Release 0.11.23 (#2136)

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

CONTRIBUTING.md

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

apps/next/CHANGELOG.md

@@ -1,5 +1,161 @@
 # @llamaindex/doc
 
+## 0.2.46
+
+### Patch Changes
+
+- Updated dependencies [f29799e]
+- Updated dependencies [7224c06]
+  - @llamaindex/workflow@1.1.19
+  - @llamaindex/core@0.6.18
+  - llamaindex@0.11.23
+  - @llamaindex/cloud@4.0.27
+  - @llamaindex/node-parser@2.0.18
+  - @llamaindex/openai@0.4.13
+  - @llamaindex/readers@3.1.17
+
+## 0.2.45
+
+### Patch Changes
+
+- Updated dependencies [9ed3195]
+  - @llamaindex/workflow@1.1.18
+  - llamaindex@0.11.22
+
+## 0.2.44
+
+### Patch Changes
+
+- 38da40b: feat: VectoryMemoryBlock
+- Updated dependencies [38da40b]
+  - @llamaindex/core@0.6.17
+  - @llamaindex/cloud@4.0.26
+  - llamaindex@0.11.21
+  - @llamaindex/node-parser@2.0.17
+  - @llamaindex/openai@0.4.12
+  - @llamaindex/readers@3.1.16
+  - @llamaindex/workflow@1.1.17
+
+## 0.2.43
+
+### Patch Changes
+
+- ea15e75: Minor updates in deployment docs
+
+## 0.2.42
+
+### Patch Changes
+
+- a8ec08c: fix: ensure correct message content in agent workflow
+- Updated dependencies [a8ec08c]
+- Updated dependencies [2967d57]
+  - @llamaindex/core@0.6.16
+  - @llamaindex/workflow@1.1.16
+  - @llamaindex/cloud@4.0.25
+  - llamaindex@0.11.20
+  - @llamaindex/node-parser@2.0.16
+  - @llamaindex/openai@0.4.11
+  - @llamaindex/readers@3.1.15
+
+## 0.2.41
+
+### Patch Changes
+
+- Updated dependencies [856dd8c]
+  - @llamaindex/openai@0.4.10
+
+## 0.2.40
+
+### Patch Changes
+
+- Updated dependencies [7ad3411]
+- Updated dependencies [5da5b3c]
+- Updated dependencies [a1fdb07]
+  - @llamaindex/core@0.6.15
+  - @llamaindex/workflow@1.1.15
+  - @llamaindex/openai@0.4.9
+  - @llamaindex/cloud@4.0.24
+  - llamaindex@0.11.19
+  - @llamaindex/node-parser@2.0.15
+  - @llamaindex/readers@3.1.14
+
+## 0.2.39
+
+### Patch Changes
+
+- Updated dependencies [a1b1598]
+  - @llamaindex/cloud@4.0.23
+  - llamaindex@0.11.18
+
+## 0.2.38
+
+### Patch Changes
+
+- Updated dependencies [d2be868]
+  - @llamaindex/cloud@4.0.22
+  - llamaindex@0.11.17
+
+## 0.2.37
+
+### Patch Changes
+
+- Updated dependencies [579ca0c]
+  - @llamaindex/cloud@4.0.21
+  - llamaindex@0.11.16
+
+## 0.2.36
+
+### Patch Changes
+
+- Updated dependencies [48b0d88]
+- Updated dependencies [f185772]
+  - @llamaindex/cloud@4.0.20
+  - llamaindex@0.11.15
+
+## 0.2.35
+
+### Patch Changes
+
+- Updated dependencies [5a0ed1f]
+- Updated dependencies [5a0ed1f]
+- Updated dependencies [8eeac33]
+  - @llamaindex/cloud@4.0.19
+  - @llamaindex/core@0.6.14
+  - llamaindex@0.11.14
+  - @llamaindex/node-parser@2.0.14
+  - @llamaindex/openai@0.4.8
+  - @llamaindex/readers@3.1.13
+  - @llamaindex/workflow@1.1.14
+
+## 0.2.34
+
+### Patch Changes
+
+- 39758ab: Add title to homepage header
+
+## 0.2.33
+
+### Patch Changes
+
+- Updated dependencies [47a7555]
+  - @llamaindex/cloud@4.0.18
+  - llamaindex@0.11.13
+
+## 0.2.32
+
+### Patch Changes
+
+- Updated dependencies [d578889]
+- Updated dependencies [0fcc92f]
+- Updated dependencies [515a8b9]
+  - @llamaindex/core@0.6.13
+  - llamaindex@0.11.12
+  - @llamaindex/cloud@4.0.17
+  - @llamaindex/node-parser@2.0.13
+  - @llamaindex/openai@0.4.7
+  - @llamaindex/readers@3.1.12
+  - @llamaindex/workflow@1.1.13
+
 ## 0.2.31
 
 ### Patch Changes

apps/next/README.md

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

apps/next/components.json

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

apps/next/next.config.mjs

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

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.31",
+  "version": "0.2.46",
   "private": true,
   "scripts": {
     "postinstall": "fumadocs-mdx",
@@ -15,7 +15,6 @@
   "dependencies": {
     "@huggingface/transformers": "^3.5.0",
     "@icons-pack/react-simple-icons": "^10.1.0",
-    "@llamaindex/workflow-docs": "0.1.1",
     "@llamaindex/chat-ui-docs": "^0.0.5",
     "@llamaindex/cloud": "workspace:*",
     "@llamaindex/core": "workspace:*",
@@ -23,8 +22,10 @@
     "@llamaindex/openai": "workspace:*",
     "@llamaindex/readers": "workspace:*",
     "@llamaindex/workflow": "workspace:*",
+    "@llamaindex/workflow-docs": "0.1.1",
     "@mdx-js/mdx": "^3.1.0",
     "@monaco-editor/react": "^4.7.0",
+    "@next/third-parties": "^15.3.4",
     "@number-flow/react": "^0.3.4",
     "@radix-ui/react-dialog": "^1.1.2",
     "@radix-ui/react-icons": "^1.3.2",
@@ -34,7 +35,7 @@
     "@radix-ui/react-tooltip": "^1.1.4",
     "@scalar/api-client-react": "^1.1.25",
     "@vercel/functions": "^1.5.0",
-    "ai": "^3.4.33",
+    "ai": "^4.3.17",
     "class-variance-authority": "^0.7.0",
     "clsx": "2.1.1",
     "foxact": "^0.2.41",
@@ -49,7 +50,7 @@
     "hast-util-to-jsx-runtime": "^2.3.2",
     "llamaindex": "workspace:*",
     "lucide-react": "^0.460.0",
-    "next": "^15.3.0",
+    "next": "^15.3.3",
     "next-themes": "^0.4.3",
     "react": "^19.1.0",
     "react-dom": "^19.1.0",
@@ -69,30 +70,30 @@
     "twoslash": "^0.3.1",
     "use-stick-to-bottom": "^1.0.42",
     "web-tree-sitter": "^0.24.4",
-    "zod": "^3.25.67"
+    "zod": "^3.25.76"
   },
   "devDependencies": {
     "@next/env": "^15.3.0",
     "@tailwindcss/postcss": "^4.0.9",
     "@types/mdx": "^2.0.13",
-    "@types/node": "22.9.0",
-    "@types/react": "^19.0.10",
-    "@types/react-dom": "^19.0.4",
+    "@types/node": "24.0.13",
+    "@types/react": "^19.1.8",
+    "@types/react-dom": "^19.1.6",
     "autoprefixer": "^10.4.20",
     "cross-env": "^7.0.3",
     "fast-glob": "^3.3.2",
     "gray-matter": "^4.0.3",
-    "postcss": "^8.5.3",
+    "postcss": "^8.5.6",
     "raw-loader": "^4.0.2",
     "remark": "^15.0.1",
     "remark-gfm": "^4.0.0",
     "remark-mdx": "^3.1.0",
     "remark-stringify": "^11.0.0",
-    "tailwindcss": "^4.0.9",
-    "tsx": "^4.19.3",
+    "tailwindcss": "^4.1.11",
+    "tsx": "^4.20.3",
     "typedoc": "0.28.3",
     "typedoc-plugin-markdown": "^4.6.2",
     "typedoc-plugin-merge-modules": " ^7.0.0",
-    "typescript": "^5.7.3"
+    "typescript": "^5.8.3"
   }
 }

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

@@ -10,7 +10,7 @@ import { MagicMove } from "@/components/magic-move";
 import { NpmInstall } from "@/components/npm-install";
 import { Supports } from "@/components/supports";
 import { Button } from "@/components/ui/button";
-import { DOCUMENT_URL } from "@/lib/const";
+import { DOCUMENT_URL } from "@/libs/const";
 import { SiStackblitz } from "@icons-pack/react-simple-icons";
 import { Blocks, Bot, Footprints, Terminal } from "lucide-react";
 import Link from "next/link";

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

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

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

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

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

@@ -1,6 +1,6 @@
 import * as demos from "@/components/demo/lazy";
-import { createMetadata, metadataImage } from "@/lib/metadata";
-import { openapi, source } from "@/lib/source";
+import { createMetadata, metadataImage } from "@/libs/metadata";
+import { openapi, source } from "@/libs/source";
 import * as Icons from "@icons-pack/react-simple-icons";
 import { APIPage } from "fumadocs-openapi/ui";
 import { Popup, PopupContent, PopupTrigger } from "fumadocs-twoslash/ui";

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

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

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

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

apps/next/src/app/layout.tsx

@@ -1,5 +1,6 @@
 import { AIProvider } from "@/actions";
 import { TooltipProvider } from "@/components/ui/tooltip";
+import { GoogleAnalytics, GoogleTagManager } from "@next/third-parties/google";
 import { RootProvider } from "fumadocs-ui/provider";
 import { Inter } from "next/font/google";
 import type { ReactNode } from "react";
@@ -31,7 +32,11 @@ export default function Layout({ children }: { children: ReactNode }) {
           sizes="16x16"
           href="/favicon-16x16.png"
         />
+        <title>
+          LlamaIndex.TS - Build LLM-powered document agents and workflows
+        </title>
       </head>
+      <GoogleTagManager gtmId="GTM-WWRFB36R" />
       <body className="flex min-h-screen flex-col">
         <TooltipProvider>
           <AIProvider>
@@ -39,6 +44,7 @@ export default function Layout({ children }: { children: ReactNode }) {
           </AIProvider>
         </TooltipProvider>
       </body>
+      <GoogleAnalytics gaId="G-NB9B8LW9W5" />
     </html>
   );
 }

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

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

apps/next/src/components/contribution.tsx

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

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

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

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

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

apps/next/src/components/feature.tsx

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

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

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

apps/next/src/components/message.tsx

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

@@ -1,70 +0,0 @@
----
-title: With Cloudflare Worker
-description: In this guide, you'll learn how to use LlamaIndex with CloudFlare Worker
----
-
-Before you start, make sure you have try LlamaIndex.TS in Node.js to make sure you understand the basics.
-
-<Card
-  title="Getting Started with LlamaIndex.TS in Node.js"
-  href="/docs/llamaindex/getting_started/installation/node"
-/>
-
-Also, you need have the basic understanding of <a href='https://developers.cloudflare.com/workers/'><SiCloudflareworkers className="inline mr-2" color="#F38020" />Cloudflare Worker</a>.
-
-## Adding environment variables
-
-```ts
-export default {
-  async fetch(request: Request, env: Env): Promise<Response> {
-    const { setEnvs } = await import("@llamaindex/env");
-    setEnvs(env);
-    const { OpenAIAgent } = await import("@llamaindex/openai");
-    // Start your code here
-    return new Response("Hello, world!");
-  },
-};
-```
-
-Then, you need create `.dev.vars` and add LLM api keys for the local development, such as `OPENAI_API_KEY` for OpenAI API key.
-
-<Callout type="warn">Do not commit the api key to git repository.</Callout>
-
-## Integrating with Hono
-
-```ts
-import { Hono } from "hono";
-
-type Bindings = {
-  OPENAI_API_KEY: string;
-};
-
-const app = new Hono<{
-  Bindings: Bindings;
-}>();
-
-app.post("/llm", async (c) => {
-  const { setEnvs } = await import("@llamaindex/env");
-  setEnvs(c.env);
-
-  // ...
-
-  return new Response('Hello, world!');
-})
-
-export default {
-  fetch: app.fetch,
-};
-```
-
-## Difference between Node.js and Cloudflare Worker
-
-In Cloudflare Worker and similar serverless JS environment, you need to be aware of the following differences:
-
-- Some Node.js modules are not available in Cloudflare Worker, such as `node:fs`, `node:child_process`, `node:cluster`...
-- You are recommend to design your code using network request, such as use `fetch` API to communicate with database, instead of a long-running process in Node.js.
-- Some of LlamaIndex.TS packages are not available in Cloudflare Worker, for example `@llamaindex/readers` and `@llamaindex/huggingface`.
-- The main `llamaindex` is designed to work in all JavaScript environment, including Cloudflare Worker. If you find any issue, please report to us.
-- `@llamaindex/env` is a JS environment binding module, which polyfill some Node.js/Modern Web API (for example, we have a memory based `fs` module, and Crypto API polyfill). It is designed to work in all JavaScript environment, including Cloudflare Worker.
-
-

