Release @llamaindex/server@0.1.6 (#1886)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>

.github/workflows/lint_on_push_or_pull.yml

@@ -8,6 +8,11 @@ on:
     branches:
       - main
 
+env:
+  TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
+  TURBO_TEAM: ${{ vars.TURBO_TEAM }}
+  TURBO_REMOTE_ONLY: true
+
 jobs:
   lint:
     runs-on: ubuntu-latest

.github/workflows/preview.yml

@@ -1,6 +1,11 @@
 name: Publish Preview
 on: [pull_request]
 
+env:
+  TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
+  TURBO_TEAM: ${{ vars.TURBO_TEAM }}
+  TURBO_REMOTE_ONLY: true
+
 jobs:
   pre_release:
     name: Pre Release

.prettierignore

@@ -7,3 +7,4 @@ dist/
 .source/
 # prttier doesn't support mdx3 we are using
 *.mdx
+packages/server/server/

CONTRIBUTING.md

@@ -14,13 +14,14 @@ There are some important folders in the repository:
     all JS runtime environments.
   - `env`: The environment package of LlamaIndex.TS, which contains the environment-specific classes and interfaces. It
     includes compatibility layers for Node.js, Deno, Vercel Edge Runtime, Cloudflare Workers...
+  - `providers/*`: The providers package of LlamaIndex.TS, which contains the providers for LLM and other services.
 - `apps/*`: The applications based on LlamaIndex.TS.
   - `next`: Our documentation website based on Next.js.
 - `examples`: The code examples of LlamaIndex.TS using Node.js.
 
 ## Getting Started
 
-Make sure you have Node.js LIS (Long-term Support) installed. You can check your Node.js version by running:
+Make sure you have Node.js LTS (Long-term Support) installed. You can check your Node.js version by running:
 
 ```shell
 node -v
@@ -30,7 +31,7 @@ node -v
 ### Use pnpm
 
 ```shell
-corepack enable
+npm install -g pnpm
 ```
 
 ### Install dependencies
@@ -41,33 +42,65 @@ pnpm install
 
 ### Build the packages
 
-You'll need Turbo to build the packages. If you don't have it, you can run it with `pnpx`.
-
 To build all packages, run:
 
 ```shell
-# Build all packages
-pnpx turbo build --filter "./packages/*"
-
-# Or if you have turbo installed, you can run:
-turbo build --filter "./packages/*"
+pnpm build
 ```
 
+### Run tests
+
+#### Unit tests
+
+After build, to run all unit tests, call:
+
+```shell
+pnpm test
+```
+
+Unit tests are located in the `tests` folder of each package. They are using their own package (e.g. `@llamaindex/core-tests` for `@llamaindex/core`). The tests are importing the package under test and the test package is not published.
+
+#### E2E tests
+
+To run all E2E tests, call:
+
+```shell
+pnpm e2e
+```
+
+All E2E tests are in the `e2e` folder.
+
 ### Docs
 
 See the [docs](./apps/next/README.md) for more information.
 
-## Changeset
+## Adding a new package
+
+Please follow these steps to add a new package:
+
+1. Only add new packages to the `packages/providers` folder.
+2. Use the `package.json` and `tsconfig.json` of an existing packages as template.
+3. Reference your new package in the root `tsconfig.json` file
+4. Add your package to the `examples/package.json` file if you add a new example.
+
+## Before sending a PR
+
+Before sending a PR, make sure of the following:
+
+1. Tests are all running and you added meaningful tests for your change.
+2. If you have a new feature, document it in the `apps/next` docs folder.
+3. If you have a new feature, add a new example in the `examples` folder.
+4. You have a descriptive changeset for each PR:
+
+### Changesets
 
 We use [changesets](https://github.com/changesets/changesets) for managing versions and changelogs. To create a new
 changeset, run in the root folder:
 
-```
+```shell
 pnpm changeset
 ```
 
-Please send a descriptive changeset for each PR.
-
 ## Publishing (maintainers only)
 
 The [Release Github Action](.github/workflows/release.yml) is automatically generating and updating a

apps/next/CHANGELOG.md

@@ -1,5 +1,165 @@
 # @llamaindex/doc
 
+## 0.2.14
+
+### Patch Changes
+
+- Updated dependencies [1e59695]
+  - @llamaindex/readers@3.1.0
+
+## 0.2.13
+
+### Patch Changes
+
+- Updated dependencies [e5c3f95]
+  - @llamaindex/openai@0.3.4
+  - llamaindex@0.10.2
+
+## 0.2.12
+
+### Patch Changes
+
+- Updated dependencies [96dd798]
+  - @llamaindex/openai@0.3.3
+  - llamaindex@0.10.1
+
+## 0.2.11
+
+### Patch Changes
+
+- 6cf928f: chore: use bunchee for llamaindex
+- Updated dependencies [6cf928f]
+  - llamaindex@0.10.0
+
+## 0.2.10
+
+### Patch Changes
+
+- 411dcea: Add Nova Premier to AWS Nova models. Add EU endpoints
+
+## 0.2.9
+
+### Patch Changes
+
+- Updated dependencies [d365eb2]
+  - @llamaindex/openai@0.3.2
+  - llamaindex@0.9.19
+
+## 0.2.8
+
+### Patch Changes
+
+- 2ffdb27: docs: correct the CondenseQuestionChatEngine path
+- Updated dependencies [88b7046]
+  - @llamaindex/openai@0.3.1
+  - llamaindex@0.9.18
+
+## 0.2.7
+
+### Patch Changes
+
+- 3ffee26: feat: enhance config params for LlamaIndexServer
+
+## 0.2.6
+
+### Patch Changes
+
+- Updated dependencies [3534c37]
+- Updated dependencies [41191d0]
+  - llamaindex@0.9.17
+  - @llamaindex/workflow@1.0.3
+  - @llamaindex/cloud@4.0.3
+
+## 0.2.5
+
+### Patch Changes
+
+- 4999df1: bump nextjs
+- Updated dependencies [f5e4d09]
+  - llamaindex@0.9.16
+
+## 0.2.4
+
+### Patch Changes
+
+- 9c63f3f: Add support for openai responses api
+- Updated dependencies [9c63f3f]
+- Updated dependencies [c515a32]
+  - @llamaindex/openai@0.3.0
+  - @llamaindex/core@0.6.2
+  - @llamaindex/workflow@1.0.2
+  - llamaindex@0.9.15
+  - @llamaindex/cloud@4.0.2
+  - @llamaindex/node-parser@2.0.2
+  - @llamaindex/readers@3.0.2
+
+## 0.2.3
+
+### Patch Changes
+
+- 648cfb5: Add support for supabase vector store
+  Added doc for the supbase vector store
+- Updated dependencies [1b6f368]
+- Updated dependencies [eaf326e]
+- Updated dependencies [9d951b2]
+  - @llamaindex/core@0.6.1
+  - llamaindex@0.9.14
+  - @llamaindex/cloud@4.0.1
+  - @llamaindex/node-parser@2.0.1
+  - @llamaindex/openai@0.2.1
+  - @llamaindex/readers@3.0.1
+  - @llamaindex/workflow@1.0.1
+
+## 0.2.2
+
+### Patch Changes
+
+- e98033e: docs: correct the number of indexes
+
+## 0.2.1
+
+### Patch Changes
+
+- Updated dependencies [75d6e29]
+  - llamaindex@0.9.13
+
+## 0.2.0
+
+### Minor Changes
+
+- f1db9b3: Adding an options parameter to vercel tool to tailor responses
+
+### Patch Changes
+
+- 21bebfc: Expose more content to fix the issue with unavailable documentation links, and adjust the documentation based on the latest code.
+- 2b39cef: Added documentation for structured output in openai and ollama
+- Updated dependencies [21bebfc]
+- Updated dependencies [93bc0ff]
+- Updated dependencies [91a18e7]
+- Updated dependencies [bf56fc0]
+- Updated dependencies [f8a86e4]
+- Updated dependencies [5189b44]
+- Updated dependencies [58a9446]
+  - @llamaindex/readers@3.0.0
+  - @llamaindex/core@0.6.0
+  - @llamaindex/openai@0.2.0
+  - @llamaindex/cloud@4.0.0
+  - @llamaindex/workflow@1.0.0
+  - llamaindex@0.9.12
+  - @llamaindex/node-parser@2.0.0
+
+## 0.1.11
+
+### Patch Changes
+
+- a8c0637: feat: simplify to provide base URL to OpenAI
+- a654f58: Added docs for using perplexity
+- 98eebf7: Add RequestOptions parameter passing to support Gemini proxy calls.
+  Add a usage example for the RequestOptions parameter.
+- Updated dependencies [a8c0637]
+  - @llamaindex/openai@0.1.61
+  - llamaindex@0.9.11
+
 ## 0.1.10
 
 ### Patch Changes

apps/next/README.md

@@ -6,8 +6,7 @@ This is a Next.js application generated with
 Run development server:
 
 ```bash
-turbo run dev
-# turbo will build all required packages before running the dev server
+pnpm run dev
 ```
 
 ## Learn More

apps/next/fallback.js

@@ -0,0 +1,2 @@
+// fallback for `fs` usage in `web-tree-sitter`
+module.exports = {};

apps/next/next.config.mjs

@@ -1,9 +1,10 @@
 import { createMDX } from "fumadocs-mdx/next";
-import MonacoWebpackPlugin from "monaco-editor-webpack-plugin";
 const withMDX = createMDX();
 
 /** @type {import('next').NextConfig} */
 const config = {
+  // default timeout for static generation is 60s, but we need to increase it to 10 minutes due to the large number of document pages
+  staticPageGenerationTimeout: 600,
   reactStrictMode: true,
   eslint: {
     ignoreDuringBuilds: true,
@@ -14,7 +15,12 @@ const config = {
     "twoslash",
     "typescript",
   ],
-  webpack: (config, { isServer }) => {
+  turbopack: {
+    resolveAlias: {
+      fs: { browser: "./fallback.js" },
+    },
+  },
+  webpack: (config) => {
     if (Array.isArray(config.target) && config.target.includes("web")) {
       config.target = ["web", "es2020"];
     }
@@ -26,14 +32,6 @@ const config = {
     };
     config.resolve.fallback ??= {};
     config.resolve.fallback.fs = false;
-    if (!isServer) {
-      config.plugins.push(
-        new MonacoWebpackPlugin({
-          languages: ["typescript"],
-          filename: "static/[name].worker.js",
-        }),
-      );
-    }
     config.resolve.alias["replicate"] = false;
     return config;
   },

apps/next/package.json

@@ -1,18 +1,21 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.1.10",
+  "version": "0.2.14",
   "private": true,
   "scripts": {
     "postinstall": "fumadocs-mdx",
     "prebuild": "pnpm run build:docs",
     "build": "next build",
-    "dev": "next dev",
+    "dev": "next dev --turbo",
     "start": "next start",
-    "postbuild": "tsx scripts/post-build.mts",
-    "build:docs": "cross-env NODE_OPTIONS=\"--max-old-space-size=8192\" typedoc && tsx scripts/generate-docs.mts"
+    "postbuild": "tsx scripts/post-build.mts && tsx scripts/validate-links.mts",
+    "build:docs": "cross-env NODE_OPTIONS=\"--max-old-space-size=8192\" typedoc && tsx scripts/generate-docs.mts",
+    "validate-links": "tsx scripts/validate-links.mts"
   },
   "dependencies": {
+    "@huggingface/transformers": "^3.5.0",
     "@icons-pack/react-simple-icons": "^10.1.0",
+    "@llama-flow/docs": "0.0.5",
     "@llamaindex/chat-ui": "0.2.0",
     "@llamaindex/cloud": "workspace:*",
     "@llamaindex/core": "workspace:*",
@@ -21,6 +24,7 @@
     "@llamaindex/readers": "workspace:*",
     "@llamaindex/workflow": "workspace:*",
     "@mdx-js/mdx": "^3.1.0",
+    "@monaco-editor/react": "^4.7.0",
     "@number-flow/react": "^0.3.4",
     "@radix-ui/react-dialog": "^1.1.2",
     "@radix-ui/react-icons": "^1.3.2",
@@ -35,22 +39,21 @@
     "clsx": "2.1.1",
     "foxact": "^0.2.41",
     "framer-motion": "^11.11.17",
-    "fumadocs-core": "^15.0.15",
+    "fumadocs-core": "^15.2.7",
     "fumadocs-docgen": "^2.0.0",
-    "fumadocs-mdx": "^11.5.6",
-    "fumadocs-openapi": "^6.3.0",
-    "fumadocs-twoslash": "^3.1.0",
-    "fumadocs-typescript": "^3.1.0",
-    "fumadocs-ui": "^15.0.15",
+    "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": "^15.2.1",
+    "next": "^15.3.0",
     "next-themes": "^0.4.3",
-    "react": "^19.0.0",
-    "react-dom": "^19.0.0",
+    "react": "^19.1.0",
+    "react-dom": "^19.1.0",
     "react-icons": "^5.3.0",
-    "react-monaco-editor": "^0.56.2",
     "react-use-measure": "^2.1.1",
     "rehype-katex": "^7.0.1",
     "remark-math": "^6.0.0",
@@ -62,12 +65,14 @@
     "tailwindcss-animate": "^1.0.7",
     "tree-sitter": "^0.22.1",
     "tree-sitter-typescript": "^0.23.2",
+    "ts-morph": "^25.0.1",
+    "twoslash": "^0.3.1",
     "use-stick-to-bottom": "^1.0.42",
     "web-tree-sitter": "^0.24.4",
     "zod": "^3.23.8"
   },
   "devDependencies": {
-    "@next/env": "^15.2.1",
+    "@next/env": "^15.3.0",
     "@tailwindcss/postcss": "^4.0.9",
     "@types/mdx": "^2.0.13",
     "@types/node": "22.9.0",
@@ -77,7 +82,6 @@
     "cross-env": "^7.0.3",
     "fast-glob": "^3.3.2",
     "gray-matter": "^4.0.3",
-    "monaco-editor-webpack-plugin": "^7.1.0",
     "postcss": "^8.5.3",
     "raw-loader": "^4.0.2",
     "remark": "^15.0.1",
@@ -86,9 +90,9 @@
     "remark-stringify": "^11.0.0",
     "tailwindcss": "^4.0.9",
     "tsx": "^4.19.3",
-    "typedoc": "0.27.4",
-    "typedoc-plugin-markdown": "^4.3.1",
-    "typedoc-plugin-merge-modules": "^6.1.0",
+    "typedoc": "0.28.3",
+    "typedoc-plugin-markdown": "^4.6.2",
+    "typedoc-plugin-merge-modules": " ^7.0.0",
     "typescript": "^5.7.3"
   }
 }

apps/next/scripts/generate-docs.mts

@@ -1,27 +1,24 @@
-import { generateFiles as openapiGenerateFiles } from "fumadocs-openapi";
-import { generateFiles as typescriptGenerateFiles } from "fumadocs-typescript";
+import {
+  createGenerator,
+  generateFiles as typescriptGenerateFiles,
+} from "fumadocs-typescript";
 import fs from "node:fs";
 import * as path from "node:path";
 import { rimrafSync } from "rimraf";
 
+const generator = createGenerator();
 const out = "./src/content/docs/cloud/api";
 const apiRefOut = "./src/content/docs/api";
 
 // clean generated files
 rimrafSync(out, {
   filter(v) {
-    return !v.endsWith("index.mdx") && !v.endsWith("meta.json");
+    return !v.endsWith("index.md") && !v.endsWith("meta.json");
   },
 });
 
-void openapiGenerateFiles({
-  input: ["../../packages/cloud/openapi.json"],
-  output: "./src/content/docs/cloud/api",
-  groupBy: "tag",
-});
-
-void typescriptGenerateFiles({
-  input: ["./src/content/docs/api/**/*.mdx"],
+void typescriptGenerateFiles(generator, {
+  input: ["./src/content/docs/api/**/*.md"],
   output: (file) => path.resolve(path.dirname(file), path.basename(file)),
   transformOutput,
 });
@@ -30,19 +27,22 @@ function transformOutput(filePath: string, content: string) {
   const fileName = path.basename(filePath);
   let title = fileName.split(".")[0];
   if (title === "index") title = "LlamaIndex API Reference";
-  return `---\ntitle: ${title}\n---\n\n${transformAbsoluteUrl(content, filePath)}`;
+  return `---\ntitle: ${title}\n---\n\n${transformAbsoluteUrl(
+    content.replace(/(?<!\\)\{([^}]+)(?<!\\)}/g, "\\{$1\\}"),
+    filePath,
+  )}`;
 }
 
