Release (#2209 )

initial sonnet 4 5 support (#2208 )
Fix broken links from Astro migration (#2206 )
2026-07-03 19:19:08 -04:00 · 2025-09-29 12:04:57 -06:00 · 2025-09-29 11:58:03 -06:00 · 2025-09-17 11:14:23 -07:00 · 2025-09-16 13:43:56 -07:00 · 2025-09-15 12:29:08 +08:00
381 changed files with 12522 additions and 42393 deletions
@@ -1,5 +0,0 @@
---
-"@llamaindex/openai": patch
---
-
-fix: assume new models are function call models
@@ -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 }}"
@@ -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
@@ -1,5 +1,173 @@
 # @llamaindex/doc

+## 0.2.56
+
+### Patch Changes
+
+- b4c5531: Add initial sonnet 4.5 support
+
+## 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
+
+- Updated dependencies [856dd8c]
+  - @llamaindex/openai@0.4.10
+
 ## 0.2.40

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/doc",
-  "version": "0.2.40",
+  "version": "0.2.56",
  "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",
@@ -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";
@@ -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>,
-      };
-    },
-  },
-});
@@ -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" />
@@ -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>
-  );
-};
@@ -0,0 +1,2 @@
+label: Getting Started
+collapsed: true
@@ -21,7 +21,7 @@ While the definition of an agentic application is broad, there are several key c
 - **Orchestration**: A hierarchical structure of LLMs is used to orchestrate lower-level actions and LLMs.
 - **Reflection**: The LLM is used to reflect and validate outputs of previous steps or LLM calls, which can be used to guide the application to the next appropriate step or state.

-In LlamaIndex, you can build agentic applications by using the workflows to orchestrate a sequence of steps and LLMs. You can [learn more about workflows](/docs/llamaindex/tutorials/workflows).
+In LlamaIndex, you can build agentic applications by using the workflows to orchestrate a sequence of steps and LLMs. You can [learn more about workflows](/typescript/framework/tutorials/workflows).

 ## Agents

@@ -34,27 +34,27 @@ What this means in practice, is something like:
 - If tools are used, the agent will then interpret the tool outputs and use them to inform the next action
 - Once the agent stops taking actions, it returns the final output to the user

-You can [learn more about agents](/docs/llamaindex/tutorials/basic_agent).
+You can [learn more about agents](/typescript/framework/tutorials/basic_agent).

 ## Retrieval Augmented Generation (RAG)

-Retrieval-Augmented Generation (RAG) is a core technique for building data-backed LLM applications with LlamaIndex. It allows LLMs to answer questions about your private data by providing it to the LLM at query time, rather than training the LLM on your data. To avoid sending **all** of your data to the LLM every time, RAG indexes your data and selectively sends only the relevant parts along with your query. You can [learn more about RAG](/docs/llamaindex/tutorials/rag).
+Retrieval-Augmented Generation (RAG) is a core technique for building data-backed LLM applications with LlamaIndex. It allows LLMs to answer questions about your private data by providing it to the LLM at query time, rather than training the LLM on your data. To avoid sending **all** of your data to the LLM every time, RAG indexes your data and selectively sends only the relevant parts along with your query. You can [learn more about RAG](/typescript/framework/tutorials/rag).

 ## Use cases

 There are endless use cases for data-backed LLM applications but they can be roughly grouped into four categories:

-[**Agents**](/docs/llamaindex/tutorials/basic_agent):
-An agent is an automated decision-maker powered by an LLM that interacts with the world via a set of [tools](/docs/llamaindex/modules/agents/tool). Agents can take an arbitrary number of steps to complete a given task, dynamically deciding on the best course of action rather than following pre-determined steps. This gives it additional flexibility to tackle more complex tasks.
+[**Agents**](/typescript/framework/tutorials/basic_agent):
+An agent is an automated decision-maker powered by an LLM that interacts with the world via a set of [tools](/typescript/framework/modules/agents/tool). Agents can take an arbitrary number of steps to complete a given task, dynamically deciding on the best course of action rather than following pre-determined steps. This gives it additional flexibility to tackle more complex tasks.

-[**Workflows**](/docs/llamaindex/tutorials/workflows):
+[**Workflows**](/typescript/framework/tutorials/workflows):
 A Workflow in LlamaIndex is a specific event-driven abstraction that allows you to orchestrate a sequence of steps and LLMs calls. Workflows can be used to implement any agentic application, and are a core component of LlamaIndex.

-[**Structured Data Extraction**](/docs/llamaindex/tutorials/structured_data_extraction):
+[**Structured Data Extraction**](/typescript/framework/tutorials/structured_data_extraction):
 Pydantic extractors allow you to specify a precise data structure to extract from your data and use LLMs to fill in the missing pieces in a type-safe way. This is useful for extracting structured data from unstructured sources like PDFs, websites, and more, and is key to automating workflows.

-[**Query Engines**](/docs/llamaindex/modules/rag/query_engines):
+[**Query Engines**](/typescript/framework/modules/rag/query_engines):
 A query engine is an end-to-end flow that allows you to ask questions over your data. It takes in a natural language query, and returns a response, along with reference context retrieved and passed to the LLM.

-[**Chat Engines**](/docs/llamaindex/modules/rag/chat_engine):
+[**Chat Engines**](/typescript/framework/modules/rag/chat_engine):
 A chat engine is an end-to-end flow for having a conversation with your data (multiple back-and-forth instead of a single question-and-answer).
@@ -0,0 +1,2 @@
+label: Installation
+collapsed: true
@@ -138,28 +138,28 @@ Choose your deployment target:
  <Card 
    title="Server APIs & Backends" 
    description="Express, Fastify, Koa, standalone Node.js servers"
-    href="/docs/llamaindex/getting_started/installation/server-apis" 
+    href="/typescript/framework/getting_started/installation/server-apis" 
  />
  <Card 
    title="Serverless Functions" 
    description="Vercel, Netlify, AWS Lambda, Cloudflare Workers"
-    href="/docs/llamaindex/getting_started/installation/serverless" 
+    href="/typescript/framework/getting_started/installation/serverless" 
  />
  <Card 
    title="Next.js Applications" 
    description="API routes, server components, edge runtime"
-    href="/docs/llamaindex/getting_started/installation/nextjs" 
+    href="/typescript/framework/getting_started/installation/nextjs" 
  />
  <Card 
    title="Troubleshooting" 
    description="Common issues, bundle optimization, compatibility"
-    href="/docs/llamaindex/getting_started/installation/troubleshooting" 
+    href="/typescript/framework/getting_started/installation/troubleshooting" 
  />
 </Cards>

 ## LLM/Embedding Providers

-Go to [LLM APIs](/docs/llamaindex/modules/models/llms) and [Embedding APIs](/docs/llamaindex/modules/models/embeddings) to find out how to use different LLM and embedding providers beyond OpenAI.
+Go to [LLM APIs](/typescript/framework/modules/models/llms) and [Embedding APIs](/typescript/framework/modules/models/embeddings) to find out how to use different LLM and embedding providers beyond OpenAI.