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

@@ -0,0 +1,228 @@
+---
+title: Memory
+description: Manage conversation history and context with agents
+---
+
+## Concept
+
+Memory is a core component of agentic systems. It allows you to store and retrieve information from the past.
+
+In LlamaIndexTS, you can create memory by using the `createMemory` function. This function will return a `Memory` object, which you can then use to store and retrieve information.
+
+As the agent runs, it will make calls to `add()` to store information, and `get()` to retrieve information. 
+
+## Usage
+
+A `Memory` object has both short-term memory (i.e. a FIFO queue of messages) and optionally long-term memory (i.e. extracting information over time).
+
+`get()` always returns all messages stored in the memory. The longer the agent runs, this will exceed the context window of the agent. To avoid this, the agent is using the `getLLM` method to get the last X messages that fit into the context window.
+
+### Configuring Memory for an Agent
+
+Here we're creating a memory with a static block (read more about [memory blocks](#long-term-memory)) that contains some information about the user.
+
+```ts twoslash
+import { openai } from "@llamaindex/openai";
+import { agent } from "@llamaindex/workflow";
+import { createMemory, staticBlock } from "llamaindex";
+
+const llm = openai({ model: "gpt-4.1-mini" });
+
+// Create memory with predefined context
+const memory = createMemory({
+  memoryBlocks: [
+    staticBlock({
+      content:
+        "The user is a software engineer who loves TypeScript and LlamaIndex.",
+    }),
+  ],
+});
+
+// Create an agent with the memory
+const workflow = agent({
+  name: "assistant",
+  llm,
+  memory,
+});
+
+const result = await workflow.run("What is my name?");
+console.log("Response:", result.data.result);
+```
+
+### Using Vercel format
+
+You can also put messages in Vercel format directly to the memory:
+
+```ts
+await memory.add({
+  id: "1",
+  createdAt: new Date(),
+  role: "user",
+  content: "Hello!",
+  options: {
+    parts: [
+      {
+        type: "file",
+        data: "base64...",
+        mimeType: "image/png",
+      },
+    ],
+  },
+});
+```
+
+If you call `get`, messages are usually retrieved in the LlamaIndexTS format (type `ChatMessage`). If you specify the `type` parameter using `get`, you can return the messages in different formats. E.g.: using `type: "vercel"`, you can return the messages in Vercel format:
+
+```ts
+const messages = await memory.get({ type: "vercel" });
+console.log(messages);
+```
+
+## Customizing Memory
+
+### Short-Term Memory
+
+The `Memory` object will store all the messages that are added to the `Memory` object. Unless you call `clear()`, no messages are removed from the memory. This is the short-term memory (usually you will store the memory of one user session there) which is augmented by the long-term memory.
+
+Calling `getLLM` will retrieve messages from long-term memory and ensure that the given `tokenLimit` is not reached. These are the messages that you will sent to the LLM.
+
+For initialization, you call `createMemory` with the following options:
+
+- `tokenLimit`: Maximum tokens for memory retrieval using `getLLM` (default: 30000).
+- `shortTermTokenLimitRatio`: Ratio of tokens for short-term vs long-term memory (default: 0.7)
+- `customAdapters`: Custom message adapters for different message formats. LlamaIndex (`ChatMessageAdapter`) and Vercel (`VercelMessageAdapter`) are built-in adapters.
+- `memoryBlocks`: Memory blocks for long-term storage, see [Long-Term Memory](#long-term-memory)
+
+Example:
+
+```ts
+const memory = createMemory({
+    tokenLimit=40000,
+    shortTermTokenLimitRatio=0.5,
+});
+```
+
+### Long-Term Memory
+
+Long-term memory is represented as `Memory Block` objects. These objects contain information that are from previous user sessions or from the beginning of the current conversation. When memory is retrieved (by calling `getLLM`), the short-term and long-term memories are merged together within the given `tokenLimit`. 
+
+Currently, there are three predefined memory blocks:
+
+- `staticBlock`: A memory block that stores a static piece of information.
+- `factExtractionBlock`: A memory block that extracts facts from the chat history.
+- `vectorBlock`: A memory block that stores and retrieves chat messages from a vector database using semantic similarity search. Messages are stored individually and retrieved based on their relevance to recent conversation context. Here we've passed in the `vectorStore` to use to store and retrieve the chat messages.
+
+This sounds a bit complicated, but it's actually quite simple. Let's look at an example:
+
+```ts
+import { createMemory, factExtractionBlock, staticBlock, vectorBlock } from "llamaindex";
+import { QdrantVectorStore } from "@llamaindex/qdrant";
+import { OpenAIEmbedding } from "@llamaindex/openai";
+
+const memoryBlocks= [
+  staticBlock({
+    content: "My name is Logan, and I live in Saskatoon. I work at LlamaIndex.",
+  }),
+  factExtractionBlock({
+    priority: 1,
+    llm: llm,
+    maxFacts: 50,
+  }),
+  vectorBlock({
+    vectorStore: new QdrantVectorStore({ url: "http://localhost:6333" }),
+    priority: 2,
+  }),
+];
+```
+
+Here, we've setup three memory blocks:
+
+- `staticBlock`: A static memory block that stores some core information about the user. This information will always be inserted into the memory. The type used is `MessageContent` to support multi-modal content.
+- `factExtractionBlock`: An extracted memory block that will extract information from the chat history. Here we've passed in the `llm` to use to extract facts from the chat history, and set the `maxFacts` to 50. If the number of extracted facts exceeds this limit, the `maxFacts` will be automatically summarized and reduced to leave room for new information.
+- `vectorBlock`: A vector memory block that will store in a vector database and retrieve them from there. Messages are stored individually and retrieved based on their relevance to recent conversation context. Here we've passed in the `vectorStore` to use to store and retrieve the chat messages.
+
+You'll also notice that we've set the `priority` for the `factExtractionBlock` block. This is used to determine the handling when the memory blocks content (i.e. long-term memory) + short-term memory exceeds the token limit on the `Memory` object.
+
+- `priority=0`: This block will always be kept in memory (`staticBlocks` always have priority 0.)
+- `priority=1, 2, 3, etc`: This determines the order in which memory blocks are truncated when the memory exceeds the token limit, to help the overall short-term memory + long-term memory content be less than or equal to the `tokenLimit`.
+
+Now, let's pass these blocks into the `createMemory` function:
+
+```ts
+const memory = createMemory({
+  tokenLimit: 40000,
+  memoryBlocks: memoryBlocks,
+)
+```
+
+When memory is retrieved (using `getLLM`), the short-term and long-term memories are merged together. The `Memory` object will ensure that the short-term memory + long-term memory content is less than or equal to the `tokenLimit`. If it is longer, messages are retrieved in the following order:
+
+1. StaticMemoryBlock (information always included)
+2. LongTermMemoryBlock (depending on priority)
+3. ShortTermMemoryBlock 
+4. Transient messages
+
+The amount of short-term memory included is specified by the `shortTermTokenLimitRatio`. If it's set to `0.7`, 70% of the `tokenLimit` is used for short-term memory (not including the static memory block).
+
+
+#### VectorBlock Configuration Options
+
+The `vectorBlock` offers several configuration options to customize its behavior:
+
+```ts
+vectorBlock({
+  vectorStore: new QdrantVectorStore({ url: "http://localhost:6333" }),
+  priority: 2,
+  retrievalContextWindow: 5, // Number of recent messages to use for context when retrieving
+  formatTemplate: new PromptTemplate({ template: "Context: {{ context }}" }), // Custom formatting template
+  nodePostprocessors: [/* custom postprocessors */], // Apply processing to retrieved nodes
+  queryOptions: {
+    similarityTopK: 3, // Number of top similar results to return (default: 2)
+    mode: VectorStoreQueryMode.DEFAULT, // Query mode for the vector store
+    sessionFilterKey: "session_id", // Metadata key for session filtering (default: "session_id")
+    // Custom filters can be added here - session filter is automatically included
+    filters: {
+      filters: [
+        { key: "custom_field", value: "custom_value", operator: "==" }
+      ],
+      condition: "and"
+    }
+  }
+})
+```
+
+**Key Configuration Options:**
+
+- **`retrievalContextWindow`**: Number of recent messages to consider when creating the retrieval query (default: 5). A larger window provides more context but may be less precise.
+- **`formatTemplate`**: Template for formatting retrieved information before adding to memory. Defaults to a simple context template.
+- **`nodePostprocessors`**: Array of postprocessors to apply to retrieved nodes, useful for filtering or transforming results.
+- **`queryOptions.similarityTopK`**: Number of most similar messages to retrieve from the vector store (default: 2).
+- **`queryOptions.sessionFilterKey`**: Metadata key used to isolate memory between different sessions (default: "session_id").
+- **`queryOptions.filters`**: Additional metadata filters for retrieval. The session filter is automatically added to ensure memory isolation.
+
+**Session Isolation:**
+
+The vectorBlock automatically adds a session filter using the block's ID to ensure that memories from different sessions don't interfere with each other. This filter uses the `sessionFilterKey` (default: "session_id") and can be customized if needed.
+
+## Persistence with Snapshots
+
+Save and restore memory state:
+
+```ts twoslash
+import { createMemory, loadMemory } from "llamaindex";
+
+const memory = createMemory();
+
+// Add some messages
+await memory.add({ role: "user", content: "Hello!" });
+
+// Create snapshot
+const snapshot = memory.snapshot();
+
+// Later, restore from the snapshot
+const restoredMemory = loadMemory(snapshot);
+```
+
+## Examples
+
+Want to learn more about the Memory class? Check out our example codes in [Github](https://github.com/run-llama/LlamaIndexTS/tree/main/examples/agents/memory).

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

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

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

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

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

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

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

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

apps/next/src/lib/metadata.ts

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

apps/next/src/lib/utils.ts

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

apps/next/src/libs/const.ts

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

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

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

apps/next/src/libs/metadata.ts

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

apps/next/src/libs/source.ts

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

apps/next/src/libs/utils.ts

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

e2e/examples/cloudflare-hono/package.json

@@ -11,7 +11,7 @@
   },
   "devDependencies": {
     "@cloudflare/workers-types": "^4.20241112.0",
-    "typescript": "^5.7.3",
+    "typescript": "^5.8.3",
     "wrangler": "^3.89.0"
   },
   "dependencies": {

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

@@ -1,5 +1,78 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.184
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.0.183
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.0.182
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
+## 0.0.181
+
+### Patch Changes
+
+- llamaindex@0.11.20
+
+## 0.0.180
+
+### Patch Changes
+
+- llamaindex@0.11.19
+
+## 0.0.179
+
+### Patch Changes
+
+- llamaindex@0.11.18
+
+## 0.0.178
+
+### Patch Changes
+
+- llamaindex@0.11.17
+
+## 0.0.177
+
+### Patch Changes
+
+- llamaindex@0.11.16
+
+## 0.0.176
+
+### Patch Changes
+
+- llamaindex@0.11.15
+
+## 0.0.175
+
+### Patch Changes
+
+- llamaindex@0.11.14
+
+## 0.0.174
+
+### Patch Changes
+
+- llamaindex@0.11.13
+
+## 0.0.173
+
+### Patch Changes
+
+- Updated dependencies [515a8b9]
+  - llamaindex@0.11.12
+
 ## 0.0.172
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.172",
+  "version": "0.0.184",
   "type": "module",
   "private": true,
   "scripts": {
@@ -16,7 +16,7 @@
     "@cloudflare/workers-types": "^4.20241112.0",
     "@vitest/runner": "2.1.5",
     "@vitest/snapshot": "2.1.5",
-    "typescript": "^5.7.3",
+    "typescript": "^5.8.3",
     "vitest": "2.1.5",
     "wrangler": "^3.87.0"
   },

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

@@ -1,5 +1,80 @@
 # @llamaindex/llama-parse-browser-test
 
+## 0.0.82
+
+### Patch Changes
+
+- @llamaindex/cloud@4.0.27
+
+## 0.0.81
+
+### Patch Changes
+
+- @llamaindex/cloud@4.0.26
+
+## 0.0.80
+
+### Patch Changes
+
+- Updated dependencies [2967d57]
+  - @llamaindex/cloud@4.0.25
+
+## 0.0.79
+
+### Patch Changes
+
+- @llamaindex/cloud@4.0.24
+
+## 0.0.78
+
+### Patch Changes
+
+- Updated dependencies [a1b1598]
+  - @llamaindex/cloud@4.0.23
+
+## 0.0.77
+
+### Patch Changes
+
+- Updated dependencies [d2be868]
+  - @llamaindex/cloud@4.0.22
+
+## 0.0.76
+
+### Patch Changes
+
+- Updated dependencies [579ca0c]
+  - @llamaindex/cloud@4.0.21
+
+## 0.0.75
+
+### Patch Changes
+
+- Updated dependencies [48b0d88]
+- Updated dependencies [f185772]
+  - @llamaindex/cloud@4.0.20
+
+## 0.0.74
+
+### Patch Changes
+
+- Updated dependencies [5a0ed1f]
+- Updated dependencies [5a0ed1f]
+  - @llamaindex/cloud@4.0.19
+
+## 0.0.73
+
+### Patch Changes
+
+- Updated dependencies [47a7555]
+  - @llamaindex/cloud@4.0.18
+
+## 0.0.72
+
+### Patch Changes
+
+- @llamaindex/cloud@4.0.17
+
 ## 0.0.71
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llama-parse-browser-test",
   "private": true,
-  "version": "0.0.71",
+  "version": "0.0.82",
   "type": "module",
   "scripts": {
     "dev": "vite",
@@ -9,7 +9,7 @@
     "preview": "vite preview"
   },
   "devDependencies": {
-    "typescript": "^5.7.3",
+    "typescript": "^5.8.3",
     "vite": "^6.3.3",
     "vite-plugin-wasm": "^3.4.1"
   },

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,78 @@
 # @llamaindex/next-agent-test
 
+## 0.1.184
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.1.183
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.1.182
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
+## 0.1.181
+
+### Patch Changes
+
+- llamaindex@0.11.20
+
+## 0.1.180
+
+### Patch Changes
+
+- llamaindex@0.11.19
+
+## 0.1.179
+
+### Patch Changes
+
+- llamaindex@0.11.18
+
+## 0.1.178
+
+### Patch Changes
+
+- llamaindex@0.11.17
+
+## 0.1.177
+
+### Patch Changes
+
+- llamaindex@0.11.16
+
+## 0.1.176
+
+### Patch Changes
+
+- llamaindex@0.11.15
+
+## 0.1.175
+
+### Patch Changes
+
+- llamaindex@0.11.14
+
+## 0.1.174
+
+### Patch Changes
+
+- llamaindex@0.11.13
+
+## 0.1.173
+
+### Patch Changes
+
+- Updated dependencies [515a8b9]
+  - llamaindex@0.11.12
+
 ## 0.1.172
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.172",
+  "version": "0.1.184",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -8,18 +8,18 @@
     "start": "next start"
   },
   "dependencies": {
-    "ai": "^4.0.0",
+    "ai": "^4.3.17",
     "llamaindex": "workspace:*",
-    "next": "^15.3.0",
+    "next": "^15.3.3",
     "react": "19.0.0",
     "react-dom": "19.0.0"
   },
   "devDependencies": {
-    "@types/node": "^22.9.0",
-    "@types/react": "^19.0.10",
-    "@types/react-dom": "^19.0.4",
-    "eslint": "9.16.0",
-    "eslint-config-next": "15.1.0",
-    "typescript": "^5.7.3"
+    "@types/node": "^24.0.13",
+    "@types/react": "^19.1.8",
+    "@types/react-dom": "^19.1.6",
+    "eslint": "9.30.1",
+    "eslint-config-next": "15.3.5",
+    "typescript": "^5.8.3"
   }
 }

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

@@ -1,5 +1,78 @@
 # test-edge-runtime
 
+## 0.1.183
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.1.182
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.1.181
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
+## 0.1.180
+
+### Patch Changes
+
+- llamaindex@0.11.20
+
+## 0.1.179
+
+### Patch Changes
+
+- llamaindex@0.11.19
+
+## 0.1.178
+
+### Patch Changes
+
+- llamaindex@0.11.18
+
+## 0.1.177
+
+### Patch Changes
+
+- llamaindex@0.11.17
+
+## 0.1.176
+
+### Patch Changes
+
+- llamaindex@0.11.16
+
+## 0.1.175
+
+### Patch Changes
+
+- llamaindex@0.11.15
+
+## 0.1.174
+
+### Patch Changes
+
+- llamaindex@0.11.14
+
+## 0.1.173
+
+### Patch Changes
+
+- llamaindex@0.11.13
+
+## 0.1.172
+
+### Patch Changes
+
+- Updated dependencies [515a8b9]
+  - llamaindex@0.11.12
+
 ## 0.1.171
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.171",
+  "version": "0.1.183",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -9,14 +9,14 @@
   },
   "dependencies": {
     "llamaindex": "workspace:*",
-    "next": "^15.3.0",
+    "next": "^15.3.3",
     "react": "^19.1.0",
     "react-dom": "^19.1.0"
   },
   "devDependencies": {
-    "@types/node": "^22.9.0",
-    "@types/react": "^19.0.10",
-    "@types/react-dom": "^19.0.4",
-    "typescript": "^5.7.3"
+    "@types/node": "^24.0.13",
+    "@types/react": "^19.1.8",
+    "@types/react-dom": "^19.1.6",
+    "typescript": "^5.8.3"
   }
 }

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

@@ -1,5 +1,96 @@
 # @llamaindex/next-node-runtime
 
+## 0.1.53
+
+### Patch Changes
+
+- llamaindex@0.11.23
+- @llamaindex/huggingface@0.1.23
+- @llamaindex/readers@3.1.17
+
+## 0.1.52
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.1.51
+
+### Patch Changes
+
+- llamaindex@0.11.21
+- @llamaindex/huggingface@0.1.22
+- @llamaindex/readers@3.1.16
+
+## 0.1.50
+
+### Patch Changes
+
+- llamaindex@0.11.20
+- @llamaindex/huggingface@0.1.21
+- @llamaindex/readers@3.1.15
+
+## 0.1.49
+
+### Patch Changes
+
+- @llamaindex/huggingface@0.1.20
+
+## 0.1.48
+
+### Patch Changes
+
+- llamaindex@0.11.19
+- @llamaindex/huggingface@0.1.19
+- @llamaindex/readers@3.1.14
+
+## 0.1.47
+
+### Patch Changes
+
+- llamaindex@0.11.18
+
+## 0.1.46
+
+### Patch Changes
+
+- llamaindex@0.11.17
+
+## 0.1.45
+
+### Patch Changes
+
+- llamaindex@0.11.16
+
+## 0.1.44
+
+### Patch Changes
+
+- llamaindex@0.11.15
+
+## 0.1.43
+
+### Patch Changes
+
+- llamaindex@0.11.14
+- @llamaindex/huggingface@0.1.18
+- @llamaindex/readers@3.1.13
+
+## 0.1.42
+
+### Patch Changes
+
+- llamaindex@0.11.13
+
+## 0.1.41
+
+### Patch Changes
+
+- Updated dependencies [515a8b9]
+  - llamaindex@0.11.12
+  - @llamaindex/huggingface@0.1.17
+  - @llamaindex/readers@3.1.12
+
 ## 0.1.40
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.40",
+  "version": "0.1.53",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -11,16 +11,16 @@
     "@llamaindex/huggingface": "workspace:*",
     "@llamaindex/readers": "workspace:*",
     "llamaindex": "workspace:*",
-    "next": "^15.3.0",
+    "next": "^15.3.3",
     "react": "19.0.0",
     "react-dom": "19.0.0"
   },
   "devDependencies": {
-    "@types/node": "^22.9.0",
-    "@types/react": "^19.0.10",
-    "@types/react-dom": "^19.0.4",
-    "eslint": "9.16.0",
-    "eslint-config-next": "15.1.0",
-    "typescript": "^5.7.3"
+    "@types/node": "^24.0.13",
+    "@types/react": "^19.1.8",
+    "@types/react-dom": "^19.1.6",
+    "eslint": "9.30.1",
+    "eslint-config-next": "15.3.5",
+    "typescript": "^5.8.3"
   }
 }

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

@@ -1,5 +1,78 @@
 # vite-import-llamaindex
 
+## 0.0.50
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.0.49
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.0.48
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
+## 0.0.47
+
+### Patch Changes
+
+- llamaindex@0.11.20
+
+## 0.0.46
+
+### Patch Changes
+
+- llamaindex@0.11.19
+
+## 0.0.45
+
+### Patch Changes
+
+- llamaindex@0.11.18
+
+## 0.0.44
+
+### Patch Changes
+
+- llamaindex@0.11.17
+
+## 0.0.43
+
+### Patch Changes
+
+- llamaindex@0.11.16
+
+## 0.0.42
+
+### Patch Changes
+
+- llamaindex@0.11.15
+
+## 0.0.41
+
+### Patch Changes
+
+- llamaindex@0.11.14
+
+## 0.0.40
+
+### Patch Changes
+
+- llamaindex@0.11.13
+
+## 0.0.39
+
+### Patch Changes
+
+- Updated dependencies [515a8b9]
+  - llamaindex@0.11.12
+
 ## 0.0.38
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.38",
+  "version": "0.0.50",
   "type": "module",
   "scripts": {
     "build": "vite build",
@@ -15,7 +15,7 @@
   "devDependencies": {
     "@size-limit/preset-big-lib": "^11.1.6",
     "size-limit": "^11.1.6",
-    "typescript": "^5.7.3",
+    "typescript": "^5.8.3",
     "vite": "^6.3.3"
   },
   "dependencies": {

e2e/examples/vite-import-llamaindex/tsconfig.tsbuildinfo

@@ -1,9 +1 @@
-{
-  "root": [
-    "./src/main.ts",
-    "./vite.config.ts",
-    "./tsconfig.json"
-  ],
-  "errors": true,
-  "version": "5.7.3"
-}
+{"root":["./src/main.ts","./vite.config.ts"],"version":"5.7.3"}

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

@@ -1,5 +1,78 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.184
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.0.183
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.0.182
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
+## 0.0.181
+
+### Patch Changes
+
+- llamaindex@0.11.20
+
+## 0.0.180
+
+### Patch Changes
+
+- llamaindex@0.11.19
+
+## 0.0.179
+
+### Patch Changes
+
+- llamaindex@0.11.18
+
+## 0.0.178
+
+### Patch Changes
+
+- llamaindex@0.11.17
+
+## 0.0.177
+
+### Patch Changes
+
+- llamaindex@0.11.16
+
+## 0.0.176
+
+### Patch Changes
+
+- llamaindex@0.11.15
+
+## 0.0.175
+
+### Patch Changes
+
+- llamaindex@0.11.14
+
+## 0.0.174
+
+### Patch Changes
+
+- llamaindex@0.11.13
+
+## 0.0.173
+
+### Patch Changes
+
+- Updated dependencies [515a8b9]
+  - llamaindex@0.11.12
+
 ## 0.0.172
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.172",
+  "version": "0.0.184",
   "type": "module",
   "private": true,
   "scripts": {
@@ -18,10 +18,10 @@
   },
   "devDependencies": {
     "@tailwindcss/postcss": "^4.1.4",
-    "@types/react": "19.0.10",
-    "@types/react-dom": "19.0.4",
+    "@types/react": "19.1.8",
+    "@types/react-dom": "19.1.6",
     "rollup": "4.38.0",
-    "tailwindcss": "^4.1.4",
-    "typescript": "5.7.3"
+    "tailwindcss": "^4.1.11",
+    "typescript": "5.8.3"
   }
 }

e2e/node/claude.e2e.ts

@@ -10,7 +10,7 @@ import { mockLLMEvent } from "./utils.js";
 let llm: LLM;
 beforeEach(async () => {
   Settings.llm = new Anthropic({
-    model: "claude-3-opus",
+    model: "claude-3.5-sonnet",
   });
   llm = Settings.llm;
 });

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

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

e2e/package.json

@@ -19,14 +19,14 @@
     "@llamaindex/openai": "workspace:*",
     "@llamaindex/pinecone": "workspace:*",
     "@llamaindex/postgres": "workspace:*",
-    "@types/node": "^22.9.0",
+    "@types/node": "^24.0.13",
     "@types/pg": "^8.11.8",
     "consola": "^3.2.3",
-    "dotenv": "^16.4.5",
+    "dotenv": "^17.2.0",
     "llamaindex": "workspace:*",
     "pg": "^8.12.0",
     "pgvector": "0.2.0",
-    "tsx": "^4.19.3",
-    "zod": "^3.25.67"
+    "tsx": "^4.20.3",
+    "zod": "^3.25.76"
   }
 }

examples/CHANGELOG.md

@@ -1,5 +1,369 @@
 # examples
 
+## 0.3.34
+
+### Patch Changes
+
+- Updated dependencies [f29799e]
+- Updated dependencies [7224c06]
+  - @llamaindex/workflow@1.1.19
+  - @llamaindex/core@0.6.18
+  - llamaindex@0.11.23
+  - @llamaindex/cloud@4.0.27
+  - @llamaindex/node-parser@2.0.18
+  - @llamaindex/anthropic@0.3.20
+  - @llamaindex/assemblyai@0.1.17
+  - @llamaindex/clip@0.0.69
+  - @llamaindex/cohere@0.0.32
+  - @llamaindex/deepinfra@0.0.69
+  - @llamaindex/discord@0.1.17
+  - @llamaindex/google@0.3.17
+  - @llamaindex/huggingface@0.1.23
+  - @llamaindex/jinaai@0.0.29
+  - @llamaindex/mistral@0.1.18
+  - @llamaindex/mixedbread@0.0.32
+  - @llamaindex/notion@0.1.17
+  - @llamaindex/ollama@0.1.18
+  - @llamaindex/openai@0.4.13
+  - @llamaindex/perplexity@0.0.26
+  - @llamaindex/portkey-ai@0.0.60
+  - @llamaindex/replicate@0.0.60
+  - @llamaindex/bm25-retriever@0.0.7
+  - @llamaindex/astra@0.0.32
+  - @llamaindex/azure@0.1.30
+  - @llamaindex/chroma@0.0.32
+  - @llamaindex/elastic-search@0.1.18
+  - @llamaindex/firestore@1.0.25
+  - @llamaindex/milvus@0.1.27
+  - @llamaindex/mongodb@0.0.33
+  - @llamaindex/pinecone@0.1.18
+  - @llamaindex/postgres@0.0.61
+  - @llamaindex/qdrant@0.1.28
+  - @llamaindex/supabase@0.1.19
+  - @llamaindex/upstash@0.0.32
+  - @llamaindex/weaviate@0.0.33
+  - @llamaindex/vercel@0.1.18
+  - @llamaindex/voyage-ai@1.0.24
+  - @llamaindex/readers@3.1.17
+  - @llamaindex/tools@0.1.8
+  - @llamaindex/deepseek@0.0.30
+  - @llamaindex/fireworks@0.0.29
+  - @llamaindex/groq@0.0.85
+  - @llamaindex/together@0.0.29
+  - @llamaindex/vllm@0.0.55
+  - @llamaindex/xai@0.0.16
+
+## 0.3.33
+
+### Patch Changes
+
+- Updated dependencies [38da40b]
+  - @llamaindex/core@0.6.17
+  - @llamaindex/cloud@4.0.26
+  - llamaindex@0.11.21
+  - @llamaindex/node-parser@2.0.17
+  - @llamaindex/anthropic@0.3.19
+  - @llamaindex/assemblyai@0.1.16
+  - @llamaindex/clip@0.0.68
+  - @llamaindex/cohere@0.0.31
+  - @llamaindex/deepinfra@0.0.68
+  - @llamaindex/discord@0.1.16
+  - @llamaindex/google@0.3.16
+  - @llamaindex/huggingface@0.1.22
+  - @llamaindex/jinaai@0.0.28
+  - @llamaindex/mistral@0.1.17
+  - @llamaindex/mixedbread@0.0.31
+  - @llamaindex/notion@0.1.16
+  - @llamaindex/ollama@0.1.17
+  - @llamaindex/openai@0.4.12
+  - @llamaindex/perplexity@0.0.25
+  - @llamaindex/portkey-ai@0.0.59
+  - @llamaindex/replicate@0.0.59
+  - @llamaindex/bm25-retriever@0.0.6
+  - @llamaindex/astra@0.0.31
+  - @llamaindex/azure@0.1.29
+  - @llamaindex/chroma@0.0.31
+  - @llamaindex/elastic-search@0.1.17
+  - @llamaindex/firestore@1.0.24
+  - @llamaindex/milvus@0.1.26
+  - @llamaindex/mongodb@0.0.32
+  - @llamaindex/pinecone@0.1.17
+  - @llamaindex/postgres@0.0.60
+  - @llamaindex/qdrant@0.1.27
+  - @llamaindex/supabase@0.1.18
+  - @llamaindex/upstash@0.0.31
+  - @llamaindex/weaviate@0.0.32
+  - @llamaindex/vercel@0.1.17
+  - @llamaindex/voyage-ai@1.0.23
+  - @llamaindex/readers@3.1.16
+  - @llamaindex/tools@0.1.7
+  - @llamaindex/workflow@1.1.17
+  - @llamaindex/deepseek@0.0.29
+  - @llamaindex/fireworks@0.0.28
+  - @llamaindex/groq@0.0.84
+  - @llamaindex/together@0.0.28
+  - @llamaindex/vllm@0.0.54
+  - @llamaindex/xai@0.0.15
+
+## 0.3.32
+
+### Patch Changes
+
+- Updated dependencies [650eeb1]
+- Updated dependencies [a8ec08c]
+- Updated dependencies [2967d57]
+  - @llamaindex/google@0.3.15
+  - @llamaindex/core@0.6.16
+  - @llamaindex/workflow@1.1.16
+  - @llamaindex/cloud@4.0.25
+  - llamaindex@0.11.20
+  - @llamaindex/node-parser@2.0.16
+  - @llamaindex/anthropic@0.3.18
+  - @llamaindex/assemblyai@0.1.15
+  - @llamaindex/clip@0.0.67
+  - @llamaindex/cohere@0.0.30
+  - @llamaindex/deepinfra@0.0.67
+  - @llamaindex/discord@0.1.15
+  - @llamaindex/huggingface@0.1.21
+  - @llamaindex/jinaai@0.0.27
+  - @llamaindex/mistral@0.1.16
+  - @llamaindex/mixedbread@0.0.30
+  - @llamaindex/notion@0.1.15
+  - @llamaindex/ollama@0.1.16
+  - @llamaindex/openai@0.4.11
+  - @llamaindex/perplexity@0.0.24
+  - @llamaindex/portkey-ai@0.0.58
+  - @llamaindex/replicate@0.0.58
+  - @llamaindex/bm25-retriever@0.0.5
+  - @llamaindex/astra@0.0.30
+  - @llamaindex/azure@0.1.28
+  - @llamaindex/chroma@0.0.30
+  - @llamaindex/elastic-search@0.1.16
+  - @llamaindex/firestore@1.0.23
+  - @llamaindex/milvus@0.1.25
+  - @llamaindex/mongodb@0.0.31
+  - @llamaindex/pinecone@0.1.16
+  - @llamaindex/postgres@0.0.59
+  - @llamaindex/qdrant@0.1.26
+  - @llamaindex/supabase@0.1.17
+  - @llamaindex/upstash@0.0.30
+  - @llamaindex/weaviate@0.0.31
+  - @llamaindex/vercel@0.1.16
+  - @llamaindex/voyage-ai@1.0.22
+  - @llamaindex/readers@3.1.15
+  - @llamaindex/tools@0.1.6
+  - @llamaindex/deepseek@0.0.28
+  - @llamaindex/fireworks@0.0.27
+  - @llamaindex/groq@0.0.83
+  - @llamaindex/together@0.0.27
+  - @llamaindex/vllm@0.0.53
+  - @llamaindex/xai@0.0.14
+
+## 0.3.31
+
+### Patch Changes
+
+- Updated dependencies [d8f4f6a]
+- Updated dependencies [856dd8c]
+  - @llamaindex/supabase@0.1.16
+  - @llamaindex/openai@0.4.10
+  - @llamaindex/clip@0.0.66
+  - @llamaindex/deepinfra@0.0.66
+  - @llamaindex/deepseek@0.0.27
+  - @llamaindex/fireworks@0.0.26
+  - @llamaindex/groq@0.0.82
+  - @llamaindex/huggingface@0.1.20
+  - @llamaindex/jinaai@0.0.26
+  - @llamaindex/perplexity@0.0.23
+  - @llamaindex/azure@0.1.27
+  - @llamaindex/together@0.0.26
+  - @llamaindex/vllm@0.0.52
+  - @llamaindex/xai@0.0.13
+
+## 0.3.30
+
+### Patch Changes
+
+- Updated dependencies [7ad3411]
+- Updated dependencies [5da5b3c]
+- Updated dependencies [a1fdb07]
+- Updated dependencies [ddc0eaf]
+  - @llamaindex/core@0.6.15
+  - @llamaindex/tools@0.1.5
+  - @llamaindex/workflow@1.1.15
+  - @llamaindex/openai@0.4.9
+  - @llamaindex/anthropic@0.3.17
+  - @llamaindex/cloud@4.0.24
+  - llamaindex@0.11.19
+  - @llamaindex/node-parser@2.0.15
+  - @llamaindex/assemblyai@0.1.14
+  - @llamaindex/clip@0.0.65
+  - @llamaindex/cohere@0.0.29
+  - @llamaindex/deepinfra@0.0.65
+  - @llamaindex/discord@0.1.14
+  - @llamaindex/google@0.3.14
+  - @llamaindex/huggingface@0.1.19
+  - @llamaindex/jinaai@0.0.25
+  - @llamaindex/mistral@0.1.15
+  - @llamaindex/mixedbread@0.0.29
+  - @llamaindex/notion@0.1.14
+  - @llamaindex/ollama@0.1.15
+  - @llamaindex/perplexity@0.0.22
+  - @llamaindex/portkey-ai@0.0.57
+  - @llamaindex/replicate@0.0.57
+  - @llamaindex/bm25-retriever@0.0.4
+  - @llamaindex/astra@0.0.29
+  - @llamaindex/azure@0.1.26
+  - @llamaindex/chroma@0.0.29
+  - @llamaindex/elastic-search@0.1.15
+  - @llamaindex/firestore@1.0.22
+  - @llamaindex/milvus@0.1.24
+  - @llamaindex/mongodb@0.0.30
+  - @llamaindex/pinecone@0.1.15
+  - @llamaindex/postgres@0.0.58
+  - @llamaindex/qdrant@0.1.25
+  - @llamaindex/supabase@0.1.15
+  - @llamaindex/upstash@0.0.29
+  - @llamaindex/weaviate@0.0.30
+  - @llamaindex/vercel@0.1.15
+  - @llamaindex/voyage-ai@1.0.21
+  - @llamaindex/readers@3.1.14
+  - @llamaindex/deepseek@0.0.26
+  - @llamaindex/fireworks@0.0.25
+  - @llamaindex/groq@0.0.81
+  - @llamaindex/together@0.0.25
+  - @llamaindex/vllm@0.0.51
+  - @llamaindex/xai@0.0.12
+
+## 0.3.29
+
+### Patch Changes
+
+- Updated dependencies [af3f866]
+  - @llamaindex/deepseek@0.0.25
+
+## 0.3.28
+
+### Patch Changes
+
+- 36773a8: Fixed start script, reverted some changes to imports
+- 891562d: Fix xai dependency in the examples
+- Updated dependencies [5a0ed1f]
+- Updated dependencies [5a0ed1f]
+- Updated dependencies [8eeac33]
+  - @llamaindex/cloud@4.0.19
+  - @llamaindex/core@0.6.14
+  - llamaindex@0.11.14
+  - @llamaindex/node-parser@2.0.14
+  - @llamaindex/anthropic@0.3.16
+  - @llamaindex/assemblyai@0.1.13
+  - @llamaindex/clip@0.0.64
+  - @llamaindex/cohere@0.0.28
+  - @llamaindex/deepinfra@0.0.64
+  - @llamaindex/discord@0.1.13
+  - @llamaindex/google@0.3.13
+  - @llamaindex/huggingface@0.1.18
+  - @llamaindex/jinaai@0.0.24
+  - @llamaindex/mistral@0.1.14
+  - @llamaindex/mixedbread@0.0.28
+  - @llamaindex/notion@0.1.13
+  - @llamaindex/ollama@0.1.14
+  - @llamaindex/openai@0.4.8
+  - @llamaindex/perplexity@0.0.21
+  - @llamaindex/portkey-ai@0.0.56
+  - @llamaindex/replicate@0.0.56
+  - @llamaindex/bm25-retriever@0.0.3
+  - @llamaindex/astra@0.0.28
+  - @llamaindex/azure@0.1.25
+  - @llamaindex/chroma@0.0.28
+  - @llamaindex/elastic-search@0.1.14
+  - @llamaindex/firestore@1.0.21
+  - @llamaindex/milvus@0.1.23
+  - @llamaindex/mongodb@0.0.29
+  - @llamaindex/pinecone@0.1.14
+  - @llamaindex/postgres@0.0.57
+  - @llamaindex/qdrant@0.1.24
+  - @llamaindex/supabase@0.1.14
+  - @llamaindex/upstash@0.0.28
+  - @llamaindex/weaviate@0.0.29
+  - @llamaindex/vercel@0.1.14
+  - @llamaindex/voyage-ai@1.0.20
+  - @llamaindex/readers@3.1.13
+  - @llamaindex/tools@0.1.4
+  - @llamaindex/workflow@1.1.14
+  - @llamaindex/deepseek@0.0.24
+  - @llamaindex/fireworks@0.0.24
+  - @llamaindex/groq@0.0.80
+  - @llamaindex/together@0.0.24
+  - @llamaindex/vllm@0.0.50
+  - @llamaindex/xai@0.0.11
+
+## 0.3.27
+
+### Patch Changes
+
+- Updated dependencies [229cdeb]
+- Updated dependencies [47a7555]
+  - @llamaindex/groq@0.0.79
+  - @llamaindex/cloud@4.0.18
+  - llamaindex@0.11.13
+
+## 0.3.26
+
+### Patch Changes
+
+- Updated dependencies [d578889]
+- Updated dependencies [0fcc92f]
+- Updated dependencies [515a8b9]
+- Updated dependencies [3cd8a57]
+- Updated dependencies [f2dfd30]
+  - @llamaindex/core@0.6.13
+  - llamaindex@0.11.12
+  - @llamaindex/tools@0.1.3
+  - @llamaindex/bm25-retriever@0.0.2
+  - @llamaindex/cloud@4.0.17
+  - @llamaindex/node-parser@2.0.13
+  - @llamaindex/anthropic@0.3.15
+  - @llamaindex/assemblyai@0.1.12
+  - @llamaindex/clip@0.0.63
+  - @llamaindex/cohere@0.0.27
+  - @llamaindex/deepinfra@0.0.63
+  - @llamaindex/discord@0.1.12
+  - @llamaindex/google@0.3.12
+  - @llamaindex/huggingface@0.1.17
+  - @llamaindex/jinaai@0.0.23
+  - @llamaindex/mistral@0.1.13
+  - @llamaindex/mixedbread@0.0.27
+  - @llamaindex/notion@0.1.12
+  - @llamaindex/ollama@0.1.13
+  - @llamaindex/openai@0.4.7
+  - @llamaindex/perplexity@0.0.20
+  - @llamaindex/portkey-ai@0.0.55
+  - @llamaindex/replicate@0.0.55
+  - @llamaindex/astra@0.0.27
+  - @llamaindex/azure@0.1.24
+  - @llamaindex/chroma@0.0.27
+  - @llamaindex/elastic-search@0.1.13
+  - @llamaindex/firestore@1.0.20
+  - @llamaindex/milvus@0.1.22
+  - @llamaindex/mongodb@0.0.28
+  - @llamaindex/pinecone@0.1.13
+  - @llamaindex/postgres@0.0.56
+  - @llamaindex/qdrant@0.1.23
+  - @llamaindex/supabase@0.1.13
+  - @llamaindex/upstash@0.0.27
+  - @llamaindex/weaviate@0.0.28
+  - @llamaindex/vercel@0.1.13
+  - @llamaindex/voyage-ai@1.0.19
+  - @llamaindex/readers@3.1.12
+  - @llamaindex/workflow@1.1.13
+  - @llamaindex/deepseek@0.0.23
+  - @llamaindex/fireworks@0.0.23
+  - @llamaindex/groq@0.0.78
+  - @llamaindex/together@0.0.23
+  - @llamaindex/vllm@0.0.49
+  - @llamaindex/xai@0.0.10
+
 ## 0.3.25
 
 ### Patch Changes

examples/README.md

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

examples/agents/agent/single-agent.ts

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

examples/agents/agent/with-ollama.ts

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

examples/agents/memory/agent-memory.ts

@@ -0,0 +1,36 @@
+import { openai } from "@llamaindex/openai";
+import { agent } from "@llamaindex/workflow";
+import { createMemory, staticBlock } from "llamaindex";
+
+// Simple example: Agent with Predefined Memory
+async function simpleAgentMemoryExample() {
+  console.log("=== Simple Agent Memory Example ===");
+
+  const memory = createMemory({
+    memoryBlocks: [
+      staticBlock({
+        content:
+          "The user is a software engineer who loves TypeScript and LlamaIndex.",
+      }),
+    ],
+  });
+
+  // Create agent workflow
+  const workflow = agent({
+    name: "assistant",
+    llm: openai({ model: "gpt-4.1-nano" }),
+    memory,
+  });
+
+  // Test - agent should remember John and the shopping cart context
+  console.log("\n--- Testing Memory Context ---");
+  const result = await workflow.run("Hi, my name is John. Do you know me?");
+
+  console.log("Assistant Response:", result.data.result);
+
+  const result2 = await workflow.run("What is my name?");
+  console.log("Assistant Response:", result2.data.result);
+}
+
+// Run the example
+simpleAgentMemoryExample().catch(console.error);

examples/agents/memory/basic.ts

@@ -0,0 +1,58 @@
+import { openai } from "@llamaindex/openai";
+import { createMemory } from "llamaindex";
+
+// Example: Basic Memory Usage with Factory
+async function basicMemoryExample() {
+  console.log("\n=== Example: Basic Memory Usage with Factory ===");
+
+  const memory = createMemory({ tokenLimit: 30 });
+
+  // Add messages to memory
+  await memory.add({
+    role: "user",
+    content: "Hi, my name is John and I'm a software engineer.",
+  });
+
+  await memory.add({
+    role: "assistant",
+    content: "Hello John! Nice to meet you. How can I help you today?",
+  });
+
+  await memory.add({
+    role: "user",
+    content: "I love working with TypeScript and React.",
+  });
+  // Not all messages are included because of token limit is set to 30
+  const llmMessages = await memory.getLLM();
+  console.log(
+    `\nLLM messages (${llmMessages.length} messages) limited by a small token limit:`,
+  );
+  llmMessages.forEach((msg, idx) => {
+    console.log(`${idx + 1}. ${msg.role}: ${msg.content}`);
+  });
+
+  // But the token limit above will be the window size of an LLM instance if you use getLLM with LLM
+  const llm = openai({ model: "gpt-4.1-mini" });
+  const llmMessagesWithLLM = await memory.getLLM(llm);
+  // Now all the messages are included because of the LLM window size of the model is much larger
+  console.log(
+    `\nLLM messages with LLM (${llmMessagesWithLLM.length} messages) limited by LLM window size:`,
+  );
+  llmMessagesWithLLM.forEach((msg, idx) => {
+    console.log(`${idx + 1}. ${msg.role}: ${msg.content}`);
+  });
+}
+
+// Main function
+async function main() {
+  console.log("🧠 Basic Memory Factory Examples");
+  console.log("===============================");
+
+  try {
+    await basicMemoryExample();
+  } catch (error) {
+    console.error("Error running basic memory examples:", error);
+  }
+}
+
+main().catch(console.error);

examples/agents/memory/fact-extraction.ts

@@ -0,0 +1,101 @@
+import { openai } from "@llamaindex/openai";
+import { createMemory, factExtractionBlock } from "llamaindex";
+
+// Configure OpenAI
+const llm = openai({ model: "gpt-4.1-mini" });
+
+// Example: Memory with Fact Extraction
+async function factExtractionMemoryExample() {
+  console.log("\n=== Memory with Fact Extraction ===");
+
+  // Create memory with a fact extraction
+  const memory = createMemory([], {
+    tokenLimit: 100,
+    shortTermTokenLimitRatio: 0.7, // 70% for short-term, 30% for long-term
+    memoryBlocks: [
+      factExtractionBlock({
+        id: "user-facts",
+        priority: 5,
+        llm: llm,
+        maxFacts: 10,
+        isLongTerm: true,
+      }),
+    ],
+  });
+
+  // Simulate a conversation with facts
+  const conversationTurns = [
+    {
+      role: "user",
+      content: "Hi, I'm Sarah and I work as a data scientist at Google.",
+    },
+    {
+      role: "assistant",
+      content:
+        "Hello Sarah! It's great to meet you. Data science at Google must be exciting!",
+    },
+    {
+      role: "user",
+      content:
+        "Yes, I specialize in machine learning and natural language processing.",
+    },
+    {
+      role: "assistant",
+      content: "That's impressive! ML and NLP are fascinating fields.",
+    },
+    {
+      role: "user",
+      content:
+        "I have a PhD in Computer Science from Stanford, and I love hiking on weekends.",
+    },
+    {
+      role: "assistant",
+      content:
+        "Wow, Stanford PhD! And hiking is a great way to unwind from tech work.",
+    },
+    {
+      role: "user",
+      content: "I also have two cats named Whiskers and Mittens.",
+    },
+    {
+      role: "assistant",
+      content:
+        "Cats make wonderful companions! Whiskers and Mittens are cute names.",
+    },
+  ];
+
+  // Add conversation turns to memory
+  console.log("Adding conversation to memory...");
+  for (const turn of conversationTurns) {
+    await memory.add(turn);
+  }
+
+  // Get messages - facts should be extracted and included
+  const messages = await memory.getLLM(llm);
+  console.log("\nMessages with extracted facts:");
+  messages.forEach((msg, idx) => {
+    console.log(`${idx + 1}. ${msg.role ?? "unknown"}: ${msg.content}`);
+  });
+  //Messages with extracted facts:
+  // 1. assistant: Cats make wonderful companions! Whiskers and Mittens are cute names.
+  // 2. user: I also have two cats named Whiskers and Mittens.
+  // 3. assistant: Wow, Stanford PhD! And hiking is a great way to unwind from tech work.
+  // 4. memory: Sarah works as a data scientist at Google
+  // Sarah specializes in machine learning and natural language processing
+  // Sarah has a PhD in Computer Science from Stanford
+  // Sarah enjoys hiking on weekends
+}
+
+// Main function
+async function main() {
+  console.log("🧠 Fact Extraction Memory Example");
+  console.log("=================================");
+
+  try {
+    await factExtractionMemoryExample();
+  } catch (error) {
+    console.error("Error running fact extraction memory example:", error);
+  }
+}
+
+main().catch(console.error);

examples/agents/memory/static-blocks.ts

@@ -0,0 +1,62 @@
+import { openai } from "@llamaindex/openai";
+import { createMemory, staticBlock } from "llamaindex";
+
+// Configure OpenAI
+const llm = openai({ model: "gpt-4.1-mini" });
+
+// Example: Memory with Static Blocks
+async function staticMemoryBlockExample() {
+  console.log("\n=== Memory with Static Blocks ===");
+  console.log("- Memory always include static block");
+  console.log("- Memory cut off the messages within token limit\n");
+
+  // Create memory with a static block
+  const memory = createMemory([], {
+    tokenLimit: 30, // A small token limit which is not enough for the whole conversation below
+    memoryBlocks: [
+      staticBlock({
+        content:
+          "The user's name is John and he is a software engineer who loves TypeScript and LlamaIndex.",
+      }),
+    ],
+  });
+
+  // Add some messages to the memory
+  await memory.add({
+    role: "user",
+    content: "What do you know about me?",
+  });
+
+  await memory.add({
+    role: "assistant",
+    content:
+      "Based on our conversation, I know you're John, a software engineer who enjoys working with TypeScript and LlamaIndex!",
+  });
+
+  await memory.add({
+    role: "user",
+    content: "Which language does LlamaIndex support?",
+  });
+
+  // Get messages
+  // static block will always be included
+  // only the last message will be included because of token limit set above
+  const messages = await memory.getLLM(llm);
+  messages.forEach((msg, idx) => {
+    console.log(`${idx + 1}. ${msg.role}: ${msg.content}`);
+  });
+  // Messages with static block:
+  // 1. user: The user's name is John and he is a software engineer who loves TypeScript and LlamaIndex.
+  // 2. user: Which language does LlamaIndex support?
+}
+
+// Main function
+async function main() {
+  try {
+    await staticMemoryBlockExample();
+  } catch (error) {
+    console.error("Error running static memory blocks example:", error);
+  }
+}
+
+main().catch(console.error);

examples/agents/memory/vector-block.ts

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

examples/agents/tools/chat-stream.ts

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

examples/agents/tools/exec-stream.ts

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

examples/agents/tools/exec.ts

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

examples/deprecated/agents/openai-task.ts

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

examples/deprecated/agents/react-task.ts

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

examples/deprecated/agents/react_agent.ts

@@ -59,7 +59,7 @@ async function main() {
 
   const anthropic = new Anthropic({
     apiKey: process.env.ANTHROPIC_API_KEY,
-    model: "claude-3-opus",
+    model: "claude-3.5-sonnet",
   });
 
   // Create an ReActAgent with the function tools

examples/deprecated/agents/step_wise_react.ts

@@ -61,7 +61,7 @@ async function main() {
   // Create an OpenAIAgent with the function tools
   const agent = new ReActAgent({
     llm: new Anthropic({
-      model: "claude-3-opus",
+      model: "claude-3.5-sonnet",
     }),
     tools: [functionTool, functionTool2],
   });

examples/models/anthropic/chat_interactive.ts

@@ -1,5 +1,5 @@
 import { Anthropic } from "@llamaindex/anthropic";
-import { ChatMemoryBuffer, SimpleChatEngine } from "llamaindex";
+import { createMemory, SimpleChatEngine } from "llamaindex";
 import { stdin as input, stdout as output } from "node:process";
 import readline from "node:readline/promises";
 
@@ -9,14 +9,12 @@ import readline from "node:readline/promises";
     model: "claude-3-7-sonnet",
   });
   // chatHistory will store all the messages in the conversation
-  const chatHistory = new ChatMemoryBuffer({
-    chatHistory: [
-      {
-        content: "You want to talk in rhymes.",
-        role: "system",
-      },
-    ],
-  });
+  const chatHistory = createMemory([
+    {
+      content: "You want to talk in rhymes.",
+      role: "system",
+    },
+  ]);
   const chatEngine = new SimpleChatEngine({
     llm,
     memory: chatHistory,