 /**
- * Transforms the content by converting relative MDX links to absolute docs API links
- * Example: [text](../type-aliases/TaskHandler.mdx) -> [text](/docs/api/type-aliases/TaskHandler)
- * [text](BaseChatEngine.mdx) -> [text](/docs/api/classes/BaseChatEngine)
- * [text](BaseVectorStore.mdx#constructors) -> [text](/docs/api/classes/BaseVectorStore#constructors)
- * [text](TaskStep.mdx) -> [text](/docs/api/type-aliases/TaskStep)
+ * Transforms the content by converting relative MD links to absolute docs API links
+ * Example: [text](../type-aliases/TaskHandler.md) -> [text](/docs/api/type-aliases/TaskHandler)
+ * [text](BaseChatEngine.md) -> [text](/docs/api/classes/BaseChatEngine)
+ * [text](BaseVectorStore.md#constructors) -> [text](/docs/api/classes/BaseVectorStore#constructors)
+ * [text](TaskStep.md) -> [text](/docs/api/type-aliases/TaskStep)
  */
 function transformAbsoluteUrl(content: string, filePath: string) {
   const group = path.dirname(filePath).split(path.sep).pop();
-  return content.replace(/\]\(([^)]+)\.mdx([^)]*)\)/g, (_, slug, anchor) => {
+  return content.replace(/\]\(([^)]+)\.md([^)]*)\)/g, (_, slug, anchor) => {
     const slugParts = slug.split("/");
     const fileName = slugParts[slugParts.length - 1];
     const fileGroup = slugParts[slugParts.length - 2] ?? group;

apps/next/scripts/validate-links.mts

@@ -0,0 +1,249 @@
+import glob from "fast-glob";
+import fs from "fs";
+import matter from "gray-matter";
+import path from "path";
+
+const CONTENT_DIR = path.join(process.cwd(), "src/content/docs");
+const BUILD_DIR = path.join(process.cwd(), ".next");
+
+// Regular expression to find internal links
+// This captures Markdown links [text](/docs/path) and href attributes href="/docs/path"
+const INTERNAL_LINK_REGEX = /(?:(?:\]\(|\bhref=["'])\/docs\/([^")]+))/g;
+
+// Regular expression to find relative links
+// This captures relative links like [text](./path) or ![alt](../images/image.png)
+const RELATIVE_LINK_REGEX = /(?:\]\()(?:\s*)(?:\.\.?)\//g;
+
+interface LinkValidationResult {
+  file: string;
+  invalidLinks: Array<{ link: string; line: number }>;
+}
+
+interface RelativeLinkResult {
+  file: string;
+  relativeLinks: Array<{ line: number; lineContent: string }>;
+}
+
+/**
+ * Get all valid documentation routes from the content directory
+ */
+async function getValidRoutes(): Promise<Set<string>> {
+  const mdxFiles = await glob("**/*.mdx?", { cwd: CONTENT_DIR });
+
+  const routes = new Set<string>();
+
+  // Add each MDX file as a valid route
+  for (const file of mdxFiles) {
+    // Remove .mdx extension and normalize to route format
+    let route = file.replace(/\.mdx?$/, "");
+
+    // Handle index files
+    if (route.endsWith("/index")) {
+      route = route.replace(/\/index$/, "");
+    } else if (route === "index") {
+      route = "";
+    }
+
+    routes.add(route);
+  }
+
+  return routes;
+}
+
+/**
+ * Extract internal links from a MDX file
+ */
+function extractLinksFromFile(
+  filePath: string,
+): Array<{ link: string; line: number }> {
+  const content = fs.readFileSync(filePath, "utf-8");
+  const { content: mdxContent } = matter(content);
+
+  const lines = mdxContent.split("\n");
+  const links: Array<{ link: string; line: number }> = [];
+
+  lines.forEach((line, lineNumber) => {
+    let match;
+    while ((match = INTERNAL_LINK_REGEX.exec(line)) !== null) {
+      if (match[1]) {
+        links.push({
+          link: match[1],
+          line: lineNumber + 1, // 1-based line numbers
+        });
+      }
+    }
+  });
+
+  return links;
+}
+
+/**
+ * Check if a link is an image link
+ */
+function isImageLink(link: string): boolean {
+  // Check for image extensions
+  const imageExtensions = [".png", ".jpg", ".jpeg", ".gif", ".svg", ".webp"];
+  const hasImageExtension = imageExtensions.some((ext) =>
+    link.toLowerCase().endsWith(ext),
+  );
+
+  // Check for markdown image syntax: ![alt](./path)
+  const isMarkdownImage = link.trim().startsWith("!");
+
+  return hasImageExtension || isMarkdownImage;
+}
+
+/**
+ * Extract relative links from a MDX file
+ */
+function findRelativeLinksInFile(
+  filePath: string,
+): Array<{ line: number; lineContent: string }> {
+  const content = fs.readFileSync(filePath, "utf-8");
+  const { content: mdxContent } = matter(content);
+
+  const lines = mdxContent.split("\n");
+  const relativeLinks: Array<{ line: number; lineContent: string }> = [];
+
+  lines.forEach((line, lineNumber) => {
+    // Check for relative links
+    if (RELATIVE_LINK_REGEX.test(line)) {
+      // Reset the regex lastIndex to start from the beginning of the line
+      RELATIVE_LINK_REGEX.lastIndex = 0;
+
+      // Skip image links
+      if (!isImageLink(line)) {
+        relativeLinks.push({
+          line: lineNumber + 1, // 1-based line numbers
+          lineContent: line.trim(),
+        });
+      }
+    }
+  });
+
+  return relativeLinks;
+}
+
+/**
+ * Validate internal links in all MDX files
+ */
+/**
+ * Find relative links in all MDX files
+ */
+async function findRelativeLinks(): Promise<RelativeLinkResult[]> {
+  const mdxFiles = await glob("**/*.mdx?", { cwd: CONTENT_DIR });
+  const results: RelativeLinkResult[] = [];
+
+  for (const file of mdxFiles) {
+    const filePath = path.join(CONTENT_DIR, file);
+    const relativeLinks = findRelativeLinksInFile(filePath);
+
+    if (relativeLinks.length > 0) {
+      results.push({
+        file,
+        relativeLinks,
+      });
+    }
+  }
+
+  return results;
+}
+
+async function validateLinks(): Promise<LinkValidationResult[]> {
+  const mdxFiles = await glob("**/*.mdx?", { cwd: CONTENT_DIR });
+  const validRoutes = await getValidRoutes();
+
+  const results: LinkValidationResult[] = [];
+
+  for (const file of mdxFiles) {
+    const filePath = path.join(CONTENT_DIR, file);
+    const links = extractLinksFromFile(filePath);
+
+    const invalidLinks = links.filter(({ link }) => {
+      // Check if the link exists in valid routes
+      // First normalize the link (remove any query string or hash)
+      const baseLink = link.split("?")[0].split("#")[0];
+      // Remove the trailing slash if present.
+      // This works with links like "api/interfaces/MetadataFilter#operator" and "api/interfaces/MetadataFilter/#operator".
+      const normalizedLink = baseLink.endsWith("/")
+        ? baseLink.slice(0, -1)
+        : baseLink;
+
+      // Remove llamaindex/ prefix if it exists as it's the root of the docs
+      let routePath = normalizedLink;
+      if (routePath.startsWith("llamaindex/")) {
+        routePath = routePath.substring("llamaindex/".length);
+      }
+
+      return !validRoutes.has(normalizedLink) && !validRoutes.has(routePath);
+    });
+
+    if (invalidLinks.length > 0) {
+      results.push({
+        file,
+        invalidLinks,
+      });
+    }
+  }
+
+  return results;
+}
+
+/**
+ * Main function to validate links and report errors
+ */
+async function main() {
+  console.log("🔍 Validating links in documentation...");
+
+  try {
+    // Check for invalid internal links
+    const validationResults: LinkValidationResult[] = await validateLinks();
+    // Check for relative links
+    const relativeLinksResults = await findRelativeLinks();
+
+    let hasErrors = false;
+
+    // Report invalid internal links
+    if (validationResults.length > 0) {
+      console.error("❌ Found invalid internal links:");
+      hasErrors = true;
+
+      for (const result of validationResults) {
+        console.error(`\nFile: ${result.file}`);
+
+        for (const { link, line } of result.invalidLinks) {
+          console.error(`  - Line ${line}: /docs/${link}`);
+        }
+      }
+    }
+
+    // Report relative links
+    if (relativeLinksResults.length > 0) {
+      console.error("\n❌ Found relative links (use absolute paths instead):");
+      hasErrors = true;
+
+      for (const result of relativeLinksResults) {
+        console.error(`\nFile: ${result.file}`);
+
+        for (const { line, lineContent } of result.relativeLinks) {
+          console.error(`  - Line ${line}: ${lineContent}`);
+        }
+      }
+    }
+
+    if (hasErrors) {
+      // Exit with error code to fail the build
+      process.exit(1);
+    } else {
+      console.log("✅ All links are valid!");
+    }
+  } catch (error) {
+    console.error("Error validating links:", error);
+    process.exit(1);
+  }
+}
+
+main().catch((error) => {
+  console.error("Unhandled error:", error);
+  process.exit(1);
+});

apps/next/source.config.ts

@@ -1,13 +1,18 @@
-import { rehypeCodeDefaultOptions } from "fumadocs-core/mdx-plugins";
+import {
+  rehypeCodeDefaultOptions,
+  remarkStructure,
+} from "fumadocs-core/mdx-plugins";
 import { fileGenerator, remarkDocGen, remarkInstall } from "fumadocs-docgen";
 import { defineConfig, defineDocs } from "fumadocs-mdx/config";
 import { transformerTwoslash } from "fumadocs-twoslash";
-import { createFileSystemTypesCache } from "fumadocs-twoslash/cache-fs";
 import rehypeKatex from "rehype-katex";
 import remarkMath from "remark-math";
 
 export const docs = defineDocs({
-  dir: "./src/content/docs",
+  dir: ["./src/content/docs", "./node_modules/@llama-flow/docs"],
+  docs: {
+    async: true,
+  },
 });
 
 export default defineConfig({
@@ -21,11 +26,7 @@ export default defineConfig({
       },
       transformers: [
         ...(rehypeCodeDefaultOptions.transformers ?? []),
-        transformerTwoslash({
-          typesCache: createFileSystemTypesCache({
-            dir: ".next/cache/twoslash",
-          }),
-        }),
+        transformerTwoslash(),
         {
           name: "transformers:remove-notation-escape",
           code(hast) {
@@ -46,6 +47,7 @@ export default defineConfig({
       ],
     },
     remarkPlugins: [
+      remarkStructure,
       remarkMath,
       [remarkInstall, { persist: { id: "package-manager" } }],
       [remarkDocGen, { generators: [fileGenerator()] }],

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

@@ -10,16 +10,55 @@ import { MagicMove } from "@/components/magic-move";
 import { NpmInstall } from "@/components/npm-install";
 import { Supports } from "@/components/supports";
 import { Button } from "@/components/ui/button";
-import { Skeleton } from "@/components/ui/skeleton";
-import { LEGACY_DOCUMENT_URL } from "@/lib/const";
+import { DOCUMENT_URL } from "@/lib/const";
 import { SiStackblitz } from "@icons-pack/react-simple-icons";
-import {
-  CodeBlock as FumaCodeBlock,
-  Pre,
-} from "fumadocs-ui/components/codeblock";
 import { Blocks, Bot, Footprints, Terminal } from "lucide-react";
 import Link from "next/link";
-import { Suspense } from "react";
+
+const codes = [
+  `import { openai } from "@llamaindex/openai";
+
+const llm = openai();
+const response = await llm.complete({ prompt: "How are you?" });`,
+  `import { openai } from "@llamaindex/openai";
+
+const llm = openai();
+const response = await llm.chat({
+  messages: [{ content: "Tell me a joke.", role: "user" }],
+});`,
+  `import { agent } from "llamaindex";
+import { openai } from "@llamaindex/openai";
+
+const analyseAgent = agent({
+  llm: openai({ model: "gpt-4o" }),
+  tools: [analyseTools],
+  systemPrompt,
+});
+const response = await analyseAgent.run(\`Analyse the given data:
+\${data}\`);`,
+  `import { agent, multiAgent } from "llamaindex";
+import { openai } from "@llamaindex/openai";
+
+const analyseAgent = agent({
+  name: "AnalyseAgent",
+  llm: openai({ model: "gpt-4o" }),
+  tools: [analyseTools],
+});
+const reporterAgent = agent({
+  name: "ReporterAgent",
+  llm: openai({ model: "gpt-4o" }),
+  tools: [reporterTools],
+  canHandoffTo: [analyseAgent],
+});
+
+const agents = multiAgent({
+  agents: [analyseAgent, reporterAgent],
+  rootAgent: reporterAgent,
+});
+
+const response = await agents.run(\`Analyse the given data:
+\${data}\`);`,
+];
 
 export default function HomePage() {
   return (
@@ -39,7 +78,7 @@ export default function HomePage() {
       </div>
 
       <div className="flex flex-wrap justify-center gap-4">
-        <Link href={LEGACY_DOCUMENT_URL}>
+        <Link href={DOCUMENT_URL}>
           <Button variant="outline">Get Started</Button>
         </Link>
         <NpmInstall />
@@ -60,63 +99,12 @@ export default function HomePage() {
           icon={Footprints}
           subheading="Progressive"
           heading="From the simplest to the most complex"
-          description="LlamaIndex.TS is designed to be simple to get started, but powerful enough to build complex, agentic AI applications."
+          description="LlamaIndex.TS is designed to be simple to get started, but powerful enough to build complex, agentic AI applications using multi-agents."
         >
-          <Suspense
-            fallback={
-              <FumaCodeBlock allowCopy={false}>
-                <Pre>
-                  <div className="space-y-2">
-                    <Skeleton className="h-4 w-[250px]" />
-                    <Skeleton className="h-4 w-[200px]" />
-                  </div>
-                </Pre>
-              </FumaCodeBlock>
-            }
-          >
-            <MagicMove
-              code={[
-                `import { OpenAI } from "@llamaindex/openai";
-
-const llm = new OpenAI();
-const response = await llm.complete({ prompt: "How are you?" });`,
-                `import { OpenAI } from "@llamaindex/openai";
-
-const llm = new OpenAI();
-const response = await llm.chat({
-  messages: [{ content: "Tell me a joke.", role: "user" }],
-});`,
-                `import { ChatMemoryBuffer } from "llamaindex";
-import { OpenAI } from "@llamaindex/openai";
-
-const llm = new OpenAI({ model: 'gpt4o-turbo' });
-const buffer = new ChatMemoryBuffer({
-  tokenLimit: 128_000,
-})
-buffer.put({ content: "Tell me a joke.", role: "user" })
-const response = await llm.chat({
-  messages: buffer.getMessages(),
-  stream: true
-});`,
-                `import { ChatMemoryBuffer } from "llamaindex";
-import { OpenAIAgent } from "@llamaindex/openai";
-
-const agent = new OpenAIAgent({
-  llm,
-  tools: [...myTools]
-  systemPrompt,
-});
-const buffer = new ChatMemoryBuffer({
-  tokenLimit: 128_000,
-})
-buffer.put({ content: "Analysis the data based on the given data.", role: "user" })
-buffer.put({ content: \`\${data}\`, role: "user" })
-const response = await agent.chat({
-  message: buffer.getMessages(),
-});`,
-              ]}
-            />
-          </Suspense>
+          <MagicMove
+            placeholder={<CodeBlock lang="ts" code={codes[0]} />}
+            code={codes}
+          />
         </Feature>
         <Feature
           icon={Bot}
@@ -125,20 +113,20 @@ const response = await agent.chat({
           description="Truly powerful retrieval-augmented generation applications use agentic techniques, and LlamaIndex.TS makes it easy to build them."
         >
           <CodeBlock
-            code={`import { agent } from "llamaindex";
-import { OpenAI } from "@llamaindex/openai";
+            code={`import { agent, SimpleDirectoryReader, VectorStoreIndex } from "llamaindex";
+import { openai } from "@llamaindex/openai";
 
-// using a previously created LlamaIndex index to query information from
-const queryTool = index.queryTool();
+// load documents from current directoy into an index
+const reader = new SimpleDirectoryReader();
+const documents = await reader.loadData(currentDir);
+const index = await VectorStoreIndex.fromDocuments(documents);
 
-const agent = agent({
-  llm: new OpenAI({
-    model: "gpt-4o",
-  }),
-  tools: [queryTool],
+const myAgent = agent({
+  llm: openai({ model: "gpt-4o" }),
+  tools: [index.queryTool()],
 });
 
-await agent.run('...');`}
+await myAgent.run('...');`}
             lang="ts"
           />
         </Feature>

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

@@ -1,4 +1,12 @@
 import { source } from "@/lib/source";
+import { structure } from "fumadocs-core/mdx-plugins";
 import { createFromSource } from "fumadocs-core/search/server";
 
-export const { GET } = createFromSource(source);
+// TODO: migrate to another search service, I don't think Vercel can handle that many of documents.
+export const { GET } = createFromSource(source, (page) => ({
+  id: page.file.path,
+  title: page.data.title,
+  description: page.data.description,
+  url: page.url,
+  structuredData: structure(page.data.content),
+}));

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

@@ -1,7 +1,14 @@
+import { ChatDemoRSC } from "@/components/demo/chat/rsc/demo";
+import * as demos from "@/components/demo/lazy";
 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";
-import { createTypeTable } from "fumadocs-typescript/ui";
+import { createGenerator } from "fumadocs-typescript";
+import { AutoTypeTable } from "fumadocs-typescript/ui";
+import { Accordion, Accordions } from "fumadocs-ui/components/accordion";
+import { Tab, Tabs } from "fumadocs-ui/components/tabs";
 import defaultMdxComponents from "fumadocs-ui/mdx";
 import {
   DocsBody,
@@ -11,7 +18,7 @@ import {
 } from "fumadocs-ui/page";
 import { notFound } from "next/navigation";
 
-const { AutoTypeTable } = createTypeTable();
+const generator = createGenerator();
 
 export const revalidate = false;
 
@@ -22,16 +29,17 @@ export default async function Page(props: {
   const page = source.getPage(params.slug);
   if (!page) notFound();
 
