Add GitHub Actions workflow for Vercel deployment

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.github/workflows/deploy-developer-hub.yml

@@ -0,0 +1,13 @@
+name: Trigger Vercel Deploy
+
+on:
+  push:
+    branches: [main]
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Trigger Vercel deployment
+        run: |
+          curl -X POST "${{ secrets.DEVELOPER_HUB_DEPLOY_HOOK }}"

.github/workflows/test.yml

@@ -105,6 +105,7 @@ jobs:
         run: |
           pnpm pack --pack-destination ${{ runner.temp }} -C packages/llamaindex
           pnpm pack --pack-destination ${{ runner.temp }} -C packages/workflow
+          pnpm pack --pack-destination ${{ runner.temp }} -C packages/core
       - name: Install packed packages
         run: npm add ${{ runner.temp }}/*.tgz
         working-directory: e2e/npm
@@ -121,7 +122,6 @@ jobs:
           - nextjs-edge-runtime
           - nextjs-node-runtime
           - waku-query-engine
-          - llama-parse-browser
           - vite-import-llamaindex
     runs-on: ubuntu-latest
     name: Build LlamaIndex Example (${{ matrix.packages }})
@@ -162,7 +162,7 @@ jobs:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           directory: e2e/examples/vite-import-llamaindex
           skip_step: "install"
-          build_script: build
+          build_script: ci-build
           package_manager: pnpm
 
   typecheck-examples:
@@ -203,7 +203,7 @@ jobs:
             fi
           done
       - name: Install
-        run: npm add ${{ runner.temp }}/*.tgz
+        run: npm add ${{ runner.temp }}/*.tgz --legacy-peer-deps
         working-directory: ${{ runner.temp }}/examples
       - name: Run Type Check
         run: npx tsc --project ./tsconfig.json

apps/next/CHANGELOG.md

@@ -1,5 +1,160 @@
 # @llamaindex/doc
 
+## 0.2.55
+
+### Patch Changes
+
+- Updated dependencies [06f884a]
+- Updated dependencies [06f884a]
+- Updated dependencies [d493015]
+  - @llamaindex/core@0.6.22
+  - @llamaindex/workflow@1.1.24
+  - llamaindex@0.12.0
+  - @llamaindex/node-parser@2.0.22
+  - @llamaindex/openai@0.4.20
+  - @llamaindex/readers@3.1.21
+
+## 0.2.54
+
+### Patch Changes
+
+- ed37c64: Addition of APAC_ANTHROPIC_CLAUDE_4_SONNET type/record in @llamaindex/aws for APAC support for claude 4 sonnet per issue 2184.
+- Updated dependencies [8929dcf]
+- Updated dependencies [5da1cda]
+  - llamaindex@0.11.29
+  - @llamaindex/core@0.6.21
+  - @llamaindex/workflow@1.1.23
+  - @llamaindex/openai@0.4.19
+  - @llamaindex/cloud@4.1.3
+  - @llamaindex/node-parser@2.0.21
+  - @llamaindex/readers@3.1.20
+
+## 0.2.53
+
+### Patch Changes
+
+- Updated dependencies [1995b38]
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/workflow@1.1.22
+  - @llamaindex/openai@0.4.18
+  - llamaindex@0.11.28
+
+## 0.2.52
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+  - @llamaindex/cloud@4.1.2
+  - llamaindex@0.11.27
+  - @llamaindex/node-parser@2.0.20
+  - @llamaindex/openai@0.4.17
+  - @llamaindex/readers@3.1.19
+  - @llamaindex/workflow@1.1.21
+
+## 0.2.51
+
+### Patch Changes
+
+- Updated dependencies [4c70376]
+  - @llamaindex/openai@0.4.16
+
+## 0.2.50
+
+### Patch Changes
+
+- Updated dependencies [b6409b6]
+  - @llamaindex/openai@0.4.15
+
+## 0.2.49
+
+### Patch Changes
+
+- Updated dependencies [4b51791]
+  - @llamaindex/cloud@4.1.1
+  - llamaindex@0.11.26
+
+## 0.2.48
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+- Updated dependencies [049471b]
+  - @llamaindex/cloud@4.1.0
+  - llamaindex@0.11.25
+
+## 0.2.47
+
+### Patch Changes
+
+- Updated dependencies [c3bf3c7]
+- Updated dependencies [f9f1de9]
+  - @llamaindex/cloud@4.0.28
+  - @llamaindex/core@0.6.19
+  - llamaindex@0.11.24
+  - @llamaindex/node-parser@2.0.19
+  - @llamaindex/openai@0.4.14
+  - @llamaindex/readers@3.1.18
+  - @llamaindex/workflow@1.1.20
+
+## 0.2.46
+
+### Patch Changes
+
+- Updated dependencies [f29799e]
+- Updated dependencies [7224c06]
+  - @llamaindex/workflow@1.1.19
+  - @llamaindex/core@0.6.18
+  - llamaindex@0.11.23
+  - @llamaindex/cloud@4.0.27
+  - @llamaindex/node-parser@2.0.18
+  - @llamaindex/openai@0.4.13
+  - @llamaindex/readers@3.1.17
+
+## 0.2.45
+
+### Patch Changes
+
+- Updated dependencies [9ed3195]
+  - @llamaindex/workflow@1.1.18
+  - llamaindex@0.11.22
+
+## 0.2.44
+
+### Patch Changes
+
+- 38da40b: feat: VectoryMemoryBlock
+- Updated dependencies [38da40b]
+  - @llamaindex/core@0.6.17
+  - @llamaindex/cloud@4.0.26
+  - llamaindex@0.11.21
+  - @llamaindex/node-parser@2.0.17
+  - @llamaindex/openai@0.4.12
+  - @llamaindex/readers@3.1.16
+  - @llamaindex/workflow@1.1.17
+
+## 0.2.43
+
+### Patch Changes
+
+- ea15e75: Minor updates in deployment docs
+
+## 0.2.42
+
+### Patch Changes
+
+- a8ec08c: fix: ensure correct message content in agent workflow
+- Updated dependencies [a8ec08c]
+- Updated dependencies [2967d57]
+  - @llamaindex/core@0.6.16
+  - @llamaindex/workflow@1.1.16
+  - @llamaindex/cloud@4.0.25
+  - llamaindex@0.11.20
+  - @llamaindex/node-parser@2.0.16
+  - @llamaindex/openai@0.4.11
+  - @llamaindex/readers@3.1.15
+
 ## 0.2.41
 
 ### Patch Changes

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.41",
+  "version": "0.2.55",
   "private": true,
   "scripts": {
     "postinstall": "fumadocs-mdx",
@@ -15,14 +15,14 @@
   "dependencies": {
     "@huggingface/transformers": "^3.5.0",
     "@icons-pack/react-simple-icons": "^10.1.0",
-    "@llamaindex/chat-ui-docs": "^0.0.5",
-    "@llamaindex/cloud": "workspace:*",
+    "@llamaindex/chat-ui-docs": "^0.1.0",
+    "llama-cloud-services": "^0.3.5",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/node-parser": "workspace:*",
     "@llamaindex/openai": "workspace:*",
     "@llamaindex/readers": "workspace:*",
     "@llamaindex/workflow": "workspace:*",
-    "@llamaindex/workflow-docs": "0.1.1",
+    "@llamaindex/workflow-docs": "0.1.4",
     "@mdx-js/mdx": "^3.1.0",
     "@monaco-editor/react": "^4.7.0",
     "@next/third-parties": "^15.3.4",
@@ -50,7 +50,7 @@
     "hast-util-to-jsx-runtime": "^2.3.2",
     "llamaindex": "workspace:*",
     "lucide-react": "^0.460.0",
-    "next": "^15.3.3",
+    "next": "^15.4.7",
     "next-themes": "^0.4.3",
     "react": "^19.1.0",
     "react-dom": "^19.1.0",

apps/next/scripts/update-llamacloud.mts

@@ -1,8 +1,8 @@
-import { upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut } from "@llamaindex/cloud/api";
 import fg from "fast-glob";
 import { fileGenerator, remarkDocGen, remarkInstall } from "fumadocs-docgen";
 import { remarkAutoTypeTable } from "fumadocs-typescript";
 import matter from "gray-matter";
+import { upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut } from "llama-cloud-services/api";
 import * as fs from "node:fs/promises";
 import path, { relative } from "node:path";
 import { fileURLToPath } from "node:url";

apps/next/src/actions/index.tsx

@@ -1,109 +0,0 @@
-import { ClientMDXContent } from "@/components/mdx";
-import { BotMessage } from "@/components/message";
-import { Skeleton } from "@/components/ui/skeleton";
-import { LlamaCloudRetriever } from "@/deps/cloud";
-import { ContextChatEngine } from "@llamaindex/core/chat-engine";
-import { Settings } from "@llamaindex/core/global";
-import { ChatMessage } from "@llamaindex/core/llms";
-import { OpenAI } from "@llamaindex/openai";
-import { createAI, createStreamableUI, getMutableAIState } from "ai/rsc";
-import { ReactNode } from "react";
-
-Settings.llm = new OpenAI({
-  model: "gpt-4o",
-});
-
-const retriever = new LlamaCloudRetriever({
-  apiKey: process.env.LLAMA_CLOUD_API_KEY!,
-  baseUrl: "https://api.cloud.llamaindex.ai/",
-
-  pipelineId: process.env.LLAMA_CLOUD_PIPELINE_ID!,
-});
-
-const initialAIState = {
-  messages: [],
-} as {
-  messages: ChatMessage[];
-};
-
-export type UIMessage = {
-  id: number;
-  display: ReactNode;
-};
-
-const initialUIState = {
-  messages: [],
-} as {
-  messages: UIMessage[];
-};
-
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-const runAsyncFnWithoutBlocking = (fn: (...args: any) => Promise<any>) => {
-  fn().catch((error) => {
-    console.error(error);
-  });
-};
-
-export const AIProvider = createAI({
-  initialAIState,
-  initialUIState,
-  actions: {
-    query: async (message: string): Promise<UIMessage> => {
-      "use server";
-      const chatEngine = new ContextChatEngine({ retriever });
-
-      const id = Date.now();
-      const aiState = getMutableAIState<typeof AIProvider>();
-      aiState.update({
-        ...aiState.get(),
-        messages: [
-          ...aiState.get().messages,
-          {
-            role: "user",
-            content: message,
-          },
-        ],
-      });
-
-      const ui = createStreamableUI(
-        <div className="space-y-2">
-          <Skeleton className="h-4 w-full" />
-          <Skeleton className="h-4 w-full" />
-        </div>,
-      );
-
-      runAsyncFnWithoutBlocking(async () => {
-        const response = await chatEngine.chat({
-          message,
-          chatHistory: aiState.get().messages,
-          stream: true,
-        });
-
-        let content = "";
-
-        for await (const { delta } of response) {
-          content += delta;
-          ui.update(<ClientMDXContent id={id} content={content} />);
-        }
-
-        ui.done();
-
-        aiState.done({
-          ...aiState.get(),
-          messages: [
-            ...aiState.get().messages,
-            {
-              role: "assistant",
-              content,
-            },
-          ],
-        });
-      });
-
-      return {
-        id,
-        display: <BotMessage>{ui.value}</BotMessage>,
-      };
-    },
-  },
-});

apps/next/src/app/layout.tsx

@@ -1,6 +1,5 @@
-import { AIProvider } from "@/actions";
 import { TooltipProvider } from "@/components/ui/tooltip";
-import { GoogleAnalytics } from "@next/third-parties/google";
+import { GoogleAnalytics, GoogleTagManager } from "@next/third-parties/google";
 import { RootProvider } from "fumadocs-ui/provider";
 import { Inter } from "next/font/google";
 import type { ReactNode } from "react";
@@ -36,11 +35,10 @@ export default function Layout({ children }: { children: ReactNode }) {
           LlamaIndex.TS - Build LLM-powered document agents and workflows
         </title>
       </head>
+      <GoogleTagManager gtmId="GTM-WWRFB36R" />
       <body className="flex min-h-screen flex-col">
         <TooltipProvider>
-          <AIProvider>
-            <RootProvider>{children}</RootProvider>
-          </AIProvider>
+          <RootProvider>{children}</RootProvider>
         </TooltipProvider>
       </body>
       <GoogleAnalytics gaId="G-NB9B8LW9W5" />

apps/next/src/components/ai-chat.tsx

@@ -1,143 +0,0 @@
-"use client";
-import type { AIProvider, UIMessage } from "@/actions";
-import { UserMessage } from "@/components/message";
-import { useActions, useUIState } from "ai/rsc";
-import { Info } from "lucide-react";
-import { ButtonHTMLAttributes, useState } from "react";
-import { Alert, AlertDescription, AlertTitle } from "./ui/alert";
-import { Button } from "./ui/button";
-import {
-  Dialog,
-  DialogContent,
-  DialogDescription,
-  DialogHeader,
-  DialogOverlay,
-  DialogPortal,
-  DialogTitle,
-  DialogTrigger,
-} from "./ui/dialog";
-import { Textarea } from "./ui/textarea";
-import { Tooltip, TooltipContent, TooltipTrigger } from "./ui/tooltip";
-
-type AITriggerProps = ButtonHTMLAttributes<HTMLButtonElement>;
-
-function ChatList({ messages }: { messages: UIMessage[] }) {
-  if (messages.length === 0) {
-    return null;
-  }
-
-  return (
-    <div className="relative mx-auto w-full px-4">
-      {messages.map((message, index) => (
-        <div key={index} className="pb-4">
-          {message.display}
-        </div>
-      ))}
-    </div>
-  );
-}
-
-export const AITrigger = (props: AITriggerProps) => {
-  const [{ messages }, setUIState] = useUIState<typeof AIProvider>();
-  const { query } = useActions<typeof AIProvider>();
-  const [inputValue, setInputValue] = useState("");
-  return (
-    <Dialog>
-      <DialogTrigger {...props} />
-      <DialogPortal>
-        <DialogOverlay className="bg-fd-background/50 data-[state=closed]:animate-fd-fade-out data-[state=open]:animate-fd-fade-in fixed inset-0 z-50 backdrop-blur-sm" />
-        <DialogContent
-          onOpenAutoFocus={(e) => {
-            document.getElementById("nd-ai-input")?.focus();
-            e.preventDefault();
-          }}
-          className="bg-fd-popover text-fd-popover-foreground data-[state=closed]:animate-fd-dialog-out data-[state=open]:animate-fd-dialog-in fixed left-1/2 z-50 my-[5vh] flex max-h-[90dvh] w-[98vw] max-w-[860px] origin-left -translate-x-1/2 flex-col rounded-lg border shadow-lg focus-visible:outline-none"
-        >
-          <DialogHeader>
-            <DialogTitle className="sr-only">Search AI</DialogTitle>
-            <DialogDescription className="sr-only">
-              Ask AI some questions.
-            </DialogDescription>
-            <Alert>
-              <Info className="size-4" />
-              <AlertTitle>Heads up!</AlertTitle>
-              <AlertDescription>
-                Answers from LlamaCloud may be inaccurate, please use with
-                discretion.
-              </AlertDescription>
-            </Alert>
-          </DialogHeader>
-          <div className="mt-4 flex-grow overflow-scroll">
-            <ChatList messages={messages} />
-          </div>
-          <form
-            className="space-y-4 px-4 py-2"
-            action={async () => {
-              const value = inputValue.trim();
-              setInputValue("");
-              if (!value) return;
-
-              // Add user message UI
-              setUIState((state) => ({
-                ...state,
-                messages: [
-                  ...state.messages,
-                  {
-                    id: Date.now(),
-                    display: <UserMessage>{value}</UserMessage>,
-                  },
-                ],
-              }));
-
-              try {
-                // Submit and get response message
-                const responseMessage = await query(value);
-                setUIState((state) => ({
-                  ...state,
-                  messages: [...state.messages, responseMessage],
-                }));
-              } catch (error) {
-                // You may want to show a toast or trigger an error state.
-                console.error(error);
-              }
-            }}
-          >
-            <div className="flex w-full flex-row items-center gap-2">
-              <Textarea
-                tabIndex={0}
-                placeholder="Ask AI about documentation."
-                className="w-full resize-none bg-transparent px-4 focus-within:outline-none sm:text-sm"
-                onKeyDown={(event) => {
-                  if (event.key === "Enter" && !event.shiftKey) {
-                    event.preventDefault();
-                    event.currentTarget.form?.requestSubmit(null);
-                  }
-                }}
-                autoFocus
-                spellCheck={false}
-                autoComplete="off"
-                autoCorrect="off"
-                name="message"
-                rows={1}
-                value={inputValue}
-                onChange={(e) => setInputValue(e.target.value)}
-              />
-              <Tooltip>
-                <TooltipTrigger asChild>
-                  <Button
-                    type="submit"
-                    size="icon"
-                    disabled={inputValue === ""}
-                  >
-                    <span className="sr-only">Send message</span>
-                  </Button>
-                </TooltipTrigger>
-                <TooltipContent>Send message</TooltipContent>
-              </Tooltip>
-            </div>
-          </form>
-        </DialogContent>
-      </DialogPortal>
-    </Dialog>
-  );
-};

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

@@ -77,7 +77,7 @@ export async function POST(request: NextRequest) {
     const agent = await initializeAgent();
     const result = await agent.run(message);
     
-    return NextResponse.json({ response: result.result });
+    return NextResponse.json({ response: result.data });
   } catch (error) {
     console.error("Chat error:", error);
     return NextResponse.json(
@@ -132,7 +132,7 @@ export default async function handler(
     const agent = await initializeAgent();
     const result = await agent.run(message);
     
-    res.json({ response: result.result });
+    res.json({ response: result.data });
   } catch (error) {
     console.error("Chat error:", error);
     res.status(500).json({ error: "Internal server error" });
@@ -220,7 +220,7 @@ export async function POST(request: NextRequest) {
     });
 
     const result = await myAgent.run(message);
-    return NextResponse.json({ response: result.result });
+    return NextResponse.json({ response: result.data });
   } catch (error) {
     return NextResponse.json({ error: error.message }, { status: 500 });
   }
@@ -233,11 +233,40 @@ Implement streaming for better user experience:
 
 ```typescript
 // app/api/chat-stream/route.ts
+import { agent } from "@llamaindex/workflow";
+import { tool } from "llamaindex";
+import { openai } from "@llamaindex/openai";
 import { agentStreamEvent } from "@llamaindex/workflow";
 import { NextRequest } from "next/server";
+import { z } from "zod";
 
-// Assume myAgent is initialized elsewhere
-declare const myAgent: any;
+// Initialize agent once (consider using a singleton pattern)
+let myAgent: any = null;
+
+async function initializeAgent() {
+  if (myAgent) return myAgent;
+  
+  try {
+    const greetTool = tool({
+      name: "greet",
+      description: "Greets a user with their name",
+      parameters: z.object({
+        name: z.string(),
+      }),
+      execute: ({ name }) => `Hello, ${name}! How can I help you today?`,
+    });
+
+    myAgent = agent({
+      tools: [greetTool],
+      llm: openai({ model: "gpt-4o-mini" }),
+    });
+    
+    return myAgent;
+  } catch (error) {
+    console.error("Failed to initialize agent:", error);
+    throw error;
+  }
+}
 
 export async function POST(request: NextRequest) {
   const { message } = await request.json();
@@ -245,9 +274,10 @@ export async function POST(request: NextRequest) {
   const stream = new ReadableStream({
     async start(controller) {
       try {
-        const context = myAgent.runStream(message);
+        const agent = await initializeAgent();
+        const events = agent.runStream(message);
         
-        for await (const event of context) {
+        for await (const event of events) {
           if (agentStreamEvent.include(event)) {
             controller.enqueue(new TextEncoder().encode(event.data.delta));
           }

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

@@ -63,7 +63,7 @@ app.post('/api/chat', async (req, res) => {
   try {
     const { message } = req.body;
     const result = await myAgent.run(message);
-    res.json({ response: result.result });
+    res.json({ response: result.data });
   } catch (error) {
     res.status(500).json({ error: 'Chat failed' });
   }
@@ -110,7 +110,7 @@ fastify.post('/api/chat', async (request, reply) => {
   try {
     const { message } = request.body as { message: string };
     const result = await myAgent.run(message);
-    return { response: result.result };
+    return { response: result.data };
   } catch (error) {
     reply.status(500).send({ error: 'Chat failed' });
   }
@@ -162,7 +162,7 @@ app.post("/api/chat", async (c) => {
   
   try {
     const result = await myAgent.run(message);
-    return c.json({ response: result.result });
+    return c.json({ response: result.data });
   } catch (error) {
     return c.json({ error: error.message }, 500);
   }
@@ -187,9 +187,9 @@ app.post('/api/chat-stream', async (req, res) => {
   });
   
   try {
-    const context = myAgent.runStream(message);
+    const events = myAgent.runStream(message);
     
-    for await (const event of context) {
+    for await (const event of events) {
       if (agentStreamEvent.include(event)) {
         res.write(event.data.delta);
       }

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

@@ -34,7 +34,7 @@ export default {
       const { message } = await request.json();
       const result = await myAgent.run(message);
       
-      return new Response(JSON.stringify({ response: result.result }), {
+      return new Response(JSON.stringify({ response: result.data }), {
         headers: { "Content-Type": "application/json" },
       });
     } catch (error) {
@@ -83,7 +83,7 @@ export default async function handler(req, res) {
   
   try {
     const result = await myAgent.run(message);
-    res.json({ response: result.result });
+    res.json({ response: result.data });
   } catch (error) {
     res.status(500).json({ error: error.message });
   }
@@ -124,7 +124,7 @@ export async function POST(request: NextRequest) {
     });
 
     const result = await myAgent.run(message);
-    return NextResponse.json({ response: result.result });
+    return NextResponse.json({ response: result.data });
   } catch (error) {
     return NextResponse.json({ error: error.message }, { status: 500 });
   }
@@ -173,7 +173,7 @@ export const handler: APIGatewayProxyHandler = async (event, context) => {
         "Content-Type": "application/json",
         "Access-Control-Allow-Origin": "*",
       },
-      body: JSON.stringify({ response: result.result }),
+      body: JSON.stringify({ response: result.data }),
     };
   } catch (error) {
     return {
@@ -222,7 +222,7 @@ export const handler: Handler = async (event, context) => {
     
     return {
       statusCode: 200,
-      body: JSON.stringify({ response: result.result }),
+      body: JSON.stringify({ response: result.data }),
     };
   } catch (error) {
     return {

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

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

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

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

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

@@ -38,7 +38,8 @@ Here's how to create a simple vector store index and query it using Vercel's AI
 import { openai } from "@ai-sdk/openai";
 import { llamaindex } from "@llamaindex/vercel";
 import { streamText } from "ai";
-import { Document, VectorStoreIndex } from "llamaindex";
+import { Document } from "llamaindex";
+import { LlamaCloudIndex } from "llama-cloud-services";
 
 // Create an index from your documents
 const document = new Document({ text: yourText, id_: "unique-id" });
@@ -69,7 +70,7 @@ streamText({
 For production deployments, you can use LlamaCloud to store and manage your documents:
 
 ```typescript
-import { LlamaCloudIndex } from "@llamaindex/cloud";
+import { LlamaCloudIndex } from "llama-cloud-services";
 
 // Create a LlamaCloud index
 const index = await LlamaCloudIndex.fromDocuments({

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

@@ -34,8 +34,61 @@ const jokeAgent = agent({
 // Run the workflow
 const result = await jokeAgent.run("Tell me something funny");
 console.log(result.data.result); // Baby Llama is called cria
+console.log(result.data.message); // { role: 'assistant', content: 'Baby Llama is called cria' }
 ```
 
+### Structured Output
+
+You can extract structured data from agent responses by providing a `responseFormat` with a Zod schema. This is useful when you need the agent's response in a specific format for further processing:
+
+```typescript
+import { z } from "zod";
+import { tool } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
+import { openai } from "@llamaindex/openai";
+
+// Define a weather tool
+const weatherTool = tool({
+  name: "weatherTool",
+  description: "Get weather information",
+  parameters: z.object({
+    location: z.string(),
+  }),
+  execute: ({ location }) => {
+    return `The weather in ${location} is sunny. The temperature is 72 degrees. The humidity is 50%. The wind speed is 10 mph.`;
+  },
+});
+
+// Define the structure you want for the response
+const responseSchema = z.object({
+  temperature: z.number(),
+  humidity: z.number(),
+  windSpeed: z.number(),
+});
+
+// Create the agent
+const weatherAgent = agent({
+  name: "weatherAgent",
+  tools: [weatherTool],
+  llm: openai({ model: "gpt-4.1-mini" }),
+});
+
+// Run with structured output
+const result = await weatherAgent.run("What's the weather in Tokyo?", {
+  responseFormat: responseSchema,
+});
+
+console.log("Natural language result:", result.data.result);
+console.log("Structured data:", result.data.object);
+// Output: { temperature: 72, humidity: 50, windSpeed: 10 }
+```
+
+The agent will:
+1. Use the weather tool to get the raw weather information
+2. Process that information through the LLM
+3. Extract structured data according to your schema
+4. Return both the natural language response and the structured object
+
 ### Event Streaming
 
 Agent Workflows provide a unified interface for event streaming, making it easy to track and respond to different events during execution:

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

@@ -0,0 +1,198 @@
+---
+title: Low-Level LLM Execution
+---
+
+Sometimes your need more control over LLM interactions than what high-level agents provide. The `llm.exec` method makes it simple for you to make a single LLM call with tools but hides the complexity of executing the tools and generating the tool messages.
+
+## When to Use `llm.exec`
+
+Use `llm.exec` when you need to:
+- Build custom agent logic in [workflow](/docs/llamaindex/modules/agents/workflows) steps
+- Have precise control over message handling and tool execution
+- Extract structured data from LLM responses
+
+## Basic Usage
+
+The `llm.exec` method takes messages and tools as parameter and executes one LLM call.
+The LLM might either request to call one or more of the tools or generate an assistant message as result.
+For each tool call that is requested, `llm.exec` executes it and generates the two tool call messages (call and result). If no tool call is requested, just the assistant message is returned. 
+
+```ts
+import { openai } from "@llamaindex/openai";
+import { ChatMessage, tool } from "llamaindex";
+import z from "zod";
+
+const llm = openai({ model: "gpt-4.1-mini" });
+const messages = [
+  {
+    content: "What's the weather like in San Francisco?",
+    role: "user",
+  } as ChatMessage,
+];
+
+const { newMessages, toolCalls } = await llm.exec({
+  messages,
+  tools: [
+    tool({
+      name: "get_weather",
+      description: "Get the current weather for a location",
+      parameters: z.object({
+        address: z.string().describe("The address"),
+      }),
+      execute: ({ address }) => {
+        return `It's sunny in ${address}!`;
+      },
+    }),
+  ],
+});
+
+// Add the new messages (including tool calls and responses) to your conversation
+messages.push(...newMessages);
+```
+
+> `newMessages` is an array as each tool call generates two messages: a tool call message and the tool call result message.
+
+## Structured Output
+
+You can use `responseFormat` with a Zod schema to get structured data from the LLM response:
+
+```ts
+import { openai } from "@llamaindex/openai";
+import { ChatMessage } from "llamaindex";
+import z from "zod";
+
+const llm = openai({ model: "gpt-4.1-mini" });
+
+const schema = z.object({
+  title: z.string(),
+  author: z.string(),
+  year: z.number(),
+});
+
+const messages = [
+  {
+    role: "user",
+    content: "I have been reading La Divina Commedia by Dante Alighieri, published in 1321",
+  } as ChatMessage,
+];
+
+const { newMessages, toolCalls, object } = await llm.exec({
+  messages,
+  responseFormat: schema,
+});
+
+console.log(object); // { title: "La Divina Commedia", author: "Dante Alighieri", year: 1321 }
+```
+
+## Agent Loop Pattern
+
+A common pattern is to use `llm.exec` in a loop until the LLM stops making tool calls:
+
+```ts
+import { openai } from "@llamaindex/openai";
+import { ChatMessage, tool } from "llamaindex";
+import z from "zod";
+
+async function runAgentLoop() {
+  const llm = openai({ model: "gpt-4.1-mini" });
+  const messages = [
+    {
+      content: "What's the weather like in San Francisco?",
+      role: "user",
+    } as ChatMessage,
+  ];
+
+  let exit = false;
+  do {
+    const { newMessages, toolCalls } = await llm.exec({
+      messages,
+      tools: [
+        tool({
+          name: "get_weather",
+          description: "Get the current weather for a location",
+          parameters: z.object({
+            address: z.string().describe("The address"),
+          }),
+          execute: ({ address }) => {
+            return `It's sunny in ${address}!`;
+          },
+        }),
+      ],
+    });
+    
+    console.log(newMessages);
+    messages.push(...newMessages);
+    
+    // Exit when no more tool calls are made
+    exit = toolCalls.length === 0;
+  } while (!exit);
+}
+```
+
+## Streaming Support
+
+For real-time responses, use the `stream` option to get the assistant's response as streamed tokens:
+
+```ts
+import { openai } from "@llamaindex/openai";
+import { ChatMessage, tool } from "llamaindex";
+import z from "zod";
+
+async function streamingAgentLoop() {
+  const llm = openai({ model: "gpt-4o-mini" });
+  const messages = [
+    {
+      content: "What's the weather like in San Francisco?",
+      role: "user",
+    } as ChatMessage,
+  ];
+
+  let exit = false;
+  do {
+    const { stream, newMessages, toolCalls } = await llm.exec({
+      messages,
+      tools: [
+        tool({
+          name: "get_weather",
+          description: "Get the current weather for a location",
+          parameters: z.object({
+            address: z.string().describe("The address"),
+          }),
+          execute: ({ address }) => {
+            return `It's sunny in ${address}!`;
+          },
+        }),
+      ],
+      stream: true,
+    });
+    
+    // Stream the response token by token
+    for await (const chunk of stream) {
+      process.stdout.write(chunk.delta);
+    }
+    
+    messages.push(...newMessages());
+    
+    exit = toolCalls.length === 0;
+  } while (!exit);
+}
+```
+
+> `newMessages` is a function when streaming. The reason is that the result only is available after streaming. Calling it before, will throw an error.
+
+## Return Values
+
+`llm.exec` returns an object with:
+
+- **`newMessages`**: Array of new chat messages including the LLM response and any tool call messages (call or result). This is a function return the array when streaming.
+- **`toolCalls`**: Array of tool calls made by the LLM
+- **`object`**: The structured object when using `responseFormat` with a Zod schema (undefined if no schema is provided)
+- **`stream`**: Async iterable for streaming responses (only when `stream: true`)
+
+## Best Practices
+
+For using `llm.exec` in an agent loop, take care to:
+
+1. **Maintain message history**: Always add `newMessages` to your conversation history
+2. **Set exit conditions**: Implement proper logic to avoid infinite loops
+3. **Handle structured output**: When using `responseFormat`, the `object` property contains your parsed data

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

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

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

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

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

@@ -28,5 +28,4 @@ Here's an example of how to use a managed index together with a chat engine:
 
 ## API Reference
 
-- [LlamaCloudIndex](/docs/api/classes/LlamaCloudIndex)
-- [LlamaCloudRetriever](/docs/api/classes/LlamaCloudRetriever)
+- [LlamaCloud Documentation](https://docs.cloud.llamaindex.ai/)

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

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

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

@@ -78,7 +78,7 @@ As the `PDFReader` is not working with the Edge runtime, here's how to use the `
 
 ```typescript
 import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
-import { LlamaParseReader } from "@llamaindex/cloud";
+import { LlamaParseReader } from "llama-cloud-services";
 
 export const DATA_DIR = "./data";
 

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

@@ -7,7 +7,7 @@ LlamaParse `json` mode supports extracting any images found in a page object by
 ## Installation
 
 ```package-install
-npm i llamaindex @llamaindex/cloud @llamaindex/openai
+npm i llamaindex llama-cloud-services @llamaindex/openai
 ```
 
 ## Usage
@@ -26,7 +26,7 @@ You can create an index across both text and image nodes by requesting alternati
 
 ```ts
 import { Document, ImageNode, VectorStoreIndex } from "llamaindex";
-import { LlamaParseReader } from "@llamaindex/cloud";
+import { LlamaParseReader } from "llama-cloud-services";
 import { OpenAI } from "@llamaindex/openai";
 import { createMessageContent } from "llamaindex";
 

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

@@ -7,7 +7,7 @@ In JSON mode, LlamaParse will return a data structure representing the parsed ob
 ## Installation
 
 ```package-install
-npm i llamaindex @llamaindex/cloud
+npm i llamaindex llama-cloud-services
 ```
 
 ## Usage
@@ -16,7 +16,7 @@ For Json mode, you need to use `loadJson`. The `resultType` is automatically set
 More information about indexing the results on the next page.
 
 ```ts
-import { LlamaParseReader } from "@llamaindex/cloud";
+import { LlamaParseReader } from "llama-cloud-services";
 
 const reader = new LlamaParseReader();
 async function main() {
@@ -68,7 +68,7 @@ However, a simple work around is to create a new reader class that extends `Llam
 
 ```ts
 import { Document } from "llamaindex";
-import { LlamaParseReader } from "@llamaindex/cloud";
+import { LlamaParseReader } from "llama-cloud-services";
 
 class LlamaParseReaderWithJson extends LlamaParseReader {
   // Override the loadData method

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

@@ -5,13 +5,13 @@ title: Bedrock
 ## Installation
 
 ```package-install
-npm i llamaindex @llamaindex/community
+npm i llamaindex @llamaindex/aws
 ```
 
 ## Usage
 
 ```ts
-import { BEDROCK_MODELS, Bedrock } from "@llamaindex/community";
+import { BEDROCK_MODELS, Bedrock } from "@llamaindex/aws";
 
 Settings.llm = new Bedrock({
   model: BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
@@ -23,9 +23,19 @@ Settings.llm = new Bedrock({
 });
 ```
 
-Currently only supports Anthropic and Meta models:
+Supported models are listed below (accessible by BEDROCK_MODELS).
 
 ```ts
+AMAZON_TITAN_TG1_LARGE = "amazon.titan-tg1-large";
+AMAZON_TITAN_TEXT_EXPRESS_V1 = "amazon.titan-text-express-v1";
+AI21_J2_GRANDE_INSTRUCT = "ai21.j2-grande-instruct";
+AI21_J2_JUMBO_INSTRUCT = "ai21.j2-jumbo-instruct";
+AI21_J2_MID = "ai21.j2-mid";
+AI21_J2_MID_V1 = "ai21.j2-mid-v1";
+AI21_J2_ULTRA = "ai21.j2-ultra";
+AI21_J2_ULTRA_V1 = "ai21.j2-ultra-v1";
+COHERE_COMMAND_TEXT_V14 = "cohere.command-text-v14";
+
 ANTHROPIC_CLAUDE_INSTANT_1 = "anthropic.claude-instant-v1";
 ANTHROPIC_CLAUDE_2 = "anthropic.claude-v2";
 ANTHROPIC_CLAUDE_2_1 = "anthropic.claude-v2:1";
@@ -33,7 +43,12 @@ ANTHROPIC_CLAUDE_3_SONNET = "anthropic.claude-3-sonnet-20240229-v1:0";
 ANTHROPIC_CLAUDE_3_HAIKU = "anthropic.claude-3-haiku-20240307-v1:0";
 ANTHROPIC_CLAUDE_3_OPUS = "anthropic.claude-3-opus-20240229-v1:0"; // available on us-west-2
 ANTHROPIC_CLAUDE_3_5_SONNET = "anthropic.claude-3-5-sonnet-20240620-v1:0";
+ANTHROPIC_CLAUDE_3_5_SONNET_V2 = "anthropic.claude-3-5-sonnet-20241022-v2:0";
 ANTHROPIC_CLAUDE_3_5_HAIKU = "anthropic.claude-3-5-haiku-20241022-v1:0";
+ANTHROPIC_CLAUDE_3_7_SONNET = "anthropic.claude-3-7-sonnet-20250219-v1:0";
+ANTHROPIC_CLAUDE_4_SONNET = "anthropic.claude-sonnet-4-20250514-v1:0";
+ANTHROPIC_CLAUDE_4_OPUS = "anthropic.claude-opus-4-20250514-v1:0";
+
 META_LLAMA2_13B_CHAT = "meta.llama2-13b-chat-v1";
 META_LLAMA2_70B_CHAT = "meta.llama2-70b-chat-v1";
 META_LLAMA3_8B_INSTRUCT = "meta.llama3-8b-instruct-v1:0";
@@ -45,41 +60,67 @@ META_LLAMA3_2_1B_INSTRUCT = "meta.llama3-2-1b-instruct-v1:0"; // only available
 META_LLAMA3_2_3B_INSTRUCT = "meta.llama3-2-3b-instruct-v1:0"; // only available via inference endpoints (see below)
 META_LLAMA3_2_11B_INSTRUCT = "meta.llama3-2-11b-instruct-v1:0"; // only available via inference endpoints (see below), multimodal and function call supported
 META_LLAMA3_2_90B_INSTRUCT = "meta.llama3-2-90b-instruct-v1:0"; // only available via inference endpoints (see below), multimodal and function call supported
+META_LLAMA3_3_70B_INSTRUCT = "meta.llama3-3-70b-instruct-v1:0";
+
+MISTRAL_7B_INSTRUCT = "mistral.mistral-7b-instruct-v0:2";
+MISTRAL_MIXTRAL_7B_INSTRUCT = "mistral.mixtral-8x7b-instruct-v0:1";
+MISTRAL_MIXTRAL_LARGE_2402 = "mistral.mistral-large-2402-v1:0";
+
 AMAZON_NOVA_PREMIER_1 = "amazon.nova-premier-v1:0";
 AMAZON_NOVA_PRO_1 = "amazon.nova-pro-v1:0";
 AMAZON_NOVA_LITE_1 = "amazon.nova-lite-v1:0";
 AMAZON_NOVA_MICRO_1 = "amazon.nova-micro-v1:0";
 ```
 
-You can also use Bedrock's Inference endpoints by using the model names:
+You can also use Bedrock's Inference endpoints by using the model names (accessible by INFERENCE_BEDROCK_MODELS).
+Note that the region must be set correctly.
 
 ```ts
-// US
+//US
 US_ANTHROPIC_CLAUDE_3_HAIKU = "us.anthropic.claude-3-haiku-20240307-v1:0";
+US_ANTHROPIC_CLAUDE_3_5_HAIKU = "us.anthropic.claude-3-5-haiku-20241022-v1:0";
 US_ANTHROPIC_CLAUDE_3_OPUS = "us.anthropic.claude-3-opus-20240229-v1:0";
 US_ANTHROPIC_CLAUDE_3_SONNET = "us.anthropic.claude-3-sonnet-20240229-v1:0";
 US_ANTHROPIC_CLAUDE_3_5_SONNET = "us.anthropic.claude-3-5-sonnet-20240620-v1:0";
-US_ANTHROPIC_CLAUDE_3_5_SONNET_V2 =
-  "us.anthropic.claude-3-5-sonnet-20241022-v2:0";
+US_ANTHROPIC_CLAUDE_3_5_SONNET_V2 = "us.anthropic.claude-3-5-sonnet-20241022-v2:0";
+US_ANTHROPIC_CLAUDE_3_7_SONNET = "us.anthropic.claude-3-7-sonnet-20250219-v1:0";
+US_ANTHROPIC_CLAUDE_4_SONNET = "us.anthropic.claude-sonnet-4-20250514-v1:0";
+US_ANTHROPIC_CLAUDE_4_OPUS = "us.anthropic.claude-opus-4-20250514-v1:0";
 US_META_LLAMA_3_2_1B_INSTRUCT = "us.meta.llama3-2-1b-instruct-v1:0";
 US_META_LLAMA_3_2_3B_INSTRUCT = "us.meta.llama3-2-3b-instruct-v1:0";
 US_META_LLAMA_3_2_11B_INSTRUCT = "us.meta.llama3-2-11b-instruct-v1:0";
 US_META_LLAMA_3_2_90B_INSTRUCT = "us.meta.llama3-2-90b-instruct-v1:0";
-US_AMAZON_NOVA_PRO_1 = "us.amazon.nova-premier-v1:0";
+US_META_LLAMA_3_3_70B_INSTRUCT = "us.meta.llama3-3-70b-instruct-v1:0";
+US_AMAZON_NOVA_PREMIER_1 = "us.amazon.nova-premier-v1:0";
 US_AMAZON_NOVA_PRO_1 = "us.amazon.nova-pro-v1:0";
 US_AMAZON_NOVA_LITE_1 = "us.amazon.nova-lite-v1:0";
 US_AMAZON_NOVA_MICRO_1 = "us.amazon.nova-micro-v1:0";
 
-// EU
+//EU
 EU_ANTHROPIC_CLAUDE_3_HAIKU = "eu.anthropic.claude-3-haiku-20240307-v1:0";
+EU_ANTHROPIC_CLAUDE_3_5_HAIKU = "eu.anthropic.claude-3-5-haiku-20240307-v1:0";
 EU_ANTHROPIC_CLAUDE_3_SONNET = "eu.anthropic.claude-3-sonnet-20240229-v1:0";
 EU_ANTHROPIC_CLAUDE_3_5_SONNET = "eu.anthropic.claude-3-5-sonnet-20240620-v1:0";
+EU_ANTHROPIC_CLAUDE_3_7_SONNET = "eu.anthropic.claude-3-7-sonnet-20250219-v1:0";
+EU_ANTHROPIC_CLAUDE_4_SONNET = "eu.anthropic.claude-sonnet-4-20250514-v1:0";
+EU_ANTHROPIC_CLAUDE_4_OPUS = "eu.anthropic.claude-opus-4-20250514-v1:0";
 EU_META_LLAMA_3_2_1B_INSTRUCT = "eu.meta.llama3-2-1b-instruct-v1:0";
 EU_META_LLAMA_3_2_3B_INSTRUCT = "eu.meta.llama3-2-3b-instruct-v1:0";
-EU_AMAZON_NOVA_PRO_1 = "eu.amazon.nova-premier-v1:0";
+EU_AMAZON_NOVA_PREMIER_1 = "eu.amazon.nova-premier-v1:0";
 EU_AMAZON_NOVA_PRO_1 = "eu.amazon.nova-pro-v1:0";
 EU_AMAZON_NOVA_LITE_1 = "eu.amazon.nova-lite-v1:0";
 EU_AMAZON_NOVA_MICRO_1 = "eu.amazon.nova-micro-v1:0";
+
+//APAC
+APAC_ANTHROPIC_CLAUDE_3_5_SONNET = "apac.anthropic.claude-3-5-sonnet-20240620-v1:0";
+APAC_ANTHROPIC_CLAUDE_3_5_SONNET_V2 = "apac.anthropic.claude-3-5-sonnet-20241022-v2:0";
+APAC_ANTHROPIC_CLAUDE_3_7_SONNET = "apac.anthropic.claude-3-7-sonnet-20250219-v1:0";
+APAC_ANTHROPIC_CLAUDE_4_SONNET = "apac.anthropic.claude-sonnet-4-20250514-v1:0";
+APAC_ANTHROPIC_CLAUDE_3_HAIKU = "apac.anthropic.claude-3-haiku-20240307-v1:0";
+APAC_ANTHROPIC_CLAUDE_3_SONNET = "apac.anthropic.claude-3-sonnet-20240229-v1:0";
+APAC_AMAZON_NOVA_PRO_1 = "apac.amazon.nova-pro-v1:0";
+APAC_AMAZON_NOVA_LITE_1 = "apac.amazon.nova-lite-v1:0";
+APAC_AMAZON_NOVA_MICRO_1 = "apac.amazon.nova-micro-v1:0";
 ```
 
 Sonnet, Haiku and Opus are multimodal, image_url only supports base64 data url format, e.g. `data:image/jpeg;base64,SGVsbG8sIFdvcmxkIQ==`
@@ -87,10 +128,11 @@ Sonnet, Haiku and Opus are multimodal, image_url only supports base64 data url f
 ## Full Example
 
 ```ts
-import { BEDROCK_MODELS, Bedrock } from "llamaindex";
+import { INFERENCE_BEDROCK_MODELS, Bedrock } from "@llamaindex/aws";
 
 Settings.llm = new Bedrock({
-  model: BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
+  model: INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_SONNET,
+  region: "us-east-1",
 });
 
 async function main() {
@@ -119,7 +161,7 @@ async function main() {
 ## Agent Example
 
 ```ts
-import { BEDROCK_MODELS, Bedrock } from "@llamaindex/community";
+import { BEDROCK_MODELS, Bedrock } from "@llamaindex/aws";
 import { tool } from "llamaindex";
 import { agent } from "@llamaindex/workflow";
 import { z } from "zod";

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

@@ -4,7 +4,6 @@ title: Retriever
 
 A retriever in LlamaIndex is what is used to fetch `Node`s from an index using a query string.
 
-- [LlamaCloudRetriever](/docs/api/classes/LlamaCloudRetriever) to retrieve nodes from a [managed index](/docs/llamaindex/modules/data/data_index/managed)
 - [VectorIndexRetriever](/docs/api/classes/VectorIndexRetriever) will fetch the top-k most similar nodes. Ideal for dense retrieval to find most relevant nodes.
 - [SummaryIndexRetriever](/docs/api/classes/SummaryIndexRetriever) will fetch all nodes no matter the query. Ideal when complete context is necessary, e.g. analyzing large datasets.
 - [SummaryIndexLLMRetriever](/docs/api/classes/SummaryIndexLLMRetriever) utilizes an LLM to score and filter nodes based on relevancy to the query.

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

@@ -0,0 +1,47 @@
+---
+title: Custom Model Per Request 
+---
+
+There are scenarios, such as the case of a multi-tenant backend API, where it may be required to handle each request with a custom model.
+
+In such a scenario, modifying the `Settings` object directly as follows is not recommended:
+
+```typescript
+import { Settings } from 'llamaindex';
+import { OpenAIEmbedding } from '@llamaindex/embeddings-openai';
+
+Settings.embedModel = new OpenAIEmbedding({ apiKey: 'CLIENT_API_KEY' });
+Settings.llm = openai({ apiKey: key,  model: 'gpt-4o' })
+```
+
+Setting `llm` and `embedModel` directly will lead to unpredictable responses, since `Settings` is global and mutable.
+This can lead to race conditions, as each request modifies `Settings.embedModel` or `Settings.llm`.
+
+The recommended approach is to use `Settings.withEmbedModel` or `Settings.withLLM` as follows:
+
+```typescript
+const embedModel = new OpenAIEmbedding({
+  apiKey: process.env.OPENAI_API_KEY,
+});
+const llm = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
+
+const llmResponse = await Settings.withEmbedModel(embedModel, async () => {
+  return Settings.withLLM(llm, async () => {
+    const path = "node_modules/llamaindex/examples/abramov.txt";
+    const essay = await fs.readFile(path, "utf-8");
+    // Create Document object with essay
+    const document = new Document({ text: essay, id_: path });
+    // Split text and create embeddings. Store them in a VectorStoreIndex
+    const index = await VectorStoreIndex.fromDocuments([document]);
+    // Query the index
+    const queryEngine = index.asQueryEngine();
+    const { message, sourceNodes } = await queryEngine.query({
+      query: "What did the author do in college?",
+    });
+    // Return response with sources
+    return message.content;
+  });
+});
+```
+
+The full example can be found [here](https://github.com/run-llama/LlamaIndexTS/tree/main/examples/local-settings).

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

@@ -93,4 +93,4 @@ async function main() {
 main().catch(console.error);
 ```
 
-You can see the [full example file](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/vectorIndexLocal.ts).
+You can see the [full example file](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/index/vectorIndexLocal.ts).

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

@@ -7,6 +7,7 @@
     "workflows",
     "local_llm",
     "chatbot",
-    "structured_data_extraction"
+    "structured_data_extraction",
+    "custom_model_per_request"
   ]
 }

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

@@ -46,3 +46,31 @@ You should expect output something like:
   ]
 }
 ```
+
+## Using the `exec` method
+
+Many LLMs do not natively support structured output, and often rely exclusively on prompt or context engineering.
+
+In this sense, we proved you with an alternative for structured data extraction, using the `exec` method with `responseFormat`.
+
+For example, you can, in a new folder, install our Anthropic integration and `zod` v3:
+
+```package-install
+npm init
+npm i -D typescript @types/node
+npm i @llamaindex/anthropic zod@3.25.76
+```
+
+And then try extracting data with this code:
+
+<include cwd>../../examples/agents/tools/response-format-exec.ts</include>
+
+The output should look like this:
+
+```json
+{
+  "title": "La Divina Commedia",
+  "author": "Dante Alighieri",
+  "year": 1321
+}
+```

apps/next/src/deps/cloud.ts

@@ -1,96 +0,0 @@
-import {
-  type MetadataFilter,
-  type MetadataFilters,
-  type RetrievalParams,
-  runSearchApiV1PipelinesPipelineIdRetrievePost,
-  type TextNodeWithScore,
-} from "@llamaindex/cloud/api";
-import { QueryBundle } from "@llamaindex/core/query-engine";
-import { BaseRetriever } from "@llamaindex/core/retriever";
-import { jsonToNode, NodeWithScore, ObjectType } from "@llamaindex/core/schema";
-import { extractText } from "@llamaindex/core/utils";
-
-export type CloudRetrieveParams = Omit<
-  RetrievalParams,
-  "query" | "search_filters" | "dense_similarity_top_k"
-> & { similarityTopK?: number; filters?: MetadataFilters };
-
-export type LlamaCloudRetrieverParams = {
-  apiKey: string;
-  baseUrl: string;
-  pipelineId: string;
-} & CloudRetrieveParams;
-
-export class LlamaCloudRetriever extends BaseRetriever {
-  baseUrl: string;
-  apiKey: string;
-
-  retrieveParams: CloudRetrieveParams;
-  organizationId?: string;
-  pipelineId: string;
-
-  private resultNodesToNodeWithScore(
-    nodes: TextNodeWithScore[],
-  ): NodeWithScore[] {
-    return nodes.map((node: TextNodeWithScore) => {
-      const textNode = jsonToNode(node.node, ObjectType.TEXT);
-      textNode.metadata = {
-        ...textNode.metadata,
-        ...node.node.extra_info,
-      };
-      return {
-        node: textNode,
-        score: node.score ?? undefined,
-      };
-    });
-  }
-
-  private convertFilter(filters?: MetadataFilters): MetadataFilters | null {
-    if (!filters) return null;
-
-    const processFilter = (
-      filter: MetadataFilter | MetadataFilters,
-    ): MetadataFilter | MetadataFilters => {
-      if ("filters" in filter) {
-        // type MetadataFilters
-        return { ...filter, filters: filter.filters.map(processFilter) };
-      }
-      return { ...filter, value: filter.value ?? null };
-    };
-
-    return { ...filters, filters: filters.filters.map(processFilter) };
-  }
-
-  constructor(params: LlamaCloudRetrieverParams) {
-    super();
-    this.baseUrl = params.baseUrl;
-    this.apiKey = params.apiKey;
-    this.retrieveParams = params;
-    this.pipelineId = params.pipelineId;
-  }
-
-  override async _retrieve(query: QueryBundle): Promise<NodeWithScore[]> {
-    const filters = this.convertFilter(this.retrieveParams.filters);
-    const pipelineId = this.pipelineId;
-
-    const { data: results } =
-      await runSearchApiV1PipelinesPipelineIdRetrievePost({
-        throwOnError: true,
-        path: {
-          pipeline_id: pipelineId,
-        },
-        baseUrl: this.baseUrl,
-        body: {
-          ...this.retrieveParams,
-          query: extractText(query),
-          search_filters: filters,
-          dense_similarity_top_k: this.retrieveParams.similarityTopK!,
-        },
-        headers: {
-          authorization: `Bearer ${this.apiKey}`,
-        },
-      });
-
-    return this.resultNodesToNodeWithScore(results.retrieval_nodes);
-  }
-}

e2e/examples/cloudflare-hono/package.json

@@ -15,6 +15,6 @@
     "wrangler": "^3.89.0"
   },
   "dependencies": {
-    "hono": "^4.6.11"
+    "hono": "^4.9.7"
   }
 }

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

@@ -1,5 +1,74 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.191
+
+### Patch Changes
+
+- Updated dependencies [d493015]
+  - llamaindex@0.12.0
+
+## 0.0.190
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 0.0.189
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.0.188
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 0.0.187
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.0.186
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
+## 0.0.185
+
+### Patch Changes
+
+- llamaindex@0.11.24
+
+## 0.0.184
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.0.183
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.0.182
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
+## 0.0.181
+
+### Patch Changes
+
+- llamaindex@0.11.20
+
 ## 0.0.180
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.180",
+  "version": "0.0.191",
   "type": "module",
   "private": true,
   "scripts": {

e2e/examples/llama-parse-browser/.gitignore

@@ -1,24 +0,0 @@
-# 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?

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

@@ -1,511 +0,0 @@
-# @llamaindex/llama-parse-browser-test
-
-## 0.0.79
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.24
-
-## 0.0.78
-
-### Patch Changes
-
-- Updated dependencies [a1b1598]
-  - @llamaindex/cloud@4.0.23
-
-## 0.0.77
-
-### Patch Changes
-
-- Updated dependencies [d2be868]
-  - @llamaindex/cloud@4.0.22
-
-## 0.0.76
-
-### Patch Changes
-
-- Updated dependencies [579ca0c]
-  - @llamaindex/cloud@4.0.21
-
-## 0.0.75
-
-### Patch Changes
-
-- Updated dependencies [48b0d88]
-- Updated dependencies [f185772]
-  - @llamaindex/cloud@4.0.20
-
-## 0.0.74
-
-### Patch Changes
-
-- Updated dependencies [5a0ed1f]
-- Updated dependencies [5a0ed1f]
-  - @llamaindex/cloud@4.0.19
-
-## 0.0.73
-
-### Patch Changes
-
-- Updated dependencies [47a7555]
-  - @llamaindex/cloud@4.0.18
-
-## 0.0.72
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.17
-
-## 0.0.71
-
-### Patch Changes
-
-- @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
-
-- @llamaindex/cloud@4.0.13
-
-## 0.0.67
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.12
-
-## 0.0.66
-
-### Patch Changes
-
-- Updated dependencies [76ff23d]
-  - @llamaindex/cloud@4.0.11
-
-## 0.0.65
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.10
-
-## 0.0.64
-
-### Patch Changes
-
-- Updated dependencies [3703f90]
-  - @llamaindex/cloud@4.0.9
-
-## 0.0.63
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.8
-
-## 0.0.62
-
-### Patch Changes
-
-- Updated dependencies [40f5f41]
-  - @llamaindex/cloud@4.0.7
-
-## 0.0.61
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.6
-
-## 0.0.60
-
-### Patch Changes
-
-- Updated dependencies [2225ffd]
-  - @llamaindex/cloud@4.0.5
-
-## 0.0.59
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.4
-
-## 0.0.58
-
-### Patch Changes
-
-- Updated dependencies [41191d0]
-  - @llamaindex/cloud@4.0.3
-
-## 0.0.57
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.2
-
-## 0.0.56
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.1
-
-## 0.0.55
-
-### Patch Changes
-
-- Updated dependencies [bf56fc0]
-- Updated dependencies [5189b44]
-  - @llamaindex/cloud@4.0.0
-
-## 0.0.54
-
-### Patch Changes
-
-- @llamaindex/cloud@3.0.9
-
-## 0.0.53
-
-### Patch Changes
-
-- @llamaindex/cloud@3.0.8
-
-## 0.0.52
-
-### Patch Changes
-
-- @llamaindex/cloud@3.0.7
-
-## 0.0.51
-
-### Patch Changes
-
-- @llamaindex/cloud@3.0.6
-
-## 0.0.50
-
-### Patch Changes
-
-- @llamaindex/cloud@3.0.5
-
-## 0.0.49
-
-### Patch Changes
-
-- @llamaindex/cloud@3.0.4
-
-## 0.0.48
-
-### Patch Changes
-
-- @llamaindex/cloud@3.0.3
-
-## 0.0.47
-
-### Patch Changes
-
-- Updated dependencies [c902fcb]
-  - @llamaindex/cloud@3.0.2
-
-## 0.0.46
-
-### Patch Changes
-
-- @llamaindex/cloud@3.0.1
-
-## 0.0.45
-
-### Patch Changes
-
-- @llamaindex/cloud@3.0.0
-
-## 0.0.44
-
-### Patch Changes
-
-- Updated dependencies [1c908fd]
-  - @llamaindex/cloud@2.0.24
-
-## 0.0.43
-
-### Patch Changes
-
-- Updated dependencies [cb608b5]
-  - @llamaindex/cloud@2.0.23
-
-## 0.0.42
-
-### Patch Changes
-
-- Updated dependencies [d6c270e]
-  - @llamaindex/cloud@2.0.22
-
-## 0.0.41
-
-### Patch Changes
-
-- Updated dependencies [5dec9f9]
-- Updated dependencies [fd9c829]
-  - @llamaindex/cloud@2.0.21
-
-## 0.0.40
-
-### Patch Changes
-
-- Updated dependencies [012495b]
-  - @llamaindex/cloud@2.0.20
-
-## 0.0.39
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.19
-
-## 0.0.38
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.18
-
-## 0.0.37
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.17
-
-## 0.0.36
-
-### Patch Changes
-
-- Updated dependencies [8be4589]
-  - @llamaindex/cloud@2.0.16
-
-## 0.0.35
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.15
-
-## 0.0.34
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.14
-
-## 0.0.33
-
-### Patch Changes
-
-- Updated dependencies [90d265c]
-  - @llamaindex/cloud@2.0.13
-
-## 0.0.32
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.12
-
-## 0.0.31
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.11
-
-## 0.0.30
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.10
-
-## 0.0.29
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.9
-
-## 0.0.28
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.8
-
-## 0.0.27
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.7
-
-## 0.0.26
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.6
-
-## 0.0.25
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.5
-
-## 0.0.24
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.4
-
-## 0.0.23
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.3
-
-## 0.0.22
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.2
-
-## 0.0.21
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.1
-
-## 0.0.20
-
-### Patch Changes
-
-- @llamaindex/cloud@2.0.0
-
-## 0.0.19
-
-### Patch Changes
-
-- @llamaindex/cloud@1.0.8
-
-## 0.0.18
-
-### Patch Changes
-
-- @llamaindex/cloud@1.0.7
-
-## 0.0.17
-
-### Patch Changes
-
-- @llamaindex/cloud@1.0.6
-
-## 0.0.16
-
-### Patch Changes
-
-- @llamaindex/cloud@1.0.5
-
-## 0.0.15
-
-### Patch Changes
-
-- Updated dependencies [06f632b]
-  - @llamaindex/cloud@1.0.4
-
-## 0.0.14
-
-### Patch Changes
-
-- @llamaindex/cloud@1.0.3
-
-## 0.0.13
-
-### Patch Changes
-
-- @llamaindex/cloud@1.0.2
-
-## 0.0.12
-
-### Patch Changes
-
-- Updated dependencies [4c38c1b]
-- Updated dependencies [24d065f]
-- Updated dependencies [a75af83]
-  - @llamaindex/cloud@1.0.1
-
-## 0.0.11
-
-### Patch Changes
-
-- @llamaindex/cloud@1.0.0
-
-## 0.0.10
-
-### Patch Changes
-
-- @llamaindex/cloud@0.2.14
-
-## 0.0.9
-
-### Patch Changes
-
-- @llamaindex/cloud@0.2.13
-
-## 0.0.8
-
-### Patch Changes
-
-- @llamaindex/cloud@0.2.12
-
-## 0.0.7
-
-### Patch Changes
-
-- Updated dependencies [0b20ff9]
-  - @llamaindex/cloud@0.2.11
-
-## 0.0.6
-
-### Patch Changes
-
-- Updated dependencies [981811e]
-  - @llamaindex/cloud@0.2.10
-
-## 0.0.5
-
-### Patch Changes
-
-- Updated dependencies [df441e2]
-  - @llamaindex/cloud@0.2.9
-
-## 0.0.4
-
-### Patch Changes
-
-- Updated dependencies [ac41ed3]
-  - @llamaindex/cloud@0.2.8
-
-## 0.0.3
-
-### Patch Changes
-
-- Updated dependencies [fb36eff]
-- Updated dependencies [d24d3d1]
-  - @llamaindex/cloud@0.2.7
-
-## 0.0.2
-
-### Patch Changes
-
-- Updated dependencies [b42adeb]
-  - @llamaindex/cloud@0.2.6
-
-## 0.0.1
-
-### Patch Changes
-
-- Updated dependencies [85c2e19]
-  - @llamaindex/cloud@0.2.5

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

@@ -1,111 +0,0 @@
-# CLAUDE.md
-
-This file provides guidance to Claude Code (claude.ai/code) when working with the LlamaParse Browser Test example.
-
-## Package Overview
-
-The `@llamaindex/llama-parse-browser-test` package is a minimal browser-based example that demonstrates how to use LlamaParse (from `@llamaindex/cloud`) in a web browser environment. This serves as both an integration test and a reference implementation for browser compatibility with LlamaIndexTS cloud services.
-
-## Purpose
-
-This example validates that:
-
-- `@llamaindex/cloud` package works correctly in browser environments
-- LlamaParse functionality can be bundled and run in web applications
-- The build process properly handles WASM dependencies and browser-specific requirements
-- TypeScript compilation works with DOM APIs and modern bundler tooling
-
-## Development Commands
-
-- `npm run dev` - Start Vite development server with hot reload
-- `npm run build` - Build for production (TypeScript compilation + Vite build)
-- `npm run preview` - Preview the production build locally
-
-## Architecture
-
-### Build Setup
-
-**Bundler**: Vite 6.x with TypeScript support
-**WASM Support**: Uses `vite-plugin-wasm` for WebAssembly module handling
-**Module System**: ESM-only (`"type": "module"`)
-**Target Environment**: Modern browsers (ES2020+)
-
-### Key Configuration
-
-**Vite Config (`vite.config.ts`):**
-
-- `vite-plugin-wasm` - Enables WASM module imports
-- `ssr.external: ["tiktoken"]` - Excludes tiktoken from SSR bundling (browser-only)
-
-**TypeScript Config (`tsconfig.json`):**
-
-- Extends root monorepo TypeScript configuration
-- DOM and DOM.Iterable libraries enabled for browser APIs
-- Bundler module resolution for optimal Vite integration
-- References `@llamaindex/cloud` package for type checking
-
-### Application Structure
-
-**Entry Point (`src/main.ts`):**
-
-- Imports `LlamaParseReader` from `@llamaindex/cloud`
-- Instantiates the reader to test browser compatibility
-- Minimal DOM manipulation for visual feedback
-
-**Styling (`src/style.css`):**
-
-- Modern CSS with light/dark theme support
-- Responsive design with flexbox layout
-- Clean, minimal UI suitable for testing environment
-
-**HTML (`index.html`):**
-
-- Standard Vite HTML template
-- Single-page application structure
-- Module script loading for ES6 imports
-
-## Dependencies
-
-**Core Dependency:**
-
-- `@llamaindex/cloud` (workspace) - LlamaCloud integration including LlamaParse
-
-**Development Dependencies:**
-
-- `vite` - Modern build tool and development server
-- `vite-plugin-wasm` - WebAssembly support for Vite
-- `typescript` - TypeScript compiler and language support
-
-## Testing Integration
-
-This example functions as an end-to-end test by:
-
-1. **Import Validation**: Verifies `@llamaindex/cloud` can be imported in browser context
-2. **Instantiation Testing**: Tests that `LlamaParseReader` can be created without errors
-3. **Bundle Compatibility**: Ensures the build process handles all dependencies correctly
-4. **Runtime Verification**: Validates the application loads and runs in actual browsers
-
-## Browser Compatibility
-
-The application targets modern browsers with:
-
-- ES2020 language features
-- ES Modules support
-- WebAssembly support (for potential WASM dependencies)
-- Modern DOM APIs
-
-## Development Notes
-
-- **Minimal Implementation**: Keeps the example simple to focus on integration testing
-- **Cloud Service Focus**: Specifically tests browser compatibility with LlamaCloud services
-- **Build Validation**: Ensures the build process works end-to-end without browser-specific issues
-- **WASM Preparation**: Configured for WASM dependencies even if not currently used
-- **Type Safety**: Full TypeScript integration with proper DOM type definitions
-
-## Common Issues
-
-- **WASM Loading**: The `vite-plugin-wasm` handles WebAssembly module loading complexities
-- **SSR Exclusions**: Tiktoken is excluded from SSR to prevent Node.js-specific dependencies in browser builds
-- **Module Resolution**: Uses bundler module resolution for optimal compatibility with modern web tooling
-
-This example serves as a foundation for integrating LlamaIndexTS cloud services into web applications and validates that the core cloud functionality works correctly in browser environments.

e2e/examples/llama-parse-browser/index.html

@@ -1,13 +0,0 @@
-<!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 + TS</title>
-  </head>
-  <body>
-    <div id="app"></div>
-    <script type="module" src="/src/main.ts"></script>
-  </body>
-</html>

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

@@ -1,19 +0,0 @@
-{
-  "name": "@llamaindex/llama-parse-browser-test",
-  "private": true,
-  "version": "0.0.79",
-  "type": "module",
-  "scripts": {
-    "dev": "vite",
-    "build": "tsc && vite build",
-    "preview": "vite preview"
-  },
-  "devDependencies": {
-    "typescript": "^5.8.3",
-    "vite": "^6.3.3",
-    "vite-plugin-wasm": "^3.4.1"
-  },
-  "dependencies": {
-    "@llamaindex/cloud": "workspace:*"
-  }
-}

e2e/examples/llama-parse-browser/src/main.ts

@@ -1,10 +0,0 @@
-import { LlamaParseReader } from "@llamaindex/cloud";
-import "./style.css";
-
-new LlamaParseReader();
-
-document.querySelector<HTMLDivElement>("#app")!.innerHTML = `
-  <div>
-    Hello, world!
-  </div>
-`;

e2e/examples/llama-parse-browser/src/style.css

@@ -1,96 +0,0 @@
-:root {
-  font-family: Inter, system-ui, Avenir, Helvetica, Arial, sans-serif;
-  line-height: 1.5;
-  font-weight: 400;
-
-  color-scheme: light dark;
-  color: rgba(255, 255, 255, 0.87);
-  background-color: #242424;
-
-  font-synthesis: none;
-  text-rendering: optimizeLegibility;
-  -webkit-font-smoothing: antialiased;
-  -moz-osx-font-smoothing: grayscale;
-}
-
-a {
-  font-weight: 500;
-  color: #646cff;
-  text-decoration: inherit;
-}
-a:hover {
-  color: #535bf2;
-}
-
-body {
-  margin: 0;
-  display: flex;
-  place-items: center;
-  min-width: 320px;
-  min-height: 100vh;
-}
-
-h1 {
-  font-size: 3.2em;
-  line-height: 1.1;
-}
-
-#app {
-  max-width: 1280px;
-  margin: 0 auto;
-  padding: 2rem;
-  text-align: center;
-}
-
-.logo {
-  height: 6em;
-  padding: 1.5em;
-  will-change: filter;
-  transition: filter 300ms;
-}
-.logo:hover {
-  filter: drop-shadow(0 0 2em #646cffaa);
-}
-.logo.vanilla:hover {
-  filter: drop-shadow(0 0 2em #3178c6aa);
-}
-
-.card {
-  padding: 2em;
-}
-
-.read-the-docs {
-  color: #888;
-}
-
-button {
-  border-radius: 8px;
-  border: 1px solid transparent;
-  padding: 0.6em 1.2em;
-  font-size: 1em;
-  font-weight: 500;
-  font-family: inherit;
-  background-color: #1a1a1a;
-  cursor: pointer;
-  transition: border-color 0.25s;
-}
-button:hover {
-  border-color: #646cff;
-}
-button:focus,
-button:focus-visible {
-  outline: 4px auto -webkit-focus-ring-color;
-}
-
-@media (prefers-color-scheme: light) {
-  :root {
-    color: #213547;
-    background-color: #ffffff;
-  }
-  a:hover {
-    color: #747bff;
-  }
-  button {
-    background-color: #f9f9f9;
-  }
-}

e2e/examples/llama-parse-browser/src/vite-env.d.ts

@@ -1 +0,0 @@
-/// <reference types="vite/client" />

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

@@ -1,26 +0,0 @@
-{
-  "extends": "../../../tsconfig.json",
-  "compilerOptions": {
-    "target": "ES2020",
-    "useDefineForClassFields": true,
-    "module": "ESNext",
-    "lib": ["ES2020", "DOM", "DOM.Iterable"],
-    "skipLibCheck": true,
-    /* Bundler mode */
-    "moduleResolution": "bundler",
-    "allowImportingTsExtensions": true,
-    "isolatedModules": true,
-    "moduleDetection": "force",
-    "noEmit": true,
-    /* Linting */
-    "strict": true,
-    "noUnusedLocals": true,
-    "noUnusedParameters": true,
-    "noFallthroughCasesInSwitch": true
-  },
-  "references": [
-    {
-      "path": "../../../packages/cloud/tsconfig.json"
-    }
-  ]
-}

e2e/examples/llama-parse-browser/vite.config.ts

@@ -1,8 +0,0 @@
-import wasm from "vite-plugin-wasm";
-
-export default {
-  plugins: [wasm()],
-  ssr: {
-    external: ["tiktoken"],
-  },
-};

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,74 @@
 # @llamaindex/next-agent-test
 
+## 0.1.191
+
+### Patch Changes
+
+- Updated dependencies [d493015]
+  - llamaindex@0.12.0
+
+## 0.1.190
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 0.1.189
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.1.188
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 0.1.187
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.1.186
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
+## 0.1.185
+
+### Patch Changes
+
+- llamaindex@0.11.24
+
+## 0.1.184
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.1.183
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.1.182
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
+## 0.1.181
+
+### Patch Changes
+
+- llamaindex@0.11.20
+
 ## 0.1.180
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.180",
+  "version": "0.1.191",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -10,7 +10,7 @@
   "dependencies": {
     "ai": "^4.3.17",
     "llamaindex": "workspace:*",
-    "next": "^15.3.3",
+    "next": "^15.4.7",
     "react": "19.0.0",
     "react-dom": "19.0.0"
   },

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

@@ -1,5 +1,74 @@
 # test-edge-runtime
 
+## 0.1.190
+
+### Patch Changes
+
+- Updated dependencies [d493015]
+  - llamaindex@0.12.0
+
+## 0.1.189
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 0.1.188
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.1.187
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 0.1.186
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.1.185
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
+## 0.1.184
+
+### Patch Changes
+
+- llamaindex@0.11.24
+
+## 0.1.183
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.1.182
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.1.181
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
+## 0.1.180
+
+### Patch Changes
+
+- llamaindex@0.11.20
+
 ## 0.1.179
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.179",
+  "version": "0.1.190",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -9,7 +9,7 @@
   },
   "dependencies": {
     "llamaindex": "workspace:*",
-    "next": "^15.3.3",
+    "next": "^15.4.7",
     "react": "^19.1.0",
     "react-dom": "^19.1.0"
   },

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

@@ -1,5 +1,101 @@
 # @llamaindex/next-node-runtime
 
+## 0.1.62
+
+### Patch Changes
+
+- Updated dependencies [d493015]
+  - llamaindex@0.12.0
+  - @llamaindex/huggingface@0.1.30
+  - @llamaindex/readers@3.1.21
+
+## 0.1.61
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+  - @llamaindex/huggingface@0.1.29
+  - @llamaindex/readers@3.1.20
+
+## 0.1.60
+
+### Patch Changes
+
+- llamaindex@0.11.28
+- @llamaindex/huggingface@0.1.28
+
+## 0.1.59
+
+### Patch Changes
+
+- llamaindex@0.11.27
+- @llamaindex/huggingface@0.1.27
+- @llamaindex/readers@3.1.19
+
+## 0.1.58
+
+### Patch Changes
+
+- @llamaindex/huggingface@0.1.26
+
+## 0.1.57
+
+### Patch Changes
+
+- @llamaindex/huggingface@0.1.25
+
+## 0.1.56
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.1.55
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
+## 0.1.54
+
+### Patch Changes
+
+- llamaindex@0.11.24
+- @llamaindex/huggingface@0.1.24
+- @llamaindex/readers@3.1.18
+
+## 0.1.53
+
+### Patch Changes
+
+- llamaindex@0.11.23
+- @llamaindex/huggingface@0.1.23
+- @llamaindex/readers@3.1.17
+
+## 0.1.52
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.1.51
+
+### Patch Changes
+
+- llamaindex@0.11.21
+- @llamaindex/huggingface@0.1.22
+- @llamaindex/readers@3.1.16
+
+## 0.1.50
+
+### Patch Changes
+
+- llamaindex@0.11.20
+- @llamaindex/huggingface@0.1.21
+- @llamaindex/readers@3.1.15
+
 ## 0.1.49
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.49",
+  "version": "0.1.62",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -11,7 +11,7 @@
     "@llamaindex/huggingface": "workspace:*",
     "@llamaindex/readers": "workspace:*",
     "llamaindex": "workspace:*",
-    "next": "^15.3.3",
+    "next": "^15.4.7",
     "react": "19.0.0",
     "react-dom": "19.0.0"
   },

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

@@ -1,5 +1,74 @@
 # vite-import-llamaindex
 
+## 0.0.57
+
+### Patch Changes
+
+- Updated dependencies [d493015]
+  - llamaindex@0.12.0
+
+## 0.0.56
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 0.0.55
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.0.54
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 0.0.53
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.0.52
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
+## 0.0.51
+
+### Patch Changes
+
+- llamaindex@0.11.24
+
+## 0.0.50
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.0.49
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.0.48
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
+## 0.0.47
+
+### Patch Changes
+
+- llamaindex@0.11.20
+
 ## 0.0.46
 
 ### Patch Changes

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

@@ -1,11 +1,12 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.46",
+  "version": "0.0.57",
   "type": "module",
   "scripts": {
     "build": "vite build",
-    "size-limit": "size-limit"
+    "size-limit": "size-limit",
+    "ci-build": "pnpm -C ../../../ build && vite build"
   },
   "size-limit": [
     {
@@ -16,7 +17,7 @@
     "@size-limit/preset-big-lib": "^11.1.6",
     "size-limit": "^11.1.6",
     "typescript": "^5.8.3",
-    "vite": "^6.3.3"
+    "vite": "^6.3.6"
   },
   "dependencies": {
     "llamaindex": "workspace:*"

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

@@ -1,5 +1,74 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.191
+
+### Patch Changes
+
+- Updated dependencies [d493015]
+  - llamaindex@0.12.0
+
+## 0.0.190
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 0.0.189
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.0.188
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 0.0.187
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.0.186
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
+## 0.0.185
+
+### Patch Changes
+
+- llamaindex@0.11.24
+
+## 0.0.184
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.0.183
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.0.182
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
+## 0.0.181
+
+### Patch Changes
+
+- llamaindex@0.11.20
+
 ## 0.0.180
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.180",
+  "version": "0.0.191",
   "type": "module",
   "private": true,
   "scripts": {

e2e/node/fixtures/tools.ts

@@ -44,9 +44,7 @@ export const getWeatherTool = FunctionTool.from(
     name: "getWeather",
     description: "Get the weather for a city",
     parameters: z.object({
-      city: z.string({
-        description: "The city to get the weather for",
-      }),
+      city: z.string().describe("The city to get the weather for"),
     }),
   },
 );

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

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

examples/CHANGELOG.md

@@ -1,5 +1,453 @@
 # examples
 
+## 0.3.42
+
+### Patch Changes
+
+- Updated dependencies [06f884a]
+- Updated dependencies [06f884a]
+- Updated dependencies [d493015]
+  - @llamaindex/core@0.6.22
+  - @llamaindex/workflow@1.1.24
+  - llamaindex@0.12.0
+  - @llamaindex/node-parser@2.0.22
+  - @llamaindex/anthropic@0.3.25
+  - @llamaindex/assemblyai@0.1.21
+  - @llamaindex/clip@0.0.76
+  - @llamaindex/cohere@0.0.36
+  - @llamaindex/deepinfra@0.0.76
+  - @llamaindex/discord@0.1.21
+  - @llamaindex/google@0.3.22
+  - @llamaindex/huggingface@0.1.30
+  - @llamaindex/jinaai@0.0.36
+  - @llamaindex/mistral@0.1.22
+  - @llamaindex/mixedbread@0.0.36
+  - @llamaindex/notion@0.1.21
+  - @llamaindex/ollama@0.1.23
+  - @llamaindex/openai@0.4.20
+  - @llamaindex/perplexity@0.0.33
+  - @llamaindex/portkey-ai@0.0.64
+  - @llamaindex/replicate@0.0.64
+  - @llamaindex/bm25-retriever@0.0.11
+  - @llamaindex/astra@0.0.36
+  - @llamaindex/azure@0.1.37
+  - @llamaindex/chroma@0.0.36
+  - @llamaindex/elastic-search@0.1.22
+  - @llamaindex/firestore@1.0.29
+  - @llamaindex/milvus@0.1.31
+  - @llamaindex/mongodb@0.0.37
+  - @llamaindex/pinecone@0.1.22
+  - @llamaindex/postgres@0.0.65
+  - @llamaindex/qdrant@0.1.32
+  - @llamaindex/supabase@0.1.23
+  - @llamaindex/upstash@0.0.36
+  - @llamaindex/weaviate@0.0.37
+  - @llamaindex/vercel@0.1.22
+  - @llamaindex/voyage-ai@1.0.28
+  - @llamaindex/readers@3.1.21
+  - @llamaindex/tools@0.1.12
+  - @llamaindex/deepseek@0.0.38
+  - @llamaindex/fireworks@0.0.36
+  - @llamaindex/groq@0.0.92
+  - @llamaindex/together@0.0.36
+  - @llamaindex/vllm@0.0.62
+  - @llamaindex/xai@0.0.23
+
+## 0.3.41
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+- Updated dependencies [5da1cda]
+- Updated dependencies [5d5cd44]
+- Updated dependencies [c40adaf]
+  - llamaindex@0.11.29
+  - @llamaindex/core@0.6.21
+  - @llamaindex/tools@0.1.11
+  - @llamaindex/workflow@1.1.23
+  - @llamaindex/ollama@0.1.22
+  - @llamaindex/openai@0.4.19
+  - @llamaindex/vercel@0.1.21
+  - @llamaindex/anthropic@0.3.24
+  - @llamaindex/google@0.3.21
+  - @llamaindex/cloud@4.1.3
+  - @llamaindex/node-parser@2.0.21
+  - @llamaindex/assemblyai@0.1.20
+  - @llamaindex/clip@0.0.75
+  - @llamaindex/cohere@0.0.35
+  - @llamaindex/deepinfra@0.0.75
+  - @llamaindex/discord@0.1.20
+  - @llamaindex/huggingface@0.1.29
+  - @llamaindex/jinaai@0.0.35
+  - @llamaindex/mistral@0.1.21
+  - @llamaindex/mixedbread@0.0.35
+  - @llamaindex/notion@0.1.20
+  - @llamaindex/perplexity@0.0.32
+  - @llamaindex/portkey-ai@0.0.63
+  - @llamaindex/replicate@0.0.63
+  - @llamaindex/bm25-retriever@0.0.10
+  - @llamaindex/astra@0.0.35
+  - @llamaindex/azure@0.1.36
+  - @llamaindex/chroma@0.0.35
+  - @llamaindex/elastic-search@0.1.21
+  - @llamaindex/firestore@1.0.28
+  - @llamaindex/milvus@0.1.30
+  - @llamaindex/mongodb@0.0.36
+  - @llamaindex/pinecone@0.1.21
+  - @llamaindex/postgres@0.0.64
+  - @llamaindex/qdrant@0.1.31
+  - @llamaindex/supabase@0.1.22
+  - @llamaindex/upstash@0.0.35
+  - @llamaindex/weaviate@0.0.36
+  - @llamaindex/voyage-ai@1.0.27
+  - @llamaindex/readers@3.1.20
+  - @llamaindex/deepseek@0.0.37
+  - @llamaindex/fireworks@0.0.35
+  - @llamaindex/groq@0.0.91
+  - @llamaindex/together@0.0.35
+  - @llamaindex/vllm@0.0.61
+  - @llamaindex/xai@0.0.22
+
+## 0.3.40
+
+### Patch Changes
+
+- Updated dependencies [1995b38]
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/workflow@1.1.22
+  - @llamaindex/openai@0.4.18
+  - llamaindex@0.11.28
+  - @llamaindex/clip@0.0.74
+  - @llamaindex/deepinfra@0.0.74
+  - @llamaindex/deepseek@0.0.36
+  - @llamaindex/fireworks@0.0.34
+  - @llamaindex/groq@0.0.90
+  - @llamaindex/huggingface@0.1.28
+  - @llamaindex/jinaai@0.0.34
+  - @llamaindex/perplexity@0.0.31
+  - @llamaindex/azure@0.1.35
+  - @llamaindex/together@0.0.34
+  - @llamaindex/vllm@0.0.60
+  - @llamaindex/xai@0.0.21
+
+## 0.3.39
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+  - @llamaindex/cloud@4.1.2
+  - llamaindex@0.11.27
+  - @llamaindex/node-parser@2.0.20
+  - @llamaindex/anthropic@0.3.23
+  - @llamaindex/assemblyai@0.1.19
+  - @llamaindex/clip@0.0.73
+  - @llamaindex/cohere@0.0.34
+  - @llamaindex/deepinfra@0.0.73
+  - @llamaindex/discord@0.1.19
+  - @llamaindex/google@0.3.20
+  - @llamaindex/huggingface@0.1.27
+  - @llamaindex/jinaai@0.0.33
+  - @llamaindex/mistral@0.1.20
+  - @llamaindex/mixedbread@0.0.34
+  - @llamaindex/notion@0.1.19
+  - @llamaindex/ollama@0.1.21
+  - @llamaindex/openai@0.4.17
+  - @llamaindex/perplexity@0.0.30
+  - @llamaindex/portkey-ai@0.0.62
+  - @llamaindex/replicate@0.0.62
+  - @llamaindex/bm25-retriever@0.0.9
+  - @llamaindex/astra@0.0.34
+  - @llamaindex/azure@0.1.34
+  - @llamaindex/chroma@0.0.34
+  - @llamaindex/elastic-search@0.1.20
+  - @llamaindex/firestore@1.0.27
+  - @llamaindex/milvus@0.1.29
+  - @llamaindex/mongodb@0.0.35
+  - @llamaindex/pinecone@0.1.20
+  - @llamaindex/postgres@0.0.63
+  - @llamaindex/qdrant@0.1.30
+  - @llamaindex/supabase@0.1.21
+  - @llamaindex/upstash@0.0.34
+  - @llamaindex/weaviate@0.0.35
+  - @llamaindex/vercel@0.1.20
+  - @llamaindex/voyage-ai@1.0.26
+  - @llamaindex/readers@3.1.19
+  - @llamaindex/tools@0.1.10
+  - @llamaindex/workflow@1.1.21
+  - @llamaindex/deepseek@0.0.35
+  - @llamaindex/fireworks@0.0.33
+  - @llamaindex/groq@0.0.89
+  - @llamaindex/together@0.0.33
+  - @llamaindex/vllm@0.0.59
+  - @llamaindex/xai@0.0.20
+
+## 0.3.38
+
+### Patch Changes
+
+- Updated dependencies [4c70376]
+  - @llamaindex/openai@0.4.16
+  - @llamaindex/clip@0.0.72
+  - @llamaindex/deepinfra@0.0.72
+  - @llamaindex/deepseek@0.0.34
+  - @llamaindex/fireworks@0.0.32
+  - @llamaindex/groq@0.0.88
+  - @llamaindex/huggingface@0.1.26
+  - @llamaindex/jinaai@0.0.32
+  - @llamaindex/perplexity@0.0.29
+  - @llamaindex/azure@0.1.33
+  - @llamaindex/together@0.0.32
+  - @llamaindex/vllm@0.0.58
+  - @llamaindex/xai@0.0.19
+
+## 0.3.37
+
+### Patch Changes
+
+- Updated dependencies [47a6f5f]
+- Updated dependencies [b80f33e]
+- Updated dependencies [b6409b6]
+- Updated dependencies [b80f33e]
+  - @llamaindex/ollama@0.1.20
+  - @llamaindex/anthropic@0.3.22
+  - @llamaindex/openai@0.4.15
+  - @llamaindex/clip@0.0.71
+  - @llamaindex/deepinfra@0.0.71
+  - @llamaindex/deepseek@0.0.33
+  - @llamaindex/fireworks@0.0.31
+  - @llamaindex/groq@0.0.87
+  - @llamaindex/huggingface@0.1.25
+  - @llamaindex/jinaai@0.0.31
+  - @llamaindex/perplexity@0.0.28
+  - @llamaindex/azure@0.1.32
+  - @llamaindex/together@0.0.31
+  - @llamaindex/vllm@0.0.57
+  - @llamaindex/xai@0.0.18
+
+## 0.3.36
+
+### Patch Changes
+
+- Updated dependencies [4b51791]
+- Updated dependencies [971d37c]
+  - @llamaindex/cloud@4.1.1
+  - @llamaindex/deepseek@0.0.32
+  - llamaindex@0.11.26
+
+## 0.3.35
+
+### Patch Changes
+
+- Updated dependencies [c3bf3c7]
+- Updated dependencies [f9f1de9]
+  - @llamaindex/cloud@4.0.28
+  - @llamaindex/core@0.6.19
+  - llamaindex@0.11.24
+  - @llamaindex/node-parser@2.0.19
+  - @llamaindex/anthropic@0.3.21
+  - @llamaindex/assemblyai@0.1.18
+  - @llamaindex/clip@0.0.70
+  - @llamaindex/cohere@0.0.33
+  - @llamaindex/deepinfra@0.0.70
+  - @llamaindex/discord@0.1.18
+  - @llamaindex/google@0.3.18
+  - @llamaindex/huggingface@0.1.24
+  - @llamaindex/jinaai@0.0.30
+  - @llamaindex/mistral@0.1.19
+  - @llamaindex/mixedbread@0.0.33
+  - @llamaindex/notion@0.1.18
+  - @llamaindex/ollama@0.1.19
+  - @llamaindex/openai@0.4.14
+  - @llamaindex/perplexity@0.0.27
+  - @llamaindex/portkey-ai@0.0.61
+  - @llamaindex/replicate@0.0.61
+  - @llamaindex/bm25-retriever@0.0.8
+  - @llamaindex/astra@0.0.33
+  - @llamaindex/azure@0.1.31
+  - @llamaindex/chroma@0.0.33
+  - @llamaindex/elastic-search@0.1.19
+  - @llamaindex/firestore@1.0.26
+  - @llamaindex/milvus@0.1.28
+  - @llamaindex/mongodb@0.0.34
+  - @llamaindex/pinecone@0.1.19
+  - @llamaindex/postgres@0.0.62
+  - @llamaindex/qdrant@0.1.29
+  - @llamaindex/supabase@0.1.20
+  - @llamaindex/upstash@0.0.33
+  - @llamaindex/weaviate@0.0.34
+  - @llamaindex/vercel@0.1.19
+  - @llamaindex/voyage-ai@1.0.25
+  - @llamaindex/readers@3.1.18
+  - @llamaindex/tools@0.1.9
+  - @llamaindex/workflow@1.1.20
+  - @llamaindex/deepseek@0.0.31
+  - @llamaindex/fireworks@0.0.30
+  - @llamaindex/groq@0.0.86
+  - @llamaindex/together@0.0.30
+  - @llamaindex/vllm@0.0.56
+  - @llamaindex/xai@0.0.17
+
+## 0.3.34
+
+### Patch Changes
+
+- Updated dependencies [f29799e]
+- Updated dependencies [7224c06]
+  - @llamaindex/workflow@1.1.19
+  - @llamaindex/core@0.6.18
+  - llamaindex@0.11.23
+  - @llamaindex/cloud@4.0.27
+  - @llamaindex/node-parser@2.0.18
+  - @llamaindex/anthropic@0.3.20
+  - @llamaindex/assemblyai@0.1.17
+  - @llamaindex/clip@0.0.69
+  - @llamaindex/cohere@0.0.32
+  - @llamaindex/deepinfra@0.0.69
+  - @llamaindex/discord@0.1.17
+  - @llamaindex/google@0.3.17
+  - @llamaindex/huggingface@0.1.23
+  - @llamaindex/jinaai@0.0.29
+  - @llamaindex/mistral@0.1.18
+  - @llamaindex/mixedbread@0.0.32
+  - @llamaindex/notion@0.1.17
+  - @llamaindex/ollama@0.1.18
+  - @llamaindex/openai@0.4.13
+  - @llamaindex/perplexity@0.0.26
+  - @llamaindex/portkey-ai@0.0.60
+  - @llamaindex/replicate@0.0.60
+  - @llamaindex/bm25-retriever@0.0.7
+  - @llamaindex/astra@0.0.32
+  - @llamaindex/azure@0.1.30
+  - @llamaindex/chroma@0.0.32
+  - @llamaindex/elastic-search@0.1.18
+  - @llamaindex/firestore@1.0.25
+  - @llamaindex/milvus@0.1.27
+  - @llamaindex/mongodb@0.0.33
+  - @llamaindex/pinecone@0.1.18
+  - @llamaindex/postgres@0.0.61
+  - @llamaindex/qdrant@0.1.28
+  - @llamaindex/supabase@0.1.19
+  - @llamaindex/upstash@0.0.32
+  - @llamaindex/weaviate@0.0.33
+  - @llamaindex/vercel@0.1.18
+  - @llamaindex/voyage-ai@1.0.24
+  - @llamaindex/readers@3.1.17
+  - @llamaindex/tools@0.1.8
+  - @llamaindex/deepseek@0.0.30
+  - @llamaindex/fireworks@0.0.29
+  - @llamaindex/groq@0.0.85
+  - @llamaindex/together@0.0.29
+  - @llamaindex/vllm@0.0.55
+  - @llamaindex/xai@0.0.16
+
+## 0.3.33
+
+### Patch Changes
+
+- Updated dependencies [38da40b]
+  - @llamaindex/core@0.6.17
+  - @llamaindex/cloud@4.0.26
+  - llamaindex@0.11.21
+  - @llamaindex/node-parser@2.0.17
+  - @llamaindex/anthropic@0.3.19
+  - @llamaindex/assemblyai@0.1.16
+  - @llamaindex/clip@0.0.68
+  - @llamaindex/cohere@0.0.31
+  - @llamaindex/deepinfra@0.0.68
+  - @llamaindex/discord@0.1.16
+  - @llamaindex/google@0.3.16
+  - @llamaindex/huggingface@0.1.22
+  - @llamaindex/jinaai@0.0.28
+  - @llamaindex/mistral@0.1.17
+  - @llamaindex/mixedbread@0.0.31
+  - @llamaindex/notion@0.1.16
+  - @llamaindex/ollama@0.1.17
+  - @llamaindex/openai@0.4.12
+  - @llamaindex/perplexity@0.0.25
+  - @llamaindex/portkey-ai@0.0.59
+  - @llamaindex/replicate@0.0.59
+  - @llamaindex/bm25-retriever@0.0.6
+  - @llamaindex/astra@0.0.31
+  - @llamaindex/azure@0.1.29
+  - @llamaindex/chroma@0.0.31
+  - @llamaindex/elastic-search@0.1.17
+  - @llamaindex/firestore@1.0.24
+  - @llamaindex/milvus@0.1.26
+  - @llamaindex/mongodb@0.0.32
+  - @llamaindex/pinecone@0.1.17
+  - @llamaindex/postgres@0.0.60
+  - @llamaindex/qdrant@0.1.27
+  - @llamaindex/supabase@0.1.18
+  - @llamaindex/upstash@0.0.31
+  - @llamaindex/weaviate@0.0.32
+  - @llamaindex/vercel@0.1.17
+  - @llamaindex/voyage-ai@1.0.23
+  - @llamaindex/readers@3.1.16
+  - @llamaindex/tools@0.1.7
+  - @llamaindex/workflow@1.1.17
+  - @llamaindex/deepseek@0.0.29
+  - @llamaindex/fireworks@0.0.28
+  - @llamaindex/groq@0.0.84
+  - @llamaindex/together@0.0.28
+  - @llamaindex/vllm@0.0.54
+  - @llamaindex/xai@0.0.15
+
+## 0.3.32
+
+### Patch Changes
+
+- Updated dependencies [650eeb1]
+- Updated dependencies [a8ec08c]
+- Updated dependencies [2967d57]
+  - @llamaindex/google@0.3.15
+  - @llamaindex/core@0.6.16
+  - @llamaindex/workflow@1.1.16
+  - @llamaindex/cloud@4.0.25
+  - llamaindex@0.11.20
+  - @llamaindex/node-parser@2.0.16
+  - @llamaindex/anthropic@0.3.18
+  - @llamaindex/assemblyai@0.1.15
+  - @llamaindex/clip@0.0.67
+  - @llamaindex/cohere@0.0.30
+  - @llamaindex/deepinfra@0.0.67
+  - @llamaindex/discord@0.1.15
+  - @llamaindex/huggingface@0.1.21
+  - @llamaindex/jinaai@0.0.27
+  - @llamaindex/mistral@0.1.16
+  - @llamaindex/mixedbread@0.0.30
+  - @llamaindex/notion@0.1.15
+  - @llamaindex/ollama@0.1.16
+  - @llamaindex/openai@0.4.11
+  - @llamaindex/perplexity@0.0.24
+  - @llamaindex/portkey-ai@0.0.58
+  - @llamaindex/replicate@0.0.58
+  - @llamaindex/bm25-retriever@0.0.5
+  - @llamaindex/astra@0.0.30
+  - @llamaindex/azure@0.1.28
+  - @llamaindex/chroma@0.0.30
+  - @llamaindex/elastic-search@0.1.16
+  - @llamaindex/firestore@1.0.23
+  - @llamaindex/milvus@0.1.25
+  - @llamaindex/mongodb@0.0.31
+  - @llamaindex/pinecone@0.1.16
+  - @llamaindex/postgres@0.0.59
+  - @llamaindex/qdrant@0.1.26
+  - @llamaindex/supabase@0.1.17
+  - @llamaindex/upstash@0.0.30
+  - @llamaindex/weaviate@0.0.31
+  - @llamaindex/vercel@0.1.16
+  - @llamaindex/voyage-ai@1.0.22
+  - @llamaindex/readers@3.1.15
+  - @llamaindex/tools@0.1.6
+  - @llamaindex/deepseek@0.0.28
+  - @llamaindex/fireworks@0.0.27
+  - @llamaindex/groq@0.0.83
+  - @llamaindex/together@0.0.27
+  - @llamaindex/vllm@0.0.53
+  - @llamaindex/xai@0.0.14
+
 ## 0.3.31
 
 ### Patch Changes

examples/agents/agent/blog-writer.ts

@@ -20,9 +20,7 @@ const saveFileTool = tool({
   description:
     "Save the written content into a file that can be downloaded by the user",
   parameters: z.object({
-    content: z.string({
-      description: "The content to save into a file",
-    }),
+    content: z.string().describe("The content to save into a file"),
   }),
   execute: ({ content }: { content: string }) => {
     const filePath = os.tmpdir() + "/report.md";

examples/agents/agent/large-toolcall.ts

@@ -17,9 +17,7 @@ const userQuestion = "which are the best comedies after 2010?";
     description:
       "Execute python code in a Jupyter notebook cell and return any result, stdout, stderr, display_data, and error.",
     parameters: z.object({
-      code: z.string({
-        description: "The python code to execute in a single cell.",
-      }),
+      code: z.string().describe("The python code to execute in a single cell."),
     }),
     execute: ({ code }) => {
       console.log(

examples/agents/agent/multiple-agents.ts

@@ -26,9 +26,7 @@ const temperatureConverterTool = tool({
   description: "Convert a temperature from Fahrenheit to Celsius",
   name: "fahrenheitToCelsius",
   parameters: z.object({
-    temperature: z.number({
-      description: "The temperature in Fahrenheit",
-    }),
+    temperature: z.number().describe("The temperature in Fahrenheit"),
   }),
   execute: ({ temperature }) => {
     return ((temperature - 32) * 5) / 9;
@@ -39,9 +37,7 @@ const temperatureFetcherTool = tool({
   description: "Fetch the temperature (in Fahrenheit) for a city",
   name: "fetchTemperature",
   parameters: z.object({
-    city: z.string({
-      description: "The city to fetch the temperature for",
-    }),
+    city: z.string().describe("The city to fetch the temperature for"),
   }),
   execute: ({ city }) => {
     const temperature = Math.floor(Math.random() * 58) + 32;

examples/agents/agent/single-agent.ts

@@ -24,6 +24,7 @@ async function main() {
     state: result.data.state,
   });
   console.log(`${JSON.stringify(caResult, null, 2)}`);
+  console.log("assistant message:", result.data.message);
 }
 
 main().catch((error) => {

examples/agents/agent/structured-object.ts

@@ -0,0 +1,39 @@
+import { z } from "zod";
+
+import { openai } from "@llamaindex/openai";
+import { agent } from "@llamaindex/workflow";
+import { tool } from "llamaindex";
+
+const weatherTool = tool({
+  name: "weatherTool",
+  description: "Get weather information",
+  parameters: z.object({
+    location: z.string(),
+  }),
+  execute: ({ location }) => {
+    return `The weather in ${location} is sunny. The temperature is 72 degrees. The humidity is 50%. The wind speed is 10 mph.`;
+  },
+});
+
+const responseSchema = z.object({
+  temperature: z.number(),
+  humidity: z.number(),
+  windSpeed: z.number(),
+});
+
+const myAgent = agent({
+  name: "myAgent",
+  tools: [weatherTool],
+  llm: openai({ model: "gpt-4.1-mini" }),
+});
+
+async function main() {
+  const result = await myAgent.run("What's the weather in Tokyo?", {
+    responseFormat: responseSchema,
+  });
+
+  console.log("result.data.result: ", result.data.result);
+  console.log("result.data.object: ", result.data.object);
+}
+
+main().catch(console.error);

examples/agents/agent/with-anthropic.ts

@@ -14,9 +14,7 @@ const weatherTool = tool({
   name: "weather",
   description: "Get the weather",
   parameters: z.object({
-    location: z.string({
-      description: "The location to get the weather for",
-    }),
+    location: z.string().describe("The location to get the weather for"),
   }),
   execute: ({ location }) => {
     return `The weather in ${location} is sunny`;
@@ -27,9 +25,7 @@ const inflationTool = tool({
   name: "inflation",
   description: "Get the inflation",
   parameters: z.object({
-    location: z.string({
-      description: "The location to get the inflation for",
-    }),
+    location: z.string().describe("The location to get the inflation for"),
   }),
   execute: ({ location }) => {
     return `The inflation in ${location} is 2%`;
@@ -41,9 +37,7 @@ const saveFileTool = tool({
   description:
     "Save the written content into a file that can be downloaded by the user",
   parameters: z.object({
-    content: z.string({
-      description: "The content to save into a file",
-    }),
+    content: z.string().describe("The content to save into a file"),
   }),
   execute: ({ content }) => {
     const filePath = "./report.md";

examples/agents/memory/vector-block.ts

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

examples/agents/natural/joke.ts

@@ -14,11 +14,8 @@ const writeJokeSchema = z.object({
     .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.",
-    ),
+    .optional(z.number().default(0))
+    .describe("The retried times for writing the joke."),
 });
 
 const critiqueSchema = z.object({

examples/agents/tools/exec-object.ts

@@ -0,0 +1,48 @@
+import { openai } from "@llamaindex/openai";
+import { ChatMessage } from "llamaindex";
+import z from "zod";
+
+const llm = openai({ model: "gpt-4.1-mini" });
+
+const schema = z.object({
+  title: z.string(),
+  author: z.string(),
+  year: z.number(),
+});
+
+const messages: ChatMessage[] = [
+  {
+    role: "user",
+    content: `I have been reading La Divina Commedia by Dante Alighieri, published in 1321`,
+  },
+];
+
+async function main() {
+  {
+    // Non-streaming
+    const { object } = await llm.exec({ messages, responseFormat: schema });
+    console.log("Non-streaming object:", object);
+  }
+
+  {
+    // Streaming
+    let exit = false;
+    do {
+      const { stream, newMessages, toolCalls, object } = await llm.exec({
+        messages,
+        stream: true,
+        responseFormat: schema,
+      });
+
+      for await (const chunk of stream) {
+        console.log(chunk.delta);
+      }
+      console.log("Streaming object:", object);
+
+      messages.push(...newMessages());
+      exit = toolCalls.length === 0;
+    } while (!exit);
+  }
+}
+
+main().catch(console.error);

examples/agents/tools/response-format-exec.ts

@@ -0,0 +1,41 @@
+import { Anthropic } from "@llamaindex/anthropic";
+import { ChatMessage, ToolCall } from "llamaindex";
+import { z } from "zod";
+
+const llm = new Anthropic({ model: "claude-4-0-sonnet" });
+
+const responseSchema = z.object({
+  title: z.string().describe("The title of the book"),
+  author: z.string().describe("The author of the book"),
+  year: z.number().describe("The publication year"),
+});
+
+async function main() {
+  const messages: ChatMessage[] = [];
+  let toolCalls: ToolCall[] = [];
+  let object: z.infer<typeof responseSchema> | undefined;
+  do {
+    const result = await llm.exec({
+      messages: [
+        {
+          role: "system",
+          content: `You are a book expert. Your task is, given a user message, extract the title, author and publication year of the book and output them in JSON format.`,
+        },
+        {
+          role: "user",
+          content: `I have been reading La Divina Commedia by Dante Alighieri, published in 1321, which tells the story of a guy who goes through Hell, Purgatory and Heaven just to meet his beloved ex-girlfriend.`,
+        },
+      ],
+      responseFormat: responseSchema,
+    });
+    object = result.object;
+    messages.push(...result.newMessages);
+    toolCalls = result.toolCalls;
+  } while (toolCalls.length == 0);
+
+  console.log(messages);
+  console.log(toolCalls);
+  console.log(object);
+}
+
+main().catch(console.error);

examples/agents/workflow/joke.ts

@@ -22,7 +22,7 @@ const { withState, getContext } = createStatefulMiddleware(() => ({
 const jokeFlow = withState(createWorkflow());
 
 // Define handlers for each step
-jokeFlow.handle([startEvent], async (event) => {
+jokeFlow.handle([startEvent], async (context, event) => {
   // Prompt the LLM to write a joke
   const prompt = `Write your best joke about ${event.data}. Write the joke between <joke> and </joke> tags.`;
   const response = await llm.complete({ prompt });
@@ -34,7 +34,7 @@ jokeFlow.handle([startEvent], async (event) => {
   return jokeEvent.with({ joke: joke });
 });
 
-jokeFlow.handle([jokeEvent], async (event) => {
+jokeFlow.handle([jokeEvent], async (context, event) => {
   // Prompt the LLM to critique the joke
   const prompt = `Give a thorough critique of the following joke. If the joke needs improvement, put "IMPROVE" somewhere in the critique: ${event.data.joke}`;
   const response = await llm.complete({ prompt });
@@ -50,9 +50,9 @@ jokeFlow.handle([jokeEvent], async (event) => {
   return resultEvent.with({ joke: event.data.joke, critique: response.text });
 });
 
-jokeFlow.handle([critiqueEvent], async (event) => {
+jokeFlow.handle([critiqueEvent], async (context, event) => {
   // Keep track of the number of iterations
-  const state = getContext().state;
+  const state = context.state;
   state.numIterations++;
 
   // Write a new joke based on the previous joke and critique

examples/cloud/chat.ts

@@ -1,7 +1,8 @@
 import { stdin as input, stdout as output } from "node:process";
 import readline from "node:readline/promises";
 
-import { ContextChatEngine, LlamaCloudIndex } from "llamaindex";
+import { LlamaCloudIndex } from "llama-cloud-services";
+import { ContextChatEngine } from "llamaindex";
 
 async function main() {
   const index = new LlamaCloudIndex({

examples/cloud/from-documents.ts

@@ -4,7 +4,8 @@ import { stdin as input, stdout as output } from "node:process";
 
 import readline from "node:readline/promises";
 
-import { Document, LlamaCloudIndex } from "llamaindex";
+import { LlamaCloudIndex } from "llama-cloud-services";
+import { Document } from "llamaindex";
 
 async function main() {
   const path = "node_modules/llamaindex/examples/abramov.txt";

examples/cloud/query.ts

@@ -1,7 +1,7 @@
 import { stdin as input, stdout as output } from "node:process";
 import readline from "node:readline/promises";
 
-import { LlamaCloudIndex } from "llamaindex";
+import { LlamaCloudIndex } from "llama-cloud-services";
 
 async function main() {
   const index = new LlamaCloudIndex({

examples/deprecated/agents/large_toolcall_with_gpt4o.ts

@@ -29,9 +29,9 @@ async function callLLM(init: { model: string }) {
       description:
         "Execute python code in a Jupyter notebook cell and return any result, stdout, stderr, display_data, and error.",
       parameters: z.object({
-        code: z.string({
-          description: "The python code to execute in a single cell.",
-        }),
+        code: z
+          .string()
+          .describe("The python code to execute in a single cell."),
       }),
     },
   );

examples/local-settings/CHANGELOG.md

@@ -0,0 +1,9 @@
+# local-settings
+
+## 1.0.1
+
+### Patch Changes
+
+- Updated dependencies [d493015]
+  - llamaindex@0.12.0
+  - @llamaindex/openai@0.4.20

examples/local-settings/local-settings.ts

@@ -0,0 +1,69 @@
+import { OpenAI, OpenAIEmbedding } from "@llamaindex/openai";
+import express, { Request, Response } from "express";
+import fs from "fs/promises";
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
+
+const app = express();
+const port = 3000;
+
+app.get("/default", async (req: Request, res: Response) => {
+  const embedModel = new OpenAIEmbedding({
+    apiKey: process.env.OPENAI_API_KEY,
+  });
+  const llm = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
+
+  const llmResponse = await Settings.withEmbedModel(embedModel, async () => {
+    return Settings.withLLM(llm, async () => {
+      const path = "node_modules/llamaindex/examples/abramov.txt";
+      const essay = await fs.readFile(path, "utf-8");
+      // Create Document object with essay
+      const document = new Document({ text: essay, id_: path });
+      // Split text and create embeddings. Store them in a VectorStoreIndex
+      const index = await VectorStoreIndex.fromDocuments([document]);
+      // Query the index
+      const queryEngine = index.asQueryEngine();
+      const { message, sourceNodes } = await queryEngine.query({
+        query: "What did the author do in college?",
+      });
+      // Return response with sources
+      return message.content;
+    });
+  });
+  // res.send(message.content)
+  res.send(llmResponse);
+});
+
+app.get("/custom", async (req: Request, res: Response) => {
+  const embedModel = new OpenAIEmbedding({
+    apiKey: process.env.OPENAI_API_KEY,
+    model: "text-embedding-3-small",
+  });
+  const llm = new OpenAI({
+    apiKey: process.env.OPENAI_API_KEY,
+    model: "gpt-3.5-turbo",
+  });
+
+  const llmResponse = await Settings.withEmbedModel(embedModel, async () => {
+    return Settings.withLLM(llm, async () => {
+      const path = "node_modules/llamaindex/examples/abramov.txt";
+      const essay = await fs.readFile(path, "utf-8");
+      // Create Document object with essay
+      const document = new Document({ text: essay, id_: path });
+      // Split text and create embeddings. Store them in a VectorStoreIndex
+      const index = await VectorStoreIndex.fromDocuments([document]);
+      // Query the index
+      const queryEngine = index.asQueryEngine();
+      const { message, sourceNodes } = await queryEngine.query({
+        query: "What did the author do in college?",
+      });
+      // Return response with sources
+      return message.content;
+    });
+  });
+  // res.send(message.content)
+  res.send(llmResponse);
+});
+
+app.listen(port, () => {
+  console.log(`Example app listening on port ${port}`);
+});

examples/local-settings/package.json

@@ -0,0 +1,22 @@
+{
+  "name": "local-settings",
+  "version": "1.0.1",
+  "main": "index.js",
+  "private": "true",
+  "scripts": {
+    "test": "echo \"No tests for example package\""
+  },
+  "keywords": [],
+  "author": "",
+  "license": "ISC",
+  "description": "",
+  "devDependencies": {
+    "@types/express": "^5.0.3",
+    "typescript": "^5.9.2"
+  },
+  "dependencies": {
+    "@llamaindex/openai": "^0.4.20",
+    "express": "^5.1.0",
+    "llamaindex": "^0.12.0"
+  }
+}

examples/local-settings/tsconfig.json

@@ -0,0 +1,8 @@
+{
+  "extends": "../tsconfig.json",
+  "compilerOptions": {
+    "moduleResolution": "node",
+    "types": ["node", "express"]
+  },
+  "include": ["*.ts"]
+}

examples/models/anthropic/opus-4.1.ts

@@ -0,0 +1,14 @@
+import { anthropic } from "@llamaindex/anthropic";
+import { agent } from "@llamaindex/workflow";
+
+(async function () {
+  const workflow = agent({
+    llm: anthropic({
+      model: "claude-4-1-opus",
+    }),
+  });
+  const result = await workflow.run(
+    "What are three compounds we should consider investigating to advance research into new antibiotics? Why should we consider them?",
+  );
+  console.log(result.data.result);
+})();

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

@@ -8,9 +8,7 @@ const weatherTool = tool({
   name: "weather",
   description: "Get the weather",
   parameters: z.object({
-    location: z.string({
-      description: "The location to get the weather for",
-    }),
+    location: z.string().describe("The location to get the weather for"),
   }),
   execute: ({ location }) => {
     return `The weather in ${location} is rainy`;

examples/models/ollama/gpt-oss.ts

@@ -0,0 +1,9 @@
+import { ollama } from "@llamaindex/ollama";
+
+(async () => {
+  const llm = ollama({
+    model: "gpt-oss:20b",
+  });
+  const response = await llm.complete({ prompt: "How are you?" });
+  console.log("Response:", response.text);
+})();

examples/models/openai/responses/tool-call.ts

@@ -7,9 +7,7 @@ async function main() {
     name: "weather",
     description: "Get the weather",
     parameters: z.object({
-      location: z.string({
-        description: "The location to get the weather for",
-      }),
+      location: z.string().describe("The location to get the weather for"),
     }),
     execute: ({ location }) => {
       return `The weather in ${location} is sunny`;

examples/models/vercel/llamacloud.ts

@@ -1,7 +1,8 @@
 import { openai } from "@ai-sdk/openai";
 import { llamaindex } from "@llamaindex/vercel";
-import { streamText } from "ai";
-import { Document, LlamaCloudIndex } from "llamaindex";
+import { stepCountIs, streamText } from "ai";
+import { LlamaCloudIndex } from "llama-cloud-services";
+import { Document } from "llamaindex";
 import fs from "node:fs/promises";
 
 async function main() {
@@ -28,7 +29,7 @@ async function main() {
           "get information from your knowledge base to answer questions.", // optional description
       }),
     },
-    maxSteps: 5,
+    stopWhen: stepCountIs(5),
   });
 
   for await (const textPart of result.textStream) {

examples/models/vercel/vector-store.ts

@@ -1,6 +1,6 @@
 import { openai } from "@ai-sdk/openai";
 import { llamaindex } from "@llamaindex/vercel";
-import { streamText } from "ai";
+import { stepCountIs, streamText } from "ai";
 import { Document, VectorStoreIndex } from "llamaindex";
 
 import fs from "node:fs/promises";
@@ -24,7 +24,7 @@ async function main() {
           "get information from your knowledge base to answer questions.", // optional description
       }),
     },
-    maxSteps: 5,
+    stopWhen: stepCountIs(5),
   });
 
   for await (const textPart of result.textStream) {

examples/package.json

@@ -1,77 +1,78 @@
 {
   "name": "@llamaindex/examples",
-  "version": "0.3.31",
+  "version": "0.3.42",
   "private": true,
   "scripts": {
     "lint": "eslint .",
     "start": "echo 'To get started, run `npx tsx <path to example>`'"
   },
   "dependencies": {
-    "@ai-sdk/openai": "^1.0.5",
+    "@ai-sdk/openai": "^2.0.27",
     "@azure/cosmos": "^4.1.1",
     "@azure/identity": "^4.4.1",
     "@azure/search-documents": "^12.1.0",
-    "@llamaindex/anthropic": "^0.3.17",
-    "@llamaindex/assemblyai": "^0.1.14",
-    "@llamaindex/astra": "^0.0.29",
-    "@llamaindex/azure": "^0.1.27",
-    "@llamaindex/bm25-retriever": "^0.0.4",
-    "@llamaindex/chroma": "^0.0.29",
-    "@llamaindex/clip": "^0.0.66",
-    "@llamaindex/cloud": "^4.0.24",
-    "@llamaindex/cohere": "^0.0.29",
-    "@llamaindex/core": "^0.6.15",
-    "@llamaindex/deepinfra": "^0.0.66",
-    "@llamaindex/deepseek": "^0.0.27",
-    "@llamaindex/discord": "^0.1.14",
-    "@llamaindex/elastic-search": "^0.1.15",
+    "@llamaindex/anthropic": "^0.3.25",
+    "@llamaindex/assemblyai": "^0.1.21",
+    "@llamaindex/astra": "^0.0.36",
+    "@llamaindex/azure": "^0.1.37",
+    "@llamaindex/bm25-retriever": "^0.0.11",
+    "@llamaindex/chroma": "^0.0.36",
+    "@llamaindex/clip": "^0.0.76",
+    "llama-cloud-services": "^0.3.5",
+    "@llamaindex/cohere": "^0.0.36",
+    "@llamaindex/core": "^0.6.22",
+    "@llamaindex/deepinfra": "^0.0.76",
+    "@llamaindex/deepseek": "^0.0.38",
+    "@llamaindex/discord": "^0.1.21",
+    "@llamaindex/elastic-search": "^0.1.22",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/firestore": "^1.0.22",
-    "@llamaindex/fireworks": "^0.0.26",
-    "@llamaindex/google": "^0.3.14",
-    "@llamaindex/groq": "^0.0.82",
-    "@llamaindex/huggingface": "^0.1.20",
-    "@llamaindex/jinaai": "^0.0.26",
-    "@llamaindex/milvus": "^0.1.24",
-    "@llamaindex/mistral": "^0.1.15",
-    "@llamaindex/mixedbread": "^0.0.29",
-    "@llamaindex/mongodb": "^0.0.30",
-    "@llamaindex/node-parser": "^2.0.15",
-    "@llamaindex/notion": "^0.1.14",
-    "@llamaindex/ollama": "^0.1.15",
-    "@llamaindex/openai": "^0.4.10",
-    "@llamaindex/perplexity": "^0.0.23",
-    "@llamaindex/pinecone": "^0.1.15",
-    "@llamaindex/portkey-ai": "^0.0.57",
-    "@llamaindex/postgres": "^0.0.58",
-    "@llamaindex/qdrant": "^0.1.25",
-    "@llamaindex/readers": "^3.1.14",
-    "@llamaindex/replicate": "^0.0.57",
-    "@llamaindex/supabase": "^0.1.16",
-    "@llamaindex/together": "^0.0.26",
-    "@llamaindex/tools": "^0.1.5",
-    "@llamaindex/upstash": "^0.0.29",
-    "@llamaindex/vercel": "^0.1.15",
-    "@llamaindex/vllm": "^0.0.52",
-    "@llamaindex/voyage-ai": "^1.0.21",
-    "@llamaindex/weaviate": "^0.0.30",
-    "@llamaindex/workflow": "^1.1.15",
-    "@llamaindex/xai": "^0.0.13",
+    "@llamaindex/firestore": "^1.0.29",
+    "@llamaindex/fireworks": "^0.0.36",
+    "@llamaindex/google": "^0.3.22",
+    "@llamaindex/groq": "^0.0.92",
+    "@llamaindex/huggingface": "^0.1.30",
+    "@llamaindex/jinaai": "^0.0.36",
+    "@llamaindex/milvus": "^0.1.31",
+    "@llamaindex/mistral": "^0.1.22",
+    "@llamaindex/mixedbread": "^0.0.36",
+    "@llamaindex/mongodb": "^0.0.37",
+    "@llamaindex/node-parser": "^2.0.22",
+    "@llamaindex/notion": "^0.1.21",
+    "@llamaindex/ollama": "^0.1.23",
+    "@llamaindex/openai": "^0.4.20",
+    "@llamaindex/perplexity": "^0.0.33",
+    "@llamaindex/pinecone": "^0.1.22",
+    "@llamaindex/portkey-ai": "^0.0.64",
+    "@llamaindex/postgres": "^0.0.65",
+    "@llamaindex/qdrant": "^0.1.32",
+    "@llamaindex/readers": "^3.1.21",
+    "@llamaindex/replicate": "^0.0.64",
+    "@llamaindex/supabase": "^0.1.23",
+    "@llamaindex/together": "^0.0.36",
+    "@llamaindex/tools": "^0.1.12",
+    "@llamaindex/upstash": "^0.0.36",
+    "@llamaindex/vercel": "^0.1.22",
+    "@llamaindex/vllm": "^0.0.62",
+    "@llamaindex/voyage-ai": "^1.0.28",
+    "@llamaindex/weaviate": "^0.0.37",
+    "@llamaindex/workflow": "^1.1.24",
+    "@llamaindex/xai": "^0.0.23",
     "@notionhq/client": "^4.0.0",
     "@pinecone-database/pinecone": "^4.0.0",
     "@vercel/postgres": "^0.10.0",
-    "ai": "^4.3.17",
+    "ai": "^5.0.39",
     "ajv": "^8.17.1",
     "commander": "^12.1.0",
     "dotenv": "^17.2.0",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.11.19",
+    "llamaindex": "^0.12.0",
     "mongodb": "6.7.0",
     "postgres": "^3.4.4",
     "wikipedia": "^2.1.2",
-    "zod": "^3.25.76"
+    "zod": "^4.1.5"
   },
   "devDependencies": {
+    "@types/express": "^5.0.3",
     "@types/node": "^24.0.13",
     "tsx": "^4.20.3",
     "typescript": "^5.8.3"

examples/readers/package.json

@@ -9,10 +9,7 @@
     "start:html": "node --import tsx ./src/html.ts",
     "start:markdown": "node --import tsx ./src/markdown.ts",
     "start:pdf": "node --import tsx ./src/pdf.ts",
-    "start:llamaparse": "node --import tsx ./src/llamaparse.ts",
     "start:notion": "node --import tsx ./src/notion.ts",
-    "start:llamaparse-dir": "node --import tsx ./src/simple-directory-reader-with-llamaparse.ts",
-    "start:llamaparse-json": "node --import tsx ./src/llamaparse-json.ts",
     "start:discord": "node --import tsx ./src/discord.ts",
     "start:json": "node --import tsx ./src/json.ts",
     "start:obsidian": "node --import tsx ./src/obsidian.ts",
@@ -20,7 +17,6 @@
     "start:excel": "node --import tsx ./src/excel.ts"
   },
   "dependencies": {
-    "@llamaindex/cloud": "workspace:* || ^2.0.24",
     "@llamaindex/excel": "workspace:*",
     "@llamaindex/readers": "workspace:* || ^1.0.25",
     "@notionhq/client": "^4.0.0",

examples/readers/src/llamaparse-docx.ts

@@ -1,52 +0,0 @@
-import { Language, LlamaParseReader } from "@llamaindex/cloud";
-import fs from "node:fs";
-import path from "node:path";
-
-type LlamaParseReaderParams = Partial<
-  Omit<LlamaParseReader, "language" | "apiKey">
-> & {
-  language?: Language | Language[] | undefined;
-  apiKey?: string | undefined;
-};
-
-async function main() {
-  const filePath = "../data/pto_policy_employee.docx";
-  if (!fs.existsSync(filePath)) {
-    console.error(`File ${filePath} does not exist`);
-    process.exit(1);
-  } else {
-    console.log(`File ${filePath} exists`);
-  }
-
-  const params: LlamaParseReaderParams = {
-    verbose: true,
-    parsingInstruction:
-      "Extract the text from the document a long with any images and tables.  This is a document for a course and the contents of the images are important.",
-    fastMode: false,
-    gpt4oMode: true,
-    useVendorMultimodalModel: true,
-    vendorMultimodalModelName: "anthropic-sonnet-3.5",
-    premiumMode: true,
-    resultType: "markdown",
-    apiKey: process.env.LLAMA_CLOUD_API_KEY,
-    doNotCache: true,
-  };
-
-  // set up the llamaparse reader
-  const reader = new LlamaParseReader(params);
-
-  const buffer = fs.readFileSync(filePath);
-  const documents = await reader.loadDataAsContent(
-    new Uint8Array(buffer),
-    path.basename(filePath),
-  );
-
-  let allText = "";
-  documents.forEach((doc) => {
-    allText += doc.text;
-  });
-
-  console.log(allText);
-}
-
-main().catch(console.error);

examples/readers/src/llamaparse-json.ts

@@ -1,72 +0,0 @@
-import { LlamaParseReader } from "@llamaindex/cloud";
-import { OpenAI } from "@llamaindex/openai";
-import {
-  Document,
-  ImageNode,
-  PromptTemplate,
-  VectorStoreIndex,
-  createMessageContent,
-} from "llamaindex";
-
-const reader = new LlamaParseReader();
-async function main() {
-  // Load PDF using LlamaParse JSON mode and return an array of json objects
-  const jsonObjs = await reader.loadJson("../data/uber_10q_march_2022.pdf");
-  // Access the first "pages" (=a single parsed file) object in the array
-  const jsonList = jsonObjs[0]["pages"];
-
-  const textDocs = getTextDocs(jsonList);
-  const imageTextDocs = await getImageTextDocs(jsonObjs);
-  const documents = [...textDocs, ...imageTextDocs];
-  // Split text, create embeddings and query the index
-  const index = await VectorStoreIndex.fromDocuments(documents);
-  const queryEngine = index.asQueryEngine();
-  const response = await queryEngine.query({
-    query:
-      "What does the bar graph titled 'Monthly Active Platform Consumers' show?",
-  });
-
-  console.log(response.toString());
-}
-
-main().catch(console.error);
-
-// Extract and assign text and page number from jsonList, return an array of Document objects
-function getTextDocs(jsonList: { text: string; page: number }[]): Document[] {
-  return jsonList.map(
-    (page) => new Document({ text: page.text, metadata: { page: page.page } }),
-  );
-}
-// Download all images from jsonObjs, send them to OpenAI API to get alt text, return an array of Document objects
-async function getImageTextDocs(
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
-  jsonObjs: Record<string, any>[],
-): Promise<Document[]> {
-  const llm = new OpenAI({
-    model: "gpt-4o",
-    temperature: 0.2,
-    maxTokens: 1000,
-  });
-  const imageDicts = await reader.getImages(jsonObjs, "images");
-  const imageDocs = [];
-
-  for (const imageDict of imageDicts) {
-    const imageDoc = new ImageNode({ image: imageDict.path });
-    const prompt = new PromptTemplate({
-      template: `Describe the image as alt text`,
-    });
-    const message = await createMessageContent(prompt, [imageDoc]);
-
-    const response = await llm.complete({
-      prompt: message,
-    });
-
-    const doc = new Document({
-      text: response.text,
-      metadata: { path: imageDict.path },
-    });
-    imageDocs.push(doc);
-  }
-
-  return imageDocs;
-}

examples/readers/src/llamaparse.ts

@@ -1,33 +0,0 @@
-import { LlamaParseReader } from "@llamaindex/cloud/reader";
-import { openai, OpenAIEmbedding } from "@llamaindex/openai";
-import { Settings, VectorStoreIndex } from "llamaindex";
-
-Settings.llm = openai({
-  model: "gpt-4.1",
-});
-Settings.embedModel = new OpenAIEmbedding({
-  model: "text-embedding-3-small",
-});
-
-async function main() {
-  // Load PDF using LlamaParse
-  const reader = new LlamaParseReader({
-    resultType: "markdown",
-    baseUrl: "https://api.cloud.llamaindex.ai", // for EU use: https://api.cloud.eu.llamaindex.ai
-  });
-  const documents = await reader.loadData("../data/TOS.pdf");
-
-  // Split text and create embeddings. Store them in a VectorStoreIndex
-  const index = await VectorStoreIndex.fromDocuments(documents);
-
-  // Query the index
-  const queryEngine = index.asQueryEngine();
-  const response = await queryEngine.query({
-    query: "What is the license grant in the TOS?",
-  });
-
-  // Output response
-  console.log(response.toString());
-}
-
-main().catch(console.error);

examples/readers/src/simple-directory-reader-with-llamaparse.ts

@@ -1,33 +0,0 @@
-import { LlamaParseReader } from "@llamaindex/cloud/reader";
-import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
-import { VectorStoreIndex } from "llamaindex";
-
-async function main() {
-  const reader = new SimpleDirectoryReader();
-
-  const docs = await reader.loadData({
-    directoryPath: "../data/parallel", // brk-2022.pdf split into 6 parts
-    numWorkers: 2,
-    // set LlamaParse as the default reader for all file types. Set apiKey here or in environment variable LLAMA_CLOUD_API_KEY
-    overrideReader: new LlamaParseReader({
-      language: "en",
-      resultType: "markdown",
-      parsingInstruction:
-        "The provided files is Berkshire Hathaway's 2022 Annual Report. They contain figures, tables and raw data. Capture the data in a structured format. Mathematical equation should be put out as LATEX markdown (between $$).",
-    }),
-  });
-
-  const index = await VectorStoreIndex.fromDocuments(docs);
-
-  // Query the index
-  const queryEngine = index.asQueryEngine();
-  const response = await queryEngine.query({
-    query:
-      "What is the general strategy for shareholder safety outlined in the report? Use a concrete example with numbers",
-  });
-
-  // Output response
-  console.log(response.toString());
-}
-
-main().catch(console.error);

examples/storage/qdrantdb/with-gemini.ts

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

examples/storage/qdrantdb/with-jina.ts

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

packages/autotool/CHANGELOG.md

@@ -1,5 +1,74 @@
 # @llamaindex/autotool
 
+## 9.0.0
+
+### Patch Changes
+
+- Updated dependencies [d493015]
+  - llamaindex@0.12.0
+
+## 8.0.29
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 8.0.28
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 8.0.27
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 8.0.26
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 8.0.25
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
+## 8.0.24
+
+### Patch Changes
+
+- llamaindex@0.11.24
+
+## 8.0.23
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 8.0.22
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 8.0.21
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
+## 8.0.20
+
+### Patch Changes
+
+- llamaindex@0.11.20
+
 ## 8.0.19
 
 ### Patch Changes

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

@@ -1,5 +1,85 @@
 # @llamaindex/autotool-01-node-example
 
+## 0.0.138
+
+### Patch Changes
+
+- Updated dependencies [d493015]
+  - llamaindex@0.12.0
+  - @llamaindex/autotool@9.0.0
+
+## 0.0.137
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+  - @llamaindex/autotool@8.0.29
+
+## 0.0.136
+
+### Patch Changes
+
+- llamaindex@0.11.28
+- @llamaindex/autotool@8.0.28
+
+## 0.0.135
+
+### Patch Changes
+
+- llamaindex@0.11.27
+- @llamaindex/autotool@8.0.27
+
+## 0.0.134
+
+### Patch Changes
+
+- llamaindex@0.11.26
+- @llamaindex/autotool@8.0.26
+
+## 0.0.133
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+  - @llamaindex/autotool@8.0.25
+
+## 0.0.132
+
+### Patch Changes
+
+- llamaindex@0.11.24
+- @llamaindex/autotool@8.0.24
+
+## 0.0.131
+
+### Patch Changes
+
+- llamaindex@0.11.23
+- @llamaindex/autotool@8.0.23
+
+## 0.0.130
+
+### Patch Changes
+
+- llamaindex@0.11.22
+- @llamaindex/autotool@8.0.22
+
+## 0.0.129
+
+### Patch Changes
+
+- llamaindex@0.11.21
+- @llamaindex/autotool@8.0.21
+
+## 0.0.128
+
+### Patch Changes
+
+- llamaindex@0.11.20
+- @llamaindex/autotool@8.0.20
+
 ## 0.0.127
 
 ### Patch Changes

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

@@ -13,5 +13,5 @@
   "scripts": {
     "start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
   },
-  "version": "0.0.127"
+  "version": "0.0.138"
 }

packages/autotool/package.json

@@ -6,7 +6,7 @@
     "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
     "directory": "packages/autotool"
   },
-  "version": "8.0.19",
+  "version": "9.0.0",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",
@@ -76,7 +76,7 @@
     "@types/json-schema": "^7.0.15",
     "@types/node": "^24.0.13",
     "llamaindex": "workspace:*",
-    "next": "^15.3.3",
+    "next": "^15.4.7",
     "rollup": "^4.28.1",
     "tsx": "^4.20.3",
     "typescript": "^5.8.3",

packages/cloud/README.md

@@ -1,9 +0,0 @@
-# @llamaindex/cloud
-
-> LlamaCloud is a new generation of managed parsing, ingestion, and retrieval services, designed to bring production-grade context-augmentation to your LLM and RAG applications.
-
-For more information, see the [API documentation](https://docs.cloud.llamaindex.ai/).
-
-## License
-
-MIT

packages/cloud/beta/agent/package.json

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

packages/cloud/openapi-ts.config.ts

@@ -1,24 +0,0 @@
-import { defaultPlugins, defineConfig } from "@hey-api/openapi-ts";
-
-export default defineConfig({
-  // you can download this file to get the latest version of the OpenAPI document
-  // @link https://api.cloud.llamaindex.ai/api/openapi.json
-  input: "./openapi.json",
-  output: {
-    path: "./src/client",
-    format: "prettier",
-    lint: "eslint",
-  },
-  plugins: [
-    ...defaultPlugins,
-    "@hey-api/client-fetch",
-    "zod",
-    "@hey-api/schemas",
-    "@hey-api/sdk",
-    {
-      enums: "javascript",
-      identifierCase: "PascalCase",
-      name: "@hey-api/typescript",
-    },
-  ],
-});