 ## What's Next?

@@ -167,11 +167,11 @@ Go to [LLM APIs](/docs/llamaindex/modules/models/llms) and [Embedding APIs](/doc
  <Card
    title="Learn LlamaIndex.TS"
    description="Learn how to use LlamaIndex.TS by starting with one of our tutorials."
-    href="/docs/llamaindex/tutorials/basic_agent"
+    href="/typescript/framework/tutorials/basic_agent"
  />
  <Card
    title="Show me code examples"
    description="Explore code examples using LlamaIndex.TS."
-    href="/docs/llamaindex/getting_started/examples"
+    href="/typescript/framework/getting_started/examples"
  />
 </Cards>
@@ -1,4 +0,0 @@
-{
-  "title": "Installation",
-  "pages": ["server-apis", "serverless", "nextjs", "troubleshooting"]
-}
@@ -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));
          }
@@ -370,6 +400,6 @@ export default function ChatInterface() {

 ## Next Steps

- Learn about [serverless deployment](/docs/llamaindex/getting_started/installation/serverless)
- Explore [server APIs](/docs/llamaindex/getting_started/installation/server-apis)
- Check [troubleshooting guide](/docs/llamaindex/getting_started/installation/troubleshooting) for common issues 
+- Learn about [serverless deployment](/typescript/framework/getting_started/installation/serverless)
+- Explore [server APIs](/typescript/framework/getting_started/installation/server-apis)
+- Check [troubleshooting guide](/typescript/framework/getting_started/installation/troubleshooting) for common issues 
@@ -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);
      }
@@ -206,6 +206,6 @@ app.post('/api/chat-stream', async (req, res) => {

 ## Next Steps

- Learn about [serverless deployment](/docs/llamaindex/getting_started/installation/serverless)
- Explore [Next.js integration](/docs/llamaindex/getting_started/installation/nextjs)
- Check [troubleshooting guide](/docs/llamaindex/getting_started/installation/troubleshooting) for common issues 
+- Learn about [serverless deployment](/typescript/framework/getting_started/installation/serverless)
+- Explore [Next.js integration](/typescript/framework/getting_started/installation/nextjs)
+- Check [troubleshooting guide](/typescript/framework/getting_started/installation/troubleshooting) for common issues 
@@ -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 {
@@ -235,6 +235,6 @@ export const handler: Handler = async (event, context) => {

 ## Next Steps

- Learn about [Next.js integration](/docs/llamaindex/getting_started/installation/nextjs)
- Explore [server deployment](/docs/llamaindex/getting_started/installation/server-apis)
- Check [troubleshooting guide](/docs/llamaindex/getting_started/installation/troubleshooting) for common issues 
+- Learn about [Next.js integration](/typescript/framework/getting_started/installation/nextjs)
+- Explore [server deployment](/typescript/framework/getting_started/installation/server-apis)
+- Check [troubleshooting guide](/typescript/framework/getting_started/installation/troubleshooting) for common issues 
@@ -492,9 +492,9 @@ Include:
 If you're still experiencing issues:

 1. **Check specific deployment guides:**
-   - [Server APIs](/docs/llamaindex/getting_started/installation/server-apis)
-   - [Serverless Functions](/docs/llamaindex/getting_started/installation/serverless)
-   - [Next.js Applications](/docs/llamaindex/getting_started/installation/nextjs)
+   - [Server APIs](/typescript/framework/getting_started/installation/server-apis)
+   - [Serverless Functions](/typescript/framework/getting_started/installation/serverless)
+   - [Next.js Applications](/typescript/framework/getting_started/installation/nextjs)

 2. **Open an issue** on GitHub with a minimal reproduction

@@ -1,4 +0,0 @@
-{
-  "title": "Getting Started",
-  "pages": ["concepts", "installation", "create_llama", "examples"]
-}
@@ -43,19 +43,19 @@ Built for modern JavaScript runtimes like <SiNodedotjs className="inline" color=

 ### What are agents?

-[Agents](/docs/llamaindex/tutorials/agents/1_setup) are LLM-powered assistants that can reason, use external tools, and take actions to accomplish tasks such as research, data extraction, and automation. 
+[Agents](/typescript/framework/tutorials/agents/1_setup) are LLM-powered assistants that can reason, use external tools, and take actions to accomplish tasks such as research, data extraction, and automation. 
 LlamaIndex.TS provides foundational building blocks for creating and orchestrating these agents.

 ### What are workflows?

-[Workflows](/docs/llamaindex/tutorials/workflows) are multi-step, event-driven processes that combine agents, data connectors, and other tools to solve complex problems. 
+[Workflows](/typescript/framework/tutorials/workflows) are multi-step, event-driven processes that combine agents, data connectors, and other tools to solve complex problems. 
 With LlamaIndex.TS you can chain together retrieval, generation, and tool-calling steps and then deploy the entire pipeline as a microservice.

 ### What is context engineering?

 LLMs come pre-trained on vast public corpora, but not on **your** private or domain-specific data. 
 Context engineering bridges that gap by injecting the right pieces of your data into the LLM prompt at the right time. 
-The most popular example is [Retrieval-Augmented Generation (RAG)](/docs/llamaindex/getting_started/concepts), but the same idea powers agent memory, evaluation, extraction, summarisation, and more.
+The most popular example is [Retrieval-Augmented Generation (RAG)](/typescript/framework/getting_started/concepts), but the same idea powers agent memory, evaluation, extraction, summarisation, and more.

 LlamaIndex.TS gives you:

@@ -65,16 +65,16 @@ LlamaIndex.TS gives you:
 - **Workflows** for fine-grained orchestration of your data and LLM-powered agents.
 - **Observability** integrations so you can iterate with confidence.

-You can learn more about these concepts in our [concepts guide](/docs/llamaindex/getting_started/concepts).
+You can learn more about these concepts in our [concepts guide](/typescript/framework/getting_started/concepts).

 ## Use cases

 Popular scenarios include:

- [LLM-Powered Agents](/docs/llamaindex/tutorials/agents/1_setup)
- [Indexing and Retrieval](/docs/llamaindex/tutorials/rag)
- [Extracting Structured Data](/docs/llamaindex/tutorials/structured_data_extraction)
- [Custom Orchestration with Workflows](/docs/llamaindex/tutorials/workflows)
+- [LLM-Powered Agents](/typescript/framework/tutorials/agents/1_setup)
+- [Indexing and Retrieval](/typescript/framework/tutorials/rag)
+- [Extracting Structured Data](/typescript/framework/tutorials/structured_data_extraction)
+- [Custom Orchestration with Workflows](/typescript/framework/tutorials/workflows)

 ## Getting started

@@ -89,10 +89,10 @@ The fastest way to get started is in StackBlitz below — no local setup require

 Want to learn more? We have several tutorials to get you started:

- [Installation + Runtime Guide](/docs/llamaindex/getting_started/installation)
- [Create your first agent](/docs/llamaindex/tutorials/agents/1_setup)
- [Learn how to index data and chat with it](/docs/llamaindex/tutorials/rag)
- [Learn how to write your own workflows and agents](/docs/llamaindex/tutorials/workflows)
+- [Installation + Runtime Guide](/typescript/framework/getting_started/installation)
+- [Create your first agent](/typescript/framework/tutorials/agents/1_setup)
+- [Learn how to index data and chat with it](/typescript/framework/tutorials/rag)
+- [Learn how to write your own workflows and agents](/typescript/framework/tutorials/workflows)

 ---

@@ -0,0 +1,2 @@
+label: Integration
+collapsed: true
@@ -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/)
@@ -1,5 +0,0 @@
-{
-  "title": "Integration",
-  "description": "See our integrations",
-  "pages": ["open-llm-metry", "lang-trace", "vercel"]
-}
@@ -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({
@@ -35,7 +35,7 @@ import { OpenAI } from "@llamaindex/openai";
 npm i @llamaindex/openai
 ```

-For more details on available AI model providers and their configuration, see the [LLMs documentation](/docs/llamaindex/modules/models/llms) and the [Embedding Models documentation](/docs/llamaindex/modules/models/embeddings).
+For more details on available AI model providers and their configuration, see the [LLMs documentation](/typescript/framework/modules/models/llms) and the [Embedding Models documentation](/typescript/framework/modules/models/embeddings).

 ### 2. Storage Providers

@@ -49,7 +49,7 @@ Now:
 import { PineconeVectorStore } from "@llamaindex/pinecone";
 ```

-For more information about available storage options, refer to the [Data Stores documentation](/docs/llamaindex/modules/data/stores).
+For more information about available storage options, refer to the [Data Stores documentation](/typescript/framework/modules/data/stores).

 ### 3. Data Loaders

@@ -63,7 +63,7 @@ Now:
 import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
 ```

-For more details about available data loaders and their usage, check the [Loading Data](/docs/llamaindex/modules/data/readers).
+For more details about available data loaders and their usage, check the [Loading Data](/typescript/framework/modules/data/readers).

 ### 4. Prefer using `llamaindex` instead of `@llamaindex/core`

@@ -0,0 +1,2 @@
+label: Migration
+collapsed: true
@@ -0,0 +1,2 @@
+label: Deprecated
+collapsed: true
@@ -0,0 +1,2 @@
+label: Agent
+collapsed: true
@@ -2,7 +2,7 @@
 title: Agents
 ---

-**Note**: Agents are deprecated, use [Agent Workflows](/docs/llamaindex/modules/agents/agent_workflow) instead.
+**Note**: Agents are deprecated, use [Agent Workflows](/typescript/framework/modules/agents/agent_workflow) instead.

 An “agent” is an automated reasoning and decision engine. It takes in a user input/query and can make internal decisions for executing that query in order to return the correct result. The key agent components can include, but are not limited to:

@@ -1,5 +0,0 @@
-{
-  "title": "Migration",
-  "description": "Migration between different versions",
-  "pages": ["0.8-to-0.9", "deprecated"]
-}
@@ -0,0 +1,2 @@
+label: Modules
+collapsed: true
@@ -0,0 +1,2 @@
+label: Agents
+collapsed: true
@@ -3,7 +3,7 @@ title: Agent Workflows
 ---


-Agent Workflows are a powerful system that enables you to create and orchestrate one or multiple agents with tools to perform specific tasks. It's built on top of the base [`Workflow`](/docs/llamaindex/modules/agents/workflows) system and provides a streamlined interface for agent interactions.
+Agent Workflows are a powerful system that enables you to create and orchestrate one or multiple agents with tools to perform specific tasks. It's built on top of the base [`Workflow`](/typescript/framework/modules/agents/workflows) system and provides a streamlined interface for agent interactions.

 ## Usage

@@ -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:
@@ -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](/typescript/framework/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
@@ -1,4 +0,0 @@
-{
-  "title": "Agents",
-  "pages": ["tool", "agent_workflow", "workflows", "natural_language_workflow"]
-}
@@ -0,0 +1,2 @@
+label: Tool
+collapsed: true
@@ -101,6 +101,9 @@ const agent = agent({
 });
 ```

+You can also use [MCP Toolbox for
+Databases](/typescript/framework/integration/mcp-toolbox) to interact with MCP tools.
+

 ## Function tool

@@ -0,0 +1,2 @@
+label: Data
+collapsed: true
@@ -0,0 +1,2 @@
+label: Data Index
+collapsed: true
@@ -2,7 +2,7 @@
 title: Index
 ---

-An index is the basic container for organizing your data. Besides managed indexes using [LlamaCloud](/docs/llamaindex/modules/data/data_index/managed), LlamaIndex.TS supports three indexes:
+An index is the basic container for organizing your data. Besides managed indexes using [LlamaCloud](/typescript/framework/modules/data/data_index/managed), LlamaIndex.TS supports three indexes:


 - `VectorStoreIndex` - will send the top-k `Node`s to the LLM when generating a response. The default top-k is 2.
@@ -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/)
@@ -0,0 +1,2 @@
+label: Ingestion Pipeline
+collapsed: true
@@ -0,0 +1,2 @@
+label: Transformations
+collapsed: true
@@ -6,9 +6,9 @@ A transformation is something that takes a list of nodes as an input, and return

 Currently, the following components are Transformation objects:

- [SentenceSplitter](/docs/llamaindex/modules/data/ingestion_pipeline/transformations/node-parser)
- [MetadataExtractor](/docs/llamaindex/modules/data/ingestion_pipeline/transformations/metadata_extraction)
- [Embeddings](/docs/llamaindex/modules/models/embeddings)
+- [SentenceSplitter](/typescript/framework/modules/data/ingestion_pipeline/transformations/node-parser)
+- [MetadataExtractor](/typescript/framework/modules/data/ingestion_pipeline/transformations/metadata_extraction)
+- [Embeddings](/typescript/framework/modules/models/embeddings)

 ## Usage Pattern

@@ -3,7 +3,7 @@ title: Node Parsers / Text Splitters
 description: Learn how to use Node Parsers and Text Splitters to extract data from documents.
 ---

-Node parsers are a simple abstraction that take a list of `Document` objects, and chunk them into `Node` objects, such that each node is a specific chunk of the parent document. When a document is broken into nodes, all of it's attributes are inherited to the children nodes (i.e. `metadata`, text and metadata templates, etc.). You can read more about `Node` and `Document` properties [here](/docs/llamaindex/modules/data).
+Node parsers are a simple abstraction that take a list of `Document` objects, and chunk them into `Node` objects, such that each node is a specific chunk of the parent document. When a document is broken into nodes, all of it's attributes are inherited to the children nodes (i.e. `metadata`, text and metadata templates, etc.). You can read more about `Node` and `Document` properties [here](/typescript/framework/modules/data).

 By default, we will use `Settings.nodeParser` to split the document into nodes. You can also assign a custom `NodeParser` to the `Settings` object.

@@ -0,0 +1,2 @@
+label: Memory
+collapsed: true
@@ -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:
@@ -1,11 +0,0 @@
-{
-  "title": "Data",
-  "pages": [
-    "index",
-    "memory",
-    "readers",
-    "data_index",
-    "ingestion_pipeline",
-    "stores"
-  ]
-}
@@ -0,0 +1,2 @@
+label: Readers
+collapsed: true
@@ -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";

@@ -0,0 +1,2 @@
+label: Llama Parse
+collapsed: true
@@ -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";

@@ -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
@@ -0,0 +1,2 @@
+label: Stores
+collapsed: true
@@ -0,0 +1,2 @@
+label: Chat Stores
+collapsed: true
@@ -6,7 +6,7 @@ Chat stores manage chat history by storing sequences of messages in a structured

 ## Available Chat Stores

- [SimpleChatStore](/docs/api/classes/SimpleChatStore): A simple in-memory chat store with support for [persisting](/docs/llamaindex/modules/data/stores#local-storage) data to disk.
+- [SimpleChatStore](/docs/api/classes/SimpleChatStore): A simple in-memory chat store with support for [persisting](/typescript/framework/modules/data/stores#local-storage) data to disk.

 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.

@@ -0,0 +1,2 @@
+label: Doc Stores
+collapsed: true
@@ -2,12 +2,12 @@
 title: Document Stores
 ---

-Document stores contain ingested document chunks, i.e. [Node](/docs/llamaindex/modules/data)s.
+Document stores contain ingested document chunks, i.e. [Node](/typescript/framework/modules/data)s.

 ## Available Document Stores

- [SimpleDocumentStore](/docs/api/classes/SimpleDocumentStore): A simple in-memory document store with support for [persisting](/docs/llamaindex/modules/data/stores#local-storage) data to disk.
- [PostgresDocumentStore](/docs/api/classes/PostgresDocumentStore): A PostgreSQL document store, see [PostgreSQL Storage](/docs/llamaindex/modules/data/stores#postgresql-storage).
+- [SimpleDocumentStore](/docs/api/classes/SimpleDocumentStore): A simple in-memory document store with support for [persisting](/typescript/framework/modules/data/stores#local-storage) data to disk.
+- [PostgresDocumentStore](/docs/api/classes/PostgresDocumentStore): A PostgreSQL document store, see [PostgreSQL Storage](/typescript/framework/modules/data/stores#postgresql-storage).

 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.

@@ -0,0 +1,2 @@
+label: Index Stores
+collapsed: true
@@ -2,12 +2,12 @@
 title: Index Stores
 ---

-Index stores are underlying storage components that contain metadata(i.e. information created when indexing) about the [index](/docs/llamaindex/modules/data/data_index) itself.
+Index stores are underlying storage components that contain metadata(i.e. information created when indexing) about the [index](/typescript/framework/modules/data/data_index) itself.

 ## Available Index Stores

- [SimpleIndexStore](/docs/api/classes/SimpleIndexStore): A simple in-memory index store with support for [persisting](/docs/llamaindex/modules/data/stores#local-storage) data to disk.
- [PostgresIndexStore](/docs/api/classes/PostgresIndexStore): A PostgreSQL index store, , see [PostgreSQL Storage](/docs/llamaindex/modules/data/stores#postgresql-storage).
+- [SimpleIndexStore](/docs/api/classes/SimpleIndexStore): A simple in-memory index store with support for [persisting](/typescript/framework/modules/data/stores#local-storage) data to disk.
+- [PostgresIndexStore](/docs/api/classes/PostgresIndexStore): A PostgreSQL index store, , see [PostgreSQL Storage](/typescript/framework/modules/data/stores#postgresql-storage).

 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.

@@ -0,0 +1,2 @@
+label: Kv Stores
+collapsed: true
@@ -2,12 +2,12 @@
 title: Key-Value Stores
 ---

-Key-Value Stores represent underlying storage components used in [Document Stores](/docs/llamaindex/modules/data/stores/doc_stores) and [Index Stores](/docs/llamaindex/modules/data/stores/index_stores)
+Key-Value Stores represent underlying storage components used in [Document Stores](/typescript/framework/modules/data/stores/doc_stores) and [Index Stores](/typescript/framework/modules/data/stores/index_stores)

 ## Available Key-Value Stores

- [SimpleKVStore](/docs/api/classes/SimpleKVStore): A simple Key-Value store with support of [persisting](/docs/llamaindex/modules/data/stores#local-storage) data to disk.
- [PostgresKVStore](/docs/api/classes/PostgresKVStore): A PostgreSQL Key-Value store, see [PostgreSQL Storage](/docs/llamaindex/modules/data/stores#postgresql-storage).
+- [SimpleKVStore](/docs/api/classes/SimpleKVStore): A simple Key-Value store with support of [persisting](/typescript/framework/modules/data/stores#local-storage) data to disk.
+- [PostgresKVStore](/docs/api/classes/PostgresKVStore): A PostgreSQL Key-Value store, see [PostgreSQL Storage](/typescript/framework/modules/data/stores#postgresql-storage).

 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.

@@ -0,0 +1,2 @@
+label: Vector Stores
+collapsed: true
@@ -8,7 +8,7 @@ Vector stores save embedding vectors of your ingested document chunks.

 Available Vector Stores are shown on the sidebar to the left. Additionally the following integrations exist without separate documentation:

- [SimpleVectorStore](/docs/api/classes/SimpleVectorStore): A simple in-memory vector store with optional [persistance](/docs/llamaindex/modules/data/stores#local-storage) to disk.
+- [SimpleVectorStore](/docs/api/classes/SimpleVectorStore): A simple in-memory vector store with optional [persistance](/typescript/framework/modules/data/stores#local-storage) to disk.
 - [AstraDBVectorStore](/docs/api/classes/AstraDBVectorStore): A cloud-native, scalable Database-as-a-Service built on Apache Cassandra, see [datastax.com](https://www.datastax.com/products/datastax-astra)
 - [ChromaVectorStore](/docs/api/classes/ChromaVectorStore): An open-source vector database, focused on ease of use and performance, see [trychroma.com](https://www.trychroma.com/)
 - [MilvusVectorStore](/docs/api/classes/MilvusVectorStore): An open-source, high-performance, highly scalable vector database, see [milvus.io](https://milvus.io/)
@@ -0,0 +1,2 @@
+label: Evaluation
+collapsed: true
@@ -29,6 +29,6 @@ These evaluation modules are in the following forms:

 ## Usage

- [Correctness Evaluator](/docs/llamaindex/modules/evaluation/correctness)
- [Faithfulness Evaluator](/docs/llamaindex/modules/evaluation/faithfulness)
- [Relevancy Evaluator](/docs/llamaindex/modules/evaluation/relevancy)
+- [Correctness Evaluator](/typescript/framework/modules/evaluation/correctness)
+- [Faithfulness Evaluator](/typescript/framework/modules/evaluation/faithfulness)
+- [Relevancy Evaluator](/typescript/framework/modules/evaluation/relevancy)
@@ -1,4 +0,0 @@
-{
-  "title": "Modules",
-  "pages": ["models", "agents", "data", "rag", "ui", "evaluation"]
-}
@@ -0,0 +1,2 @@
+label: Models
+collapsed: true
@@ -0,0 +1,2 @@
+label: Embeddings
+collapsed: true
@@ -23,7 +23,7 @@ Settings.embedModel = new OpenAIEmbedding({

 ## Local Embedding

-For local embeddings, you can use the [HuggingFace](/docs/llamaindex/modules/models/embeddings/huggingface) embedding model.
+For local embeddings, you can use the [HuggingFace](/typescript/framework/modules/models/embeddings/huggingface) embedding model.

 ## Local Ollama Embeddings With Remote Host

@@ -0,0 +1,2 @@
+label: Llms
+collapsed: true
@@ -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 +43,15 @@ 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";
+ANTHROPIC_CLAUDE_4_1_OPUS = "anthropic.claude-opus-4-1-20250805-v1:0";
+ANTHROPIC_CLAUDE_4_5_SONNET = "anthropic.claude-sonnet-4-5-20250929-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 +63,71 @@ 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_ANTHROPIC_CLAUDE_4_1_OPUS = "us.anthropic.claude-opus-4-1-20250805-v1:0";
+US_ANTHROPIC_CLAUDE_4_5_SONNET = "us.anthropic.claude-sonnet-4-5-20250929-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_ANTHROPIC_CLAUDE_4_1_OPUS = "eu.anthropic.claude-opus-4-1-20250805-v1:0";
+EU_ANTHROPIC_CLAUDE_4_5_SONNET = "eu.anthropic.claude-sonnet-4-5-20250929-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 +135,11 @@ 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 +168,7 @@ 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";
@@ -33,7 +33,7 @@ export AZURE_OPENAI_DEPLOYMENT="gpt-4" # or some other deployment name

 ## Local LLM

-For local LLMs, currently we recommend the use of [Ollama](/docs/llamaindex/modules/models/llms/ollama) LLM.
+For local LLMs, currently we recommend the use of [Ollama](/typescript/framework/modules/models/llms/ollama) LLM.

 ## Available LLMs

@@ -1,4 +0,0 @@
-{
-  "title": "Models",
-  "pages": ["embeddings", "llms", "prompt"]
-}
@@ -0,0 +1,2 @@
+label: Prompt
+collapsed: true
@@ -82,5 +82,5 @@ const response = await queryEngine.query({

 ## API Reference

- [Response Synthesizer](/docs/llamaindex/modules/rag/response_synthesizer)
+- [Response Synthesizer](/typescript/framework/modules/rag/response_synthesizer)
 - [CompactAndRefine](/docs/api/classes/CompactAndRefine)
@@ -0,0 +1,2 @@
+label: RAG
+collapsed: true
@@ -1,11 +0,0 @@
-{
-  "title": "RAG",
-  "pages": [
-    "retriever",
-    "response_synthesizer",
-    "query_engines",
-    "chat_engine",
-    "node_postprocessors",
-    "evaluation"
-  ]
-}
@@ -0,0 +1,2 @@
+label: Node Postprocessors
+collapsed: true
@@ -0,0 +1,2 @@
+label: Query Engines
+collapsed: true
@@ -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.
@@ -0,0 +1,2 @@
+label: Chat UI
+collapsed: true
@@ -5,7 +5,7 @@ description: Running LlamaIndex workflows with both API endpoints and a user int

 # LlamaIndex Server

-LlamaIndexServer is a Next.js-based application that allows you to quickly launch your [LlamaIndex Workflows](https://ts.llamaindex.ai/docs/llamaindex/modules/agents/workflows) and [Agent Workflows](https://ts.llamaindex.ai/docs/llamaindex/modules/agents/agent_workflow) as an API server with an optional chat UI. It provides a complete environment for running LlamaIndex workflows with both API endpoints and a user interface for interaction.
+LlamaIndexServer is a Next.js-based application that allows you to quickly launch your [LlamaIndex Workflows](https://ts.llamaindex.ai/typescript/framework/modules/agents/workflows) and [Agent Workflows](https://ts.llamaindex.ai/typescript/framework/modules/agents/agent_workflow) as an API server with an optional chat UI. It provides a complete environment for running LlamaIndex workflows with both API endpoints and a user interface for interaction.

 ## Features

@@ -1,6 +0,0 @@
-{
-  "title": "Chat UI",
-  "description": "Use chat-ui to add a chat interface to your LlamaIndexTS application.",
-  "defaultOpen": false,
-  "pages": ["index", "llamaindex-server"]
-}
@@ -0,0 +1,2 @@
+label: Tutorials
+collapsed: true
@@ -0,0 +1,2 @@
+label: Agent with RAG
+collapsed: true
@@ -1,12 +0,0 @@
-{
-  "title": "Agent with RAG",
-  "pages": [
-    "1_setup",
-    "2_create_agent",
-    "3_local_model",
-    "4_agentic_rag",
-    "5_rag_and_tools",
-    "6_llamaparse",
-    "7_qdrant"
-  ]
-}
@@ -2,7 +2,7 @@
 title: Basic Agent 
 ---

-We have a comprehensive, step-by-step [guide to building agents in LlamaIndex.TS](/docs/llamaindex/tutorials/agents/1_setup) that we recommend to learn what agents are and how to build them for production. But building a basic agent is simple:
+We have a comprehensive, step-by-step [guide to building agents in LlamaIndex.TS](/typescript/framework/tutorials/agents/1_setup) that we recommend to learn what agents are and how to build them for production. But building a basic agent is simple:

 ## Set up

@@ -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).
@@ -2,7 +2,7 @@
 title: Local LLMs
 ---

-LlamaIndex.TS supports OpenAI and [other remote LLM APIs](/docs/llamaindex/modules/models/llms). You can also run a local LLM on your machine!
+LlamaIndex.TS supports OpenAI and [other remote LLM APIs](/typescript/framework/modules/models/llms). You can also run a local LLM on your machine!

 ## Using a local model via Ollama

@@ -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).
@@ -1,12 +0,0 @@
-{
-  "title": "Tutorials",
-  "pages": [
-    "basic_agent",
-    "rag",
-    "agents",
-    "workflows",
-    "local_llm",
-    "chatbot",
-    "structured_data_extraction"
-  ]
-}
@@ -0,0 +1,2 @@
+label: Rag
+collapsed: true
@@ -30,12 +30,12 @@ LlamaIndex.TS help you prepare the knowledge base with a suite of data connector

 ![](/_static/concepts/indexing.jpg)

-[**Data Loaders**](/docs/llamaindex/modules/data/readers):
+[**Data Loaders**](/typescript/framework/modules/data/readers):
 A data connector (i.e. `Reader`) ingest data from different data sources and data formats into a simple `Document` representation (text and simple metadata).

-[**Documents / Nodes**](/docs/llamaindex/modules/data): A `Document` is a generic container around any data source - for instance, a PDF, an API output, or retrieved data from a database. A `Node` is the atomic unit of data in LlamaIndex and represents a "chunk" of a source `Document`. It's a rich representation that includes metadata and relationships (to other nodes) to enable accurate and expressive retrieval operations.
+[**Documents / Nodes**](/typescript/framework/modules/data): A `Document` is a generic container around any data source - for instance, a PDF, an API output, or retrieved data from a database. A `Node` is the atomic unit of data in LlamaIndex and represents a "chunk" of a source `Document`. It's a rich representation that includes metadata and relationships (to other nodes) to enable accurate and expressive retrieval operations.

-[**Data Indexes**](/docs/llamaindex/modules/data/data_index):
+[**Data Indexes**](/typescript/framework/modules/data/data_index):
 Once you've ingested your data, LlamaIndex helps you index data into a format that's easy to retrieve.

 Under the hood, LlamaIndex parses the raw documents into intermediate representations, calculates vector embeddings, and stores your data in-memory or to disk.
@@ -58,19 +58,19 @@ These building blocks can be customized to reflect ranking preferences, as well

 #### Building Blocks

-[**Retrievers**](/docs/llamaindex/modules/rag/retriever):
+[**Retrievers**](/typescript/framework/modules/rag/retriever):
 A retriever defines how to efficiently retrieve relevant context from a knowledge base (i.e. index) when given a query.
 The specific retrieval logic differs for different indices, the most popular being dense retrieval against a vector index.

-[**Response Synthesizers**](/docs/llamaindex/modules/rag/response_synthesizer):
+[**Response Synthesizers**](/typescript/framework/modules/rag/response_synthesizer):
 A response synthesizer generates a response from an LLM, using a user query and a given set of retrieved text chunks.

 #### Pipelines

-[**Query Engines**](/docs/llamaindex/modules/rag/query_engines):
+[**Query Engines**](/typescript/framework/modules/rag/query_engines):
 A query engine is an end-to-end pipeline that allow you to ask question over your data.
 It takes in a natural language query, and returns a response, along with reference context retrieved and passed to the LLM.

-[**Chat Engines**](/docs/llamaindex/modules/rag/chat_engine):
+[**Chat Engines**](/typescript/framework/modules/rag/chat_engine):
 A chat engine is an end-to-end pipeline for having a conversation with your data
 (multiple back-and-forth instead of a single question & answer).
@@ -2,7 +2,7 @@
 title: Retrieval Augmented Generation (RAG) 
 ---

-One of the most common use-cases for LlamaIndex is Retrieval-Augmented Generation or RAG, in which your data is indexed and selectively retrieved to be given to an LLM as source material for responding to a query. You can learn more about the [concepts behind RAG](/docs/llamaindex/tutorials/rag/concepts).
+One of the most common use-cases for LlamaIndex is Retrieval-Augmented Generation or RAG, in which your data is indexed and selectively retrieved to be given to an LLM as source material for responding to a query. You can learn more about the [concepts behind RAG](/typescript/framework/tutorials/rag/concepts).

 ## Set up the project

@@ -14,9 +14,9 @@ npm i -D typescript @types/node
 npm i llamaindex
 ```

-Then, check out the [installation](/docs/llamaindex/getting_started/installation) steps to install LlamaIndex.TS and prepare an OpenAI key.
+Then, check out the [installation](/typescript/framework/getting_started/installation) steps to install LlamaIndex.TS and prepare an OpenAI key.

-You can use [other LLMs](/docs/llamaindex/modules/models/llms) via their APIs; if you would prefer to use local models check out our [local LLM example](/docs/llamaindex/tutorials/local_llm).
+You can use [other LLMs](/typescript/framework/modules/models/llms) via their APIs; if you would prefer to use local models check out our [local LLM example](/typescript/framework/tutorials/local_llm).

 ## Run queries

@@ -2,9 +2,9 @@
 title: Structured data extraction 
 ---

-Make sure you have installed LlamaIndex.TS and have an OpenAI key. If you haven't, check out the [installation](/docs/llamaindex/getting_started/installation) guide.
+Make sure you have installed LlamaIndex.TS and have an OpenAI key. If you haven't, check out the [installation](/typescript/framework/getting_started/installation) guide.

-You can use [other LLMs](/docs/llamaindex/modules/models/llms) via their APIs; if you would prefer to use local models check out our [local LLM example](/docs/llamaindex/tutorials/local_llm).
+You can use [other LLMs](/typescript/framework/modules/models/llms) via their APIs; if you would prefer to use local models check out our [local LLM example](/typescript/framework/tutorials/local_llm).

 ## Set up

@@ -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
+}
+```
@@ -173,4 +173,4 @@ You can combine these utilities with other stream operators like `filter` and `m

 ## Next Steps

-To learn more about workflows, check out [the Workflows documentation](/docs/llamaindex/modules/agents/workflows).
+To learn more about workflows, check out [the Workflows documentation](/typescript/framework/modules/agents/workflows).
@@ -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);
-  }
-}
@@ -15,6 +15,6 @@
    "wrangler": "^3.89.0"
  },
  "dependencies": {
-    "hono": "^4.6.11"
+    "hono": "^4.9.7"
  }
 }
@@ -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
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
github-actions[bot]	768d99a488	Release (#2209 )	2025-09-29 12:04:57 -06:00
Logan	b4c55319da	initial sonnet 4 5 support (#2208 )	2025-09-29 11:58:03 -06:00
Laurie Voss	d3a8b764f0	Fix broken links from Astro migration (#2206 )	2025-09-17 11:14:23 -07:00
Laurie Voss	676e3f8993	Add GitHub Actions workflow for Vercel deployment of developer hub (#2205 )	2025-09-16 13:43:56 -07:00
dependabot[bot]	7283909755	chore(deps): bump next from 15.3.3 to 15.4.7 (#2183 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-09-15 12:29:08 +08:00
github-actions[bot]	19e5c318a0	Release 0.12.0 (#2204 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-09-15 12:28:24 +08:00
Marcus Schiesser	d49301555f	chore: replace cloud package with llama-cloud-services (#2145 ) Co-authored-by: Thuc Pham <thuc@lingble.com>	2025-09-15 12:09:17 +08:00
dependabot[bot]	f648bb7b90	chore(deps): bump hono from 4.7.7 to 4.9.7 (#2203 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-09-15 10:52:50 +08:00
Thuc Pham	06f884a437	feat: return structured object from llm.exec (#2198 )	2025-09-15 10:51:06 +08:00
dependabot[bot]	9e66861d07	chore(deps): bump vite from 5.4.19 to 6.3.6 (#2199 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-09-12 10:32:22 +08:00
Marcus Schiesser	ae74f70d7d	chore: update @llamaindex/workflow-docs (#2197 )	2025-09-11 15:47:46 +08:00
github-actions[bot]	5b4a53177e	Release 0.11.29 (#2188 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-09-11 10:44:29 +08:00
Thuc Pham	5da1cda939	feat: support zod v4 & v3 (#2186 ) Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>	2025-09-11 10:34:45 +08:00
Thuc Pham	1285e381bd	feat: add ci-build script for size limit testing (#2194 )	2025-09-10 18:09:47 +08:00
Neha Prasad	5d5cd44276	fix: anthropic temperature parameter not respecting value 0 (#2190 ) Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>	2025-09-10 11:45:12 +08:00
hunter	ed37c645af	chore: addition of apac claude 4 sonnet to aws records (#2189 )	2025-09-10 11:44:57 +08:00
hunter	c40adafecc	chore: add latest google models (#2191 )	2025-09-10 11:44:30 +08:00
dependabot[bot]	995b465205	chore(deps-dev): bump vite from 6.3.3 to 6.3.6 (#2193 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-09-10 10:46:55 +08:00
Jeremy B. Merrill	8929dcf1dd	vectorStoreIndex has new option progressCallback (#2187 ) Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>	2025-09-05 10:37:22 +08:00
github-actions[bot]	af0b79f1cd	Release 0.11.28 (#2174 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-08-28 17:28:15 +08:00
Thuc Pham	1995b38660	chore: bump @llamaindex/workflow-core in @llamaindex/workflow package (#2181 )	2025-08-27 17:30:09 +08:00
Raj Shrestha	001a5159cf	chore: add minimal reasoning effort for gpt5 (#2177 ) Co-authored-by: Raj Shrestha <raj.shrestha@carelon.com>	2025-08-27 11:52:58 +08:00
Zhanghao	9d7d2052e7	fix: fix the problem that the usage field in the streaming response was not handled correctly (#2173 )	2025-08-24 12:33:14 +08:00
Orry	fd90e25f0e	Docs settings per request (#2166 ) Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de> Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>	2025-08-20 16:31:26 +08:00
github-actions[bot]	97c00d67c3	Release 0.11.27 (#2169 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-08-19 12:11:06 +08:00
Daniel	6ebd7c2f13	fix: bedrock complete using actual modelId (#2172 )	2025-08-19 11:04:32 +08:00
Clelia (Astra) Bertelli	0267bb0e8e	feat: add responseFormat to llm.exec (#2167 )	2025-08-13 12:39:37 +08:00
Marcus Schiesser	7875ee91e6	chore: update chat-ui docs (#2168 )	2025-08-13 12:26:22 +08:00
Orry	e3405fca44	chore: point the local llm full example to the correct URL (#2162 ) Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>	2025-08-08 14:56:35 +08:00
github-actions[bot]	f3bc2b61e7	Release (#2164 )	2025-08-07 15:18:42 -06:00
Logan	4c703767b7	Adding GPT-5 support (#2163 )	2025-08-07 13:39:47 -06:00
github-actions[bot]	a27648200d	Release (#2161 )	2025-08-07 13:39:20 -06:00
abdeliibrahim	c93bb02002	#2159 Remove unneeded console logs from gemini stream (#2160 ) Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>	2025-08-07 11:38:35 +08:00
github-actions[bot]	e9ded4e65f	Release (#2154 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-08-06 12:18:06 +08:00
Marcus Schiesser	47a6f5fe5a	chore: bump ollama (#2156 )	2025-08-06 12:11:17 +08:00
Marcus Schiesser	b80f33e264	chore: add opus 4.1 and fix prompt caching (#2155 )	2025-08-06 11:54:27 +08:00
Alex Yang	b6409b6823	chore: bump openai (#2152 ) Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>	2025-08-06 10:58:45 +08:00
github-actions[bot]	db3f556cb4	Release 0.11.26 (#2149 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-08-05 12:00:17 +08:00
Marcus Schiesser	4b5179169b	chore: add deprecation to readme (#2150 )	2025-08-05 11:53:35 +08:00
abdeliibrahim	971d37ceba	fix(deepseek): add 'as const' assertion to DEEPSEEK_MODELS for correct TypeScript inference (#2148 ) Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>	2025-08-05 10:30:13 +08:00
github-actions[bot]	3e0ffdc688	Release 0.11.25 (#2144 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>	2025-07-31 12:18:18 +08:00
Marcus Schiesser	049471bade	chore: deprecate cloud packages (#2143 )	2025-07-31 12:12:56 +08:00
github-actions[bot]	1e296ebe72	Release 0.11.24 (#2141 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-07-30 12:56:45 -04:00
Marcus Schiesser	f9f1de9516	chore: use Logger for core (#2139 )	2025-07-30 11:43:45 +08:00
Twisha Bansal	f576812e7a	docs: Using MCP Toolbox for Databases with LlamaIndex (#2138 )	2025-07-30 11:19:34 +08:00
Adrian Lyjak	c3bf3c7178	Adding support for page citations, and refactor the confidence into the field metadata (#2140 )	2025-07-30 10:25:19 +08:00
github-actions[bot]	38487da65d	Release 0.11.23 (#2136 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-07-28 14:07:23 +08:00
Marcus Schiesser	f29799e385	feat: Add toolcall callbacks to agent workflows (#2137 )	2025-07-24 15:37:14 +08:00
Marcus Schiesser	9bca30620b	fix: docs build	2025-07-23 12:55:35 +08:00
Marcus Schiesser	7224c06409	feat: Add logger and callbacks to llm.exec (#2135 )	2025-07-23 12:37:02 +08:00
github-actions[bot]	29c7cf0989	Release 0.11.22 (#2131 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>	2025-07-23 11:30:04 +08:00
Marcus Schiesser	c65a2dc4a7	chore: Deprecate community package and link to AWS package (#2134 )	2025-07-23 11:05:50 +08:00
Terence Sim	f1c5079290	docs: updated bedrock import and supported models (#2129 ) Co-authored-by: Terence Sim <40583743+InTheAxis@users.noreply.github.com>	2025-07-23 10:40:49 +08:00
Terence Sim	9ed31958a7	chore: add logger as param to AgentWorkflow constructor (#2130 ) Co-authored-by: Terence Sim <40583743+InTheAxis@users.noreply.github.com> Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>	2025-07-22 16:35:28 +08:00
github-actions[bot]	e4c7113614	Release 0.11.21 (#2128 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-07-22 12:23:58 +08:00
Thuc Pham	38da40bc98	feat: VectoryMemoryBlock (#2110 ) Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>	2025-07-22 12:18:09 +08:00
Marcus Schiesser	4d50ca4d84	chore: add streamchat test (#2122 )	2025-07-22 11:30:01 +08:00
github-actions[bot]	8b5253a297	Release (#2127 )	2025-07-21 15:40:31 -06:00
Logan	ea15e75c89	deployment docs nits (#2126 )	2025-07-21 15:30:37 -06:00
github-actions[bot]	3be87d4670	Release 0.11.20 (#2121 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: himself65 <14026360+himself65@users.noreply.github.com>	2025-07-21 09:37:44 -07:00
Terence Sim	94da13db0d	fix: azure openai streamchat empty delta throw TypeError (#2118 ) Co-authored-by: Terence Sim <40583743+InTheAxis@users.noreply.github.com>	2025-07-21 09:16:09 -07:00
Terence Sim	acd50ea99f	chore: replaced console.log with logger type from @llamaindex/env (#2123 ) Co-authored-by: Terence Sim <40583743+InTheAxis@users.noreply.github.com>	2025-07-21 09:14:06 -07:00
Adrian Lyjak	2967d57ac0	feat: default to _public agent data (#2117 )	2025-07-21 09:07:15 -07:00
Thuc Pham	a8ec08c682	fix: ensure correct message content in agent workflow (#2114 ) Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>	2025-07-21 15:13:27 +08:00
Terence Sim	678b327051	feat: added apac bedrock models (#2119 ) Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>	2025-07-21 12:13:37 +08:00
Jeremy B. Merrill	650eeb1df3	fix: GeminiEmbedding should send batches of max 100 (#2099 ) Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>	2025-07-21 12:12:42 +08:00
Laurie Voss	50f6747758	Instrumenting with Google Tag Manager (in addition to Google Analytics) (#2116 )	2025-07-20 13:18:09 -07:00
github-actions[bot]	12414a6836	Release (#2113 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-07-18 13:54:38 +08:00
Marcus Schiesser	856dd8cca8	fix: assume new models are function call models (#2112 )	2025-07-18 12:52:43 +08:00
Jerry Cheng	d8f4f6a859	Update SupabaseVectorStore.ts to fix score calculating error (#2109 ) Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>	2025-07-18 12:48:47 +08:00