Release 0.10.5 (#1922)

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

.github/workflows/lint_on_push_or_pull.yml

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

.github/workflows/preview.yml

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

.github/workflows/test.yml

@@ -23,7 +23,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        node-version: [18.x, 20.x, 22.x, 23.x]
+        node-version: [20.x, 22.x, 23.x]
     name: E2E on Node.js ${{ matrix.node-version }}
     runs-on: ubuntu-latest
     steps:
@@ -53,7 +53,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        node-version: [18.x, 20.x, 22.x, 23.x]
+        node-version: [20.x, 22.x, 23.x]
     name: Test on Node.js ${{ matrix.node-version }}
     runs-on: ubuntu-latest
     steps:

.nvmrc

@@ -1 +1 @@
-20
+22

.prettierignore

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

apps/next/CHANGELOG.md

@@ -1,5 +1,51 @@
 # @llamaindex/doc
 
+## 0.2.17
+
+### Patch Changes
+
+- Updated dependencies [9b2e25a]
+  - @llamaindex/openai@0.3.6
+  - @llamaindex/core@0.6.4
+  - llamaindex@0.10.5
+  - @llamaindex/cloud@4.0.6
+  - @llamaindex/node-parser@2.0.4
+  - @llamaindex/readers@3.1.2
+  - @llamaindex/workflow@1.1.1
+
+## 0.2.16
+
+### Patch Changes
+
+- Updated dependencies [7e8e454]
+- Updated dependencies [2225ffd]
+- Updated dependencies [6ddf1c1]
+- Updated dependencies [bc53342]
+- Updated dependencies [41953a3]
+  - @llamaindex/workflow@1.1.0
+  - @llamaindex/cloud@4.0.5
+  - llamaindex@0.10.4
+
+## 0.2.15
+
+### Patch Changes
+
+- Updated dependencies [3ee8c83]
+  - @llamaindex/core@0.6.3
+  - llamaindex@0.10.3
+  - @llamaindex/openai@0.3.5
+  - @llamaindex/cloud@4.0.4
+  - @llamaindex/node-parser@2.0.3
+  - @llamaindex/readers@3.1.1
+  - @llamaindex/workflow@1.0.4
+
+## 0.2.14
+
+### Patch Changes
+
+- Updated dependencies [1e59695]
+  - @llamaindex/readers@3.1.0
+
 ## 0.2.13
 
 ### Patch Changes

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.13",
+  "version": "0.2.17",
   "private": true,
   "scripts": {
     "postinstall": "fumadocs-mdx",
@@ -15,7 +15,7 @@
   "dependencies": {
     "@huggingface/transformers": "^3.5.0",
     "@icons-pack/react-simple-icons": "^10.1.0",
-    "@llama-flow/docs": "0.0.3",
+    "@llama-flow/docs": "0.0.8",
     "@llamaindex/chat-ui": "0.2.0",
     "@llamaindex/cloud": "workspace:*",
     "@llamaindex/core": "workspace:*",
@@ -90,9 +90,9 @@
     "remark-stringify": "^11.0.0",
     "tailwindcss": "^4.0.9",
     "tsx": "^4.19.3",
-    "typedoc": "0.28.2",
+    "typedoc": "0.28.3",
     "typedoc-plugin-markdown": "^4.6.2",
-    "typedoc-plugin-merge-modules": "^7.0.0",
+    "typedoc-plugin-merge-modules": " ^7.0.0",
     "typescript": "^5.7.3"
   }
 }

apps/next/scripts/generate-docs.mts

@@ -1,4 +1,3 @@
-import { generateFiles as openapiGenerateFiles } from "fumadocs-openapi";
 import {
   createGenerator,
   generateFiles as typescriptGenerateFiles,
@@ -14,18 +13,12 @@ const apiRefOut = "./src/content/docs/api";
 // clean generated files
 rimrafSync(out, {
   filter(v) {
-    return !v.endsWith("index.mdx") && !v.endsWith("meta.json");
+    return !v.endsWith("index.md") && !v.endsWith("meta.json");
   },
 });
 
-void openapiGenerateFiles({
-  input: ["../../packages/cloud/openapi.json"],
-  output: "./src/content/docs/cloud/api",
-  groupBy: "tag",
-});
-
 void typescriptGenerateFiles(generator, {
-  input: ["./src/content/docs/api/**/*.mdx"],
+  input: ["./src/content/docs/api/**/*.md"],
   output: (file) => path.resolve(path.dirname(file), path.basename(file)),
   transformOutput,
 });
@@ -34,19 +27,22 @@ function transformOutput(filePath: string, content: string) {
   const fileName = path.basename(filePath);
   let title = fileName.split(".")[0];
   if (title === "index") title = "LlamaIndex API Reference";
-  return `---\ntitle: ${title}\n---\n\n${transformAbsoluteUrl(content, filePath)}`;
+  return `---\ntitle: ${title}\n---\n\n${transformAbsoluteUrl(
+    content.replace(/(?<!\\)\{([^}]+)(?<!\\)}/g, "\\{$1\\}"),
+    filePath,
+  )}`;
 }
 
 /**
- * Transforms the content by converting relative MDX links to absolute docs API links
- * Example: [text](../type-aliases/TaskHandler.mdx) -> [text](/docs/api/type-aliases/TaskHandler)
- * [text](BaseChatEngine.mdx) -> [text](/docs/api/classes/BaseChatEngine)
- * [text](BaseVectorStore.mdx#constructors) -> [text](/docs/api/classes/BaseVectorStore#constructors)
- * [text](TaskStep.mdx) -> [text](/docs/api/type-aliases/TaskStep)
+ * Transforms the content by converting relative MD links to absolute docs API links
+ * Example: [text](../type-aliases/TaskHandler.md) -> [text](/docs/api/type-aliases/TaskHandler)
+ * [text](BaseChatEngine.md) -> [text](/docs/api/classes/BaseChatEngine)
+ * [text](BaseVectorStore.md#constructors) -> [text](/docs/api/classes/BaseVectorStore#constructors)
+ * [text](TaskStep.md) -> [text](/docs/api/type-aliases/TaskStep)
  */
 function transformAbsoluteUrl(content: string, filePath: string) {
   const group = path.dirname(filePath).split(path.sep).pop();
-  return content.replace(/\]\(([^)]+)\.mdx([^)]*)\)/g, (_, slug, anchor) => {
+  return content.replace(/\]\(([^)]+)\.md([^)]*)\)/g, (_, slug, anchor) => {
     const slugParts = slug.split("/");
     const fileName = slugParts[slugParts.length - 1];
     const fileGroup = slugParts[slugParts.length - 2] ?? group;

apps/next/scripts/validate-links.mts

@@ -28,14 +28,14 @@ interface RelativeLinkResult {
  * Get all valid documentation routes from the content directory
  */
 async function getValidRoutes(): Promise<Set<string>> {
-  const mdxFiles = await glob("**/*.mdx", { cwd: CONTENT_DIR });
+  const mdxFiles = await glob("**/*.mdx?", { cwd: CONTENT_DIR });
 
   const routes = new Set<string>();
 
   // Add each MDX file as a valid route
   for (const file of mdxFiles) {
     // Remove .mdx extension and normalize to route format
-    let route = file.replace(/\.mdx$/, "");
+    let route = file.replace(/\.mdx?$/, "");
 
     // Handle index files
     if (route.endsWith("/index")) {
@@ -131,7 +131,7 @@ function findRelativeLinksInFile(
  * Find relative links in all MDX files
  */
 async function findRelativeLinks(): Promise<RelativeLinkResult[]> {
-  const mdxFiles = await glob("**/*.mdx", { cwd: CONTENT_DIR });
+  const mdxFiles = await glob("**/*.mdx?", { cwd: CONTENT_DIR });
   const results: RelativeLinkResult[] = [];
 
   for (const file of mdxFiles) {
@@ -150,7 +150,7 @@ async function findRelativeLinks(): Promise<RelativeLinkResult[]> {
 }
 
 async function validateLinks(): Promise<LinkValidationResult[]> {
-  const mdxFiles = await glob("**/*.mdx", { cwd: CONTENT_DIR });
+  const mdxFiles = await glob("**/*.mdx?", { cwd: CONTENT_DIR });
   const validRoutes = await getValidRoutes();
 
   const results: LinkValidationResult[] = [];

apps/next/source.config.ts

@@ -1,8 +1,10 @@
-import { rehypeCodeDefaultOptions } from "fumadocs-core/mdx-plugins";
+import {
+  rehypeCodeDefaultOptions,
+  remarkStructure,
+} from "fumadocs-core/mdx-plugins";
 import { fileGenerator, remarkDocGen, remarkInstall } from "fumadocs-docgen";
 import { defineConfig, defineDocs } from "fumadocs-mdx/config";
 import { transformerTwoslash } from "fumadocs-twoslash";
-import { createFileSystemTypesCache } from "fumadocs-twoslash/cache-fs";
 import rehypeKatex from "rehype-katex";
 import remarkMath from "remark-math";
 
@@ -24,11 +26,7 @@ export default defineConfig({
       },
       transformers: [
         ...(rehypeCodeDefaultOptions.transformers ?? []),
-        transformerTwoslash({
-          typesCache: createFileSystemTypesCache({
-            dir: ".next/cache/twoslash",
-          }),
-        }),
+        transformerTwoslash(),
         {
           name: "transformers:remove-notation-escape",
           code(hast) {
@@ -49,6 +47,7 @@ export default defineConfig({
       ],
     },
     remarkPlugins: [
+      remarkStructure,
       remarkMath,
       [remarkInstall, { persist: { id: "package-manager" } }],
       [remarkDocGen, { generators: [fileGenerator()] }],

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

@@ -26,7 +26,7 @@ const llm = openai();
 const response = await llm.chat({
   messages: [{ content: "Tell me a joke.", role: "user" }],
 });`,
-  `import { agent } from "llamaindex";
+  `import { agent } from "@llamaindex/workflow";
 import { openai } from "@llamaindex/openai";
 
 const analyseAgent = agent({
@@ -36,7 +36,7 @@ const analyseAgent = agent({
 });
 const response = await analyseAgent.run(\`Analyse the given data:
 \${data}\`);`,
-  `import { agent, multiAgent } from "llamaindex";
+  `import { agent, multiAgent } from "@llamaindex/workflow";
 import { openai } from "@llamaindex/openai";
 
 const analyseAgent = agent({
@@ -113,8 +113,9 @@ export default function HomePage() {
           description="Truly powerful retrieval-augmented generation applications use agentic techniques, and LlamaIndex.TS makes it easy to build them."
         >
           <CodeBlock
-            code={`import { agent, SimpleDirectoryReader, VectorStoreIndex } from "llamaindex";
+            code={`import { SimpleDirectoryReader, VectorStoreIndex } from "llamaindex";
 import { openai } from "@llamaindex/openai";
+import { agent } from "@llamaindex/workflow";
 
 // load documents from current directoy into an index
 const reader = new SimpleDirectoryReader();

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

@@ -4,7 +4,7 @@ import { createFromSource } from "fumadocs-core/search/server";
 
 // TODO: migrate to another search service, I don't think Vercel can handle that many of documents.
 export const { GET } = createFromSource(source, (page) => ({
-  id: page.url,
+  id: page.file.path,
   title: page.data.title,
   description: page.data.description,
   url: page.url,

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

@@ -9,6 +9,7 @@ export default function Layout({ children }: { children: ReactNode }) {
     <DocsLayout
       tree={source.pageTree}
       {...baseOptions}
+      links={[]}
       nav={{
         ...baseOptions.nav,
       }}

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

@@ -27,9 +27,19 @@ export const baseOptions: BaseLayoutProps = {
   githubUrl: "https://github.com/run-llama/LlamaIndexTS",
   links: [
     {
-      text: "Docs",
+      text: "TypeScript",
       url: DOCUMENT_URL,
       active: "nested-url",
     },
+    {
+      text: "Python",
+      url: "https://docs.llamaindex.ai",
+      active: "url",
+    },
+    {
+      text: "LlamaCloud",
+      url: "https://docs.cloud.llamaindex.ai/",
+      active: "url",
+    },
   ],
 };

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

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

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

@@ -11,8 +11,3 @@ export const CodeNodeParserDemo = dynamic(() =>
     (mod) => mod.CodeNodeParserDemo,
   ),
 );
-export const WorkflowStreamingDemo = dynamic(() =>
-  import("@/components/demo/workflow-streaming-ui").then(
-    (mod) => mod.WorkflowStreamingDemo,
-  ),
-);

apps/next/src/components/demo/workflow-streaming-ui.tsx

@@ -1,152 +0,0 @@
-"use client";
-import FlowInput from "@/components/flow-input";
-import { Button } from "@/components/ui/button";
-import {
-  StartEvent,
-  StopEvent,
-  Workflow,
-  WorkflowEvent,
-} from "@llamaindex/workflow";
-import { ReactNode, startTransition, useState } from "react";
-import { StickToBottom, useStickToBottomContext } from "use-stick-to-bottom";
-
-class ComputeEvent extends WorkflowEvent<number> {
-  constructor(data: number) {
-    super(data);
-  }
-}
-
-class ComputeResultEvent extends WorkflowEvent<number> {
-  constructor(data: number) {
-    super(data);
-  }
-}
-
-type ContextData = {
-  sum: number;
-};
-
-const workflow = new Workflow<ContextData, number, number>();
-
-const max = 1000;
-const min = 100;
-
-workflow.addStep(
-  {
-    inputs: [StartEvent<number>],
-    outputs: [StopEvent<number>],
-  },
-  async (context, event) => {
-    const total = event.data;
-    for (let i = 0; i < total; i++) {
-      context.sendEvent(new ComputeEvent(i));
-    }
-    console.log("waiting");
-    const computeResults = await Promise.all(
-      Array.from({ length: total }).map(() =>
-        context.requireEvent(ComputeResultEvent),
-      ),
-    );
-    context.data.sum = computeResults.reduce(
-      (acc, result) => acc + result.data,
-      0,
-    );
-    console.log("stop");
-    return new StopEvent(context.data.sum);
-  },
-);
-
-workflow.addStep(
-  {
-    inputs: [ComputeEvent],
-    outputs: [ComputeResultEvent],
-  },
-  async (context, event) => {
-    await new Promise((resolve) =>
-      setTimeout(resolve, Math.floor(Math.random() * (max - min + 1) + min)),
-    );
-    return new ComputeResultEvent(event.data);
-  },
-);
-
-function ScrollToBottom() {
-  const { isAtBottom, scrollToBottom } = useStickToBottomContext();
-
-  return (
-    !isAtBottom && (
-      <button
-        className="i-ph-arrow-circle-down-fill absolute bottom-0 left-[50%] translate-x-[-50%] rounded-lg text-4xl"
-        onClick={() => scrollToBottom()}
-      />
-    )
-  );
-}
-
-export function WorkflowStreamingDemo() {
-  const [ui, setUI] = useState<ReactNode[]>([
-    <div key={0} className="bg-gray-100 dark:bg-gray-800">
-      Waiting for workflow to start
-    </div>,
-  ]);
-  const [total, setTotal] = useState<number>(10);
-
-  return (
-    <div className="flex w-full flex-col items-start gap-2">
-      <div className="flex flex-row items-center justify-center">
-        <div className="mr-2 text-lg">Compute total</div>{" "}
-        <FlowInput value={total} onChange={(value) => setTotal(value)} />
-      </div>
-      <Button
-        onClick={async () => {
-          startTransition(() => {
-            setUI([]);
-          });
-          const context = workflow.run(total, {
-            sum: 0,
-          });
-          let i = 0;
-          for await (const event of context) {
-            console.log(event);
-            if (event instanceof ComputeEvent) {
-              setUI((ui) => [
-                ...ui,
-                <div key={i++} className="bg-yellow-100 dark:bg-yellow-800">
-                  Computing task id: {event.data}
-                </div>,
-              ]);
-            } else if (event instanceof ComputeResultEvent) {
-              setUI((ui) => [
-                ...ui,
-                <div key={i++} className="bg-green-100 dark:bg-green-800">
-                  Computed task id: {event.data}
-                </div>,
-              ]);
-            } else if (event instanceof StartEvent) {
-              setUI((ui) => [
-                ...ui,
-                <div key={i++} className="bg-blue-100 dark:bg-blue-800">
-                  Started workflow with total {event.data}
-                </div>,
-              ]);
-            } else if (event instanceof StopEvent) {
-              setUI((ui) => [
-                ...ui,
-                <div key={i++} className="bg-red-100 dark:bg-red-800">
-                  Workflow stopped
-                </div>,
-              ]);
-            }
-          }
-        }}
-      >
-        Start Workflow
-      </Button>
-      <StickToBottom className="flex max-h-96 w-full flex-col gap-2 overflow-y-auto rounded-lg border border-gray-200 p-2">
-        <StickToBottom.Content className="flex flex-col gap-2">
-          {ui}
-        </StickToBottom.Content>
-        <ScrollToBottom />
-      </StickToBottom>
-    </div>
-  );
-}

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

@@ -1,8 +0,0 @@
----
-title: LlamaCloud
-description: LlamaCloud is a new generation of managed parsing, ingestion, and retrieval services, designed to bring production-grade context-augmentation to your LLM and RAG applications.
----
-
-This is TypeScript binding for LlamaCloud API. It provides a simple way to interact with LlamaCloud API.
-
-If you are looking for the official documentation, please visit the [Official Document](https://docs.cloud.llamaindex.ai/)

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

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

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

@@ -9,10 +9,10 @@ To install llamaindex, run the following command:
 npm i llamaindex
 ```
 
-In most cases, you'll also need an LLM package to use LlamaIndex. For example, to use the OpenAI LLM, you would install the following:
+In most cases, you'll also need an LLM package and the Workflow package to use LlamaIndex. For example, to use the OpenAI LLM with agents, you would install the following:
 
 ```package-install
-npm i @llamaindex/openai
+npm i @llamaindex/openai @llamaindex/workflow
 ```
 
 Go to [LLM APIs](/docs/llamaindex/modules/models/llms) to find out how to use other LLMs.

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

@@ -40,19 +40,7 @@ Make sure to set [moduleResolution](https://www.typescriptlang.org/docs/handbook
 }
 ```
 
-We recommend using `bundler` or `nodenext`, but due to popularity of `node`, we still added support for it, but with import path limitations.
-
-So you may encounter type errors when importing sub paths from the `llamaindex` package like:
-
-```ts
-import { Settings } from "llamaindex";
-```
-
-The simplest way to fix this without changing `moduleResolution` is to import directly from `llamaindex`:
-
-```ts
-import { Settings } from "llamaindex";
-```
+We recommend using `bundler` or `nodenext`, but due to popularity of `node`, we still added support for it.
 
 ## Enable AsyncIterable for `Web Stream` API
 
@@ -68,7 +56,8 @@ Some modules uses `Web Stream` API like `ReadableStream` and `WritableStream`, y
 ```
 
 ```typescript
-import { agent, tool } from 'llamaindex'
+import { tool } from 'llamaindex'
+import { agent } from "@llamaindex/workflow";
 import { openai } from "@llamaindex/openai";
 
 Settings.llm = openai({

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

@@ -12,7 +12,8 @@ Agent Workflows are a powerful system that enables you to create and orchestrate
 The simplest use case is creating a single agent with specific tools. Here's an example of creating an assistant that tells jokes:
 
 ```typescript
-import { agent, tool } from "llamaindex";
+import { tool } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
 import { openai } from "@llamaindex/openai";
 
 // Define a joke-telling tool
@@ -40,17 +41,17 @@ console.log(result); // Baby Llama is called cria
 Agent Workflows provide a unified interface for event streaming, making it easy to track and respond to different events during execution:
 
 ```typescript
-import { AgentToolCall, AgentStream } from "llamaindex";
+import { agentToolCallEvent, agentStreamEvent } from "@llamaindex/workflow";
 
 // Get the workflow execution context
-const context = workflow.run("Tell me something funny");
+const events = workflow.runStream("Tell me something funny");
 
 // Stream and handle events
-for await (const event of context) {
-  if (event instanceof AgentToolCall) {
+for await (const event of events) {
+  if (agentToolCallEvent.include(event)) {
     console.log(`Tool being called: ${event.data.toolName}`);
   }
-  if (event instanceof AgentStream) {
+  if (agentStreamEvent.include(event)) {
     process.stdout.write(event.data.delta);
   }
 }
@@ -68,7 +69,8 @@ An Agent Workflow can orchestrate multiple agents, enabling complex interactions
 Here's an example of a multi-agent system that combines joke-telling and weather information:
 
 ```typescript
-import { multiAgent, agent, tool } from "llamaindex";
+import { tool } from "llamaindex";
+import { multiAgent, agent } from "@llamaindex/workflow";
 import { openai } from "@llamaindex/openai";
 import { z } from "zod";
 

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

@@ -17,7 +17,8 @@ The `parameters` field in the tool configuration is defined using `zod`, a TypeS
 
 Example:
 ```ts
-import { agent, tool } from "llamaindex";
+import { tool } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
 import { z } from "zod";
 
 // first arg is LLM input, second is bound arg
@@ -46,7 +47,7 @@ In this example, `z.object` is used to define a schema for the `parameters` wher
 You can import built-in tools from the `@llamaindex/tools` package.
 
 ```ts
-import { agent } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
 import { wiki } from "@llamaindex/tools";
 
 const researchAgent = agent({
@@ -57,6 +58,41 @@ const researchAgent = agent({
 });
 ```
 
+## MCP tools
+
+If you have a MCP server running, you can fetch tools from the server and use them in your agents.
+
+```ts
+// 1. Import MCP tools adapter
+import { mcp } from "@llamaindex/tools";
+import { agent } from "@llamaindex/workflow";
+
+// 2. Initialize a MCP client
+// by npx
+const server = mcp({
+  command: "npx",
+  args: ["-y", "@modelcontextprotocol/server-filesystem", "."],
+  verbose: true,
+});
+// or by SSE
+const server = mcp({
+  url: "http://localhost:8000/mcp",
+  verbose: true,
+});
+
+// 3. Get tools from MCP server
+const tools = await server.tools();
+
+// Now you can create an agent with the tools
+const agent = agent({
+  name: "My Agent",
+  systemPrompt: "You are a helpful assistant that can use the provided tools to answer questions.",
+  llm: openai({ model: "gpt-4o" }),
+  tools: tools,
+});
+```
+
+
 ## Function tool
 
 You can still use the `FunctionTool` class to define a tool.
@@ -79,7 +115,8 @@ Note: calling the `bind` method will return a new `FunctionTool` instance, witho
 
 Example to pass a `userToken` as additional argument:
 ```ts
-import { agent, tool } from "llamaindex";
+import { tool } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
 
 // first arg is LLM input, second is bound arg
 const queryKnowledgeBase = async ({ question }, { userToken }) => {

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

@@ -2,149 +2,17 @@
 title: Workflows
 ---
 
-A `Workflow` in LlamaIndexTS is an event-driven abstraction used to chain together several events. Workflows are made up of `steps`, with each step responsible for handling certain event types and emitting new events.
+A `Workflow` in LlamaIndex is a lightweight, event-driven abstraction used to chain together several events. Workflows are made up of `handlers`, with each one responsible for processing specific event types and emitting new events.
 
-Workflows in LlamaIndexTS work by defining step functions that handle specific event types and emit new events.
-
-When a step function is added to a workflow, you need to specify the input and optionally the output event types (used for validation). The specification of the input events ensures each step only runs when an accepted event is ready.
-
-You can create a `Workflow` to do anything! Build an agent, a RAG flow, an extraction flow, or anything else you want.
+Workflows are designed to be flexible and can be used to build agents, RAG flows, extraction flows, or anything else you want to implement.
 
+To use workflows install this package:
 
 ```package-install
 npm i @llamaindex/workflow
 ```
 
-## Getting Started
+This package is a stable, production-ready version of our [llama-flow](../../../llamaflow) project. 
 
-As an illustrative example, let's consider a naive workflow where a joke is generated and then critiqued.
+While you can still reference the llama-flow documentation for detailed information about the underlying concepts, we recommend using the `@llamaindex/workflow` package for all new projects to ensure stability and long-term availability.
 
-<include cwd>../../examples/workflow/joke.ts</include>
-
-There's a few moving pieces here, so let's go through this piece by piece.
-
-### Defining Workflow Events
-
-```typescript
-export class JokeEvent extends WorkflowEvent<{ joke: string }> {}
-```
-
-Events are user-defined classes that extend `WorkflowEvent` and contain arbitrary data provided as template argument. In this case, our workflow relies on a single user-defined event, the `JokeEvent` with a `joke` attribute of type `string`.
-
-### Setting up the Workflow Class
-
-```typescript
-const llm = new OpenAI();
-...
-const jokeFlow = new Workflow<unknown, string, string>();
-```
-
-Our workflow is implemented by initiating the `Workflow` class with three generic types: the context type (unknown), input type (string), and output type (string). The context type is `unknown`, as we're not using a shared context in this example.
-
-For simplicity, we created an `OpenAI` llm instance that we're using for inference in our workflow.
-
-### Workflow Entry Points
-
-```typescript
-const generateJoke = async (_: unknown, ev: StartEvent<string>) => {
-  const prompt = `Write your best joke about ${ev.data}.`;
-  const response = await llm.complete({ prompt });
-  return new JokeEvent({ joke: response.text });
-};
-```
-
-Here, we come to the entry-point of our workflow. While events are user-defined, there are two special-case events, the `StartEvent` and the `StopEvent`. These events are predefined, but we can specify the payload type using generic types. We're using `StartEvent<string>` to indicate that we're going to send an input of type string.
-
-To add this step to the workflow, we use the `addStep` method with an object specifying the input and output event types:
-
-```typescript
-jokeFlow.addStep(
-  {
-    inputs: [StartEvent<string>],
-    outputs: [JokeEvent],
-  },
-  generateJoke
-);
-```
-
-### Workflow Exit Points
-
-```typescript
-const critiqueJoke = async (_: unknown, ev: JokeEvent) => {
-  const prompt = `Give a thorough critique of the following joke: ${ev.data.joke}`;
-  const response = await llm.complete({ prompt });
-  return new StopEvent(response.text);
-};
-```
-
-Here, we have our second and last step in the workflow. We know it's the last step because the special `StopEvent` is returned. When the workflow encounters a returned `StopEvent`, it immediately stops the workflow and returns the result. Note that we're using the generic type `StopEvent<string>` to indicate that we're returning a string.
-
-Add this step to the workflow:
-
-```typescript
-jokeFlow.addStep(
-  {
-    inputs: [JokeEvent],
-    outputs: [StopEvent<string>],
-  },
-  critiqueJoke
-);
-```
-
-### Running the Workflow
-
-```typescript
-const result = await jokeFlow.run("pirates");
-console.log(result.data.result);
-```
-
-Lastly, we run the workflow. The `.run()` method is async, so we use await here to wait for the result.
-
-## Working with Shared Context/State
-
-Optionally, you can choose to use a shared context between steps by specifying a context type when creating the workflow. Here's an example where multiple steps access a shared state:
-
-```typescript
-import { HandlerContext } from "llamaindex";
-
-type MyContextData = {
-  query: string;
-  intermediateResults: any[];
-}
-
-const query = async (context: HandlerContext<MyContextData>, ev: MyEvent) => {
-  // get the query from the context
-  const query = context.data.query;
-  // do something with context and event
-  const val = ...
-  // store in context
-  context.data.intermediateResults.push(val);
-
-  return new StopEvent({ result });
-};
-```
-
-## Waiting for Multiple Events
-
-The context does more than just hold data, it also provides utilities to buffer and wait for multiple events.
-
-For example, you might have a step that waits for a query and retrieved nodes before synthesizing a response:
-
-```typescript
-const synthesize = async (context: Context, ev1: QueryEvent, ev2: RetrieveEvent) => {
-  const subPrompts = [`Answer this query using the context provided: ${ev1.data.query}`, `Context: ${ev2.data.context}`];
-  const prompt = subPrompts.join("\n");
-  const response = await llm.complete({ prompt });
-  return new StopEvent({ result: response.text });
-};
-```
-
-Passing multiple events, we can buffer and wait for ALL expected events to arrive. The receiving step function will only be called once all events have arrived.
-
-## Manually Triggering Events
-
-Normally, events are triggered by returning another event during a step. However, events can also be manually dispatched using the `ctx.sendEvent(event)` method within a workflow.
-
-## Examples
-
-You can find many useful examples of using workflows in the [examples folder](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/workflow).

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

@@ -5,6 +5,12 @@ title: DiscordReader
 DiscordReader is a simple data loader that reads all messages in a given Discord channel and returns them as Document objects.
 It uses the [@discordjs/rest](https://github.com/discordjs/discord.js/tree/main/packages/rest) library to fetch the messages.
 
+## Installation
+
+```package-install
+npm install @llamaindex/discord
+```
+
 ## Usage
 
 First step is to create a Discord Application and generating a bot token [here](https://discord.com/developers/applications).
@@ -12,7 +18,7 @@ In your Discord Application, go to the `OAuth2` tab and generate an invite URL b
 This will invite the bot with the necessary permissions to read messages.
 Copy the URL in your browser and select the server you want your bot to join.
 
-<include cwd>../../examples/readers/src/discord.ts</include>
+<include cwd>../../examples/discord/reader.ts</include>
 
 ### Params
 

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

@@ -21,27 +21,18 @@ To install readers call:
 
 We offer readers for different file formats.
 
-```ts twoslash 
-import { CSVReader } from '@llamaindex/readers/csv'
-import { PDFReader } from '@llamaindex/readers/pdf'
-import { JSONReader } from '@llamaindex/readers/json'
-import { MarkdownReader } from '@llamaindex/readers/markdown'
-import { HTMLReader } from '@llamaindex/readers/html'
-// you can find more readers in the documentation
+```ts twoslash
+import { CSVReader } from '@llamaindex/readers/csv';
+import { DocxReader } from '@llamaindex/readers/docx';
+import { HTMLReader } from '@llamaindex/readers/html';
+import { ImageReader } from '@llamaindex/readers/image';
+import { JSONReader } from '@llamaindex/readers/json';
+import { MarkdownReader } from '@llamaindex/readers/markdown';
+import { ObsidianReader } from '@llamaindex/readers/obsidian';
+import { PDFReader } from '@llamaindex/readers/pdf';
+import { TextFileReader } from '@llamaindex/readers/text';
 ```
 
-Additionally the following loaders exist without separate documentation:
-
-- `AssemblyAIReader` transcribes audio using [AssemblyAI](https://www.assemblyai.com/).
-  - [AudioTranscriptReader](/docs/api/classes/AudioTranscriptReader): loads entire transcript as a single document.
-  - [AudioTranscriptParagraphsReader](/docs/api/classes/AudioTranscriptParagraphsReader): creates a document per paragraph.
-  - [AudioTranscriptSentencesReader](/docs/api/classes/AudioTranscriptSentencesReader): creates a document per sentence.
-  - [AudioSubtitlesReader](/docs/api/classes/AudioTranscriptParagraphsReader): creates a document containing the subtitles of a transcript.
-- [NotionReader](/docs/api/classes/NotionReader) loads [Notion](https://www.notion.so/) pages.
-- [SimpleMongoReader](/docs/api/classes/SimpleMongoReader) loads data from a [MongoDB](https://www.mongodb.com/).
-
-Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
-
 ## SimpleDirectoryReader
 
 [Open in StackBlitz](https://stackblitz.com/github/run-llama/LlamaIndexTS/tree/main/examples/readers?file=src/simple-directory-reader.ts&title=Simple%20Directory%20Reader)

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

@@ -112,6 +112,3 @@ The returned `imageDocs` have the alt text assigned as text and the image path a
 
 You can see the full example file [here](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/readers/src/llamaparse-json.ts).
 
-## API Reference
-
-- [LlamaParseReader](/docs/api/classes/LlamaParseReader)

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

@@ -32,7 +32,7 @@ They can be divided into two groups.
 #### Advanced params:
 
 - `resultType` can be set to `markdown`, `text` or `json`. Defaults to `text`. More information about `json` mode on the next pages.
-- `language` primarily helps with OCR recognition. Defaults to `en`. Click [here](/docs/api/type-aliases/Language) for a list of supported languages.
+- `language` primarily helps with OCR recognition. Defaults to `en`.
 - `parsingInstructions?` Optional. Can help with complicated document structures. See this [LlamaIndex Blog Post](https://www.llamaindex.ai/blog/launching-the-first-genai-native-document-parsing-platform) for an example.
 - `skipDiagonalText?` Optional. Set to true to ignore diagonal text. (Text that is not rotated 0, 90, 180 or 270 degrees)
 - `invalidateCache?` Optional. Set to true to ignore the LlamaCloud cache. All document are kept in cache for 48hours after the job was completed to avoid processing the same document twice. Can be useful for testing when trying to re-parse the same document with, e.g. different `parsingInstructions`.
@@ -61,4 +61,3 @@ Below a full example of `LlamaParse` integrated in `SimpleDirectoryReader` with
 ## API Reference
 
 - [SimpleDirectoryReader](/docs/api/classes/SimpleDirectoryReader)
-- [LlamaParseReader](/docs/api/classes/LlamaParseReader)

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

@@ -98,5 +98,4 @@ You can assign any other values of the JSON response to the Document as needed.
 
 ## API Reference
 
-- [LlamaParseReader](/docs/api/classes/LlamaParseReader)
 - [SimpleDirectoryReader](/docs/api/classes/SimpleDirectoryReader)

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

@@ -120,11 +120,11 @@ async function main() {
 
 ```ts
 import { BEDROCK_MODELS, Bedrock } from "@llamaindex/community";
-import { FunctionTool, LLMAgent } from "llamaindex";
+import { tool } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
 import { z } from "zod";
 
-const sumNumbers = FunctionTool.from(
-  ({ a, b }: { a: number; b: number }) => `${a + b}`,
+const sumNumbers = tool(
   {
     name: "sumNumbers",
     description: "Use this function to sum two numbers",
@@ -136,11 +136,11 @@ const sumNumbers = FunctionTool.from(
         description: "The second number",
       }),
     }),
+    execute: ({ a, b }: { a: number; b: number }) => `${a + b}`,
   },
 );
 
-const divideNumbers = FunctionTool.from(
-  ({ a, b }: { a: number; b: number }) => `${a / b}`,
+const divideNumbers = tool(
   {
     name: "divideNumbers",
     description: "Use this function to divide two numbers",
@@ -152,6 +152,7 @@ const divideNumbers = FunctionTool.from(
         description: "The divisor b to divide by",
       }),
     }),
+    execute: ({ a, b }: { a: number; b: number }) => `${a / b}`,
   },
 );
 
@@ -161,15 +162,15 @@ const bedrock = new Bedrock({
 });
 
 async function main() {
-  const agent = new LLMAgent({
+  const myAgent = agent({
     llm: bedrock,
     tools: [sumNumbers, divideNumbers],
   });
 
-  const response = await agent.chat({
-    message: "How much is 5 + 5? then divide by 2",
-  });
+  const response = await myAgent.run(
+    "How much is 5 + 5? then divide by 2",
+  );
 
-  console.log(response.message);
+  console.log(response);
 }
 ```

apps/next/src/content/docs/llamaindex/tutorials/agents/1_setup.mdx

@@ -15,7 +15,7 @@ In LlamaIndex, an agent is a semi-autonomous piece of software powered by an LLM
 You'll need to have a recent version of [Node.js](https://nodejs.org/en) installed. Then you can install LlamaIndex.TS by running
 
 ```package-install
-npm i llamaindex @llamaindex/openai @llamaindex/readers @llamaindex/huggingface
+npm i llamaindex @llamaindex/openai @llamaindex/readers @llamaindex/huggingface @llamaindex/workflow
 ```
 
 ## Choose your model

apps/next/src/content/docs/llamaindex/tutorials/agents/2_create_agent.mdx

@@ -35,11 +35,16 @@ First we'll need to pull in our dependencies. These are:
 import "dotenv/config";
 import {
   agent,
-  AgentStream,
-  tool,
+  agentStreamEvent,
   openai,
+} from "@llamaindex/workflow";
+import {
+  tool,
   Settings,
 } from "llamaindex";
+import {
+  openai,
+} from "@llamaindex/openai";
 import { z } from "zod";
 ```
 
@@ -108,11 +113,10 @@ const myAgent = agent({ tools });
 
 ### Ask the agent a question
 
-We can use the `chat` interface to ask our agent a question, and it will use the tools we've defined to find an answer.
+We can use the `run` method to ask our agent a question, and it will use the tools we've defined to find an answer.
 
 ```javascript
-const context = myAgent.run("Sum 101 and 303");
-const result = await context;
+const result = await myAgent.run("Sum 101 and 303");
 console.log(result.data);
 ```
 You will see the following output:
@@ -123,12 +127,13 @@ You will see the following output:
 { result: 'The sum of 101 and 303 is 404.' }
 ```
 
-To stream the response, you can use the `AgentStream` event which provides chunks of the response as they become available. This allows you to display the response incrementally rather than waiting for the full response:
+To stream the response, you need to call `runStream`, which returns a stream of events. 
+The `agentStreamEvent` provides chunks of the response as they become available. This allows you to display the response incrementally rather than waiting for the full response:
 
 ```javascript
-const context = myAgent.run("Add 101 and 303");
-for await (const event of context) {
-  if (event instanceof AgentStream) {
+const events = myAgent.runStream("Add 101 and 303");
+for await (const event of events) {
+  if (agentStreamEvent.include(event)) {
     process.stdout.write(event.data.delta);
   }
 }
@@ -140,18 +145,18 @@ for await (const event of context) {
 The sum of 101 and 303 is 404.
 ```
 
+Note that we're filtering for `agentStreamEvent` as an agent might return other events - more about that in the following section.
+
 ### Logging workflow events
 
 To log the workflow events, you can check the event type and log the event data.
 
 ```javascript
-const context = myAgent.run("Sum 202 and 404");
-for await (const event of context) {
-  if (event instanceof AgentStream) {
+const events = myAgent.runStream("Sum 202 and 404");
+for await (const event of events) {
+  if (agentStreamEvent.include(event)) {
     // Stream the response
-    for (const chunk of event.data.delta) {
-      process.stdout.write(chunk);
-    }
+    process.stdout.write(event.data.delta);
   } else {
     // Log other events
     console.log("\nWorkflow event:", JSON.stringify(event, null, 2));

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

@@ -30,16 +30,16 @@ Settings.llm = ollama({
 
 ### Run local agent
 
-You can also create local agent by importing `agent` from `llamaindex`.
+You can also create local agent by importing `agent` from `@llamaindex/workflow`.
 
 ```javascript
-import { agent } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
 
 const workflow = agent({
   tools: [getWeatherTool],
 });
 
-const workflowContext = workflow.run(
+const resutl = workflow.run(
   "What's the weather like in San Francisco?",
 );
 ```

apps/next/src/content/docs/llamaindex/tutorials/agents/4_agentic_rag.mdx

@@ -25,7 +25,8 @@ We'll be bringing in `SimpleDirectoryReader`, `HuggingFaceEmbedding`, `VectorSto
 
 ```javascript
 import { QueryEngineTool, Settings, VectorStoreIndex } from "llamaindex";
-import { OpenAI, OpenAIAgent } from "@llamaindex/openai";
+import { agent } from "@llamaindex/workflow";
+import { openai } from "@llamaindex/openai";
 import { HuggingFaceEmbedding } from "@llamaindex/huggingface";
 import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
 ```
@@ -58,25 +59,9 @@ We will convert our text into embeddings using the `VectorStoreIndex` class thro
 const index = await VectorStoreIndex.fromDocuments(documents);
 ```
 
-### Configure a retriever
-
-Before LlamaIndex can send a query to the LLM, it needs to find the most relevant chunks to send. That's the purpose of a `Retriever`. We're going to get `VectorStoreIndex` to act as a retriever for us
-
-```javascript
-const retriever = await index.asRetriever();
-```
-
-### Configure how many documents to retrieve
-
-By default LlamaIndex will retrieve just the 2 most relevant chunks of text. This document is complex though, so we'll ask for more context.
-
-```javascript
-retriever.similarityTopK = 10;
-```
-
 ### Use index.queryTool
 
-`index.queryTool` creates a `QueryEngineTool` that can be used be an agent to query data from the index. 
+`index.queryTool` creates a `QueryEngineTool` that can be used be an agent to query data from the index:
 
 ```javascript
 const tools = [
@@ -85,9 +70,17 @@ const tools = [
       name: "san_francisco_budget_tool",
       description: `This tool can answer detailed questions about the individual components of the budget of San Francisco in 2023-2024.`,
     },
+    options: { similarityTopK: 10 },
   }),
 ];
+```
 
+The `metadata` that we're setting helps the agent to decide when to use the tool.
+Note that by default LlamaIndex will retrieve just the 2 most relevant chunks of text. This document is complex though, so we'll ask for more context by setting `similarityTopK` to 10.
+
+Now, we can create an agent using the `QueryEngineTool`:
+
+```javascript
 // Create an agent using the tools array
 const ragAgent = agent({ tools });
 

apps/next/src/content/docs/llamaindex/tutorials/agents/5_rag_and_tools.mdx

@@ -12,6 +12,7 @@ const tools = [
       name: "san_francisco_budget_tool",
       description: `This tool can answer detailed questions about the individual components of the budget of San Francisco in 2023-2024.`,
     },
+    options: { similarityTopK: 10 },
   }),
   tool({
     name: "sumNumbers",

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

@@ -8,9 +8,10 @@ We have a comprehensive, step-by-step [guide to building agents in LlamaIndex.TS
 
 In a new folder:
 
-```bash npm2yarn
+```package-install
 npm init
 npm i -D typescript @types/node
+npm i @llamaindex/openai @llamaindex/workflow llamaindex zod
 ```
 
 ## Run agent
@@ -20,15 +21,14 @@ Create the file `example.ts`. This code will:
 - Create two tools for use by the agent:
   - A `sumNumbers` tool that adds two numbers
   - A `divideNumbers` tool that divides numbers
--
 - Give an example of the data structure we wish to generate
 - Prompt the LLM with instructions and the example, plus a sample transcript
 
-<include cwd>../../examples/agent/openai.ts</include>
+<include cwd>../../examples/agents/agent/openai.ts</include>
 
 To run the code:
 
-```bash
+```package-install
 npx tsx example.ts
 ```
 
@@ -36,9 +36,18 @@ You should expect output something like:
 
 ```
 {
-  content: 'The sum of 5 + 5 is 10. When you divide 10 by 2, you get 5.',
-  role: 'assistant',
-  options: {}
+  result: '5 + 5 is 10. Then, 10 divided by 2 is 5.',
+  state: {
+    memory: ChatMemoryBuffer {
+      chatStore: SimpleChatStore {},
+      chatStoreKey: 'chat_history',
+      tokenLimit: 750000
+    },
+    scratchpad: [],
+    currentAgentName: 'Agent',
+    agents: [ 'Agent' ],
+    nextAgentName: null
+  }
 }
 Done
 ```

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

@@ -4,7 +4,7 @@
     "basic_agent",
     "rag",
     "agents",
-    "workflow",
+    "workflows",
     "local_llm",
     "chatbot",
     "structured_data_extraction"

apps/next/src/content/docs/llamaindex/tutorials/rag/concepts.mdx

@@ -16,7 +16,7 @@ LlamaIndex uses a two stage method when using an LLM with your data:
 1. **indexing stage**: preparing a knowledge base, and
 2. **querying stage**: retrieving relevant context from the knowledge to assist the LLM in responding to a question
 
-![](./_static/concepts/rag.jpg)
+![](/_static/concepts/rag.jpg)
 
 This process is also known as Retrieval Augmented Generation (RAG).
 
@@ -28,7 +28,7 @@ Let's explore each stage in detail.
 
 LlamaIndex.TS help you prepare the knowledge base with a suite of data connectors and indexes.
 
-![](./_static/concepts/indexing.jpg)
+![](/_static/concepts/indexing.jpg)
 
 [**Data Loaders**](/docs/llamaindex/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).
@@ -54,7 +54,7 @@ LlamaIndex provides composable modules that help you build and integrate RAG pip
 
 These building blocks can be customized to reflect ranking preferences, as well as composed to reason over multiple knowledge bases in a structured way.
 
-![](./_static/concepts/querying.jpg)
+![](/_static/concepts/querying.jpg)
 
 #### Building Blocks
 

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

@@ -8,9 +8,10 @@ One of the most common use-cases for LlamaIndex is Retrieval-Augmented Generatio
 
 In a new folder, run:
 
-```bash npm2yarn
+```package-install
 npm init
 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.
@@ -34,7 +35,7 @@ Create a `tsconfig.json` file in the same folder:
 
 Now you can run the code with
 
-```bash
+```package-install
 npx tsx example.ts
 ```
 

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

@@ -10,9 +10,10 @@ You can use [other LLMs](/docs/llamaindex/modules/models/llms) via their APIs; i
 
 In a new folder:
 
-```bash npm2yarn
+```package-install
 npm init
 npm i -D typescript @types/node
+npm i @llamaindex/openai zod
 ```
 
 ## Extract data
@@ -27,7 +28,7 @@ Create the file `example.ts`. This code will:
 
 To run the code:
 
-```bash
+```package-install
 npx tsx example.ts
 ```
 

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

@@ -1,224 +0,0 @@
----
-title: Inputs / Outputs
-description: Learn how to use different inputs and outputs in your workflows.
----
-
-Inputs and outputs are the way to communicate between steps in a workflow. In the previous example,
-we used `StartEvent` and `StopEvent` to communicate between steps. However, you can use any type of event to communicate between steps.
-
-## Multiple inputs
-
-You can define multiple inputs for a step.
-
-In the following example, we define a complex workflow with multiple inputs and outputs.
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent, WorkflowEvent } from '@llamaindex/workflow';
-
-class AEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-class BEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-class ResultEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-```
-
-First, let's define the events that we will use in the workflow.
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent, WorkflowEvent } from '@llamaindex/workflow';
-
-class AEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-class BEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-class ResultEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-const workflow = new Workflow<never, string, string>();
-
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [StopEvent<string>]
-}, async (
-	context,
-	startEvent
-) => {
-	const input = startEvent.data;
-	const aEvent = await context.requireEvent(AEvent);
-	const bEvent = await context.requireEvent(BEvent);
-	const a = aEvent.data;
-	const b = bEvent.data;
-	return new StopEvent(`Hello, ${input}! A: ${a}, B: ${b}`);
-});
-
-// ---cut---
-workflow.addStep({
-	inputs: [AEvent, BEvent],
-	outputs: [ResultEvent]
-}, async (
-	context,
-	aEvent,
-	bEvent
-) => {
-	const a = aEvent.data;
-	const b = bEvent.data;
-	return new ResultEvent(`A: ${a}, B: ${b}`);
-});
-```
-
-This step means that it requires two events: `AEvent` and `BEvent`. It will return a `ResultEvent` with the data `A: ${a}, B: ${b}`.
-
-## A or B input
-
-If we want to have a step that can accept either `AEvent` or `BEvent`, we can define the step like this:
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent, WorkflowEvent } from '@llamaindex/workflow';
-
-class AEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-class BEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-class ResultEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-const workflow = new Workflow<never, string, string>();
-
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [StopEvent<string>]
-}, async (
-	context,
-	startEvent
-) => {
-	const input = startEvent.data;
-	const aEvent = await context.requireEvent(AEvent);
-	const bEvent = await context.requireEvent(BEvent);
-	const a = aEvent.data;
-	const b = bEvent.data;
-	return new StopEvent(`Hello, ${input}! A: ${a}, B: ${b}`);
-});
-
-// ---cut---
-workflow.addStep({
-	inputs: [WorkflowEvent.or(AEvent, BEvent)],
-	outputs: [ResultEvent]
-}, async (
-	context,
-	aOrBEvent
-) => {
-	if (aOrBEvent instanceof AEvent) {
-		// ^?
-
-
-		const a = aOrBEvent.data;
-		//        ^?
-
-
-		return new ResultEvent(`A: ${a}`);
-	} else {
-		const b = aOrBEvent.data;
-		//        ^?
-
-
-		return new ResultEvent(`B: ${b}`);
-	}
-});
-```
-
-This step means that it requires either `AEvent` or `BEvent`. It will return a `ResultEvent` with the data `A: ${a}` or `B: ${b}`.
-
-You can still combine the logic with `context.requireEvent` to get the data from the event.
-
-<Accordions>
-	<Accordion title="Under the hood">
-		We use JavaScript Inheritance and the prototype chain to implement the `or` logic.
-		The `or` method creates a new class that extends the two classes that you pass to it.
-
-		<a
-			target="_blank"
-			href="https://developer.mozilla.org/en-US/docs/Web/JavaScript/Inheritance_and_the_prototype_chain"
-		>
-			MDN - Inheritance and the prototype chain
-		</a>
-	</Accordion>
-</Accordions>
-
-## Multiple outputs
-
-You can define multiple outputs for a step.
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent, WorkflowEvent } from '@llamaindex/workflow';
-
-class AEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-class BEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-class ResultEvent extends WorkflowEvent<string> {
-	constructor(data: string) {
-		super(data);
-	}
-}
-
-const workflow = new Workflow<never, string, string>();
-// ---cut---
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [AEvent, BEvent]
-}, async (
-	context,
-	startEvent
-) => {
-	const input = startEvent.data;
-	if (Math.random() > 0.5) {
-		return new AEvent(`Hello, ${input}!`);
-	} else {
-		return new BEvent(42);
-	}
-});
-```
-
-This step will return either an `AEvent` or a `BEvent` based on a random number.

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

@@ -1,196 +0,0 @@
----
-title: Basic Usage
-description: Learn how to use the LlamaIndex workflow.
----
-
-A `Workflow` in LlamaIndex.TS is an event-driven abstraction used to chain together several events.
-Workflows are made up of steps, with each step responsible for handling certain event types and emitting new events.
-
-Workflows are designed for any cases that benefit from event-driven programming, not only for LLM and AI tasks.
-
-```package-install
-npm i @llamaindex/workflow
-```
-
-## Start from scratch
-
-Let's start from a Hello World workflow.
-
-```ts twoslash
-import { Workflow } from '@llamaindex/workflow';
-
-type ContextData = {
-	counter: number;
-}
-// ---cut---
-const contextData: ContextData = { counter: 0 };
-
-const workflow = new Workflow<ContextData, string, string>();
-//     ^?
-
-
-
-```
-
-First, we define a workflow with 3 generic types: `ContextData`, `Input`, and `Output`.
-
-In general, `ContextData` is used to store the shared data between steps, `Input` is the type of the input event, and `Output` is the type of the output event.
-
-In you code logic, you should **share state between steps via `ContextData`**.
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent } from '@llamaindex/workflow';
-
-type ContextData = {
-	counter: number;
-}
-
-const contextData: ContextData = { counter: 0 };
-
-const workflow = new Workflow<ContextData, string, string>();
-// ---cut---
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [StopEvent<string>]
-}, async (context, startEvent) => {
-	const input = startEvent.data;
-	context.data.counter++;
-	return new StopEvent(`Hello, ${input}!`);
-});
-```
-
-In the workflow, we add a step that listens to `StartEvent<string>` and emits `StopEvent<string>`.
-
-The step is an async function that takes two arguments: `context` and `event`.
-
-### `context` type
-
-<AutoTypeTable path="./src/deps/type.ts" name="HandlerContext" />
-
-There are two more properties in `HandlerContext`:
-
-- `sendEvent`: invoke another event in the workflow, other than `StartEvent`, `StopEvent`, or the current event. (Or there will have circular reference)
-- `requireEvent`: wait for a specific event to be emitted.
-
-You can use `sendEvent` and `requireEvent` to build complex workflows.
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent, WorkflowEvent } from '@llamaindex/workflow';
-
-type ContextData = {
-	counter: number;
-}
-
-const contextData: ContextData = { counter: 0 };
-
-const workflow = new Workflow<ContextData, string, string>();
-
-// ---cut---
-class AnalysisStartEvent extends WorkflowEvent<string> {}
-class AnalysisStopEvent extends WorkflowEvent<boolean> {}
-workflow.addStep({
-	inputs: [AnalysisStartEvent],
-	outputs: [AnalysisStopEvent]
-}, async (...args) => {
-	// do some analysis
-	return new AnalysisStopEvent(true);
-})
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [StopEvent<string>]
-}, async (context, startEvent) => {
-	const input = startEvent.data;
-	context.sendEvent(new AnalysisStartEvent('start'));
-	context.data.counter++;
-	const { data } = await context.requireEvent(AnalysisStopEvent);
-	return new StopEvent(`Hello, ${input}! Analysis result: ${data ? 'success' : 'fail'}`);
-});
-```
-
-For example, you can compile `requireEvent` with `waitUntil` in [Vercel Functions](https://vercel.com/docs/functions/functions-api-reference#waituntil) or [Cloudflare Worker](https://developers.cloudflare.com/workers/runtime-apis/context/#waituntil)
-
-```ts twoslash
-import { waitUntil } from '@vercel/functions';
-import { Workflow, StartEvent, StopEvent, WorkflowEvent } from '@llamaindex/workflow';
-
-type ContextData = {
-	counter: number;
-}
-
-const contextData: ContextData = { counter: 0 };
-
-const workflow = new Workflow<ContextData, string, string>();
-
-class AnalysisStartEvent extends WorkflowEvent<string> {}
-class AnalysisStopEvent extends WorkflowEvent<boolean> {}
-
-// ---cut---
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [StopEvent<string>]
-}, async (context, startEvent) => {
-	const input = startEvent.data;
-	context.sendEvent(new AnalysisStartEvent('start'));
-	context.data.counter++;
-	waitUntil(context.requireEvent(AnalysisStopEvent));
-	// note that `waitUntil` is not a promise, it will extend the lifetime of the workflow
-	// you can wait for some background tasks to finish
-	return new StopEvent(`Hello, ${input}!`);
-});
-```
-
-## Multiple runs
-
-You can run the same workflow multiple times with different inputs.
-
-```ts twoslash
-import { Workflow, StartEvent, StopEvent } from '@llamaindex/workflow';
-
-type ContextData = {
-	counter: number;
-}
-
-const contextData: ContextData = { counter: 0 };
-
-const workflow = new Workflow<ContextData, string, string>();
-
-workflow.addStep({
-	inputs: [StartEvent<string>],
-	outputs: [StopEvent<string>]
-}, async (context, startEvent) => {
-	const input = startEvent.data;
-	context.data.counter++;
-	return new StopEvent(`Hello, ${input}!`);
-});
-
-// ---cut---
-{
-	const ret = await workflow.run('Alex', contextData);
-	console.log(ret.data); // Hello, Alex!
-}
-
-{
-	const ret = await workflow.run('World', contextData);
-	console.log(ret.data); // Hello, World!
-}
-```
-
-Context is shared between runs, so the counter will be increased.
-
-Ideally, it should be serializable to make sure it can be recovered from HTTP requests or other storage.
-
-### Full example
-
-<iframe
-	className="w-full h-[440px]"
-	aria-label="Workflow example"
-	src="https://stackblitz.com/github/run-llama/LlamaIndexTS/tree/main/examples?file=node/workflow/basic.ts"
-/>
-
-## `Workflow` type
-
-<AutoTypeTable path="./src/deps/type.ts" name="Workflow" />
-
-## `WorkflowContext` type
-
-<AutoTypeTable path="./src/deps/type.ts" name="WorkflowContext" />

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

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

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

@@ -1,198 +0,0 @@
----
-title: Streaming
-description: Learn how to use the LlamaIndex workflow with streaming.
----
-
-`Workflow` API by default is designed for streaming data. In this guide, we will show you how to use the `Workflow` API with streaming data.
-
-Each `workflow.run` call returns `WorkflowContext`, which implements `AsyncIterable` interface. You can use it to stream data.
-
-```ts twoslash
-import { Workflow, WorkflowEvent, StartEvent, StopEvent } from '@llamaindex/workflow';
-class ComputeEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-class ComputeResultEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-type ContextData = {
-	sum: number;
-}
-
-const workflow = new Workflow<ContextData, number, number>();
-workflow.addStep({
-	inputs: [StartEvent<number>],
-	outputs: [StopEvent<number>]
-}, async (context, startEvent) => {
-	const total = startEvent.data;
-	for (let i = 0; i < total; i++) {
-		context.sendEvent(new ComputeEvent(i));
-	}
-	const computeResults = await Promise.all(Array.from({ length: total }).map(() => context.requireEvent(ComputeResultEvent)));
-	// Workflow API allows you to start events in parallel and wait for all of them to finish
-	context.data.sum = computeResults.reduce((acc, curr) => acc + curr.data, 0);
-	return new StopEvent(context.data.sum);
-});
-```
-
-We define a parallel computation workflow that computes the sum of numbers from 0 to `total`.
-
-The workflow sends `ComputeEvent` events for each number and waits for `ComputeResultEvent` events. After receiving all `ComputeResultEvent` events, the workflow returns the sum as a `StopEvent`.
-
-What if we want cutoff if the sum exceeds a certain value?
-
-## Streaming
-
-```ts twoslash
-import { Workflow, WorkflowEvent, StartEvent, StopEvent } from '@llamaindex/workflow';
-import { StopCircle } from 'lucide-react';
-class ComputeEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-class ComputeResultEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-
-type ContextData = {
-	sum: number;
-}
-
-const workflow = new Workflow<ContextData, number, number>();
-// ---cut---
-const context = workflow.run(1000, {
-	sum: 0
-});
-
-for await (const event of context) {
-	if (event instanceof ComputeEvent) {
-		if (context.data.sum > 100) {
-			throw new Error('Sum exceeds 100');
-		}
-	}
-	if (event instanceof StopEvent) {
-		console.log('result', event.data);
-	}
-}
-```
-
-You can define more custom logic using `AsyncIterable` interface.
-
-For example. I just want to stop the workflow if I get a `ComputeResultEvent`
-
-
-```ts twoslash
-import { Workflow, WorkflowEvent, StartEvent, StopEvent } from '@llamaindex/workflow';
-import { StopCircle } from 'lucide-react';
-class ComputeEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-class ComputeResultEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-
-type ContextData = {
-	sum: number;
-}
-
-const workflow = new Workflow<ContextData, number, number>();
-// ---cut---
-async function compute() {
-	const context = workflow.run(1000, {
-		sum: 0
-	});
-	for await (const event of context) {
-		if (event instanceof ComputeResultEvent) {
-			return event.data;
-		}
-	}
-	throw new Error('UNREACHABLE');
-}
-
-const result = await compute();
-```
-
-### Streaming with UI
-
-You can use the `Workflow` API with UI libraries like React.
-
-```tsx twoslash
-// @filename: utils.ts
-export async function runWithoutBlocking(fn: () => Promise<void>) {
-	fn();
-}
-// @filename: action.ts
-// ---cut---
-'use server';
-// "use server" is required to enable server side feature in React
-import { createStreamableUI } from 'ai/rsc';
-import { runWithoutBlocking } from './utils';
-// ---cut-start---
-import { Workflow, WorkflowEvent, StartEvent, StopEvent } from '@llamaindex/workflow';
-class ComputeEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-class ComputeResultEvent extends WorkflowEvent<number> {
-	constructor(data: number) {
-		super(data);
-	}
-}
-
-
-type ContextData = {
-	sum: number;
-}
-
-const workflow = new Workflow<ContextData, number, number>();
-const min = 100;
-const max = 1000;
-workflow.addStep(
-	{
-		inputs: [ComputeEvent],
-		outputs: [ComputeResultEvent]
-	},
-	async (context, event) => {
-		await new Promise((resolve) =>
-			setTimeout(resolve, Math.floor(Math.random() * (max - min + 1) + min))
-		);
-		return new ComputeResultEvent(event.data);
-	}
-);
-// ---cut-end---
-export async function compute() {
-	'use server';
-	const ui = createStreamableUI();
-	const context = workflow.run(100, {
-		sum: 0
-	});
-	runWithoutBlocking(async () => {
-		for await (const event of context) {
-			if (event instanceof ComputeResultEvent) {
-				// Update UI
-			} else if (event instanceof StopEvent) {
-				// Update UI
-			}
-			// ...
-		}
-	});
-	return ui.value;
-}
-```
-
-<WorkflowStreamingDemo />

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

@@ -0,0 +1,176 @@
+---
+title: Workflows
+---
+
+A `Workflow` in LlamaIndex is a lightweight, event-driven abstraction used to chain together several events. Workflows are made up of `handlers`, with each one responsible for processing specific event types and emitting new events.
+
+Workflows are designed to be flexible and can be used to build agents, RAG flows, extraction flows, or anything else you want to implement.
+
+```package-install
+npm i @llamaindex/workflow @llamaindex/openai
+```
+
+## Getting Started
+
+Let's explore a simple workflow example where a joke is generated and then critiqued and iterated on:
+
+<include cwd>../../examples/agents/workflow/joke.ts</include>
+
+There are a few moving pieces here, so let's go through this step by step.
+
+### Defining Workflow Events
+
+```typescript
+const startEvent = workflowEvent<string>(); // Input topic for joke
+const jokeEvent = workflowEvent<{ joke: string }>(); // Intermediate joke
+const critiqueEvent = workflowEvent<{ joke: string; critique: string }>(); // Intermediate critique
+const resultEvent = workflowEvent<{ joke: string; critique: string }>(); // Final joke + critique
+```
+
+Events are defined using the `workflowEvent` function and contain arbitrary data provided as a generic type. In this example, we have four events:
+- `startEvent`: Takes a string input (the joke topic)
+- `jokeEvent`: Contains an object with a joke property
+- `critiqueEvent`: Contains both the joke and its critique, used for the feedback loop
+- `resultEvent`: Contains the final joke and critique after any iterations
+
+### Setting up the Workflow with Stateful Middleware
+
+```typescript
+const { withState, getContext } = createStatefulMiddleware(() => ({
+  numIterations: 0,
+  maxIterations: 3,
+}));
+const jokeFlow = withState(createWorkflow());
+```
+
+Our workflow is implemented using the `createWorkflow()` function, enhanced with the `withState` middleware. This middleware provides shared state across all handlers, which in this case tracks:
+- `numIterations`: Counts how many iterations of joke improvement we've done
+- `maxIterations`: Sets a limit to prevent infinite loops
+
+This state will be accessible within workflows by using the `getContext().state` function.
+
+### Adding Handlers with Loops
+
+We have three key handlers in our workflow:
+
+1. The first handler processes the `startEvent`, generates an initial joke, and emits a `jokeEvent`:
+
+```typescript
+jokeFlow.handle([startEvent], async (event) => {
+  // Prompt the LLM to write a joke
+  const prompt = `Write your best joke about ${event.data}. Write the joke between <joke> and </joke> tags.`;
+  const response = await llm.complete({ prompt });
+ 
+  // Parse the joke from the response
+  const joke =
+    response.text.match(/<joke>([\s\S]*?)<\/joke>/)?.[1]?.trim() ??
+    response.text;
+  return jokeEvent.with({ joke: joke });
+});
+```
+
+2. The second handler handles the `jokeEvent`, critiques the joke, and either:
+   - Emits a `critiqueEvent` if the joke needs improvement
+   - Emits a `resultEvent` if the joke is good enough
+
+```typescript
+jokeFlow.handle([jokeEvent], async (event) => {
+  // Prompt the LLM to critique the joke
+  const prompt = `Give a thorough critique of the following joke. If the joke needs improvement, put "IMPROVE" somewhere in the critique: ${event.data.joke}`;
+  const response = await llm.complete({ prompt });
+ 
+  // If the critique includes "IMPROVE", keep iterating, else, return the result
+  if (response.text.includes("IMPROVE")) {
+    return critiqueEvent.with({
+      joke: event.data.joke,
+      critique: response.text,
+    });
+  }
+ 
+  return resultEvent.with({ joke: event.data.joke, critique: response.text });
+});
+```
+
+3. The third handler processes the `critiqueEvent`, generates an improved joke based on the critique, and either:
+   - Loops back to the joke evaluation (if under the iteration limit)
+   - Emits the final `resultEvent` (if iteration limit reached)
+
+```typescript
+jokeFlow.handle([critiqueEvent], async (event) => {
+  // Keep track of the number of iterations
+  const state = getContext().state;
+  state.numIterations++;
+ 
+  // Write a new joke based on the previous joke and critique
+  const prompt = `Write a new joke based on the following critique and the original joke. Write the joke between <joke> and </joke> tags.\n\nJoke: ${event.data.joke}\n\nCritique: ${event.data.critique}`;
+  const response = await llm.complete({ prompt });
+ 
+  // Parse the joke from the response
+  const joke =
+    response.text.match(/<joke>([\s\S]*?)<\/joke>/)?.[1]?.trim() ??
+    response.text;
+ 
+  // If we've done less than the max number of iterations, keep iterating
+  // else, return the result
+  if (state.numIterations < state.maxIterations) {
+    return jokeEvent.with({ joke: joke });
+  }
+ 
+  return resultEvent.with({ joke: joke, critique: event.data.critique });
+});
+```
+
+### Running the Workflow
+
+```typescript
+async function main() {
+  const { stream, sendEvent } = jokeFlow.createContext();
+  sendEvent(startEvent.with("pirates"));
+
+  let result: { joke: string, critique: string } | undefined;
+
+  for await (const event of stream) {
+    // console.log(event.data);  optionally log the event data
+    if (resultEvent.include(event)) {
+      result = event.data;
+      break; // Stop when we get the final result
+    }
+  }
+  
+  console.log(result);
+}
+```
+
+To run the workflow, we:
+1. Create a workflow context with `createContext()`
+2. Trigger the initial event with `sendEvent()`
+3. Listen to the event stream and process events as they arrive
+4. Use `include()` to check if an event is of a specific type
+5. Break the loop when we receive our final result
+
+### Using Stream Utilities
+
+The `stream` returned by `createContext` contains utility functions to make working with event streams easier:
+
+```typescript
+// Create a workflow context and send the initial event
+const { stream, sendEvent } = jokeFlow.createContext();
+sendEvent(startEvent.with("pirates"));
+
+// Collect all events until we get a resultEvent
+const allEvents = await stream.until(resultEvent).toArray(); 
+
+// The last event will be the resultEvent
+const finalEvent = allEvents.at(-1);
+console.log(finalEvent.data); // Output the joke and critique
+```
+
+The stream utilities make it easier to work with the asynchronous event flow. In this example, we use:
+- `toArray`: Aggregates all events into an array
+- `until`: Creates a stream that emits events until a condition is met (in this case, until a resultEvent is received)
+
+You can combine these utilities with other stream operators like `filter` and `map` to create powerful processing pipelines.
+
+## Next Steps
+
+To learn more about workflows, check out [the Workflows documentation](/docs/llamaindex/modules/agents/workflows).

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

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

apps/next/src/deps/type.ts

@@ -1,5 +0,0 @@
-export type {
-  HandlerContext,
-  Workflow,
-  WorkflowContext,
-} from "@llamaindex/workflow";

apps/next/turbo.json

@@ -3,12 +3,19 @@
   "extends": ["//"],
   "tasks": {
     "build": {
+      "inputs": [
+        "node_modules/@llama-flow/docs/**",
+        "src/**/*.ts",
+        "src/**/*.tsx",
+        "src/**/*.mdx",
+        "src/**/*.md"
+      ],
       "outputs": [
         ".next",
         ".source",
         "next-env.d.ts",
-        "src/content/docs/cloud/api/**",
-        "src/content/docs/api/**"
+        "src/content/docs/api/**",
+        "tsconfig.json"
       ],
       "env": [
         "LLAMA_CLOUD_API_KEY",

apps/next/typedoc.json

@@ -2,12 +2,10 @@
   "plugin": ["typedoc-plugin-markdown", "typedoc-plugin-merge-modules"],
   "entryPoints": [
     "../../packages/{,**/}index.ts",
-    "../../packages/readers/src/*.ts",
-    "../../packages/cloud/src/{reader,utils}.ts"
+    "../../packages/readers/src/*.ts"
   ],
   "exclude": [
     "../../packages/autotool/**/src/index.ts",
-    "../../packages/cloud/src/client/index.ts",
     "**/node_modules/**",
     "**/dist/**",
     "**/test/**",
@@ -22,7 +20,7 @@
   "categoryOrder": ["Classes", "Enums", "Functions", "Interfaces", "Types"],
   "sort": ["source-order"],
   "entryFileName": "index.md",
-  "fileExtension": ".mdx",
+  "fileExtension": ".md",
   "hidePageTitle": true,
   "hidePageHeader": true,
   "hideGroupHeadings": true,

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

@@ -1,5 +1,27 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.159
+
+### Patch Changes
+
+- llamaindex@0.10.5
+
+## 0.0.158
+
+### Patch Changes
+
+- Updated dependencies [2225ffd]
+- Updated dependencies [6ddf1c1]
+- Updated dependencies [41953a3]
+  - llamaindex@0.10.4
+
+## 0.0.157
+
+### Patch Changes
+
+- Updated dependencies [3ee8c83]
+  - llamaindex@0.10.3
+
 ## 0.0.156
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.156",
+  "version": "0.0.159",
   "type": "module",
   "private": true,
   "scripts": {

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

@@ -1,5 +1,24 @@
 # @llamaindex/llama-parse-browser-test
 
+## 0.0.61
+
+### