LLM when generating a response. The default top-k is 2.
+- `SummaryIndex` - will send every `Node` in the index to the LLM in order to generate a response
+- `KeywordTableIndex` extracts and provides keywords from `Node`s to the LLM
+
+```typescript
+import { Document, VectorStoreIndex } from "llamaindex";
+
+const document = new Document({ text: "test" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+```
+
+## API Reference
+
+- [SummaryIndex](/docs/api/classes/SummaryIndex)
+- [VectorStoreIndex](/docs/api/classes/VectorStoreIndex)
+- [KeywordTableIndex](/docs/api/classes/KeywordTableIndex)

docs/llamaindexTS/modules/data/data_index/managed.mdx

@@ -0,0 +1,32 @@
+---
+title: Managed Index
+description: Managed index using LlamaCloud
+---
+
+LlamaCloud is a new generation of managed parsing, ingestion, and retrieval services, designed to bring production-grade context-augmentation to your LLM and RAG applications.
+
+LlamaCloud supports
+
+- Managed Ingestion API, handling parsing and document management
+- Managed Retrieval API, configuring optimal retrieval for your RAG system
+
+## Access
+
+Visit [LlamaCloud](https://cloud.llamaindex.ai) to sign in and get an API key.
+
+## Create a Managed Index
+
+Here's an example of how to create a managed index by ingesting a couple of documents:
+
+<include cwd>../../examples/cloud/chat.ts</include>
+
+## Use a Managed Index
+
+Here's an example of how to use a managed index together with a chat engine:
+
+<include cwd>../../examples/cloud/from-documents.ts</include>
+
+## API Reference
+
+- [LlamaCloudIndex](/docs/api/classes/LlamaCloudIndex)
+- [LlamaCloudRetriever](/docs/api/classes/LlamaCloudRetriever)

docs/llamaindexTS/modules/data/index.mdx

@@ -0,0 +1,17 @@
+---
+title: Documents and Nodes
+description: Data structure for storing data in LlamaIndex
+---
+
+`Document`s and `Node`s are the basic building blocks of data in LlamaIndexTS. While the API for these objects is similar, `Document` objects represent entire files, while `Node`s are smaller pieces of that original document, that are suitable for an LLM and Q&A.
+
+```typescript
+import { Document } from "llamaindex";
+
+document = new Document({ text: "text", metadata: { key: "val" } });
+```
+
+## API Reference
+
+- [Document](/docs/api/classes/Document)
+- [TextNode](/docs/api/classes/TextNode)