-  const MDX = page.data.body;
+  const { body: MDX, toc, lastModified } = await page.data.load();
 
   return (
     <DocsPage
-      toc={page.data.toc}
+      toc={toc}
       full={page.data.full}
-      lastUpdate={page.data.lastModified}
+      lastUpdate={lastModified}
       editOnGithub={{
         owner: "run-llama",
         repo: "LlamaIndexTS",
+        sha: "main",
         path: `apps/next/src/content/docs/${page.file.path}`,
       }}
     >
@@ -40,12 +48,21 @@ export default async function Page(props: {
       <DocsBody>
         <MDX
           components={{
+            ...Icons,
             ...defaultMdxComponents,
-            APIPage: openapi.APIPage,
+            ...demos,
+            ChatDemoRSC,
+            Accordion,
+            Accordions,
+            APIPage: (props) => <APIPage {...openapi.getAPIPageProps(props)} />,
+            Tab,
+            Tabs,
             Popup,
             PopupContent,
             PopupTrigger,
-            AutoTypeTable,
+            AutoTypeTable: (props) => (
+              <AutoTypeTable generator={generator} {...props} />
+            ),
           }}
         />
       </DocsBody>

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

@@ -1,11 +1,7 @@
 import { baseOptions } from "@/app/layout.config";
-import { AITrigger } from "@/components/ai-chat";
-import { buttonVariants } from "@/components/ui/button";
 import { source } from "@/lib/source";
-import { cn } from "@/lib/utils";
 import "fumadocs-twoslash/twoslash.css";
 import { DocsLayout } from "fumadocs-ui/layouts/docs";
-import { MessageCircle } from "lucide-react";
 import type { ReactNode } from "react";
 
 export default function Layout({ children }: { children: ReactNode }) {
@@ -13,23 +9,9 @@ export default function Layout({ children }: { children: ReactNode }) {
     <DocsLayout
       tree={source.pageTree}
       {...baseOptions}
+      links={[]}
       nav={{
         ...baseOptions.nav,
-        children: (
-          <AITrigger
-            className={cn(
-              buttonVariants({
-                variant: "secondary",
-                size: "xs",
-                className:
-                  "text-fd-muted-foreground ms-2 gap-1.5 rounded-full px-2 md:flex-1",
-              }),
-            )}
-          >
-            <MessageCircle className="size-3" />
-            Ask LlamaCloud
-          </AITrigger>
-        ),
       }}
     >
       {children}

apps/next/src/app/global.css

@@ -1,7 +1,7 @@
 @import "tailwindcss";
 @import "fumadocs-ui/css/neutral.css";
 @import "fumadocs-ui/css/preset.css";
-@import "../../node_modules/fumadocs-twoslash/dist/twoslash.css";
+@import "../../node_modules/fumadocs-twoslash/styles/twoslash.css";
 @plugin "tailwindcss-animate";
 @source '../../node_modules/fumadocs-ui/dist/**/*.js';
 @source "../../node_modules/fumadocs-openapi/dist/**/*.js",

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

@@ -1,4 +1,4 @@
-import { LEGACY_DOCUMENT_URL } from "@/lib/const";
+import { DOCUMENT_URL } from "@/lib/const";
 import type { BaseLayoutProps } from "fumadocs-ui/layouts/shared";
 import Image from "next/image";
 
@@ -27,9 +27,19 @@ export const baseOptions: BaseLayoutProps = {
   githubUrl: "https://github.com/run-llama/LlamaIndexTS",
   links: [
     {
-      text: "Docs",
-      url: LEGACY_DOCUMENT_URL,
+      text: "TypeScript",
+      url: DOCUMENT_URL,
       active: "nested-url",
     },
+    {
+      text: "Python",
+      url: "https://docs.llamaindex.ai",
+      active: "url",
+    },
+    {
+      text: "LlamaCloud",
+      url: "https://docs.cloud.llamaindex.ai/",
+      active: "url",
+    },
   ],
 };

apps/next/src/app/llms.txt/route.ts

@@ -13,11 +13,7 @@ import remarkStringify from "remark-stringify";
 export const revalidate = false;
 
 export async function GET() {
-  const files = await fg([
-    "./src/content/docs/**/*.mdx",
-    // remove generated openapi files
-    "!./src/content/docs/cloud/api/**/*",
-  ]);
+  const files = await fg(["./src/content/docs/**/*.mdx"]);
 
   const scan = files.map(async (file) => {
     const fileContent = await fs.readFile(file);

apps/next/src/components/demo/code-node-parser.tsx

@@ -1,24 +1,26 @@
 "use client";
-import { createContextState } from "foxact/context-state";
-import { useIsClient } from "foxact/use-is-client";
-import { useShiki } from "fumadocs-core/utils/use-shiki";
-import { CodeBlock, Pre } from "fumadocs-ui/components/codeblock";
-import { lazy, Suspense, use, useMemo } from "react";
-import { StickToBottom, useStickToBottomContext } from "use-stick-to-bottom";
-import Parser from "web-tree-sitter";
-
 import { Label } from "@/components/ui/label";
 import { Skeleton } from "@/components/ui/skeleton";
 import { Slider } from "@/components/ui/slider";
 import { CodeSplitter } from "@llamaindex/node-parser/code";
+import { Editor } from "@monaco-editor/react";
+import { createContextState } from "foxact/context-state";
+import { useIsClient } from "foxact/use-is-client";
+import { useShiki } from "fumadocs-core/highlight/client";
+import { CodeBlock, Pre } from "fumadocs-ui/components/codeblock";
+import { Suspense, use, useMemo } from "react";
+import { StickToBottom, useStickToBottomContext } from "use-stick-to-bottom";
 
 let promise: Promise<CodeSplitter>;
 if (typeof window !== "undefined") {
-  promise = Parser.init({
-    locateFile(scriptName: string) {
-      return "/" + scriptName;
-    },
-  }).then(async () => {
+  async function run() {
+    const { default: Parser } = await import("web-tree-sitter");
+    await Parser.init({
+      locateFile(scriptName: string) {
+        return "/" + scriptName;
+      },
+    });
+
     const parser = new Parser();
     const Lang = await Parser.Language.load("/tree-sitter-typescript.wasm");
     parser.setLanguage(Lang);
@@ -26,7 +28,9 @@ if (typeof window !== "undefined") {
       getParser: () => parser,
       maxChars: 100,
     });
-  });
+  }
+
+  promise = run();
 }
 
 const [SliderProvider, useSlider, useSetSlider] = createContextState(100);
@@ -48,8 +52,6 @@ const john: Person = {
 
 console.log(greet(john));`);
 
-const Editor = lazy(() => import("react-monaco-editor"));
-
 export const IDE = () => {
   const codeSplitter = use(promise);
   const code = useCode();
@@ -73,21 +75,6 @@ export const IDE = () => {
         />
       </div>
       <Editor
-        editorWillMount={() => {}}
-        editorDidMount={() => {
-          window.MonacoEnvironment!.getWorkerUrl = (
-            _moduleId: string,
-            label: string,
-          ) => {
-            if (label === "json") return "/_next/static/json.worker.js";
-            if (label === "css") return "/_next/static/css.worker.js";
-            if (label === "html") return "/_next/static/html.worker.js";
-            if (label === "typescript" || label === "javascript")
-              return "/_next/static/ts.worker.js";
-            return "/_next/static/editor.worker.js";
-          };
-        }}
-        editorWillUnmount={() => {}}
         options={{
           minimap: {
             enabled: false,
@@ -97,7 +84,9 @@ export const IDE = () => {
         height="100%"
         width="100%"
         language="typescript"
-        onChange={setCode}
+        onChange={(v) => {
+          if (v) setCode(v);
+        }}
         value={code}
       />
     </div>

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

@@ -0,0 +1,18 @@
+"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,
+  ),
+);
+export const WorkflowStreamingDemo = dynamic(() =>
+  import("@/components/demo/workflow-streaming-ui").then(
+    (mod) => mod.WorkflowStreamingDemo,
+  ),
+);

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

@@ -1,25 +1,27 @@
 "use client";
 import { Button } from "@/components/ui/button";
 import { cn } from "@/lib/utils";
-import { CodeBlock, Pre } from "fumadocs-ui/components/codeblock";
+import { CodeBlock } from "fumadocs-ui/components/codeblock";
 import { RotateCcw } from "lucide-react";
 import { useTheme } from "next-themes";
-import { use, useCallback, useEffect, useState } from "react";
-import { getSingletonHighlighter } from "shiki";
+import { type ReactNode, use, useCallback, useEffect, useState } from "react";
+import { createJavaScriptRegexEngine, getSingletonHighlighter } from "shiki";
 import { ShikiMagicMove } from "shiki-magic-move/react";
-import { createOnigurumaEngine } from "shiki/engine/oniguruma";
 
+const engine = createJavaScriptRegexEngine();
 const highlighterPromise = getSingletonHighlighter({
-  engine: createOnigurumaEngine(() => import("shiki/wasm")),
+  engine,
   themes: ["vesper", "github-light"],
   langs: ["js", "ts", "tsx"],
 });
 
 export type MagicMoveProps = {
   code: string[];
+  placeholder: ReactNode;
 };
 
 export function MagicMove(props: MagicMoveProps) {
+  const [mounted, setMounted] = useState(false);
   const [move, setMove] = useState<number>(0);
   const currentCode = props.code[move];
   const highlighter = use(highlighterPromise);
@@ -38,24 +40,27 @@ export function MagicMove(props: MagicMoveProps) {
     }
   }, [animate, move, props.code]);
 
+  useEffect(() => {
+    setMounted(true);
+  }, []);
+
+  if (!mounted) return props.placeholder;
+
   return (
     <CodeBlock allowCopy={false}>
-      {highlighter && (
-        <Pre>
-          <ShikiMagicMove
-            lang="ts"
-            theme={resolvedTheme === "dark" ? "vesper" : "github-light"}
-            highlighter={highlighter}
-            code={currentCode}
-            options={{
-              duration: 800,
-              stagger: 0.3,
-              lineNumbers: false,
-              containerStyle: false,
-            }}
-          />
-        </Pre>
-      )}
+      <ShikiMagicMove
+        className="shiki !block p-4 *:!inline"
+        lang="ts"
+        theme={resolvedTheme === "dark" ? "vesper" : "github-light"}
+        highlighter={highlighter}
+        code={currentCode}
+        options={{
+          duration: 800,
+          stagger: 0.3,
+          lineNumbers: false,
+          containerStyle: false,
+        }}
+      />
       <Button
         className={cn(
           "absolute bottom-2 right-2",

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

@@ -1,8 +0,0 @@
----
-title: LlamaCloud
-description: 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.
----
-
-This is TypeScript binding for LlamaCloud API. It provides a simple way to interact with LlamaCloud API.
-
-If you are looking for the official documentation, please visit the [Official Document](https://docs.cloud.llamaindex.ai/)

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

@@ -1,6 +0,0 @@
-{
-  "title": "LlamaCloud",
-  "description": "The Cloud framework for LLM",
-  "root": true,
-  "pages": ["---Guide---", "index", "..."]
-}

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

@@ -1,12 +0,0 @@
----
-title: Agents
----
-
-A built-in agent that can take decisions and reasoning based on the tools provided to it.
-
-## OpenAI Agent
-
-import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
-import CodeSource from "!raw-loader!../../../../../../../examples/agent/openai";
-
-<DynamicCodeBlock lang="ts" code={CodeSource} />

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

@@ -1,28 +0,0 @@
----
-title: Gemini Agent
----
-
-import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
-import CodeSourceGemini from "!raw-loader!../../../../../../../examples/gemini/agent.ts";
-
-## Installation
-
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install llamaindex @llamaindex/google
-	```
-
-	```shell tab="yarn"
-	yarn add llamaindex @llamaindex/google
-	```
-
-	```shell tab="pnpm"
-	pnpm add llamaindex @llamaindex/google
-	```
-</Tabs>
-
-## Source 
-
-<DynamicCodeBlock lang="ts" code={CodeSourceGemini} />

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

@@ -1,10 +0,0 @@
----
-title: Chat Engine
----
-
-import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
-import CodeSource from "!raw-loader!../../../../../../../examples/chatEngine";
-
-Chat Engine is a class that allows you to create a chatbot from a retriever. It is a wrapper around a retriever that allows you to chat with it in a conversational manner.
-
-<DynamicCodeBlock lang="ts" code={CodeSource} />

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

@@ -1,59 +0,0 @@
----
-title: Context-Aware Agent
----
-
-The Context-Aware Agent enhances the capabilities of standard LLM agents by incorporating relevant context from a retriever for each query. This allows the agent to provide more informed and specific responses based on the available information.
-
-## Usage
-
-Here's a simple example of how to use the Context-Aware Agent:
-
-```typescript
-import {
-  Document,
-  VectorStoreIndex,
-} from "llamaindex";
-import { OpenAI, OpenAIContextAwareAgent } from "@llamaindex/openai";
-
-async function createContextAwareAgent() {
-  // Create and index some documents
-  const documents = [
-    new Document({
-      text: "LlamaIndex is a data framework for LLM applications.",
-      id_: "doc1",
-    }),
-    new Document({
-      text: "The Eiffel Tower is located in Paris, France.",
-      id_: "doc2",
-    }),
-  ];
-
-  const index = await VectorStoreIndex.fromDocuments(documents);
-  const retriever = index.asRetriever({ similarityTopK: 1 });
-
-  // Create the Context-Aware Agent
-  const agent = new OpenAIContextAwareAgent({
-    llm: new OpenAI({ model: "gpt-3.5-turbo" }),
-    contextRetriever: retriever,
-  });
-
-  // Use the agent to answer queries
-  const response = await agent.chat({
-    message: "What is LlamaIndex used for?",
-  });
-
-  console.log("Agent Response:", response.response);
-}
-
-createContextAwareAgent().catch(console.error);
-```
-
-In this example, the Context-Aware Agent uses the retriever to fetch relevant context for each query, allowing it to provide more accurate and informed responses based on the indexed documents.
-
-## Key Components
-
-- `contextRetriever`: A retriever (e.g., from a VectorStoreIndex) that fetches relevant documents or passages for each query.
-
-## Available Context-Aware Agents
-
-- `OpenAIContextAwareAgent`: A context-aware agent using OpenAI's models.

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

@@ -1,15 +0,0 @@
-{
-  "title": "Examples",
-  "pages": [
-    "more_examples",
-    "chat_engine",
-    "vector_index",
-    "summary_index",
-    "save_load_index",
-    "context_aware_agent",
-    "agent",
-    "agent_gemini",
-    "local_llm",
-    "other_llms"
-  ]
-}

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

@@ -1,66 +0,0 @@
----
-title: Using other LLM APIs
----
-
-import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
-import CodeSource from "!raw-loader!../../../../../../../examples/mistral";
-
-By default LlamaIndex.TS uses OpenAI's LLMs and embedding models, but we support [lots of other LLMs](../modules/llms) including models from Mistral (Mistral, Mixtral), Anthropic (Claude) and Google (Gemini).
-
-If you don't want to use an API at all you can [run a local model](../../examples/local_llm).
-
-This example runs you through the process of setting up a Mistral model:
-
-
-## Installation
-
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install llamaindex @llamaindex/mistral
-	```
-
-	```shell tab="yarn"
-	yarn add llamaindex @llamaindex/mistral
-	```
-
-	```shell tab="pnpm"
-	pnpm add llamaindex @llamaindex/mistral
-	```
-</Tabs>
-
-## Using another LLM
-
-You can specify what LLM LlamaIndex.TS will use on the `Settings` object, like this:
-
-```typescript
-import { MistralAI } from "@llamaindex/mistral";
-import { Settings } from "llamaindex";
-
-Settings.llm = new MistralAI({
-  model: "mistral-tiny",
-  apiKey: "<YOUR_API_KEY>",
-});
-```
-
-You can see examples of other APIs we support by checking out "Available LLMs" in the sidebar of our [LLMs section](../modules/llms).
-
-## Using another embedding model
-
-A frequent gotcha when trying to use a different API as your LLM is that LlamaIndex will also by default index and embed your data using OpenAI's embeddings. To completely switch away from OpenAI you will need to set your embedding model as well, for example:
-
-```typescript
-import { MistralAIEmbedding } from "@llamaindex/mistral";
-import { Settings } from "llamaindex";
-
-Settings.embedModel = new MistralAIEmbedding();
-```
-
-We support [many different embeddings](../modules/embeddings).
-
-## Full example
-
-This example uses Mistral's `mistral-tiny` model as the LLM and Mistral for embeddings as well.
-
-<DynamicCodeBlock lang="ts" code={CodeSource} />

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

@@ -1,8 +0,0 @@
----
-title: Save/Load an Index
----
-
-import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
-import CodeSource from "!raw-loader!../../../../../../../examples/storageContext";
-
-<DynamicCodeBlock lang="ts" code={CodeSource} />

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

@@ -1,8 +0,0 @@
----
-title: Summary Index
----
-
-import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
-import CodeSource from "!raw-loader!../../../../../../../examples/summaryIndex";
-
-<DynamicCodeBlock lang="ts" code={CodeSource} />

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

@@ -1,8 +0,0 @@
----
-title: Vector Index
----
-
-import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
-import CodeSource from "!raw-loader!../../../../../../../examples/vectorIndex";
-
-<DynamicCodeBlock lang="ts" code={CodeSource} />

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

@@ -1,11 +1,7 @@
 ---
-title: Chatbot tutorial
+title: Create-Llama
 ---
 
-Once you've mastered basic [retrieval-augment generation](retrieval_augmented_generation) you may want to create an interface to chat with your data. You can do this step-by-step, but we recommend getting started quickly using `create-llama`.
-
-## Using 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:
@@ -22,4 +18,4 @@ 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)
+![create-llama interface](/images/create_llama.png)

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

@@ -1,17 +1,17 @@
 ---
-title: See all examples
+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.
 
-## Check out all examples
+## 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 install
+npm i
 ```
 
 Then you can run any example in the folder with `tsx`, e.g.:
@@ -19,3 +19,14 @@ 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
+  className="w-full h-[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"
+/>

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

@@ -1,56 +0,0 @@
----
-title: Installation
-description: How to install llamaindex packages.
----
-
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-To install llamaindex, run the following command:
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install llamaindex
-	```
-
-	```shell tab="yarn"
-	yarn add llamaindex
-	```
-
-	```shell tab="pnpm"
-	pnpm add llamaindex
-	```
-</Tabs>
-
-In most cases, you'll also need an LLM package to use LlamaIndex. For example, to use the OpenAI LLM, you would install the following:
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install @llamaindex/openai
-	```
-
-	```shell tab="yarn"
-	yarn add @llamaindex/openai
-	```
-
-	```shell tab="pnpm"
-	pnpm add @llamaindex/openai
-	```
-</Tabs>
-
-Go to [Using other LLM APIs](/docs/llamaindex/examples/other_llms) to find out how to use other LLMs.
-
-
-## What's next?
-
-<Cards>
-	<Card
-		title="I want to try LlamaIndex.TS"
-		description="Learn how to use LlamaIndex.TS with different JS runtime and frameworks."
-		href="/docs/llamaindex/getting_started/setup"
-	/>
-	<Card
-		title="Show me code examples"
-		description="Explore code examples using LlamaIndex.TS."
-		href="https://stackblitz.com/github/run-llama/LlamaIndexTS/tree/main/examples?file=README.md"
-	/>
-</Cards>

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

@@ -3,18 +3,11 @@ title: With Cloudflare Worker
 description: In this guide, you'll learn how to use LlamaIndex with CloudFlare Worker
 ---
 
-import {
-  SiNodedotjs,
-  SiDeno,
-  SiBun,
-  SiCloudflareworkers,
-} from "@icons-pack/react-simple-icons";
-
 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/setup/node"
+  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>.
@@ -69,7 +62,7 @@ export default {
 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, insteadof a long-running process in Node.js.
+- You are recommend to design your code using network request, such as use `fetch` API to communicate with database, instead of a long-running process in Node.js.
 - Some of LlamaIndex.TS packages are not available in Cloudflare Worker, for example `@llamaindex/readers` and `@llamaindex/huggingface`.
 - The main `llamaindex` is designed to work in all JavaScript environment, including Cloudflare Worker. If you find any issue, please report to us.
 - `@llamaindex/env` is a JS environment binding module, which polyfill some Node.js/Modern Web API (for example, we have a memory based `fs` module, and Crypto API polyfill). It is designed to work in all JavaScript environment, including Cloudflare Worker.

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

@@ -0,0 +1,69 @@
+---
+title: Installation
+description: How to install llamaindex packages.
+---
+
+To install llamaindex, run the following command:
+
+```package-install
+npm i llamaindex
+```
+
+In most cases, you'll also need an LLM package to use LlamaIndex. For example, to use the OpenAI LLM, you would install the following:
+
+```package-install
+npm i @llamaindex/openai
+```
+
+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.
+
+<Cards>
+	<Card title={
+		<>
+			<SiNodedotjs className="inline" color="#5FA04E" /> Node.js
+		</>
+	} href="/docs/llamaindex/getting_started/installation/node" />
+	<Card title={
+		<>
+			<SiTypescript className="inline" color="#3178C6" /> TypeScript
+		</>
+	} href="/docs/llamaindex/getting_started/installation/typescript" />
+	<Card title={
+		<>
+			<SiVite className='inline' color='#646CFF' /> Vite
+		</>
+	} href="/docs/llamaindex/getting_started/installation/vite" />
+	<Card
+		title={
+			<>
+				<SiNextdotjs className='inline' /> Next.js (React Server Component)
+			</>
+		}
+		href="/docs/llamaindex/getting_started/installation/next"
+	/>
+	<Card title={
+		<>
+			<SiCloudflareworkers className='inline' color='#F38020' /> Cloudflare Workers
+		</>
+	} href="/docs/llamaindex/getting_started/installation/cloudflare" />
+</Cards>
+
+## What's next?
+
+<Cards>
+	<Card
+		title="Learn LlamaIndex.TS"
+		description="Learn how to use LlamaIndex.TS by starting with one of our tutorials."
+		href="/docs/llamaindex/tutorials/rag"
+	/>
+	<Card
+		title="Show me code examples"
+		description="Explore code examples using LlamaIndex.TS."
+		href="/docs/llamaindex/getting_started/examples"
+	/>
+</Cards>

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

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

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

@@ -7,7 +7,7 @@ Before you start, make sure you have try LlamaIndex.TS in Node.js to make sure y
 
 <Card
   title="Getting Started with LlamaIndex.TS in Node.js"
-  href="/docs/llamaindex/getting_started/setup/node"
+  href="/docs/llamaindex/getting_started/installation/node"
 />
 
 ## Differences between Node.js and Next.js
@@ -17,9 +17,9 @@ 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.
-LlamaIndex.TS has lots of upstream dependencies, some of them are not compatible with Next.js.
+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. 
 
-You might need to use `withNext` to make sure that LlamaIndex.TS works well with Next.js.
+Make sure to use `withLlamaIndex` to make sure that LlamaIndex.TS works well with Next.js.
 
 ```js
 // next.config.mjs / next.config.ts
@@ -35,7 +35,7 @@ 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](./cloudflare#difference-between-nodejs-and-cloudflare-worker),
+[Vercel Edge Runtime](https://edge-runtime.vercel.app/) is a subset of Node.js APIs. Similar to [Cloudflare Workers](/docs/llamaindex/getting_started/installation/cloudflare#difference-between-nodejs-and-cloudflare-worker),
 it is a serverless platform that runs your code on the edge.
 
 Not all features of Node.js are supported in Vercel Edge Runtime, so does LlamaIndex.TS, we are working on more compatibility with all JavaScript runtimes.

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

@@ -3,8 +3,6 @@ title: With Node.js/Bun/Deno
 description: In this guide, you'll learn how to use LlamaIndex with Node.js, Bun, and Deno.
 ---
 
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
 ## 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.
@@ -28,25 +26,15 @@ For more information, see the [How to read environment variables from Node.js](h
 
 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:
 
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install gpt-tokenizer
-	```
+```package-install
+npm i gpt-tokenizer
+```
 
-	```shell tab="yarn"
-	yarn add gpt-tokenizer
-	```
-
-	```shell tab="pnpm"
-	pnpm add gpt-tokenizer
-	```
-</Tabs>
-
-> Note: This only works for Node.js
+**Note**: This only works for Node.js
 
 ## TypeScript support
 
 <Card
 	title="Getting Started with LlamaIndex.TS in TypeScript"
-	href="/docs/llamaindex/getting_started/setup/typescript"
+	href="/docs/llamaindex/getting_started/installation/typescript"
 />

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

@@ -0,0 +1,110 @@
+---
+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, but with import path limitations.
+
+So you may encounter type errors when importing sub paths from the `llamaindex` package like:
+
+```ts
+import { Settings } from "llamaindex";
+```
+
+The simplest way to fix this without changing `moduleResolution` is to import directly from `llamaindex`:
+
+```ts
+import { Settings } from "llamaindex";
+```
+
+## 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 { agent, tool } from 'llamaindex'
+import { openai } from "@llamaindex/openai";
+
+Settings.llm = openai({
+  model: "gpt-4o-mini",
+});
+
+const addTool = tool({
+  name: "add", 
+  description: "Adds two numbers",
+  parameters: z.object({x: z.number(), y: z.number()}),
+  execute: ({ x, y }) => x + y,
+});
+
+const myAgent = agent({
+  tools: [addTool],
+});
+
+// Chat with the agent
+const context = myAgent.run("Hello, how are you?");
+
+for await (const event of context) {
+  if (event instanceof AgentStream) {
+    for (const chunk of event.data.delta) {
+      process.stdout.write(chunk); // stream response
+    }
+  } else {
+    console.log(event); // other events
+  }
+}
+
+```
+
+## Run TypeScript Script in Node.js
+
+We recommend to use [tsx](https://www.npmjs.com/package/tsx) to run TypeScript script in Node.js.
+
+```shell
+node --import tsx ./my-script.ts
+```

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

@@ -7,7 +7,7 @@ Before you start, make sure you have try LlamaIndex.TS in Node.js to make sure y
 
 <Card
   title="Getting Started with LlamaIndex.TS in Node.js"
-  href="/docs/llamaindex/getting_started/setup/node"
+  href="/docs/llamaindex/getting_started/installation/node"
 />
 
 Also, make sure you have a basic understanding of [Vite](https://vitejs.dev/).

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

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

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

@@ -1,42 +0,0 @@
----
-title: Choose Framework
-description: We support multiple JS runtime and frameworks, bundlers.
----
-import {
-	SiNodedotjs,
-	SiTypescript,
-	SiNextdotjs,
-	SiCloudflareworkers,
-	SiVite
-} from "@icons-pack/react-simple-icons";
-
-<Cards>
-	<Card title={
-		<>
-			<SiNodedotjs className="inline" color="#5FA04E" /> Node.js
-		</>
-	} href="/docs/llamaindex/getting_started/setup/node" />
-	<Card title={
-		<>
-			<SiTypescript className="inline" color="#3178C6" /> TypeScript
-		</>
-	} href="/docs/llamaindex/getting_started/setup/typescript" />
-	<Card title={
-		<>
-			<SiVite className='inline' color='#646CFF' /> Vite
-		</>
-	} href="/docs/llamaindex/getting_started/setup/vite" />
-	<Card
-		title={
-			<>
-				<SiNextdotjs className='inline' /> Next.js (React Server Component)
-			</>
-		}
-		href="/docs/llamaindex/getting_started/setup/next"
-	/>
-	<Card title={
-		<>
-			<SiCloudflareworkers className='inline' color='#F38020' /> Cloudflare Workers
-		</>
-	} href="/docs/llamaindex/getting_started/setup/cloudflare" />
-</Cards>

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

@@ -1,6 +0,0 @@
-{
-  "title": "Setup",
-  "description": "The setup guide",
-  "defaultOpen": true,
-  "pages": ["index", "next", "node", "typescript", "vite", "cloudflare"]
-}

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

@@ -1,132 +0,0 @@
----
-title: With TypeScript
-description: In this guide, you'll learn how to use LlamaIndex with TypeScript
----
-import { Accordion, Accordions } from 'fumadocs-ui/components/accordion';
-
-LlamaIndex.TS is written in TypeScript and designed to be used in TypeScript projects.
-
-We do lots of work on strong typing to make sure you have a great typing experience with LlamaIndex.TS.
-
-```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
-//^|
-})
-```
-
-```ts twoslash
-import { FunctionTool } from 'llamaindex'
-import { z } from 'zod'
-
-// ---cut-before---
-const inputSchema = z.object({
-	time: z.string(),
-	city: z.string(),
-})
-
-type Input = z.infer<typeof inputSchema>
-
-FunctionTool.from<Input>((input) => {
-// @noErrors
-	input.t
-//      ^|
-}, {
-	name: 'getWeather',
-	description: 'Get the weather information',
-	parameters: inputSchema,
-})
-```
-
-## Enable TypeScript
-
-
-```json5
-{
-  compilerOptions: {
-    // ⬇️ add this line to your tsconfig.json
-    moduleResolution: "bundler", // or "node16"
-  },
-}
-```
-
-<Accordions>
-	<Accordion
-		title="Why modify tsconfig.json"
-	>
-
-We are shipping both ESM and CJS module, and compatible with Vercel Edge, Cloudflare Workers, and other serverless platforms.
-
-So we are using [conditional exports](https://nodejs.org/api/packages.html#conditional-exports) to support all environments.
-
-This is a kind of modern way of shipping packages, but might cause TypeScript type check to fail because of legacy module resolution.
-
-Imaging you put output file into `/dist/openai.js` but you are importing `llamaindex/openai` in your code, and set `package.json` like this:
-
-```json5
-{
-	"exports": {
-		"./openai": "./dist/openai.js"
-	}
-}
-```
-
-In old module resolution, TypeScript will not be able to find the module because it is not following the file structure, even you run `node index.js` successfully. (on Node.js >=16)
-
-See more about [moduleResolution](https://www.typescriptlang.org/docs/handbook/modules/theory.html#module-resolution) or
-[TypeScript 5.0 blog](https://devblogs.microsoft.com/typescript/announcing-typescript-5-0/#--moduleresolution-bundler7).
-
-
-	</Accordion>
-</Accordions>
-
-## 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"],
-  },
-}
-```
-
-```ts twoslash
-import { OpenAIAgent } from '@llamaindex/openai'
-
-const agent = new OpenAIAgent({
-  tools: []
-})
-
-const response = await agent.chat({
-  message: 'Hello, how are you?',
-  stream: true
-})
-for await (const _ of response) {
-                      //^?
-  // ...
-}
-```
-
-## Run TypeScript Script in Node.js
-
-We recommend to use [tsx](https://www.npmjs.com/package/tsx) to run TypeScript script in Node.js.
-
-```shell
-node --import tsx ./my-script.ts
-```

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

@@ -1,9 +0,0 @@
-{
-  "title": "Starter Tutorials",
-  "pages": [
-    "retrieval_augmented_generation",
-    "chatbot",
-    "structured_data_extraction",
-    "agent"
-  ]
-}

apps/next/src/content/docs/llamaindex/guide/agents/3_local_model.mdx

@@ -1,92 +0,0 @@
----
-title: Using a local model via Ollama
----
-
-If you're happy using OpenAI, you can skip this section, but many people are interested in using models they run themselves. The easiest way to do this is via the great work of our friends at [Ollama](https://ollama.com/), who provide a simple to use client that will download, install and run a [growing range of models](https://ollama.com/library) for you.
-
-### Install Ollama
-
-They provide a one-click installer for Mac, Linux and Windows on their [home page](https://ollama.com/).
-
-### Pick and run a model
-
-Since we're going to be doing agentic work, we'll need a very capable model, but the largest models are hard to run on a laptop. We think `mixtral 8x7b` is a good balance between power and resources, but `llama3` is another great option. You can run it simply by running
-
-```bash
-ollama run mixtral:8x7b
-```
-
-The first time you run it will also automatically download and install the model for you.
-
-### Switch the LLM in your code
-
-There are two changes you need to make to the code we already wrote in `1_agent` to get Mixtral 8x7b to work. First, you need to switch to that model. Replace the call to `Settings.llm` with this:
-
-```javascript
-Settings.llm = new Ollama({
-  model: "mixtral:8x7b",
-});
-```
-
-### Swap to a ReActAgent
-
-In our original code we used a specific OpenAIAgent, so we'll need to switch to a more generic agent pattern, the ReAct pattern. This is simple: change the `const agent` line in your code to read
-
-```javascript
-const agent = new ReActAgent({ tools });
-```
-
-(You will also need to bring in `Ollama` and `ReActAgent` in your imports)
-
-### Run your totally local agent
-
-Because your embeddings were already local, your agent can now run entirely locally without making any API calls.
-
-```bash
-node agent.mjs
-```
-
-Note that your model will probably run a lot slower than OpenAI, so be prepared to wait a while!
-
-**_Output_**
-
-```javascript
-{
-  response: {
-    message: {
-      role: 'assistant',
-      content: ' Thought: I need to use a tool to add the numbers 101 and 303.\n' +
-        'Action: sumNumbers\n' +
-        'Action Input: {"a": 101, "b": 303}\n' +
-        '\n' +
-        'Observation: 404\n' +
-        '\n' +
-        'Thought: I can answer without using any more tools.\n' +
-        'Answer: The sum of 101 and 303 is 404.'
-    },
-    raw: {
-      model: 'mixtral:8x7b',
-      created_at: '2024-05-09T00:24:30.339473Z',
-      message: [Object],
-      done: true,
-      total_duration: 64678371209,
-      load_duration: 57394551334,
-      prompt_eval_count: 475,
-      prompt_eval_duration: 4163981000,
-      eval_count: 94,
-      eval_duration: 3116692000
-    }
-  },
-  sources: [Getter]
-}
-```
-
-Tada! You can see all of this in the folder `1a_mixtral`.
-
-### Extending to other examples
-
-You can use a ReActAgent instead of an OpenAIAgent in any of the further examples below, but keep in mind that GPT-4 is a lot more capable than Mixtral 8x7b, so you may see more errors or failures in reasoning if you are using an entirely local setup.
-
-### Next steps
-
-Now you've got a local agent, you can [add Retrieval-Augmented Generation to your agent](4_agentic_rag).

apps/next/src/content/docs/llamaindex/guide/cost-analysis.mdx

@@ -1,16 +0,0 @@
----
-title: Cost Analysis
----
-
-This page shows how to track LLM cost using APIs.
-
-## Callback Manager
-
-The callback manager is a class that manages the callback functions.
-
-You can register `llm-start`, `llm-end`, and `llm-stream` callbacks to the callback manager for tracking the cost.
-
-import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
-import CodeSource from "!raw-loader!../../../../../../../examples/recipes/cost-analysis";
-
-<DynamicCodeBlock lang="ts" code={CodeSource} />

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

@@ -1,106 +0,0 @@
----
-title: Document and Nodes
-description: llamaindex readers is a collection of readers for different file formats.
----
-
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-import { Accordion, Accordions } from 'fumadocs-ui/components/accordion';
-
-<Accordions>
-	<Accordion title="Install @llamaindex/readers">
-
-		If you want to use the reader module, you need to install `@llamaindex/readers`
-
-		<Tabs groupId="install-llamaindex" items={["npm", "yarn", "pnpm"]} persist>
-			```shell tab="npm"
-			npm install @llamaindex/readers
-			```
-
-			```shell tab="yarn"
-			yarn add @llamaindex/readers
-			```
-
-			```shell tab="pnpm"
-			pnpm add @llamaindex/readers
-			```
-
-		</Tabs>
-	</Accordion>
-</Accordions>
-
-We offer readers for different file formats.
-
-```ts twoslash 
-import { CSVReader } from '@llamaindex/readers/csv'
-import { PDFReader } from '@llamaindex/readers/pdf'
-import { JSONReader } from '@llamaindex/readers/json'
-import { MarkdownReader } from '@llamaindex/readers/markdown'
-import { HTMLReader } from '@llamaindex/readers/html'
-// you can find more readers in the documentation
-```
-
-## SimpleDirectoryReader
-
-`SimpleDirectoryReader` is the simplest way to load data from local files into LlamaIndex.
-
-```ts twoslash 
-import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
-
-const reader = new SimpleDirectoryReader()
-const documents = await reader.loadData("./data")
-//    ^?
-
-
-const texts = documents.map(doc => doc.getText())
-//    ^?
-```
-
-
-## Tips when using in non-Node.js environments
-
-When using `@llamaindex/readers` in a non-Node.js environment (such as Vercel Edge, Cloudflare Workers, etc.)
-Some classes are not exported from top-level entry file.
-
-The reason is that some classes are only compatible with Node.js runtime, (e.g. `PDFReader`) which uses Node.js specific APIs (like `fs`, `child_process`, `crypto`).
-
-If you need any of those classes, you have to import them instead directly through their file path in the package.
-
-As the `PDFReader` is not working with the Edge runtime, here's how to use the `SimpleDirectoryReader` with the `LlamaParseReader` to load PDFs:
-
-```typescript
-import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
-import { LlamaParseReader } from "@llamaindex/cloud";
-
-export const DATA_DIR = "./data";
-
-export async function getDocuments() {
-  const reader = new SimpleDirectoryReader();
-  // Load PDFs using LlamaParseReader
-  return await reader.loadData({
-    directoryPath: DATA_DIR,
-    fileExtToReader: {
-      pdf: new LlamaParseReader({ resultType: "markdown" }),
-    },
-  });
-}
-```
-
-> _Note_: Reader classes have to be added explicitly to the `fileExtToReader` map in the Edge version of the `SimpleDirectoryReader`.
-
-You'll find a complete example with LlamaIndexTS here: https://github.com/run-llama/create_llama_projects/tree/main/nextjs-edge-llamaparse
-
-
-## Load file natively using Node.js Customization Hooks
-
-We have a helper utility to allow you to import a file in Node.js script.
-
-```shell 
-node --import @llamaindex/readers/node ./script.js
-```
-
-```ts
-import csv from './path/to/data.csv';
-
-const text = csv.getText()
-```

apps/next/src/content/docs/llamaindex/guide/loading/meta.json

@@ -1,5 +0,0 @@
-{
-  "title": "Loading Data",
-  "description": "Loading Data using LlamaIndex.TS",
-  "pages": ["index", "node-parser"]
-}

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

@@ -1,5 +0,0 @@
-{
-  "title": "Guide",
-  "description": "See our guide",
-  "pages": ["loading", "workflow", "chat", "agents", "cost-analysis"]
-}

apps/next/src/content/docs/llamaindex/guide/workflow/different-inputs-outputs.mdx

@@ -1,226 +0,0 @@
----
-title: Inputs / Outputs
-description: Learn how to use different inputs and outputs in your workflows.
----
-
-Inputs and outputs are the way to communicate between steps in a workflow. In the previous example,
-we used `StartEvent` and `StopEvent` to communicate between steps. However, you can use any type of event to communicate between steps.
-
-## Multiple inputs
-
-You can define multiple inputs for a step.
-
-In the following example, we define a complex workflow with multiple inputs and outputs.
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent, WorkflowEvent } from '@llamaindex/workflow';
-
-class AEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-class BEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-class ResultEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-```
-
-First, let's define the events that we will use in the workflow.
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent, WorkflowEvent } from '@llamaindex/workflow';
-
-class AEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-class BEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-class ResultEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-const workflow = new Workflow<never, string, string>();
-
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [StopEvent<string>]
-}, async (
-	context,
-	startEvent
-) => {
-	const input = startEvent.data;
-	const aEvent = await context.requireEvent(AEvent);
-	const bEvent = await context.requireEvent(BEvent);
-	const a = aEvent.data;
-	const b = bEvent.data;
-	return new StopEvent(`Hello, ${input}! A: ${a}, B: ${b}`);
-});
-
-// ---cut---
-workflow.addStep({
-	inputs: [AEvent, BEvent],
-	outputs: [ResultEvent]
-}, async (
-	context,
-	aEvent,
-	bEvent
-) => {
-	const a = aEvent.data;
-	const b = bEvent.data;
-	return new ResultEvent(`A: ${a}, B: ${b}`);
-});
-```
-
-This step means that it requires two events: `AEvent` and `BEvent`. It will return a `ResultEvent` with the data `A: ${a}, B: ${b}`.
-
-## A or B input
-
-If we want to have a step that can accept either `AEvent` or `BEvent`, we can define the step like this:
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent, WorkflowEvent } from '@llamaindex/workflow';
-
-class AEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-class BEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-class ResultEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-const workflow = new Workflow<never, string, string>();
-
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [StopEvent<string>]
-}, async (
-	context,
-	startEvent
-) => {
-	const input = startEvent.data;
-	const aEvent = await context.requireEvent(AEvent);
-	const bEvent = await context.requireEvent(BEvent);
-	const a = aEvent.data;
-	const b = bEvent.data;
-	return new StopEvent(`Hello, ${input}! A: ${a}, B: ${b}`);
-});
-
-// ---cut---
-workflow.addStep({
-	inputs: [WorkflowEvent.or(AEvent, BEvent)],
-	outputs: [ResultEvent]
-}, async (
-	context,
-	aOrBEvent
-) => {
-	if (aOrBEvent instanceof AEvent) {
-		// ^?
-
-
-		const a = aOrBEvent.data;
-		//        ^?
-
-
-		return new ResultEvent(`A: ${a}`);
-	} else {
-		const b = aOrBEvent.data;
-		//        ^?
-
-
-		return new ResultEvent(`B: ${b}`);
-	}
-});
-```
-
-This step means that it requires either `AEvent` or `BEvent`. It will return a `ResultEvent` with the data `A: ${a}` or `B: ${b}`.
-
-You can still combine the logic with `context.requireEvent` to get the data from the event.
-
-import { Accordion, Accordions } from 'fumadocs-ui/components/accordion';
-
-<Accordions>
-	<Accordion title="Under the hood">
-		We use JavaScript Inheritance and the prototype chain to implement the `or` logic.
-		The `or` method creates a new class that extends the two classes that you pass to it.
-
-		<a
-			target="_blank"
-			href="https://developer.mozilla.org/en-US/docs/Web/JavaScript/Inheritance_and_the_prototype_chain"
-		>
-			MDN - Inheritance and the prototype chain
-		</a>
-	</Accordion>
-</Accordions>
-
-## Multiple outputs
-
-You can define multiple outputs for a step.
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent, WorkflowEvent } from '@llamaindex/workflow';
-
-class AEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-class BEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-class ResultEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-const workflow = new Workflow<never, string, string>();
-// ---cut---
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [AEvent, BEvent]
-}, async (
-	context,
-	startEvent
-) => {
-	const input = startEvent.data;
-	if (Math.random() > 0.5) {
-		return new AEvent(`Hello, ${input}!`);
-	} else {
-		return new BEvent(42);
-	}
-});
-```
-
-This step will return either an `AEvent` or a `BEvent` based on a random number.

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

@@ -1,208 +0,0 @@
----
-title: Basic Usage
-description: Learn how to use the LlamaIndex workflow.
----
-
-A `Workflow` in LlamaIndex.TS is an event-driven abstraction used to chain together several events.
-Workflows are made up of steps, with each step responsible for handling certain event types and emitting new events.
-
-Workflows are designed for any cases that benefit from event-driven programming, not only for LLM and AI tasks.
-
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install @llamaindex/workflow
-	```
-
-	```shell tab="yarn"
-	yarn add @llamaindex/workflow
-	```
-
-	```shell tab="pnpm"
-	pnpm add @llamaindex/workflow
-	```
-</Tabs>
-
-## Start from scratch
-
-Let's start from a Hello World workflow.
-
-```ts twoslash
-import { Workflow } from '@llamaindex/workflow';
-
-type ContextData = {
-	counter: number;
-}
-// ---cut---
-const contextData: ContextData = { counter: 0 };
-
-const workflow = new Workflow<ContextData, string, string>();
-//     ^?
-
-
-
-```
-
-First, we define a workflow with 3 generic types: `ContextData`, `Input`, and `Output`.
-
-In general, `ContextData` is used to store the shared data between steps, `Input` is the type of the input event, and `Output` is the type of the output event.
-
-In you code logic, you should **share state between steps via `ContextData`**.
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent } from '@llamaindex/workflow';
-
-type ContextData = {
-	counter: number;
-}
-
-const contextData: ContextData = { counter: 0 };
-
-const workflow = new Workflow<ContextData, string, string>();
-// ---cut---
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [StopEvent<string>]
-}, async (context, startEvent) => {
-	const input = startEvent.data;
-	context.data.counter++;
-	return new StopEvent(`Hello, ${input}!`);
-});
-```
-
-In the workflow, we add a step that listens to `StartEvent<string>` and emits `StopEvent<string>`.
-
-The step is an async function that takes two arguments: `context` and `event`.
-
-### `context` type
-
-<AutoTypeTable path="./src/deps/type.ts" name="HandlerContext" />
-
-There are two more properties in `HandlerContext`:
-
-- `sendEvent`: invoke another event in the workflow, other than `StartEvent`, `StopEvent`, or the current event. (Or there will have circular reference)
-- `requireEvent`: wait for a specific event to be emitted.
-
-You can use `sendEvent` and `requireEvent` to build complex workflows.
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent, WorkflowEvent } from '@llamaindex/workflow';
-
-type ContextData = {
-	counter: number;
-}
-
-const contextData: ContextData = { counter: 0 };
-
-const workflow = new Workflow<ContextData, string, string>();
-
-// ---cut---
-class AnalysisStartEvent extends WorkflowEvent<string> {}
-class AnalysisStopEvent extends WorkflowEvent<boolean> {}
-workflow.addStep({
-	inputs: [AnalysisStartEvent],
-	outputs: [AnalysisStopEvent]
-}, async (...args) => {
-	// do some analysis
-	return new AnalysisStopEvent(true);
-})
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [StopEvent<string>]
-}, async (context, startEvent) => {
-	const input = startEvent.data;
-	context.sendEvent(new AnalysisStartEvent('start'));
-	context.data.counter++;
-	const { data } = await context.requireEvent(AnalysisStopEvent);
-	return new StopEvent(`Hello, ${input}! Analysis result: ${data ? 'success' : 'fail'}`);
-});
-```
-
-For example, you can compile `requireEvent` with `waitUntil` in [Vercel Functions](https://vercel.com/docs/functions/functions-api-reference#waituntil) or [Cloudflare Worker](https://developers.cloudflare.com/workers/runtime-apis/context/#waituntil)
-
-```ts twoslash
-import { waitUntil } from '@vercel/functions';
-import { Workflow, StartEvent, StopEvent, WorkflowEvent } from '@llamaindex/workflow';
-
-type ContextData = {
-	counter: number;
-}
-
-const contextData: ContextData = { counter: 0 };
-
-const workflow = new Workflow<ContextData, string, string>();
-
-class AnalysisStartEvent extends WorkflowEvent<string> {}
-class AnalysisStopEvent extends WorkflowEvent<boolean> {}
-
-// ---cut---
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [StopEvent<string>]
-}, async (context, startEvent) => {
-	const input = startEvent.data;
-	context.sendEvent(new AnalysisStartEvent('start'));
-	context.data.counter++;
-	waitUntil(context.requireEvent(AnalysisStopEvent));
-	// note that `waitUntil` is not a promise, it will extend the lifetime of the workflow
-	// you can wait for some background tasks to finish
-	return new StopEvent(`Hello, ${input}!`);
-});
-```
-
-## Multiple runs
-
-You can run the same workflow multiple times with different inputs.
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent } from '@llamaindex/workflow';
-
-type ContextData = {
-	counter: number;
-}
-
-const contextData: ContextData = { counter: 0 };
-
-const workflow = new Workflow<ContextData, string, string>();
-
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [StopEvent<string>]
-}, async (context, startEvent) => {
-	const input = startEvent.data;
-	context.data.counter++;
-	return new StopEvent(`Hello, ${input}!`);
-});
-
-// ---cut---
-{
-	const ret = await workflow.run('Alex', contextData);
-	console.log(ret.data); // Hello, Alex!
-}
-
-{
-	const ret = await workflow.run('World', contextData);
-	console.log(ret.data); // Hello, World!
-}
-```
-
-Context is shared between runs, so the counter will be increased.
-
-Ideally, it should be serializable to make sure it can be recovered from HTTP requests or other storage.
-
-### Full example
-
-<iframe
-	className="w-full h-[440px]"
-	aria-label="Workflow example"
-	src="https://stackblitz.com/github/run-llama/LlamaIndexTS/tree/main/examples?file=node/workflow/basic.ts"
-/>
-
-## `Workflow` type
-
-<AutoTypeTable path="./src/deps/type.ts" name="Workflow" />
-
-## `WorkflowContext` type
-
-<AutoTypeTable path="./src/deps/type.ts" name="WorkflowContext" />

apps/next/src/content/docs/llamaindex/guide/workflow/meta.json

@@ -1,6 +0,0 @@
-{
-  "title": "Workflow",
-  "description": "See how to use @llamaindex/workflow",
-  "defaultOpen": false,
-  "pages": ["index", "different-inputs-outputs", "streaming"]
-}

apps/next/src/content/docs/llamaindex/guide/workflow/streaming.mdx

@@ -1,199 +0,0 @@
----
-title: Streaming
-description: Learn how to use the LlamaIndex workflow with streaming.
----
-import { WorkflowStreamingDemo } from '../../../../../components/demo/workflow-streaming-ui';
-
-`Workflow` API by default is designed for streaming data. In this guide, we will show you how to use the `Workflow` API with streaming data.
-
-Each `workflow.run` call returns `WorkflowContext`, which implements `AsyncIterable` interface. You can use it to stream data.
-
-```ts twoslash
-import { Workflow, WorkflowEvent, StartEvent, StopEvent } from '@llamaindex/workflow';
-class ComputeEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-class ComputeResultEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-type ContextData = {
-	sum: number;
-}
-
-const workflow = new Workflow<ContextData, number, number>();
-workflow.addStep({
-	inputs: [StartEvent<number>],
-	outputs: [StopEvent<number>]
-}, async (context, startEvent) => {
-	const total = startEvent.data;
-	for (let i = 0; i < total; i++) {
-		context.sendEvent(new ComputeEvent(i));
-	}
-	const computeResults = await Promise.all(Array.from({ length: total }).map(() => context.requireEvent(ComputeResultEvent)));
-	// Workflow API allows you to start events in parallel and wait for all of them to finish
-	context.data.sum = computeResults.reduce((acc, curr) => acc + curr.data, 0);
-	return new StopEvent(context.data.sum);
-});
-```
-
-We define a parallel computation workflow that computes the sum of numbers from 0 to `total`.
-
-The workflow sends `ComputeEvent` events for each number and waits for `ComputeResultEvent` events. After receiving all `ComputeResultEvent` events, the workflow returns the sum as a `StopEvent`.
-
-What if we want cutoff if the sum exceeds a certain value?
-
-## Streaming
-
-```ts twoslash
-import { Workflow, WorkflowEvent, StartEvent, StopEvent } from '@llamaindex/workflow';
-import { StopCircle } from 'lucide-react';
-class ComputeEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-class ComputeResultEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-
-type ContextData = {
-	sum: number;
-}
-
-const workflow = new Workflow<ContextData, number, number>();
-// ---cut---
-const context = workflow.run(1000, {
-	sum: 0
-});
-
-for await (const event of context) {
-	if (event instanceof ComputeEvent) {
-		if (context.data.sum > 100) {
-			throw new Error('Sum exceeds 100');
-		}
-	}
-	if (event instanceof StopEvent) {
-		console.log('result', event.data);
-	}
-}
-```
-
-You can define more custom logic using `AsyncIterable` interface.
-
-For example. I just want to stop the workflow if I get a `ComputeResultEvent`
-
-
-```ts twoslash
-import { Workflow, WorkflowEvent, StartEvent, StopEvent } from '@llamaindex/workflow';
-import { StopCircle } from 'lucide-react';
-class ComputeEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-class ComputeResultEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-
-type ContextData = {
-	sum: number;
-}
-
-const workflow = new Workflow<ContextData, number, number>();
-// ---cut---
-async function compute() {
-	const context = workflow.run(1000, {
-		sum: 0
-	});
-	for await (const event of context) {
-		if (event instanceof ComputeResultEvent) {
-			return event.data;
-		}
-	}
-	throw new Error('UNREACHABLE');
-}
-
-const result = await compute();
-```
-
-### Streaming with UI
-
-You can use the `Workflow` API with UI libraries like React.
-
-```tsx twoslash
-// @filename: utils.ts
-export async function runWithoutBlocking(fn: () => Promise<void>) {
-	fn();
-}
-// @filename: action.ts
-// ---cut---
-'use server';
-// "use server" is required to enable server side feature in React
-import { createStreamableUI } from 'ai/rsc';
-import { runWithoutBlocking } from './utils';
-// ---cut-start---
-import { Workflow, WorkflowEvent, StartEvent, StopEvent } from '@llamaindex/workflow';
-class ComputeEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-class ComputeResultEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-
-type ContextData = {
-	sum: number;
-}
-
-const workflow = new Workflow<ContextData, number, number>();
-const min = 100;
-const max = 1000;
-workflow.addStep(
-	{
-		inputs: [ComputeEvent],
-		outputs: [ComputeResultEvent]
-	},
-	async (context, event) => {
-		await new Promise((resolve) =>
-			setTimeout(resolve, Math.floor(Math.random() * (max - min + 1) + min))
-		);
-		return new ComputeResultEvent(event.data);
-	}
-);
-// ---cut-end---
-export async function compute() {
-	'use server';
-	const ui = createStreamableUI();
-	const context = workflow.run(100, {
-		sum: 0
-	});
-	runWithoutBlocking(async () => {
-		for await (const event of context) {
-			if (event instanceof ComputeResultEvent) {
-				// Update UI
-			} else if (event instanceof StopEvent) {
-				// Update UI
-			}
-			// ...
-		}
-	});
-	return ui.value;
-}
-```
-
-<WorkflowStreamingDemo />

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

@@ -3,22 +3,19 @@ title: What is LlamaIndex.TS
 description: LlamaIndex is the leading data framework for building LLM applications
 ---
 
-import {
-  SiNodedotjs,
-  SiDeno,
-  SiBun,
-  SiCloudflareworkers,
-} 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
   className="w-full h-[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).

apps/next/src/content/docs/llamaindex/integration/lang-trace.mdx

@@ -2,7 +2,6 @@
 title: Langtrace
 description: Learn how to integrate LlamaIndex.TS with Langtrace.
 ---
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
 
 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.
 
@@ -10,19 +9,9 @@ Enhance your observability with Langtrace, a robust open-source tool supports Op
 
 - Self-host or sign-up and generate an API key using [Langtrace](https://www.langtrace.ai) Cloud
 
-<Tabs groupId="install-langtrase" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install @langtrase/typescript-sdk
-	```
-
-	```shell tab="yarn"
-	yarn add @langtrase/typescript-sdk
-	```
-
-	```shell tab="pnpm"
-	pnpm add @langtrase/typescript-sdk
-	```
-</Tabs>
+```package-install
+npm i @langtrase/typescript-sdk
+```
 
 ## Initialize
 

apps/next/src/content/docs/llamaindex/integration/open-llm-metry.mdx

@@ -2,27 +2,15 @@
 title: OpenLLMetry
 description: Learn how to integrate LlamaIndex.TS with OpenLLMetry.
 ---
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
 
 [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
 
-
-<Tabs groupId="install-traceloop" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install @traceloop/node-server-sdk
-	```
-
-	```shell tab="yarn"
-	yarn add @traceloop/node-server-sdk
-	```
-
-	```shell tab="pnpm"
-	pnpm add @traceloop/node-server-sdk
-	```
-</Tabs>
+```package-install
+npm i @traceloop/node-server-sdk
+```
 
 ```js
 import * as traceloop from "@traceloop/node-server-sdk";

apps/next/src/content/docs/llamaindex/integration/vercel.mdx

@@ -11,8 +11,8 @@ LlamaIndex provides integration with Vercel's AI SDK, allowing you to create pow
 
 First, install the required dependencies:
 
-```bash
-npm install @llamaindex/vercel ai
+```package-install
+npm i @llamaindex/vercel ai
 ```
 
 ## Using Vercel AI's Model Providers 
@@ -84,6 +84,7 @@ 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

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

@@ -4,13 +4,11 @@
   "root": true,
   "pages": [
     "---Guide---",
-    "what-is-llamaindex",
     "index",
     "getting_started",
-    "migration",
-    "guide",
-    "examples",
+    "tutorials",
     "modules",
-    "integration"
+    "integration",
+    "migration"
   ]
 }

apps/next/src/content/docs/llamaindex/migration/0.8-to-0.9.mdx

@@ -2,8 +2,6 @@
 title: Migrating from v0.8 to v0.9
 ---
 
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
 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
@@ -33,21 +31,11 @@ import { OpenAI } from "@llamaindex/openai";
 
 > Note: This examples requires installing the `@llamaindex/openai` package: 
 
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install @llamaindex/openai
-	```
+```package-install
+npm i @llamaindex/openai
+```
 
-	```shell tab="yarn"
-	yarn add @llamaindex/openai
-	```
-
-	```shell tab="pnpm"
-	pnpm add @llamaindex/openai
-	```
-</Tabs>
-
-For more details on available AI model providers and their configuration, see the [LLMs documentation](/docs/llamaindex/modules/llms) and the [Embedding Models documentation](/docs/llamaindex/modules/embeddings).
+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
 
@@ -61,7 +49,7 @@ Now:
 import { PineconeVectorStore } from "@llamaindex/pinecone";
 ```
 
-For more information about available storage options, refer to the [Data Stores documentation](/docs/llamaindex/modules/data_stores).
+For more information about available storage options, refer to the [Data Stores documentation](/docs/llamaindex/modules/data/stores).
 
 ### 3. Data Loaders
 
@@ -75,7 +63,7 @@ Now:
 import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
 ```
 
-For more details about available data loaders and their usage, check the [Loading Data](/docs/llamaindex/guide/loading).
+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`
 

apps/next/src/content/docs/llamaindex/migration/deprecated/agent/index.mdx

@@ -2,6 +2,8 @@
 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
@@ -19,11 +21,6 @@ LlamaIndex.TS comes with a few built-in agents, but you can also create your own
 - ReACT Agent
 - Meta3.1 504B via Bedrock (in `@llamaIndex/community`)
 
-## Examples
-
-- [OpenAI Agent](/docs/llamaindex/examples/agent)
-- [Gemini Agent](/docs/llamaindex/examples/agent_gemini)
-
 ## Api References
 
 - [OpenAIAgent](/docs/api/classes/OpenAIAgent)

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

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

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

@@ -1,12 +1,9 @@
 ---
-title: Agent Workflow
+title: Agent Workflows
 ---
 
-import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
-import CodeSource from "!raw-loader!../../../../../../../examples/agentworkflow/blog-writer.ts";
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
 
-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` system and provides a streamlined interface for agent interactions.
+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
 
@@ -15,11 +12,11 @@ Agent Workflows are a powerful system that enables you to create and orchestrate
 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 { agent, FunctionTool } from "llamaindex";
-import { OpenAI } from "@llamaindex/openai";
+import { agent, tool } from "llamaindex";
+import { openai } from "@llamaindex/openai";
 
 // Define a joke-telling tool
-const jokeTool = FunctionTool.from(
+const jokeTool = tool(
   () => "Baby Llama is called cria",
   {
     name: "joke",
@@ -28,15 +25,13 @@ const jokeTool = FunctionTool.from(
 );
 
 // Create an single agent workflow with the tool
-const workflow = agent({
+const jokeAgent = agent({
   tools: [jokeTool],
-  llm: new OpenAI({
-    model: "gpt-4o-mini",
-  }),
+  llm: openai({ model: "gpt-4o-mini" }),
 });
 
 // Run the workflow
-const result = await workflow.run("Tell me something funny");
+const result = await jokeAgent.run("Tell me something funny");
 console.log(result); // Baby Llama is called cria
 ```
 
@@ -73,8 +68,8 @@ An Agent Workflow can orchestrate multiple agents, enabling complex interactions
 Here's an example of a multi-agent system that combines joke-telling and weather information:
 
 ```typescript
-import { multiAgent, agent, FunctionTool } from "llamaindex";
-import { OpenAI } from "@llamaindex/openai";
+import { multiAgent, agent, tool } from "llamaindex";
+import { openai } from "@llamaindex/openai";
 import { z } from "zod";
 
 // Create a weather agent
@@ -82,18 +77,18 @@ const weatherAgent = agent({
   name: "WeatherAgent",
   description: "Provides weather information for any city",
   tools: [
-    FunctionTool.from(
-      ({ city }: { city: string }) => `The weather in ${city} is sunny`,
+    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: new OpenAI({ model: "gpt-4o-mini" }),
+  llm: openai({ model: "gpt-4o-mini" }),
 });
 
 // Create a joke-telling agent
@@ -101,18 +96,18 @@ const jokeAgent = agent({
   name: "JokeAgent",
   description: "Tells jokes and funny stories",
   tools: [jokeTool], // Using the joke tool defined earlier
-  llm: new OpenAI({ model: "gpt-4o-mini" }),
+  llm: openai({ model: "gpt-4o-mini" }),
   canHandoffTo: [weatherAgent], // Can hand off to the weather agent
 });
 
 // Create the multi-agent workflow
-const workflow = multiAgent({
+const agents = multiAgent({
   agents: [jokeAgent, weatherAgent],
   rootAgent: jokeAgent, // Start with the joke agent
 });
 
 // Run the workflow
-const result = await workflow.run(
+const result = await agents.run(
   "Give me a morning greeting with a joke and the weather in San Francisco"
 );
 ```

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

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

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

@@ -0,0 +1,142 @@
+---
+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 { agent, tool } from "llamaindex";
+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";
+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";
+
+// 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 { agent, tool } from "llamaindex";
+
+// 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
+})
+```

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

@@ -0,0 +1,261 @@
+---
+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.
+
+```package-install
+npm i @llama-flow/core @llamaindex/openai
+```
+
+## Getting Started
+
+Let's explore a simple workflow example where a joke is generated and then critiqued and iterated on:
+
+```typescript
+import { OpenAI } from "@llamaindex/openai";
+import { createWorkflow, workflowEvent } from "@llama-flow/core";
+import { withStore } from "@llama-flow/core/middleware/store";
+
+// Create LLM instance
+const llm = new OpenAI({ model: "gpt-4.1-mini", apiKey: "..."});
+
+// Define our workflow events
+const startEvent = workflowEvent<string>(); // Input topic for joke
+const jokeEvent = workflowEvent<{ joke: string }>(); // Intermediate joke
+const critiqueEvent = workflowEvent<{ joke: string, critique: string }>(); // Intermediate critique
+const resultEvent = workflowEvent<{ joke: string, critique: string }>(); // Final joke + critique
+
+// Create our workflow
+const jokeFlow = withStore(
+    () => ({
+        numIterations: 0,
+        maxIterations: 3,
+    }),
+    createWorkflow()
+);
+
+// Define handlers for each step
+jokeFlow.handle([startEvent], async (event) => {
+  // Prompt the LLM to write a joke
+  const prompt = `Write your best joke about ${event.data}. Write the joke between <joke> and </joke> tags.`;
+  const response = await llm.complete({ prompt });
+
+  // Parse the joke from the response
+  const joke = response.text.match(/<joke>([\s\S]*?)<\/joke>/)?.[1]?.trim() ?? response.text;
+  return jokeEvent.with({ joke: joke });
+});
+
+jokeFlow.handle([jokeEvent], async (event) => {
+  // Prompt the LLM to critique the joke
+  const prompt = `Give a thorough critique of the following joke. If the joke needs improvement, put "IMPROVE" somewhere in the critique: ${event.data.joke}`;
+  const response = await llm.complete({ prompt });
+
+  // If the critique includes "IMPROVE", keep iterating, else, return the result
+  if (response.text.includes("IMPROVE")) {
+    return critiqueEvent.with({ joke: event.data.joke, critique: response.text });
+  }
+
+  return resultEvent.with({ joke: event.data.joke, critique: response.text });
+});
+
+jokeFlow.handle([critiqueEvent], async (event) => {
+  // Keep track of the number of iterations
+  const store = jokeFlow.getStore();
+  store.numIterations++;
+
+  // Write a new joke based on the previous joke and critique
+  const prompt = `Write a new joke based on the following critique and the original joke. Write the joke between <joke> and </joke> tags.\n\nJoke: ${event.data.joke}\n\nCritique: ${event.data.critique}`;
+  const response = await llm.complete({ prompt });
+  
+  // Parse the joke from the response
+  const joke = response.text.match(/<joke>([\s\S]*?)<\/joke>/)?.[1]?.trim() ?? response.text;
+  
+  // If we've done less than the max number of iterations, keep iterating
+  // else, return the result
+  if (store.numIterations < store.maxIterations) {
+    return jokeEvent.with({ joke: joke });
+  }
+
+  return resultEvent.with({ joke: joke, critique: event.data.critique });
+});
+
+// Usage
+async function main() {
+  const { stream, sendEvent } = jokeFlow.createContext();
+  sendEvent(startEvent.with("pirates"));
+
+  let result: { joke: string, critique: string } | undefined;
+
+  for await (const event of stream) {
+    // console.log(event.data);  optionally log the event data
+    if (resultEvent.include(event)) {
+      result = event.data;
+      break; // Stop when we get the final result
+    }
+  }
+  
+  console.log(result);
+}
+
+main().catch(console.error);
+```
+
+There are a few moving pieces here, so let's go through this step by step.
+
+### Defining Workflow Events
+
+```typescript
+const startEvent = workflowEvent<string>(); // Input topic for joke
+const jokeEvent = workflowEvent<{ joke: string }>(); // Intermediate joke
+const critiqueEvent = workflowEvent<{ joke: string, critique: string }>(); // Intermediate critique
+const resultEvent = workflowEvent<{ joke: string, critique: string }>(); // Final joke + critique
+```
+
+Events are defined using the `workflowEvent` function and contain arbitrary data provided as a generic type. In this example, we have four events:
+- `startEvent`: Takes a string input (the joke topic)
+- `jokeEvent`: Contains an object with a joke property
+- `critiqueEvent`: Contains both the joke and its critique, used for the feedback loop
+- `resultEvent`: Contains the final joke and critique after any iterations
+
+### Setting up the Workflow with Store Middleware
+
+```typescript
+const jokeFlow = withStore(
+    () => ({
+        numIterations: 0,
+        maxIterations: 3,
+    }),
+    createWorkflow()
+);
+```
+
+Our workflow is implemented using the `createWorkflow()` function, enhanced with the `withStore` middleware. The store provides shared state across all handlers, which in this case tracks:
+- `numIterations`: Counts how many iterations of joke improvement we've done
+- `maxIterations`: Sets a limit to prevent infinite loops
+
+This store will be accesible within workflows by using the `jokeFlow.getStore()` function.
+
+### Adding Handlers with Loops
+
+We have three key handlers in our workflow:
+
+1. The first handler processes the `startEvent`, generates an initial joke, and emits a `jokeEvent`:
+
+```typescript
+jokeFlow.handle([startEvent], async (event) => {
+  // Prompt the LLM to write a joke
+  const prompt = `Write your best joke about ${event.data}. Write the joke between <joke> and </joke> tags.`;
+  const response = await llm.complete({ prompt });
+
+  // Parse the joke from the response
+  const joke = response.text.match(/<joke>([\s\S]*?)<\/joke>/)?.[1]?.trim() ?? response.text;
+  return jokeEvent.with({ joke: joke });
+});
+```
+
+2. The second handler handles the `jokeEvent`, critiques the joke, and either:
+   - Emits a `critiqueEvent` if the joke needs improvement
+   - Emits a `resultEvent` if the joke is good enough
+
+```typescript
+jokeFlow.handle([jokeEvent], async (event) => {
+  // Prompt the LLM to critique the joke
+  const prompt = `Give a thorough critique of the following joke. If the joke needs improvement, put "IMPROVE" somewhere in the critique: ${event.data.joke}`;
+  const response = await llm.complete({ prompt });
+
+  // If the critique includes "IMPROVE", keep iterating, else, return the result
+  if (response.text.includes("IMPROVE")) {
+    return critiqueEvent.with({ joke: event.data.joke, critique: response.text });
+  }
+
+  return resultEvent.with({ joke: event.data.joke, critique: response.text });
+});
+```
+
+3. The third handler processes the `critiqueEvent`, generates an improved joke based on the critique, and either:
+   - Loops back to the joke evaluation (if under the iteration limit)
+   - Emits the final `resultEvent` (if iteration limit reached)
+
+```typescript
+jokeFlow.handle([critiqueEvent], async (event) => {
+  // Keep track of the number of iterations
+  const store = jokeFlow.getStore();
+  store.numIterations++;
+
+  // Write a new joke based on the previous joke and critique
+  const prompt = `Write a new joke based on the following critique and the original joke. Write the joke between <joke> and </joke> tags.\n\nJoke: ${event.data.joke}\n\nCritique: ${event.data.critique}`;
+  const response = await llm.complete({ prompt });
+  
+  // Parse the joke from the response
+  const joke = response.text.match(/<joke>([\s\S]*?)<\/joke>/)?.[1]?.trim() ?? response.text;
+  
+  // If we've done less than the max number of iterations, keep iterating
+  // else, return the result
+  if (store.numIterations < store.maxIterations) {
+    return jokeEvent.with({ joke: joke });
+  }
+
+  return resultEvent.with({ joke: joke, critique: event.data.critique });
+});
+```
+
+### Running the Workflow
+
+```typescript
+async function main() {
+  const { stream, sendEvent } = jokeFlow.createContext();
+  sendEvent(startEvent.with("pirates"));
+
+  let result: { joke: string, critique: string } | undefined;
+
+  for await (const event of stream) {
+    // console.log(event.data);  optionally log the event data
+    if (resultEvent.include(event)) {
+      result = event.data;
+      break; // Stop when we get the final result
+    }
+  }
+  
+  console.log(result);
+}
+```
+
+To run the workflow, we:
+1. Create a workflow context with `createContext()`
+2. Trigger the initial event with `sendEvent()`
+3. Listen to the event stream and process events as they arrive
+4. Use `include()` to check if an event is of a specific type
+5. Break the loop when we receive our final result
+
+### Using Stream Utilities
+
+Workflows provide utility functions to make working with event streams easier:
+
+```typescript
+import { collect } from "@llama-flow/core/stream/consumer";
+import { until } from "@llama-flow/core/stream/until";
+
+// Create a workflow context and send the initial event
+const { stream, sendEvent } = jokeFlow.createContext();
+sendEvent(startEvent.with("pirates"));
+
+// Collect all events until we get a resultEvent
+const allEvents = await collect(until(stream, resultEvent));
+
+// The last event will be the resultEvent
+const finalEvent = allEvents[allEvents.length - 1];
+console.log(finalEvent.data); // Output the joke and critique
+```
+
+The stream utilities make it easier to work with the asynchronous event flow. In this example, we use:
+- `collect`: Aggregates all events into an array
+- `until`: Creates a stream that emits events until a condition is met (in this case, until a resultEvent is received)
+
+You can combine these utilities with other stream operators like `filter` and `map` to create powerful processing pipelines.
+
+## Next Steps
+
+To learn more about workflows, check out [the documentation in the tutorial section](../../../llamaflow).

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

@@ -2,7 +2,8 @@
 title: Index
 ---
 
-An index is the basic container and organization for your data. LlamaIndex.TS supports two indexes:
+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

apps/next/src/content/docs/llamaindex/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)

apps/next/src/content/docs/llamaindex/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)

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

@@ -7,21 +7,9 @@ These `Transformations` are applied to your input data, and the resulting nodes
 
 ## Installation
 
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install llamaindex @llamaindex/openai @llamaindex/qdrant
-	```
-
-	```shell tab="yarn"
-	yarn add llamaindex @llamaindex/openai @llamaindex/qdrant
-	```
-
-	```shell tab="pnpm"
-	pnpm add llamaindex @llamaindex/openai @llamaindex/qdrant
-	```
-</Tabs>
+```package-install
+npm i llamaindex @llamaindex/openai @llamaindex/qdrant
+```
 
 ## Usage Pattern
 

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

@@ -6,9 +6,9 @@ A transformation is something that takes a list of nodes as an input, and return
 
 Currently, the following components are Transformation objects:
 
-- [SentenceSplitter](/docs/api/classes/SentenceSplitter)
-- [MetadataExtractor](/docs/llamaindex/modules/documents_and_nodes/metadata_extraction)
-- [Embeddings](/docs/llamaindex/modules/embeddings/index)
+- [SentenceSplitter](/docs/llamaindex/modules/data/ingestion_pipeline/transformations/node-parser)
+- [MetadataExtractor](/docs/llamaindex/modules/data/ingestion_pipeline/transformations/metadata_extraction)
+- [Embeddings](/docs/llamaindex/modules/models/embeddings)
 
 ## Usage Pattern
 

apps/next/src/content/docs/llamaindex/modules/data/ingestion_pipeline/transformations/metadata_extraction.mdx

@@ -1,5 +1,5 @@
 ---
-title: Metadata Extraction Usage Pattern
+title: Metadata Extraction 
 ---
 
 You can use LLMs to automate metadata extraction with our `Metadata Extractor` modules.

apps/next/src/content/docs/llamaindex/modules/data/ingestion_pipeline/transformations/node-parser.mdx

@@ -2,17 +2,15 @@
 title: Node Parsers / Text Splitters
 description: Learn how to use Node Parsers and Text Splitters to extract data from documents.
 ---
-import { CodeNodeParserDemo } from '../../../../../components/demo/code-node-parser.tsx';
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
 
-Node parsers are a simple abstraction that take a list of documents, and chunk them into `Node` objects, such that each node is a specific chunk of the parent document. When a document is broken into nodes, all of it's attributes are inherited to the children nodes (i.e. `metadata`, text and metadata templates, etc.). You can read more about `Node` and `Document` properties [here](./).
-
-## NodeParser
-
-The `NodeParser` in LlamaIndex is responsible for splitting `Document` objects into more manageable `Node` objects.
+Node parsers are a simple abstraction that take a list of `Document` objects, and chunk them into `Node` objects, such that each node is a specific chunk of the parent document. When a document is broken into nodes, all of it's attributes are inherited to the children nodes (i.e. `metadata`, text and metadata templates, etc.). You can read more about `Node` and `Document` properties [here](/docs/llamaindex/modules/data).
 
 By default, we will use `Settings.nodeParser` to split the document into nodes. You can also assign a custom `NodeParser` to the `Settings` object.
 
+## SentenceSplitter
+
+The `SentenceSplitter` is the default `NodeParser` in LlamaIndex. It will split the text from a `Document` into sentences.
+
 ```ts twoslash
 import { TextFileReader } from '@llamaindex/readers/text'
 import { SentenceSplitter } from 'llamaindex';
@@ -23,8 +21,6 @@ Settings.nodeParser = nodeParser;
 //		     ^?
 ```
 
-## TextSplitter
-
 The underlying text splitter will split text by sentences. It can also be used as a standalone module for splitting raw text.
 
 ```ts twoslash
@@ -68,6 +64,46 @@ The `MarkdownNodeParser` is a more advanced `NodeParser` that can handle markdow
 	```
 </Tabs>
 
+The output metadata will be something like:
+
+```bash
+[
+  TextNode {
+    id_: '008e41a8-b097-487c-bee8-bd88b9455844',
+    metadata: { 'Header 1': 'Main Header' },
+    excludedEmbedMetadataKeys: [],
+    excludedLlmMetadataKeys: [],
+    relationships: { PARENT: [Array] },
+    hash: 'KJ5e/um/RkHaNR6bonj9ormtZY7I8i4XBPVYHXv1A5M=',
+    text: 'Main Header\nMain content',
+    textTemplate: '',
+    metadataSeparator: '\n'
+  },
+  TextNode {
+    id_: '0f5679b3-ba63-4aff-aedc-830c4208d0b5',
+    metadata: { 'Header 1': 'Header 2' },
+    excludedEmbedMetadataKeys: [],
+    excludedLlmMetadataKeys: [],
+    relationships: { PARENT: [Array] },
+    hash: 'IP/g/dIld3DcbK+uHzDpyeZ9IdOXY4brxhOIe7wc488=',
+    text: 'Header 2\nHeader 2 content',
+    textTemplate: '',
+    metadataSeparator: '\n'
+  },
+  TextNode {
+    id_: 'e81e9bd0-121c-4ead-8ca7-1639d65fdf90',
+    metadata: { 'Header 1': 'Header 2', 'Header 2': 'Sub-header' },
+    excludedEmbedMetadataKeys: [],
+    excludedLlmMetadataKeys: [],
+    relationships: { PARENT: [Array] },
+    hash: 'B3kYNnxaYi9ghtAgwza0ZEVKF4MozobkNUlcekDL7JQ=',
+    text: 'Sub-header\nSub-header content',
+    textTemplate: '',
+    metadataSeparator: '\n'
+  }
+]
+```
+
 ## CodeSplitter
 
 The `CodeSplitter` is a more advanced `NodeParser` that can handle code documents.
@@ -113,8 +149,6 @@ Try it out ⬇️
 
 <CodeNodeParserDemo/>
 
-import { Accordion, Accordions } from 'fumadocs-ui/components/accordion';
-
 <Accordions>
 	<Accordion title="Use it in browser">
 		You might setup WASM files for `web-tree-sitter` and use it in the browser.
@@ -155,3 +189,9 @@ import { Accordion, Accordions } from 'fumadocs-ui/components/accordion';
 		```
 	</Accordion>
 </Accordions>
+
+## API Reference
+
+- [SentenceSplitter](/docs/api/classes/SentenceSplitter)
+- [MarkdownNodeParser](/docs/api/classes/MarkdownNodeParser)
+- [CodeSplitter](/docs/api/classes/CodeSplitter)

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

@@ -0,0 +1,4 @@
+{
+  "title": "Data",
+  "pages": ["index", "readers", "data_index", "ingestion_pipeline", "stores"]
+}

apps/next/src/content/docs/llamaindex/modules/data/readers/discord.mdx

@@ -2,12 +2,15 @@
 title: DiscordReader
 ---
 
-import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
-import CodeSource from "!raw-loader!../../../../../../../../examples/readers/src/discord";
-
 DiscordReader is a simple data loader that reads all messages in a given Discord channel and returns them as Document objects.
 It uses the [@discordjs/rest](https://github.com/discordjs/discord.js/tree/main/packages/rest) library to fetch the messages.
 
+## Installation
+
+```package-install
+npm install @llamaindex/discord
+```
+
 ## Usage
 
 First step is to create a Discord Application and generating a bot token [here](https://discord.com/developers/applications).
@@ -15,7 +18,7 @@ In your Discord Application, go to the `OAuth2` tab and generate an invite URL b
 This will invite the bot with the necessary permissions to read messages.
 Copy the URL in your browser and select the server you want your bot to join.
 
-<DynamicCodeBlock lang="ts" code={CodeSource} />
+<include cwd>../../examples/discord/reader.ts</include>
 
 ### Params
 

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

@@ -0,0 +1,118 @@
+---
+title: Loading Data
+description: Loading data using Readers into Documents
+---
+
+Before you can start indexing your documents, you need to load them into memory.
+A reader is a module that loads data from a file into a `Document` object.
+
+To install readers call:
+
+<Accordions>
+	<Accordion title="Install @llamaindex/readers">
+
+		If you want to use the reader module, you need to install `@llamaindex/readers`
+
+    ```package-install
+    npm i @llamaindex/readers
+    ```
+	</Accordion>
+</Accordions>
+
+We offer readers for different file formats.
+
+```ts twoslash
+import { CSVReader } from '@llamaindex/readers/csv';
+import { DocxReader } from '@llamaindex/readers/docx';
+import { HTMLReader } from '@llamaindex/readers/html';
+import { ImageReader } from '@llamaindex/readers/image';
+import { JSONReader } from '@llamaindex/readers/json';
+import { MarkdownReader } from '@llamaindex/readers/markdown';
+import { ObsidianReader } from '@llamaindex/readers/obsidian';
+import { PDFReader } from '@llamaindex/readers/pdf';
+import { TextFileReader } from '@llamaindex/readers/text';
+```
+
+## SimpleDirectoryReader
+
+[Open in StackBlitz](https://stackblitz.com/github/run-llama/LlamaIndexTS/tree/main/examples/readers?file=src/simple-directory-reader.ts&title=Simple%20Directory%20Reader)
+
+LlamaIndex.TS supports easy loading of files from folders using the `SimpleDirectoryReader` class.
+
+It is a simple reader that reads all files from a directory and its subdirectories and delegates the actual reading to the reader specified in the `fileExtToReader` map.
+
+<include cwd>../../examples/readers/src/simple-directory-reader.ts</include>
+
+Currently, the following readers are mapped to specific file types:
+
+- [TextFileReader](/docs/api/classes/TextFileReader): `.txt`
+- [PDFReader](/docs/api/classes/PDFReader): `.pdf`
+- [CSVReader](/docs/api/classes/CSVReader): `.csv`
+- [MarkdownReader](/docs/api/classes/MarkdownReader): `.md`
+- [DocxReader](/docs/api/classes/DocxReader): `.docx`
+- [HTMLReader](/docs/api/classes/HTMLReader): `.htm`, `.html`
+- [ImageReader](/docs/api/classes/ImageReader): `.jpg`, `.jpeg`, `.png`, `.gif`
+
+You can modify the reader three different ways:
+
+- `overrideReader` overrides the reader for all file types, including unsupported ones.
+- `fileExtToReader` maps a reader to a specific file type. Can override reader for existing file types or add support for new file types.
+- `defaultReader` sets a fallback reader for files with unsupported extensions. By default it is `TextFileReader`.
+
+SimpleDirectoryReader supports up to 9 concurrent requests. Use the `numWorkers` option to set the number of concurrent requests. By default it runs in sequential mode, i.e. set to 1.
+
+### Example
+
+<include cwd>../../examples/readers/src/custom-simple-directory-reader.ts</include>
+
+## Tips when using in non-Node.js environments
+
+When using `@llamaindex/readers` in a non-Node.js environment (such as Vercel Edge, Cloudflare Workers, etc.)
+Some classes are not exported from top-level entry file.
+
+The reason is that some classes are only compatible with Node.js runtime, (e.g. `PDFReader`) which uses Node.js specific APIs (like `fs`, `child_process`, `crypto`).
+
+If you need any of those classes, you have to import them instead directly through their file path in the package.
+
+As the `PDFReader` is not working with the Edge runtime, here's how to use the `SimpleDirectoryReader` with the `LlamaParseReader` to load PDFs:
+
+```typescript
+import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
+import { LlamaParseReader } from "@llamaindex/cloud";
+
+export const DATA_DIR = "./data";
+
+export async function getDocuments() {
+  const reader = new SimpleDirectoryReader();
+  // Load PDFs using LlamaParseReader
+  return await reader.loadData({
+    directoryPath: DATA_DIR,
+    fileExtToReader: {
+      pdf: new LlamaParseReader({ resultType: "markdown" }),
+    },
+  });
+}
+```
+
+> _Note_: Reader classes have to be added explicitly to the `fileExtToReader` map in the Edge version of the `SimpleDirectoryReader`.
+
+You'll find a complete example with LlamaIndexTS here: https://github.com/run-llama/create_llama_projects/tree/main/nextjs-edge-llamaparse
+
+
+## Load file natively using Node.js Customization Hooks
+
+We have a helper utility to allow you to import a file in Node.js script.
+
+```shell 
+node --import @llamaindex/readers/node ./script.js
+```
+
+```ts
+import csv from './path/to/data.csv';
+
+const text = csv.getText()
+```
+
+## API Reference
+
+- [SimpleDirectoryReader](/docs/api/classes/SimpleDirectoryReader)

apps/next/src/content/docs/llamaindex/modules/data/readers/json.mdx

@@ -8,21 +8,9 @@ Supports streaming of large JSON data using [@discoveryjs/json-ext](https://gith
 
 ## Installation
 
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install llamaindex @llamaindex/readers
-	```
-
-	```shell tab="yarn"
-	yarn add llamaindex @llamaindex/readers
-	```
-
-	```shell tab="pnpm"
-	pnpm add llamaindex @llamaindex/readers
-	```
-</Tabs>
+```package-install
+npm i llamaindex @llamaindex/readers
+```
 
 ## Usage
 

apps/next/src/content/docs/llamaindex/modules/data/readers/llama_parse/images.mdx

@@ -6,21 +6,9 @@ LlamaParse `json` mode supports extracting any images found in a page object by
 
 ## Installation
 
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install llamaindex @llamaindex/cloud @llamaindex/openai
-	```
-
-	```shell tab="yarn"
-	yarn add llamaindex @llamaindex/cloud @llamaindex/openai
-	```
-
-	```shell tab="pnpm"
-	pnpm add llamaindex @llamaindex/cloud @llamaindex/openai
-	```
-</Tabs>
+```package-install
+npm i llamaindex @llamaindex/cloud @llamaindex/openai
+```
 
 ## Usage
 
@@ -124,6 +112,3 @@ The returned `imageDocs` have the alt text assigned as text and the image path a
 
 You can see the full example file [here](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/readers/src/llamaparse-json.ts).
 
-## API Reference
-
-- [LlamaParseReader](/docs/api/classes/LlamaParseReader)

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

@@ -2,10 +2,6 @@
 title: LlamaParse
 ---
 
-import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
-import CodeSource from "!raw-loader!../../../../../../../../../examples/readers/src/llamaparse";
-import CodeSource2 from "!raw-loader!../../../../../../../../../examples/readers/src/simple-directory-reader-with-llamaparse.ts";
-
 LlamaParse is an API created by LlamaIndex to efficiently parse files, e.g. it's great at converting PDF tables into markdown.
 
 To use it, first login and get an API key from https://cloud.llamaindex.ai. Make sure to store the key as `apiKey` parameter or in the environment variable `LLAMA_CLOUD_API_KEY`.
@@ -17,7 +13,7 @@ Official documentation for LlamaParse can be found [here](https://docs.cloud.lla
 You can then use the `LlamaParseReader` class to load local files and convert them into a parsed document that can be used by LlamaIndex.
 See [reader.ts](https://github.com/run-llama/LlamaIndexTS/blob/main/packages/cloud/src/reader.ts) for a list of supported file types:
 
-<DynamicCodeBlock lang="ts" code={CodeSource} />
+<include cwd>../../examples/readers/src/llamaparse.ts</include>
 
 ### Params
 
@@ -36,7 +32,7 @@ They can be divided into two groups.
 #### Advanced params:
 
 - `resultType` can be set to `markdown`, `text` or `json`. Defaults to `text`. More information about `json` mode on the next pages.
-- `language` primarily helps with OCR recognition. Defaults to `en`. Click [here](/docs/api/type-aliases/Language) for a list of supported languages.
+- `language` primarily helps with OCR recognition. Defaults to `en`.
 - `parsingInstructions?` Optional. Can help with complicated document structures. See this [LlamaIndex Blog Post](https://www.llamaindex.ai/blog/launching-the-first-genai-native-document-parsing-platform) for an example.
 - `skipDiagonalText?` Optional. Set to true to ignore diagonal text. (Text that is not rotated 0, 90, 180 or 270 degrees)
 - `invalidateCache?` Optional. Set to true to ignore the LlamaCloud cache. All document are kept in cache for 48hours after the job was completed to avoid processing the same document twice. Can be useful for testing when trying to re-parse the same document with, e.g. different `parsingInstructions`.
@@ -60,9 +56,8 @@ They can be divided into two groups.
 
 Below a full example of `LlamaParse` integrated in `SimpleDirectoryReader` with additional options.
 
-<DynamicCodeBlock lang="ts" code={CodeSource2} />
+<include cwd>../../examples/readers/src/simple-directory-reader-with-llamaparse.ts</include>
 
 ## API Reference
 
 - [SimpleDirectoryReader](/docs/api/classes/SimpleDirectoryReader)
-- [LlamaParseReader](/docs/api/classes/LlamaParseReader)

apps/next/src/content/docs/llamaindex/modules/data/readers/llama_parse/json_mode.mdx

@@ -6,21 +6,9 @@ In JSON mode, LlamaParse will return a data structure representing the parsed ob
 
 ## Installation
 
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install llamaindex @llamaindex/cloud
-	```
-
-	```shell tab="yarn"
-	yarn add llamaindex @llamaindex/cloud
-	```
-
-	```shell tab="pnpm"
-	pnpm add llamaindex @llamaindex/cloud
-	```
-</Tabs>
+```package-install
+npm i llamaindex @llamaindex/cloud
+```
 
 ## Usage
 
@@ -110,5 +98,4 @@ You can assign any other values of the JSON response to the Document as needed.
 
 ## API Reference
 
-- [LlamaParseReader](/docs/api/classes/LlamaParseReader)
 - [SimpleDirectoryReader](/docs/api/classes/SimpleDirectoryReader)

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

@@ -6,11 +6,11 @@ Chat stores manage chat history by storing sequences of messages in a structured
 
 ## Available Chat Stores
 
-- [SimpleChatStore](/docs/api/classes/SimpleChatStore): A simple in-memory chat store with support for [persisting](/docs/llamaindex/modules/data_stores/#local-storage) data to disk.
+- [SimpleChatStore](/docs/api/classes/SimpleChatStore): A simple in-memory chat store with support for [persisting](/docs/llamaindex/modules/data/stores#local-storage) data to disk.
 
 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
 
 ## API Reference
 
-- [BaseChatStore](/docs/api/interfaces/BaseChatStore)
+- [BaseChatStore](/docs/api/classes/BaseChatStore)
 

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

@@ -2,32 +2,20 @@
 title: Document Stores
 ---
 
-Document stores contain ingested document chunks, i.e. [Node](/docs/llamaindex/modules/documents_and_nodes/index)s.
+Document stores contain ingested document chunks, i.e. [Node](/docs/llamaindex/modules/data)s.
 
 ## Available Document Stores
 
-- [SimpleDocumentStore](/docs/api/classes/SimpleDocumentStore): A simple in-memory document store with support for [persisting](/docs/llamaindex/modules/data_stores/#local-storage) data to disk.
-- [PostgresDocumentStore](/docs/api/classes/PostgresDocumentStore): A PostgreSQL document store, see [PostgreSQL Storage](/docs/llamaindex/modules/data_stores/#postgresql-storage).
+- [SimpleDocumentStore](/docs/api/classes/SimpleDocumentStore): A simple in-memory document store with support for [persisting](/docs/llamaindex/modules/data/stores#local-storage) data to disk.
+- [PostgresDocumentStore](/docs/api/classes/PostgresDocumentStore): A PostgreSQL document store, see [PostgreSQL Storage](/docs/llamaindex/modules/data/stores#postgresql-storage).
 
 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
 
 ## Using PostgreSQL as Document Store
 
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install llamaindex @llamaindex/postgres
-	```
-
-	```shell tab="yarn"
-	yarn add llamaindex @llamaindex/postgres
-	```
-
-	```shell tab="pnpm"
-	pnpm add llamaindex @llamaindex/postgres
-	```
-</Tabs>
+```package-install
+npm i llamaindex @llamaindex/postgres
+```
 
 You can configure the `schemaName`, `tableName`, `namespace`, and
 `connectionString`. If a `connectionString` is not

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

@@ -2,32 +2,20 @@
 title: Index Stores
 ---
 
-Index stores are underlying storage components that contain metadata(i.e. information created when indexing) about the [index](/docs/llamaindex/modules/data_index) itself.
+Index stores are underlying storage components that contain metadata(i.e. information created when indexing) about the [index](/docs/llamaindex/modules/data/data_index) itself.
 
 ## Available Index Stores
 
-- [SimpleIndexStore](/docs/api/classes/SimpleIndexStore): A simple in-memory index store with support for [persisting](/docs/llamaindex/modules/data_stores/#local-storage) data to disk.
-- [PostgresIndexStore](/docs/api/classes/PostgresIndexStore): A PostgreSQL index store, , see [PostgreSQL Storage](/docs/llamaindex/modules/data_stores/#postgresql-storage).
+- [SimpleIndexStore](/docs/api/classes/SimpleIndexStore): A simple in-memory index store with support for [persisting](/docs/llamaindex/modules/data/stores#local-storage) data to disk.
+- [PostgresIndexStore](/docs/api/classes/PostgresIndexStore): A PostgreSQL index store, , see [PostgreSQL Storage](/docs/llamaindex/modules/data/stores#postgresql-storage).
 
 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
 
 ## Using PostgreSQL as Index Store
 
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install llamaindex @llamaindex/postgres
-	```
-
-	```shell tab="yarn"
-	yarn add llamaindex @llamaindex/postgres
-	```
-
-	```shell tab="pnpm"
-	pnpm add llamaindex @llamaindex/postgres
-	```
-</Tabs>
+```package-install
+npm i llamaindex @llamaindex/postgres
+```
 
 You can configure the `schemaName`, `tableName`, `namespace`, and
 `connectionString`. If a `connectionString` is not

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

@@ -2,12 +2,12 @@
 title: Key-Value Stores
 ---
 
-Key-Value Stores represent underlying storage components used in [Document Stores](/docs/llamaindex/modules/data_stores/doc_stores/index) and [Index Stores](/docs/llamaindex/modules/data_stores/index_stores/index)
+Key-Value Stores represent underlying storage components used in [Document Stores](/docs/llamaindex/modules/data/stores/doc_stores) and [Index Stores](/docs/llamaindex/modules/data/stores/index_stores)
 
 ## Available Key-Value Stores
 
-- [SimpleKVStore](/docs/api/classes/SimpleKVStore): A simple Key-Value store with support of [persisting](/docs/llamaindex/modules/data_stores/#local-storage) data to disk.
-- [PostgresKVStore](/docs/api/classes/PostgresKVStore): A PostgreSQL Key-Value store, see [PostgreSQL Storage](/docs/llamaindex/modules/data_stores/#postgresql-storage).
+- [SimpleKVStore](/docs/api/classes/SimpleKVStore): A simple Key-Value store with support of [persisting](/docs/llamaindex/modules/data/stores#local-storage) data to disk.
+- [PostgresKVStore](/docs/api/classes/PostgresKVStore): A PostgreSQL Key-Value store, see [PostgreSQL Storage](/docs/llamaindex/modules/data/stores#postgresql-storage).
 
 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
 

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

@@ -8,7 +8,7 @@ Vector stores save embedding vectors of your ingested document chunks.
 
 Available Vector Stores are shown on the sidebar to the left. Additionally the following integrations exist without separate documentation:
 
-- [SimpleVectorStore](/docs/api/classes/SimpleVectorStore): A simple in-memory vector store with optional [persistance](/docs/llamaindex/modules/data_stores/#local-storage) to disk.
+- [SimpleVectorStore](/docs/api/classes/SimpleVectorStore): A simple in-memory vector store with optional [persistance](/docs/llamaindex/modules/data/stores#local-storage) to disk.
 - [AstraDBVectorStore](/docs/api/classes/AstraDBVectorStore): A cloud-native, scalable Database-as-a-Service built on Apache Cassandra, see [datastax.com](https://www.datastax.com/products/datastax-astra)
 - [ChromaVectorStore](/docs/api/classes/ChromaVectorStore): An open-source vector database, focused on ease of use and performance, see [trychroma.com](https://www.trychroma.com/)
 - [MilvusVectorStore](/docs/api/classes/MilvusVectorStore): An open-source, high-performance, highly scalable vector database, see [milvus.io](https://milvus.io/)
@@ -19,6 +19,3 @@ Available Vector Stores are shown on the sidebar to the left. Additionally the f
 
 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
 
-## API Reference
-
-- [BaseVectorStore](/docs/api/classes/BaseVectorStore)

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

@@ -13,21 +13,9 @@ docker run -p 6333:6333 qdrant/qdrant
 
 ## Installation
 
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install llamaindex @llamaindex/qdrant
-	```
-
-	```shell tab="yarn"
-	yarn add llamaindex @llamaindex/qdrant
-	```
-
-	```shell tab="pnpm"
-	pnpm add llamaindex @llamaindex/qdrant
-	```
-</Tabs>
+```package-install
+npm i llamaindex @llamaindex/qdrant
+```
 
 ## Importing the modules
 
@@ -56,10 +44,10 @@ const vectorStore = new QdrantVectorStore({
 
 ```ts
 const document = new Document({ text: essay, id_: path });
-
-const index = await VectorStoreIndex.fromDocuments([document], {
-  vectorStore,
-});
+const storageContext = await storageContextFromDefaults({ vectorStore });
+  const index = await VectorStoreIndex.fromDocuments([document], {
+    storageContext,
+  });
 ```
 
 ## Query the index
@@ -91,11 +79,11 @@ async function main() {
   });
 
   const document = new Document({ text: essay, id_: path });
-
+  const storageContext = await storageContextFromDefaults({ vectorStore });
   const index = await VectorStoreIndex.fromDocuments([document], {
-    vectorStore,
+    storageContext,
   });
-
+  
   const queryEngine = index.asQueryEngine();
 
   const response = await queryEngine.query({

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

@@ -0,0 +1,154 @@
+---
+title: Supabase Vector Store
+---
+
+[supabase.com](https://supabase.com/)
+
+To use this vector store, you need a Supabase project. You can create one at [supabase.com](https://supabase.com/).
+
+## Installation
+
+```package-install
+npm i llamaindex @llamaindex/supabase
+```
+
+## Database Setup
+
+Before using the vector store, you need to:
+1. Enable the `pgvector` extension
+2. Create a table for storing vectors
+3. Create a vector similarity search function
+
+```sql
+create table documents (
+id uuid primary key,
+content text,
+metadata jsonb,
+embedding vector(1536)
+);
+```
+
+-- Create a function for similarity search
+```sql
+create function match_documents (
+query_embedding vector(1536),
+match_count int
+) returns table (
+id uuid,
+content text,
+metadata jsonb,
+embedding vector(1536),
+similarity float
+)
+language plpgsql
+as $$
+begin
+return query
+select
+id,
+content,
+metadata,
+embedding,
+1 - (embedding <=> query_embedding) as similarity
+from documents
+order by embedding <=> query_embedding
+limit match_count;
+end;
+$$;
+```
+
+## Importing the modules
+
+```ts
+import { Document, VectorStoreIndex } from "llamaindex";
+import { SupabaseVectorStore } from "@llamaindex/supabase";
+```
+
+## Setup Supabase
+
+```ts
+const vectorStore = new SupabaseVectorStore({
+  supabaseUrl: process.env.SUPABASE_URL,
+  supabaseKey: process.env.SUPABASE_KEY,
+  table: "documents",
+});
+```
+
+## Setup the index
+
+```ts
+const documents = [
+  new Document({ 
+    text: "Sample document text",
+    metadata: { source: "example" }
+  })
+];
+
+const storageContext = await storageContextFromDefaults({ vectorStore });
+const index = await VectorStoreIndex.fromDocuments(documents, {
+  storageContext,
+});
+```
+
+## Query the index
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const response = await queryEngine.query({
+  query: "What is in the document?",
+});
+
+// Output response
+console.log(response.toString());
+```
+
+## Full code
+
+```ts
+import { Document, VectorStoreIndex, storageContextFromDefaults } from "llamaindex";
+import { SupabaseVectorStore } from "@llamaindex/supabase";
+
+async function main() {
+  // Initialize the vector store
+  const vectorStore = new SupabaseVectorStore({
+    supabaseUrl: process.env.SUPABASE_URL,
+    supabaseKey: process.env.SUPABASE_KEY,
+    table: "documents",
+  });
+
+  // Create sample documents
+  const documents = [
+    new Document({
+      text: "Vector search enables semantic similarity search",
+      metadata: {
+        source: "research_paper",
+        author: "Jane Smith",
+      },
+    }),
+  ];
+
+  // Create storage context
+  const storageContext = await storageContextFromDefaults({ vectorStore });
+
+  // Create and store embeddings
+  const index = await VectorStoreIndex.fromDocuments(documents, {
+    storageContext,
+  });
+
+  // Query the index
+  const queryEngine = index.asQueryEngine();
+  const response = await queryEngine.query({
+    query: "What is vector search?",
+  });
+
+  // Output response
+  console.log(response.toString());
+}
+
+main().catch(console.error);
+```
+
+## API Reference
+
+- [SupabaseVectorStore](/docs/api/classes/SupabaseVectorStore)

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

@@ -1,58 +0,0 @@
----
-title: Loader
----
-
-import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
-import CodeSource from "!raw-loader!../../../../../../../../examples/readers/src/simple-directory-reader";
-import CodeSource2 from "!raw-loader!../../../../../../../../examples/readers/src/custom-simple-directory-reader";
-
-Before you can start indexing your documents, you need to load them into memory.
-
-All "basic" data loaders can be seen below, mapped to their respective filetypes in `SimpleDirectoryReader`. More loaders are shown in the sidebar on the left.
-Additionally the following loaders exist without separate documentation:
-
-- `AssemblyAIReader` transcribes audio using [AssemblyAI](https://www.assemblyai.com/).
-  - [AudioTranscriptReader](/docs/api/classes/AudioTranscriptReader): loads entire transcript as a single document.
-  - [AudioTranscriptParagraphsReader](/docs/api/classes/AudioTranscriptParagraphsReader): creates a document per paragraph.
-  - [AudioTranscriptSentencesReader](/docs/api/classes/AudioTranscriptSentencesReader): creates a document per sentence.
-  - [AudioSubtitlesReader](/docs/api/classes/AudioTranscriptParagraphsReader): creates a document containing the subtitles of a transcript.
-- [NotionReader](/docs/api/classes/NotionReader) loads [Notion](https://www.notion.so/) pages.
-- [SimpleMongoReader](/docs/api/classes/SimpleMongoReader) loads data from a [MongoDB](https://www.mongodb.com/).
-
-Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
-
-## SimpleDirectoryReader
-
-[Open in StackBlitz](https://stackblitz.com/github/run-llama/LlamaIndexTS/tree/main/examples/readers?file=src/simple-directory-reader.ts&title=Simple%20Directory%20Reader)
-
-LlamaIndex.TS supports easy loading of files from folders using the `SimpleDirectoryReader` class.
-
-It is a simple reader that reads all files from a directory and its subdirectories.
-
-<DynamicCodeBlock lang="ts" code={CodeSource} />
-
-Currently, the following readers are mapped to specific file types:
-
-- [TextFileReader](/docs/api/classes/TextFileReader): `.txt`
-- [PDFReader](/docs/api/classes/PDFReader): `.pdf`
-- [PapaCSVReader](/docs/api/classes/PapaCSVReader): `.csv`
-- [MarkdownReader](/docs/api/classes/MarkdownReader): `.md`
-- [DocxReader](/docs/api/classes/DocxReader): `.docx`
-- [HTMLReader](/docs/api/classes/HTMLReader): `.htm`, `.html`
-- [ImageReader](/docs/api/classes/ImageReader): `.jpg`, `.jpeg`, `.png`, `.gif`
-
-You can modify the reader three different ways:
-
-- `overrideReader` overrides the reader for all file types, including unsupported ones.
-- `fileExtToReader` maps a reader to a specific file type. Can override reader for existing file types or add support for new file types.
-- `defaultReader` sets a fallback reader for files with unsupported extensions. By default it is `TextFileReader`.
-
-SimpleDirectoryReader supports up to 9 concurrent requests. Use the `numWorkers` option to set the number of concurrent requests. By default it runs in sequential mode, i.e. set to 1.
-
-### Example
-
-<DynamicCodeBlock lang="ts" code={CodeSource2} />
-
-## API Reference
-
-- [SimpleDirectoryReader](/docs/api/classes/SimpleDirectoryReader)

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

@@ -1,16 +0,0 @@
----
-title: Documents and Nodes
----
-
-`Document`s and `Node`s are the basic building blocks of any index. 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)

apps/next/src/content/docs/llamaindex/modules/evaluation/correctness.mdx

@@ -10,21 +10,9 @@ This is useful for measuring if the response was correct. The evaluator returns
 
 Firstly, you need to install the package:
 
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install llamaindex @llamaindex/openai
-	```
-
-	```shell tab="yarn"
-	yarn add llamaindex @llamaindex/openai
-	```
-
-	```shell tab="pnpm"
-	pnpm add llamaindex @llamaindex/openai
-	```
-</Tabs>
+```package-install
+npm i llamaindex @llamaindex/openai
+```
 
 Set the OpenAI API key:
 
@@ -74,4 +62,4 @@ the response is not correct with a score of 2.5
 
 ## API Reference
 
-- [CorrectnessEvaluator](/docs/api/classes/CorrectnessEvaluator)
+- [CorrectnessEvaluator](/docs/api/classes/CorrectnessEvaluator)

apps/next/src/content/docs/llamaindex/modules/evaluation/faithfulness.mdx

@@ -12,22 +12,9 @@ This is useful for measuring if the response was hallucinated. The evaluator ret
 
 Firstly, you need to install the package:
 
-import { Tab, Tabs } from "fumadocs-ui/components/tabs";
-
-<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
-	```shell tab="npm"
-	npm install llamaindex @llamaindex/openai
-	```
-
-	```shell tab="yarn"
-	yarn add llamaindex @llamaindex/openai
-	```
-
-	```shell tab="pnpm"
-	pnpm add llamaindex @llamaindex/openai
-	```
-</Tabs>
-
+```package-install
+npm i llamaindex @llamaindex/openai
+```
 
 Set the OpenAI API key: