Create cold-sloths-scream.md

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

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

.changeset/cold-sloths-scream.md

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

.changeset/funny-donuts-approve.md

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

.changeset/sixty-wasps-flow.md

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

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 +1,112 @@
 # @llamaindex/doc
 
+## 0.2.34
+
+### Patch Changes
+
+- 39758ab: Add title to homepage header
+
+## 0.2.33
+
+### Patch Changes
+
+- Updated dependencies [47a7555]
+  - @llamaindex/cloud@4.0.18
+  - llamaindex@0.11.13
+
+## 0.2.32
+
+### Patch Changes
+
+- Updated dependencies [d578889]
+- Updated dependencies [0fcc92f]
+- Updated dependencies [515a8b9]
+  - @llamaindex/core@0.6.13
+  - llamaindex@0.11.12
+  - @llamaindex/cloud@4.0.17
+  - @llamaindex/node-parser@2.0.13
+  - @llamaindex/openai@0.4.7
+  - @llamaindex/readers@3.1.12
+  - @llamaindex/workflow@1.1.13
+
+## 0.2.31
+
+### Patch Changes
+
+- Updated dependencies [7039e1a]
+- Updated dependencies [7039e1a]
+  - llamaindex@0.11.11
+  - @llamaindex/core@0.6.12
+  - @llamaindex/cloud@4.0.16
+  - @llamaindex/node-parser@2.0.12
+  - @llamaindex/openai@0.4.6
+  - @llamaindex/readers@3.1.11
+  - @llamaindex/workflow@1.1.12
+
+## 0.2.30
+
+### Patch Changes
+
+- Updated dependencies [f7ec293]
+  - @llamaindex/workflow@1.1.11
+  - llamaindex@0.11.10
+
+## 0.2.29
+
+### Patch Changes
+
+- Updated dependencies [c5846bd]
+  - @llamaindex/readers@3.1.10
+
+## 0.2.28
+
+### Patch Changes
+
+- Updated dependencies [a89e187]
+- Updated dependencies [62699b7]
+- Updated dependencies [c5b2691]
+- Updated dependencies [d8ac8d3]
+  - @llamaindex/core@0.6.11
+  - @llamaindex/openai@0.4.5
+  - @llamaindex/cloud@4.0.15
+  - llamaindex@0.11.9
+  - @llamaindex/node-parser@2.0.11
+  - @llamaindex/readers@3.1.9
+  - @llamaindex/workflow@1.1.10
+
+## 0.2.27
+
+### Patch Changes
+
+- 8a51c16: Add natural language agent page
+- Updated dependencies [8a51c16]
+- Updated dependencies [1b5af14]
+  - @llamaindex/workflow@1.1.9
+  - @llamaindex/core@0.6.10
+  - llamaindex@0.11.8
+  - @llamaindex/cloud@4.0.14
+  - @llamaindex/node-parser@2.0.10
+  - @llamaindex/openai@0.4.4
+  - @llamaindex/readers@3.1.8
+
+## 0.2.26
+
+### Patch Changes
+
+- a4d394f: fix: correct SimpleDirectoryReader import path in documentation example
+- Updated dependencies [dbd857f]
+- Updated dependencies [3c857f4]
+  - @llamaindex/workflow@1.1.8
+  - llamaindex@0.11.7
+
+## 0.2.25
+
+### Patch Changes
+
+- Updated dependencies [40161fe]
+  - @llamaindex/workflow@1.1.7
+  - llamaindex@0.11.6
+
 ## 0.2.24
 
 ### Patch Changes

apps/next/CLAUDE.md

@@ -111,7 +111,7 @@ Key build process:
 **Content Sources:**
 
 - Local MDX files in `src/content/docs/`
-- External docs from `@llama-flow/docs` package
+- External docs from `@llamaindex/workflow-docs` package
 - Generated API docs from TypeScript source
 
 ### Development Notes

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

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

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.24",
+  "version": "0.2.34",
   "private": true,
   "scripts": {
     "postinstall": "fumadocs-mdx",
@@ -15,16 +15,17 @@
   "dependencies": {
     "@huggingface/transformers": "^3.5.0",
     "@icons-pack/react-simple-icons": "^10.1.0",
-    "@llama-flow/docs": "0.0.8",
-    "@llamaindex/chat-ui-docs": "0.0.3",
+    "@llamaindex/chat-ui-docs": "^0.0.5",
     "@llamaindex/cloud": "workspace:*",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/node-parser": "workspace:*",
     "@llamaindex/openai": "workspace:*",
     "@llamaindex/readers": "workspace:*",
     "@llamaindex/workflow": "workspace:*",
+    "@llamaindex/workflow-docs": "0.1.1",
     "@mdx-js/mdx": "^3.1.0",
     "@monaco-editor/react": "^4.7.0",
+    "@next/third-parties": "^15.3.4",
     "@number-flow/react": "^0.3.4",
     "@radix-ui/react-dialog": "^1.1.2",
     "@radix-ui/react-icons": "^1.3.2",
@@ -34,22 +35,22 @@
     "@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",
     "framer-motion": "^11.11.17",
-    "fumadocs-core": "^15.2.7",
+    "fumadocs-core": "^15.5.0",
     "fumadocs-docgen": "^2.0.0",
-    "fumadocs-mdx": "^11.6.0",
-    "fumadocs-openapi": "^8.0.1",
-    "fumadocs-twoslash": "^3.1.1",
-    "fumadocs-typescript": "^4.0.2",
-    "fumadocs-ui": "^15.2.7",
+    "fumadocs-mdx": "^11.6.6",
+    "fumadocs-openapi": "^9.0.5",
+    "fumadocs-twoslash": "^3.1.3",
+    "fumadocs-typescript": "^4.0.5",
+    "fumadocs-ui": "^15.5.0",
     "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",
@@ -69,7 +70,7 @@
     "twoslash": "^0.3.1",
     "use-stick-to-bottom": "^1.0.42",
     "web-tree-sitter": "^0.24.4",
-    "zod": "^3.23.8"
+    "zod": "^3.25.76"
   },
   "devDependencies": {
     "@next/env": "^15.3.0",
@@ -93,6 +94,6 @@
     "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/scripts/validate-links.mts

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

apps/next/source.config.ts

@@ -11,8 +11,13 @@ import remarkMath from "remark-math";
 export const docs = defineDocs({
   dir: [
     "./src/content/docs",
-    "./node_modules/@llama-flow/docs",
+    "./node_modules/@llamaindex/workflow-docs",
     "./node_modules/@llamaindex/chat-ui-docs",
+    // NOTE: When adding external docs (like chat-ui or workflow-docs above),
+    // make sure to also update:
+    // 1. scripts/validate-links.mts - add to ALLOWED_LINKS array
+    // 2. next.config.mjs - add redirect for .mdx files
+    // 3. src/content/docs/meta.json - add to pages array
   ],
   docs: {
     async: true,

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

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

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

@@ -1,4 +1,4 @@
-import { source } from "@/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 } from "@next/third-parties/google";
 import { RootProvider } from "fumadocs-ui/provider";
 import { Inter } from "next/font/google";
 import type { ReactNode } from "react";
@@ -31,6 +32,9 @@ export default function Layout({ children }: { children: ReactNode }) {
           sizes="16x16"
           href="/favicon-16x16.png"
         />
+        <title>
+          LlamaIndex.TS - Build LLM-powered document agents and workflows
+        </title>
       </head>
       <body className="flex min-h-screen flex-col">
         <TooltipProvider>
@@ -39,6 +43,7 @@ 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/modules/agents/meta.json

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

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

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

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

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

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

@@ -9,10 +9,13 @@ Workflows are designed to be flexible and can be used to build agents, RAG flows
 To use workflows install this package:
 
 ```package-install
-npm i @llamaindex/workflow
+npm i @llamaindex/workflow-core
 ```
 
-This package is a stable, production-ready version of our [llama-flow](/docs/llamaflow) project. 
+This contains the core functionality for the workflow system. You can read more about the core concepts in the [workflow-core](/docs/workflows) section.
 
-While you can still reference the llama-flow documentation for detailed information about the underlying concepts, we recommend using the `@llamaindex/workflow` package for all new projects to ensure stability and long-term availability.
+In contrast, the `@llamaindex/workflow` package contains more utiltities, such as prebuilt agents.
 
+```package-install
+npm i @llamaindex/workflow
+```

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

@@ -0,0 +1,182 @@
+---
+title: Memory
+description: Manage conversation history and context with agents
+---
+
+## Concept
+
+Memory is a core component of agentic systems. It allows you to store and retrieve information from the past.
+
+In LlamaIndexTS, you can create memory by using the `createMemory` function. This function will return a `Memory` object, which you can then use to store and retrieve information.
+
+As the agent runs, it will make calls to `add()` to store information, and `get()` to retrieve information. 
+
+## Usage
+
+A `Memory` object has both short-term memory (i.e. a FIFO queue of messages) and optionally long-term memory (i.e. extracting information over time).
+
+`get()` always returns all messages stored in the memory. The longer the agent runs, this will exceed the context window of the agent. To avoid this, the agent is using the `getLLM` method to get the last X messages that fit into the context window.
+
+### Configuring Memory for an Agent
+
+Here we're creating a memory with a static block (read more about [memory blocks](#long-term-memory)) that contains some information about the user.
+
+```ts twoslash
+import { openai } from "@llamaindex/openai";
+import { agent } from "@llamaindex/workflow";
+import { createMemory, staticBlock } from "llamaindex";
+
+const llm = openai({ model: "gpt-4.1-mini" });
+
+// Create memory with predefined context
+const memory = createMemory({
+  memoryBlocks: [
+    staticBlock({
+      content:
+        "The user is a software engineer who loves TypeScript and LlamaIndex.",
+    }),
+  ],
+});
+
+// Create an agent with the memory
+const workflow = agent({
+  name: "assistant",
+  llm,
+  memory,
+});
+
+const result = await workflow.run("What is my name?");
+console.log("Response:", result.data.result);
+```
+
+### Using Vercel format
+
+You can also put messages in Vercel format directly to the memory:
+
+```ts
+await memory.add({
+  id: "1",
+  createdAt: new Date(),
+  role: "user",
+  content: "Hello!",
+  options: {
+    parts: [
+      {
+        type: "file",
+        data: "base64...",
+        mimeType: "image/png",
+      },
+    ],
+  },
+});
+```
+
+If you call `get`, messages are usually retrieved in the LlamaIndexTS format (type `ChatMessage`). If you specify the `type` parameter using `get`, you can return the messages in different formats. E.g.: using `type: "vercel"`, you can return the messages in Vercel format:
+
+```ts
+const messages = await memory.get({ type: "vercel" });
+console.log(messages);
+```
+
+## Customizing Memory
+
+### Short-Term Memory
+
+The `Memory` object will store all the messages that are added to the `Memory` object. Unless you call `clear()`, no messages are removed from the memory. This is the short-term memory (usually you will store the memory of one user session there) which is augmented by the long-term memory.
+
+Calling `getLLM` will retrieve messages from long-term memory and ensure that the given `tokenLimit` is not reached. These are the messages that you will sent to the LLM.
+
+For initialization, you call `createMemory` with the following options:
+
+- `tokenLimit`: Maximum tokens for memory retrieval using `getLLM` (default: 30000).
+- `shortTermTokenLimitRatio`: Ratio of tokens for short-term vs long-term memory (default: 0.7)
+- `customAdapters`: Custom message adapters for different message formats. LlamaIndex (`ChatMessageAdapter`) and Vercel (`VercelMessageAdapter`) are built-in adapters.
+- `memoryBlocks`: Memory blocks for long-term storage, see [Long-Term Memory](#long-term-memory)
+
+Example:
+
+```ts
+const memory = createMemory({
+    tokenLimit=40000,
+    shortTermTokenLimitRatio=0.5,
+});
+```
+
+### Long-Term Memory
+
+Long-term memory is represented as `Memory Block` objects. These objects contain information that are from previous user sessions or from the beginning of the current conversation. When memory is retrieved (by calling `getLLM`), the short-term and long-term memories are merged together within the given `tokenLimit`. 
+
+Currently, there are two predefined memory blocks:
+
+- `staticBlock`: A memory block that stores a static piece of information.
+- `factExtractionBlock`: A memory block that extracts facts from the chat history.
+
+This sounds a bit complicated, but it's actually quite simple. Let's look at an example:
+
+```ts
+import { createMemory, factExtractionBlock, staticBlock } from "llamaindex";
+
+const memoryBlocks= [
+  staticBlock({
+    id: "core_info",
+    content: "My name is Logan, and I live in Saskatoon. I work at LlamaIndex.",
+  }),
+  factExtractionBlock({
+    id: "user-extracted_info",
+    priority: 1,
+    llm: llm,
+    maxFacts: 50,
+  }),
+];
+```
+
+Here, we've setup two memory blocks:
+
+- `core_info`: A static memory block that stores some core information about the user. This information will always be inserted into the memory. The type used is `MessageContent` to support multi-modal content.
+- `extracted_info`: An extracted memory block that will extract information from the chat history. Here we've passed in the `llm` to use to extract facts from the chat history, and set the `maxFacts` to 50. If the number of extracted facts exceeds this limit, the `maxFacts` will be automatically summarized and reduced to leave room for new information.
+
+You'll also notice that we've set the `priority` for the `factExtractionBlock` block. This is used to determine the handling when the memory blocks content (i.e. long-term memory) + short-term memory exceeds the token limit on the `Memory` object.
+
+- `priority=0`: This block will always be kept in memory (`staticBlocks` always have priority 0.)
+- `priority=1, 2, 3, etc`: This determines the order in which memory blocks are truncated when the memory exceeds the token limit, to help the overall short-term memory + long-term memory content be less than or equal to the `tokenLimit`.
+
+Now, let's pass these blocks into the `createMemory` function:
+
+```ts
+const memory = createMemory({
+  tokenLimit: 40000,
+  memoryBlocks: memoryBlocks,
+)
+```
+
+When memory is retrieved (using `getLLM`), the short-term and long-term memories are merged together. The `Memory` object will ensure that the short-term memory + long-term memory content is less than or equal to the `tokenLimit`. If it is longer, messages are retrieved in the following order:
+
+1. StaticMemoryBlock (information always included)
+2. LongTermMemoryBlock (depending on priority)
+3. ShortTermMemoryBlock 
+4. Transient messages
+
+The amount of short-term memory included is specified by the `shortTermTokenLimitRatio`. If it's set to `0.7`, 70% of the `tokenLimit` is used for short-term memory (not including the static memory block).
+
+## Persistence with Snapshots
+
+Save and restore memory state:
+
+```ts twoslash
+import { createMemory, loadMemory } from "llamaindex";
+
+const memory = createMemory();
+
+// Add some messages
+await memory.add({ role: "user", content: "Hello!" });
+
+// Create snapshot
+const snapshot = memory.snapshot();
+
+// Later, restore from the snapshot
+const restoredMemory = loadMemory(snapshot);
+```
+
+## Examples
+
+Want to learn more about the Memory class? Check out our example codes in [Github](https://github.com/run-llama/LlamaIndexTS/tree/main/examples/agents/memory).

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

@@ -1,4 +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/data/stores/vector_stores/supabase.mdx

@@ -28,11 +28,12 @@ embedding vector(1536)
 );
 ```
 
--- Create a function for similarity search
+-- Create a function for similarity search with filtering support
 ```sql
 create function match_documents (
 query_embedding vector(1536),
-match_count int
+match_count int,
+filter jsonb DEFAULT '{}'
 ) returns table (
 id uuid,
 content text,
@@ -52,6 +53,7 @@ metadata,
 embedding,
 1 - (embedding <=> query_embedding) as similarity
 from documents
+where metadata @> filter
 order by embedding <=> query_embedding
 limit match_count;
 end;
@@ -96,6 +98,7 @@ const index = await VectorStoreIndex.fromDocuments(documents, {
 ```ts
 const queryEngine = index.asQueryEngine();
 
+// Basic query without filters
 const response = await queryEngine.query({
   query: "What is in the document?",
 });
@@ -104,6 +107,32 @@ const response = await queryEngine.query({
 console.log(response.toString());
 ```
 
+## Query with filters
+
+You can filter documents based on metadata when querying:
+
+```ts
+import { FilterOperator, MetadataFilters } from "llamaindex";
+
+// Create a filter for documents with author = "Jane Smith"
+const filters: MetadataFilters = {
+  filters: [
+    {
+      key: "author",
+      value: "Jane Smith",
+      operator: FilterOperator.EQ,
+    },
+  ],
+};
+
+// Query with filters
+const filteredResponse = await vectorStore.query({
+  queryEmbedding: embedModel.getQueryEmbedding("What is vector search?"),
+  similarityTopK: 5,
+  filters,
+});
+```
+
 ## Full code
 
 ```ts

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

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

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

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

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

@@ -11,6 +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/meta.json

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

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));
+}

apps/next/turbo.json

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

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 +1,56 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 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
+
+- Updated dependencies [7039e1a]
+  - llamaindex@0.11.11
+
+## 0.0.171
+
+### Patch Changes
+
+- llamaindex@0.11.10
+
+## 0.0.170
+
+### Patch Changes
+
+- llamaindex@0.11.9
+
+## 0.0.169
+
+### Patch Changes
+
+- llamaindex@0.11.8
+
+## 0.0.168
+
+### Patch Changes
+
+- Updated dependencies [3c857f4]
+  - llamaindex@0.11.7
+
+## 0.0.167
+
+### Patch Changes
+
+- llamaindex@0.11.6
+
 ## 0.0.166
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.166",
+  "version": "0.0.174",
   "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 +1,36 @@
 # @llamaindex/llama-parse-browser-test
 
+## 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
+
+- @llamaindex/cloud@4.0.16
+
+## 0.0.70
+
+### Patch Changes
+
+- @llamaindex/cloud@4.0.15
+
+## 0.0.69
+
+### Patch Changes
+
+- @llamaindex/cloud@4.0.14
+
 ## 0.0.68
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llama-parse-browser-test",
   "private": true,
-  "version": "0.0.68",
+  "version": "0.0.73",
   "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 +1,56 @@
 # @llamaindex/next-agent-test
 
+## 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
+
+- Updated dependencies [7039e1a]
+  - llamaindex@0.11.11
+
+## 0.1.171
+
+### Patch Changes
+
+- llamaindex@0.11.10
+
+## 0.1.170
+
+### Patch Changes
+
+- llamaindex@0.11.9
+
+## 0.1.169
+
+### Patch Changes
+
+- llamaindex@0.11.8
+
+## 0.1.168
+
+### Patch Changes
+
+- Updated dependencies [3c857f4]
+  - llamaindex@0.11.7
+
+## 0.1.167
+
+### Patch Changes
+
+- llamaindex@0.11.6
+
 ## 0.1.166
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.166",
+  "version": "0.1.174",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -8,9 +8,9 @@
     "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"
   },
@@ -20,6 +20,6 @@
     "@types/react-dom": "^19.0.4",
     "eslint": "9.16.0",
     "eslint-config-next": "15.1.0",
-    "typescript": "^5.7.3"
+    "typescript": "^5.8.3"
   }
 }

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

@@ -1,5 +1,56 @@
 # test-edge-runtime
 
+## 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
+
+- Updated dependencies [7039e1a]
+  - llamaindex@0.11.11
+
+## 0.1.170
+
+### Patch Changes
+
+- llamaindex@0.11.10
+
+## 0.1.169
+
+### Patch Changes
+
+- llamaindex@0.11.9
+
+## 0.1.168
+
+### Patch Changes
+
+- llamaindex@0.11.8
+
+## 0.1.167
+
+### Patch Changes
+
+- Updated dependencies [3c857f4]
+  - llamaindex@0.11.7
+
+## 0.1.166
+
+### Patch Changes
+
+- llamaindex@0.11.6
+
 ## 0.1.165
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.165",
+  "version": "0.1.173",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -9,7 +9,7 @@
   },
   "dependencies": {
     "llamaindex": "workspace:*",
-    "next": "^15.3.0",
+    "next": "^15.3.3",
     "react": "^19.1.0",
     "react-dom": "^19.1.0"
   },
@@ -17,6 +17,6 @@
     "@types/node": "^22.9.0",
     "@types/react": "^19.0.10",
     "@types/react-dom": "^19.0.4",
-    "typescript": "^5.7.3"
+    "typescript": "^5.8.3"
   }
 }

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

@@ -1,5 +1,71 @@
 # @llamaindex/next-node-runtime
 
+## 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
+
+- Updated dependencies [7039e1a]
+  - llamaindex@0.11.11
+  - @llamaindex/huggingface@0.1.16
+  - @llamaindex/readers@3.1.11
+
+## 0.1.39
+
+### Patch Changes
+
+- llamaindex@0.11.10
+
+## 0.1.38
+
+### Patch Changes
+
+- Updated dependencies [c5846bd]
+  - @llamaindex/readers@3.1.10
+
+## 0.1.37
+
+### Patch Changes
+
+- llamaindex@0.11.9
+- @llamaindex/huggingface@0.1.15
+- @llamaindex/readers@3.1.9
+
+## 0.1.36
+
+### Patch Changes
+
+- llamaindex@0.11.8
+- @llamaindex/huggingface@0.1.14
+- @llamaindex/readers@3.1.8
+
+## 0.1.35
+
+### Patch Changes
+
+- Updated dependencies [3c857f4]
+  - llamaindex@0.11.7
+
+## 0.1.34
+
+### Patch Changes
+
+- llamaindex@0.11.6
+
 ## 0.1.33
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.33",
+  "version": "0.1.42",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -11,7 +11,7 @@
     "@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"
   },
@@ -21,6 +21,6 @@
     "@types/react-dom": "^19.0.4",
     "eslint": "9.16.0",
     "eslint-config-next": "15.1.0",
-    "typescript": "^5.7.3"
+    "typescript": "^5.8.3"
   }
 }

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

@@ -1,5 +1,56 @@
 # vite-import-llamaindex
 
+## 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
+
+- Updated dependencies [7039e1a]
+  - llamaindex@0.11.11
+
+## 0.0.37
+
+### Patch Changes
+
+- llamaindex@0.11.10
+
+## 0.0.36
+
+### Patch Changes
+
+- llamaindex@0.11.9
+
+## 0.0.35
+
+### Patch Changes
+
+- llamaindex@0.11.8
+
+## 0.0.34
+
+### Patch Changes
+
+- Updated dependencies [3c857f4]
+  - llamaindex@0.11.7
+
+## 0.0.33
+
+### Patch Changes
+
+- llamaindex@0.11.6
+
 ## 0.0.32
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.32",
+  "version": "0.0.40",
   "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/waku-query-engine/CHANGELOG.md

@@ -1,5 +1,56 @@
 # @llamaindex/waku-query-engine-test
 
+## 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
+
+- Updated dependencies [7039e1a]
+  - llamaindex@0.11.11
+
+## 0.0.171
+
+### Patch Changes
+
+- llamaindex@0.11.10
+
+## 0.0.170
+
+### Patch Changes
+
+- llamaindex@0.11.9
+
+## 0.0.169
+
+### Patch Changes
+
+- llamaindex@0.11.8
+
+## 0.0.168
+
+### Patch Changes
+
+- Updated dependencies [3c857f4]
+  - llamaindex@0.11.7
+
+## 0.0.167
+
+### Patch Changes
+
+- llamaindex@0.11.6
+
 ## 0.0.166
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.166",
+  "version": "0.0.174",
   "type": "module",
   "private": true,
   "scripts": {
@@ -22,6 +22,6 @@
     "@types/react-dom": "19.0.4",
     "rollup": "4.38.0",
     "tailwindcss": "^4.1.4",
-    "typescript": "5.7.3"
+    "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/npm/package.json

@@ -7,7 +7,7 @@
   "dependencies": {
     "@llamaindex/workflow": "1.1.1",
     "llamaindex": "0.10.5",
-    "zod": "^3.23.8"
+    "zod": "^3.25.67"
   },
   "devDependencies": {
     "tsx": "^4.19.1",

e2e/package.json

@@ -27,6 +27,6 @@
     "pg": "^8.12.0",
     "pgvector": "0.2.0",
     "tsx": "^4.19.3",
-    "zod": "^3.24.2"
+    "zod": "^3.25.76"
   }
 }

examples/CHANGELOG.md

@@ -1,5 +1,255 @@
 # examples
 
+## 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
+
+- Updated dependencies [7039e1a]
+- Updated dependencies [7039e1a]
+  - llamaindex@0.11.11
+  - @llamaindex/core@0.6.12
+  - @llamaindex/google@0.3.11
+  - @llamaindex/cloud@4.0.16
+  - @llamaindex/node-parser@2.0.12
+  - @llamaindex/anthropic@0.3.14
+  - @llamaindex/assemblyai@0.1.11
+  - @llamaindex/clip@0.0.62
+  - @llamaindex/cohere@0.0.26
+  - @llamaindex/deepinfra@0.0.62
+  - @llamaindex/discord@0.1.11
+  - @llamaindex/huggingface@0.1.16
+  - @llamaindex/jinaai@0.0.22
+  - @llamaindex/mistral@0.1.12
+  - @llamaindex/mixedbread@0.0.26
+  - @llamaindex/notion@0.1.11
+  - @llamaindex/ollama@0.1.12
+  - @llamaindex/openai@0.4.6
+  - @llamaindex/perplexity@0.0.19
+  - @llamaindex/portkey-ai@0.0.54
+  - @llamaindex/replicate@0.0.54
+  - @llamaindex/astra@0.0.26
+  - @llamaindex/azure@0.1.23
+  - @llamaindex/chroma@0.0.26
+  - @llamaindex/elastic-search@0.1.12
+  - @llamaindex/firestore@1.0.19
+  - @llamaindex/milvus@0.1.21
+  - @llamaindex/mongodb@0.0.27
+  - @llamaindex/pinecone@0.1.12
+  - @llamaindex/postgres@0.0.55
+  - @llamaindex/qdrant@0.1.22
+  - @llamaindex/supabase@0.1.12
+  - @llamaindex/upstash@0.0.26
+  - @llamaindex/weaviate@0.0.27
+  - @llamaindex/vercel@0.1.12
+  - @llamaindex/voyage-ai@1.0.18
+  - @llamaindex/readers@3.1.11
+  - @llamaindex/tools@0.1.1
+  - @llamaindex/workflow@1.1.12
+  - @llamaindex/deepseek@0.0.22
+  - @llamaindex/fireworks@0.0.22
+  - @llamaindex/groq@0.0.77
+  - @llamaindex/together@0.0.22
+  - @llamaindex/vllm@0.0.48
+  - @llamaindex/xai@0.0.9
+
+## 0.3.24
+
+### Patch Changes
+
+- Updated dependencies [096bf2b]
+- Updated dependencies [c5846bd]
+  - @llamaindex/tools@0.1.0
+  - @llamaindex/readers@3.1.10
+
+## 0.3.23
+
+### Patch Changes
+
+- Updated dependencies [a89e187]
+- Updated dependencies [62699b7]
+- Updated dependencies [c5b2691]
+- Updated dependencies [d8ac8d3]
+  - @llamaindex/core@0.6.11
+  - @llamaindex/google@0.3.10
+  - @llamaindex/openai@0.4.5
+  - @llamaindex/cloud@4.0.15
+  - llamaindex@0.11.9
+  - @llamaindex/node-parser@2.0.11
+  - @llamaindex/anthropic@0.3.13
+  - @llamaindex/assemblyai@0.1.10
+  - @llamaindex/clip@0.0.61
+  - @llamaindex/cohere@0.0.25
+  - @llamaindex/deepinfra@0.0.61
+  - @llamaindex/discord@0.1.10
+  - @llamaindex/huggingface@0.1.15
+  - @llamaindex/jinaai@0.0.21
+  - @llamaindex/mistral@0.1.11
+  - @llamaindex/mixedbread@0.0.25
+  - @llamaindex/notion@0.1.10
+  - @llamaindex/ollama@0.1.11
+  - @llamaindex/perplexity@0.0.18
+  - @llamaindex/portkey-ai@0.0.53
+  - @llamaindex/replicate@0.0.53
+  - @llamaindex/astra@0.0.25
+  - @llamaindex/azure@0.1.22
+  - @llamaindex/chroma@0.0.25
+  - @llamaindex/elastic-search@0.1.11
+  - @llamaindex/firestore@1.0.18
+  - @llamaindex/milvus@0.1.20
+  - @llamaindex/mongodb@0.0.26
+  - @llamaindex/pinecone@0.1.11
+  - @llamaindex/postgres@0.0.54
+  - @llamaindex/qdrant@0.1.21
+  - @llamaindex/supabase@0.1.10
+  - @llamaindex/upstash@0.0.25
+  - @llamaindex/weaviate@0.0.26
+  - @llamaindex/vercel@0.1.11
+  - @llamaindex/voyage-ai@1.0.17
+  - @llamaindex/readers@3.1.9
+  - @llamaindex/tools@0.0.17
+  - @llamaindex/workflow@1.1.10
+  - @llamaindex/deepseek@0.0.21
+  - @llamaindex/fireworks@0.0.21
+  - @llamaindex/groq@0.0.76
+  - @llamaindex/together@0.0.21
+  - @llamaindex/vllm@0.0.47
+  - @llamaindex/xai@0.0.8
+
+## 0.3.22
+
+### Patch Changes
+
+- Updated dependencies [8a51c16]
+- Updated dependencies [1b5af14]
+  - @llamaindex/workflow@1.1.9
+  - @llamaindex/core@0.6.10
+  - llamaindex@0.11.8
+  - @llamaindex/cloud@4.0.14
+  - @llamaindex/node-parser@2.0.10
+  - @llamaindex/anthropic@0.3.12
+  - @llamaindex/assemblyai@0.1.9
+  - @llamaindex/clip@0.0.60
+  - @llamaindex/cohere@0.0.24
+  - @llamaindex/deepinfra@0.0.60
+  - @llamaindex/discord@0.1.9
+  - @llamaindex/google@0.3.9
+  - @llamaindex/huggingface@0.1.14
+  - @llamaindex/jinaai@0.0.20
+  - @llamaindex/mistral@0.1.10
+  - @llamaindex/mixedbread@0.0.24
+  - @llamaindex/notion@0.1.9
+  - @llamaindex/ollama@0.1.10
+  - @llamaindex/openai@0.4.4
+  - @llamaindex/perplexity@0.0.17
+  - @llamaindex/portkey-ai@0.0.52
+  - @llamaindex/replicate@0.0.52
+  - @llamaindex/astra@0.0.24
+  - @llamaindex/azure@0.1.21
+  - @llamaindex/chroma@0.0.24
+  - @llamaindex/elastic-search@0.1.10
+  - @llamaindex/firestore@1.0.17
+  - @llamaindex/milvus@0.1.19
+  - @llamaindex/mongodb@0.0.25
+  - @llamaindex/pinecone@0.1.10
+  - @llamaindex/postgres@0.0.53
+  - @llamaindex/qdrant@0.1.20
+  - @llamaindex/supabase@0.1.9
+  - @llamaindex/upstash@0.0.24
+  - @llamaindex/weaviate@0.0.25
+  - @llamaindex/vercel@0.1.10
+  - @llamaindex/voyage-ai@1.0.16
+  - @llamaindex/readers@3.1.8
+  - @llamaindex/tools@0.0.16
+  - @llamaindex/deepseek@0.0.20
+  - @llamaindex/fireworks@0.0.20
+  - @llamaindex/groq@0.0.75
+  - @llamaindex/together@0.0.20
+  - @llamaindex/vllm@0.0.46
+  - @llamaindex/xai@0.0.7
+
+## 0.3.21
+
+### Patch Changes
+
+- Updated dependencies [dbd857f]
+- Updated dependencies [3c857f4]
+  - @llamaindex/workflow@1.1.8
+  - llamaindex@0.11.7
+  - @llamaindex/tools@0.0.15
+
+## 0.3.20
+
+### Patch Changes
+
+- Updated dependencies [e7484ef]
+  - @llamaindex/weaviate@0.0.24
+
 ## 0.3.19
 
 ### Patch Changes

examples/agents/agent/blog-writer.ts

@@ -1,4 +1,3 @@
-import { tool } from "@llamaindex/core/tools";
 import { openai } from "@llamaindex/openai";
 import {
   agent,
@@ -7,6 +6,7 @@ import {
   multiAgent,
 } from "@llamaindex/workflow";
 import fs from "fs";
+import { tool } from "llamaindex";
 import os from "os";
 import { z } from "zod";
 

examples/agents/agent/mcp-tools.ts

@@ -6,15 +6,24 @@ async function main() {
   // Create an MCP server for filesystem tools
   const server = mcp({
     command: "npx",
-    args: ["-y", "@modelcontextprotocol/server-filesystem", "."],
+    args: ["-y", "@modelcontextprotocol/server-filesystem@latest", "."],
     verbose: true,
   });
-  // You can also connect to the MCP server using SSE
-  // See: https://modelcontextprotocol.io/docs/concepts/transports#server-sent-events-sse
+  //
+  // You can also connect to a remote MCP server using:
+  // 1. StreamableHTTP transport (recommended)
+  // See: https://modelcontextprotocol.io/docs/concepts/transports#streamable-http
   // const server = mcp({
   //   url: "http://localhost:8000/mcp",
   //   verbose: true,
   // });
+  // 2.Or using SSE transport (will be deprecated soon)
+  // See: https://modelcontextprotocol.io/docs/concepts/transports#server-sent-events-sse-deprecated
+  // const server = mcp({
+  //   url: "http://localhost:8000/mcp",
+  //   useSSETransport: true,
+  //   verbose: true,
+  // });
 
   try {
     // Create an agent that uses the MCP tools

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/natural/doc-workflow.ts

@@ -0,0 +1,130 @@
+import { ToolCallLLM } from "llamaindex";
+
+import {
+  agentHandler,
+  createWorkflow,
+  workflowEvent,
+  zodEvent,
+} from "@llamaindex/workflow";
+
+import { openai } from "@llamaindex/openai";
+import { z } from "zod";
+
+// ===== 1. Define events =====
+// An event to trigger the workflow
+const planEvent = workflowEvent<{ topic: string }>();
+
+// Generate artifact event
+const ArtifactRequirementSchema = z.object({
+  type: z.literal("markdown"),
+  title: z.string().describe("The title of the artifact."),
+  requirement: z
+    .string()
+    .describe("The requirement for the artifact generation."),
+});
+
+const generateArtifactEvent = zodEvent(ArtifactRequirementSchema, {
+  debugLabel: "generateArtifactEvent",
+});
+
+// Artifact output event
+const ArtifactSchema = z.object({
+  type: z.literal("artifact"),
+  data: z.object({
+    type: z.literal("document"),
+    data: z.object({
+      title: z.string().describe("The title of the data."),
+      content: z.string().describe("The content of the data."),
+      type: z.enum(["markdown", "html"]).describe("The type of the data."),
+    }),
+  }),
+});
+const outputArtifactEvent = zodEvent(ArtifactSchema, {
+  debugLabel: "outputArtifactEvent",
+});
+
+// Events for updating UI
+// assume that we have a UI that can render different states of the workflow
+// and update the UI based on the state and the requirement
+export const UIEventSchema = z.object({
+  type: z.literal("ui_event"),
+  data: z.object({
+    state: z
+      .enum(["plan", "generate", "completed"])
+      .describe("The current state of the workflow."),
+    requirement: z
+      .string()
+      .optional()
+      .describe(
+        "An optional requirement creating or updating a document, if applicable.",
+      ),
+  }),
+});
+const uiEvent = zodEvent(UIEventSchema, { debugLabel: "uiEvent" });
+
+// ===== 2. Define workflow with agents using natural language =====
+// We have a document artifact workflow that made up of 2 steps:
+// 1. Generate requirement for the document
+// 2. Generate document content based on the requirement
+export function createDocumentArtifactWorkflow(llm: ToolCallLLM) {
+  const workflow = createWorkflow();
+
+  // Generate requirement for the document
+  workflow.handle(
+    [planEvent],
+    agentHandler({
+      instructions: `
+Your task is to analyze the request and provide requirements for document generation or update.
+1. Send an uiEvent with the \`plan\` to show UI what you are going to do.
+2. Analyze the conversation history and the user's request carefully to determine the completed tasks and the next steps.
+3. Return the generateArtifactEvent with the requirement for the next step of the document generation or update.
+`,
+      results: [generateArtifactEvent],
+      events: [uiEvent],
+      llm,
+    }),
+  );
+
+  // Generate document content based on the requirement
+  workflow.handle(
+    [generateArtifactEvent],
+    agentHandler({
+      instructions: `
+You are a skilled technical writer who can assist users with documentation.
+Your task is to generate document content based on the requirement and update the UI state.
+
+Here are the steps to handle this task:
+1. First, send an uiEvent with the \`generate\` state and the requirement you received from the input.
+2. Next, start generating the content based on the requirement then send an uiEvent with the \`completed\` state to update the state.
+3. Finally, return the outputArtifactEvent with the document values.
+`,
+      results: [outputArtifactEvent],
+      events: [uiEvent],
+      llm,
+    }),
+  );
+
+  return workflow;
+}
+
+async function main() {
+  const llm = openai({ model: "gpt-4.1-mini" });
+  const workflow = createDocumentArtifactWorkflow(llm);
+  const { stream, sendEvent } = workflow.createContext();
+
+  // Ask the workflow to generate a document about `llama`
+  sendEvent(planEvent.with({ topic: "llama" }));
+
+  await stream.until(outputArtifactEvent).forEach((event) => {
+    if (planEvent.include(event)) {
+      console.log("Starting workflow: ", event.data);
+    }
+    if (uiEvent.include(event)) {
+      console.log("UI event: ", event.data);
+    } else if (outputArtifactEvent.include(event)) {
+      console.log("Output artifact event: ", event.data);
+    }
+  });
+}
+
+main();

examples/agents/natural/joke.ts

@@ -0,0 +1,93 @@
+import { openai } from "@llamaindex/openai";
+import { agentHandler, createWorkflow, zodEvent } from "@llamaindex/workflow";
+import { Settings } from "llamaindex";
+import { z } from "zod";
+
+// Create LLM instance
+const llm = openai({ model: "gpt-4.1-mini" });
+Settings.llm = llm;
+
+// Define our workflow events
+const writeJokeSchema = z.object({
+  description: z
+    .string()
+    .describe("The topic to write a joke or describe the joke to improve."),
+  writtenJoke: z.optional(z.string()).describe("The written joke."),
+  retriedTimes: z
+    .number()
+    .default(0)
+    .describe(
+      "The retried times for writing the joke. Always increase this from the input retriedTimes.",
+    ),
+});
+
+const critiqueSchema = z.object({
+  joke: z.string().describe("The joke to critique"),
+  retriedTimes: z.number().describe("The retried times for writing the joke."),
+});
+
+const finalResultSchema = z.object({
+  joke: z.string().describe("The joke to critique"),
+  critique: z.string().describe("The critique of the joke"),
+});
+
+const writeJokeEvent = zodEvent(writeJokeSchema, {
+  debugLabel: "writeJokeEvent",
+}); // Input topic for writing a joke
+const critiqueEvent = zodEvent(critiqueSchema, {
+  debugLabel: "critiqueEvent",
+}); // Ask for critique of the joke
+const finalResultEvent = zodEvent(finalResultSchema, {
+  debugLabel: "finalResultEvent",
+}); // Final result
+
+// Create our workflow
+const jokeFlow = createWorkflow();
+
+// Define handlers for each step
+// This step always write a joke based on the description
+jokeFlow.handle(
+  [writeJokeEvent],
+  agentHandler({
+    instructions: `You are a joke writer. You are given a topic and you need to write a joke about it.`,
+    results: [critiqueEvent],
+  }),
+);
+
+// This step critiques the joke and asks the writer to improve the joke or send a final result event for stopping.
+jokeFlow.handle(
+  [critiqueEvent],
+  agentHandler({
+    instructions: `
+You are given a joke and you need to critique it. Follow the following guidelines:
+1. You have maximum 3 times to improve the joke.
+2. If the joke is not good, increase the retriedTimes, describe how to improve the joke and send a writeJokeEvent.
+3. If the joke is good, trigger the finalResultEvent event.
+`,
+    results: [writeJokeEvent, finalResultEvent],
+  }),
+);
+
+// Usage
+async function main() {
+  const { stream, sendEvent } = jokeFlow.createContext();
+  sendEvent(writeJokeEvent.with({ description: "write a joke about llama" }));
+
+  await stream.until(finalResultEvent).forEach((event) => {
+    if (writeJokeEvent.include(event)) {
+      console.log(
+        "Triggering write joke: ",
+        JSON.stringify(event.data, null, 2),
+      );
+    } else if (critiqueEvent.include(event)) {
+      console.log("Written joke:  ", JSON.stringify(event.data, null, 2));
+    } else if (finalResultEvent.include(event)) {
+      console.log("Output: ", JSON.stringify(event.data, null, 2));
+    } else {
+      console.log("Unknown event: ", JSON.stringify(event.data, null, 2));
+    }
+  });
+  console.log("Done");
+}
+
+main().catch(console.error);

examples/data/company.xml

@@ -0,0 +1,72 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<company name="MidSizeCorp" founded="2008">
+  <division name="Engineering" head="Dana White">
+    <department name="Frontend" lead="Alex Kim">
+      <team name="Web">
+        <employee id="E01">
+          <name>Jordan Lee</name>
+          <role>Lead Developer</role>
+          <projects>
+            <project code="PRJ101" status="active">
+              <title>User Portal</title>
+              <deadline>2025-08-01</deadline>
+              <tasks>
+                <task id="T1011">
+                  <description>Implement login page</description>
+                  <due>2025-05-10</due>
+                </task>
+                <task id="T1012">
+                  <description>Design dashboard</description>
+                  <due>2025-05-20</due>
+                </task>
+              </tasks>
+            </project>
+          </projects>
+        </employee>
+        <employee id="E02">
+          <name>Riley Chen</name>
+          <role>UI Designer</role>
+        </employee>
+      </team>
+      <team name="Mobile">
+        <employee id="E03">
+          <name>Sam Patel</name>
+          <role>iOS Developer</role>
+        </employee>
+      </team>
+    </department>
+    <department name="Backend" lead="Morgan Reed">
+      <team name="API">
+        <employee id="E04">
+          <name>Taylor Jones</name>
+          <role>API Engineer</role>
+        </employee>
+      </team>
+      <team name="Database">
+        <employee id="E05">
+          <name>Casey Nguyen</name>
+          <role>DB Administrator</role>
+        </employee>
+      </team>
+    </department>
+  </division>
+
+  <division name="Marketing" head="Pat Morgan">
+    <department name="Digital" lead="Alex Rivera">
+      <team name="Content">
+        <employee id="M01">
+          <name>Charlie Brooks</name>
+          <role>Content Strategist</role>
+        </employee>
+      </team>
+    </department>
+  </division>
+
+  <headquarters location="Chicago, USA">
+    <address>
+      <street>789 Lake Shore Drive</street>
+      <city>Chicago</city>
+      <zip>60601</zip>
+    </address>
+  </headquarters>
+</company>

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,

examples/models/gemini/chat.ts

@@ -1,14 +1,16 @@
-import { Gemini, GEMINI_MODEL } from "@llamaindex/google";
+import { gemini, GEMINI_MODEL } from "@llamaindex/google";
 import fs from "fs";
+import { tool } from "llamaindex";
+import { z } from "zod";
 
 (async () => {
   if (!process.env.GOOGLE_API_KEY) {
     throw new Error("Please set the GOOGLE_API_KEY environment variable.");
   }
-  const gemini = new Gemini({
-    model: GEMINI_MODEL.GEMINI_PRO_1_5,
-  });
-  const result = await gemini.chat({
+  const llm = gemini({ model: GEMINI_MODEL.GEMINI_2_0_FLASH });
+
+  // normal chat
+  const result = await llm.chat({
     messages: [
       { content: "You want to talk in rhymes.", role: "system" },
       {
@@ -18,10 +20,10 @@ import fs from "fs";
       },
     ],
   });
-  console.log(result);
+  console.log("\n normal chat: \n", result);
 
   // chat with file
-  const resultWithFile = await gemini.chat({
+  const resultWithFile = await llm.chat({
     messages: [
       {
         role: "user",
@@ -39,6 +41,52 @@ import fs from "fs";
       },
     ],
   });
+  console.log("\n chat with file: \n", resultWithFile);
 
-  console.log(resultWithFile);
+  // chat with image base64
+  const resultWithImageFile = await llm.chat({
+    messages: [
+      {
+        role: "user",
+        content: [
+          {
+            type: "text",
+            text: "What's in this image?",
+          },
+          {
+            type: "image",
+            data: fs
+              .readFileSync("./multimodal/data/60.jpg")
+              .toString("base64"),
+            mimeType: "image/png",
+          },
+        ],
+      },
+    ],
+  });
+  console.log("\n chat with image base64: \n", resultWithImageFile);
+
+  // chat with tool
+  const resultWithTool = await llm.chat({
+    messages: [
+      {
+        content: "What's the weather in Tokyo?",
+        role: "user",
+      },
+    ],
+    tools: [
+      tool({
+        name: "weather",
+        description: "Get the weather",
+        parameters: z.object({
+          location: z.string().describe("The location to get the weather for"),
+        }),
+        execute: ({ location }) => {
+          console.log("weather", location);
+          return `The weather in ${location} is sunny and hot`;
+        },
+      }),
+    ],
+  });
+  console.log("\n chat with tool: \n", resultWithTool.message.options); // should have toolCall
 })();

examples/models/gemini/chatVertex.ts

@@ -1,11 +1,14 @@
-import { Gemini, GEMINI_MODEL, GeminiVertexSession } from "@llamaindex/google";
+import { gemini, GEMINI_MODEL } from "@llamaindex/google";
 
 (async () => {
-  const gemini = new Gemini({
-    model: GEMINI_MODEL.GEMINI_PRO,
-    session: new GeminiVertexSession(),
+  const llm = gemini({
+    model: GEMINI_MODEL.GEMINI_2_0_FLASH,
+    vertex: {
+      project: "your-cloud-project", // update to your cloud project
+      location: "us-central1",
+    },
   });
-  const result = await gemini.chat({
+  const result = await llm.chat({
     messages: [
       { content: "You want to talk in rhymes.", role: "system" },
       {

examples/models/gemini/live/complex.ts

@@ -16,9 +16,19 @@ async function main() {
 
   console.log("🚀 Initializing Gemini Live API example...");
 
+  // Server-side (token creation):
+  const serverllm = gemini({
+    model: GEMINI_MODEL.GEMINI_2_0_FLASH_LIVE,
+    httpOptions: { apiVersion: "v1alpha" }, // must use v1alpha to generate ephemeral key
+  });
+  const ephemeralKey = await serverllm.live.getEphemeralKey();
+
+  // Client-side (Live API connection):
   const llm = gemini({
+    apiKey: ephemeralKey, // use ephemeral key for client-side
     model: GEMINI_MODEL.GEMINI_2_0_FLASH_LIVE,
     voiceName: "Zephyr",
+    httpOptions: { apiVersion: "v1alpha" }, // must use v1alpha to init client with ephemeral key
   });
 
   console.log("📡 Connecting to Gemini Live session...");

examples/models/gemini/live/simple.ts

@@ -3,8 +3,18 @@ import { liveEvents } from "llamaindex";
 import { saveWavFile } from "./util";
 
 async function main() {
-  const llm = gemini({
+  // Server-side (token creation):
+  const serverllm = gemini({
     model: GEMINI_MODEL.GEMINI_2_0_FLASH_LIVE,
+    httpOptions: { apiVersion: "v1alpha" }, // must use v1alpha to generate ephemeral key
+  });
+  const ephemeralKey = await serverllm.live.getEphemeralKey();
+
+  // Client-side (Live API connection):
+  const llm = gemini({
+    apiKey: ephemeralKey, // use ephemeral key for client-side
+    model: GEMINI_MODEL.GEMINI_2_0_FLASH_LIVE,
+    httpOptions: { apiVersion: "v1alpha" }, // must use v1alpha to init client with ephemeral key
   });
 
   const session = await llm.live.connect();
@@ -23,10 +33,7 @@ async function main() {
         content: "Say something about you for 10 seconds",
         role: "user",
       });
-    } else if (
-      liveEvents.audio.include(event) &&
-      typeof event.data === "string"
-    ) {
+    } else if (liveEvents.audio.include(event)) {
       const chunk = Buffer.from(event.data, "base64");
       audioChunks.push(chunk);
       console.log(`Received audio chunk: ${chunk.length} bytes`);

examples/models/gemini/live/tool-call.ts

@@ -1,6 +1,5 @@
-import { ModalityType } from "@llamaindex/core/schema";
-import { tool } from "@llamaindex/core/tools";
 import { gemini, GEMINI_MODEL } from "@llamaindex/google";
+import { ModalityType, tool } from "llamaindex";
 
 import { liveEvents } from "llamaindex";
 import { z } from "zod";

examples/models/openai/live/browser/open-ai-realtime/.gitignore

@@ -0,0 +1,24 @@
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+pnpm-debug.log*
+lerna-debug.log*
+
+node_modules
+dist
+dist-ssr
+*.local
+
+# Editor directories and files
+.vscode/*
+!.vscode/extensions.json
+.idea
+.DS_Store
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.sw?

examples/models/openai/live/browser/open-ai-realtime/README.md

@@ -0,0 +1,54 @@
+# OpenAI Realtime Chat with LlamaIndex
+
+This is a demo application showcasing real-time audio and text chat capabilities using OpenAI's GPT-4 with voice through LlamaIndex. The application demonstrates bidirectional audio communication and text chat with an AI assistant.
+
+## Features
+
+- Real-time voice communication with GPT-4
+- Text-based chat interface
+- WebRTC-based audio streaming
+- Bidirectional communication (both text and voice)
+- React + TypeScript implementation
+
+## Prerequisites
+
+- Node.js (v18 or higher)
+- OpenAI API key with access to GPT-4 voice models
+- Modern browser with WebRTC support
+
+## Getting Started
+
+1. Install dependencies:
+
+```bash
+pnpm install
+```
+
+2. Start the development server:
+
+```bash
+pnpm run dev
+```
+
+## Usage
+
+The application provides a simple interface where you can:
+
+- Start/Stop a chat session
+- Speak to the AI assistant through your microphone
+- Receive audio responses from the assistant
+- See text transcripts of the conversation
+
+## Technical Details
+
+This project uses:
+
+- LlamaIndex for AI interaction management
+- WebRTC for real-time audio streaming
+- React for the UI
+- Vite for development and building
+- TypeScript for type safety
+
+```
+
+```

examples/models/openai/live/browser/open-ai-realtime/eslint.config.js

@@ -0,0 +1,28 @@
+import js from "@eslint/js";
+import reactHooks from "eslint-plugin-react-hooks";
+import reactRefresh from "eslint-plugin-react-refresh";
+import globals from "globals";
+import tseslint from "typescript-eslint";
+
+export default tseslint.config(
+  { ignores: ["dist"] },
+  {
+    extends: [js.configs.recommended, ...tseslint.configs.recommended],
+    files: ["**/*.{ts,tsx}"],
+    languageOptions: {
+      ecmaVersion: 2020,
+      globals: globals.browser,
+    },
+    plugins: {
+      "react-hooks": reactHooks,
+      "react-refresh": reactRefresh,
+    },
+    rules: {
+      ...reactHooks.configs.recommended.rules,
+      "react-refresh/only-export-components": [
+        "warn",
+        { allowConstantExport: true },
+      ],
+    },
+  },
+);

examples/models/openai/live/browser/open-ai-realtime/index.html

@@ -0,0 +1,13 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <link rel="icon" type="image/svg+xml" href="/vite.svg" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>Vite + React + TS</title>
+  </head>
+  <body>
+    <div id="root"></div>
+    <script type="module" src="/src/main.tsx"></script>
+  </body>
+</html>

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

@@ -0,0 +1,29 @@
+{
+  "name": "open-ai-realtime",
+  "private": true,
+  "version": "0.0.0",
+  "type": "module",
+  "scripts": {
+    "dev": "vite",
+    "build": "tsc -b && vite build",
+    "lint": "eslint .",
+    "preview": "vite preview"
+  },
+  "dependencies": {
+    "react": "^19.1.0",
+    "react-dom": "^19.1.0"
+  },
+  "devDependencies": {
+    "@eslint/js": "^9.25.0",
+    "@types/react": "^19.1.2",
+    "@types/react-dom": "^19.1.2",
+    "@vitejs/plugin-react": "^4.5.2",
+    "eslint": "^9.25.0",
+    "eslint-plugin-react-hooks": "^5.2.0",
+    "eslint-plugin-react-refresh": "^0.4.19",
+    "globals": "^16.0.0",
+    "typescript": "~5.8.3",
+    "typescript-eslint": "^8.30.1",
+    "vite": "^6.3.5"
+  }
+}

examples/models/openai/live/browser/open-ai-realtime/public/vite.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" class="iconify iconify--logos" width="31.88" height="32" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 257"><defs><linearGradient id="IconifyId1813088fe1fbc01fb466" x1="-.828%" x2="57.636%" y1="7.652%" y2="78.411%"><stop offset="0%" stop-color="#41D1FF"></stop><stop offset="100%" stop-color="#BD34FE"></stop></linearGradient><linearGradient id="IconifyId1813088fe1fbc01fb467" x1="43.376%" x2="50.316%" y1="2.242%" y2="89.03%"><stop offset="0%" stop-color="#FFEA83"></stop><stop offset="8.333%" stop-color="#FFDD35"></stop><stop offset="100%" stop-color="#FFA800"></stop></linearGradient></defs><path fill="url(#IconifyId1813088fe1fbc01fb466)" d="M255.153 37.938L134.897 252.976c-2.483 4.44-8.862 4.466-11.382.048L.875 37.958c-2.746-4.814 1.371-10.646 6.827-9.67l120.385 21.517a6.537 6.537 0 0 0 2.322-.004l117.867-21.483c5.438-.991 9.574 4.796 6.877 9.62Z"></path><path fill="url(#IconifyId1813088fe1fbc01fb467)" d="M185.432.063L96.44 17.501a3.268 3.268 0 0 0-2.634 3.014l-5.474 92.456a3.268 3.268 0 0 0 3.997 3.378l24.777-5.718c2.318-.535 4.413 1.507 3.936 3.838l-7.361 36.047c-.495 2.426 1.782 4.5 4.151 3.78l15.304-4.649c2.372-.72 4.652 1.36 4.15 3.788l-11.698 56.621c-.732 3.542 3.979 5.473 5.943 2.437l1.313-2.028l72.516-144.72c1.215-2.423-.88-5.186-3.54-4.672l-25.505 4.922c-2.396.462-4.435-1.77-3.759-4.114l16.646-57.705c.677-2.35-1.37-4.583-3.769-4.113Z"></path></svg>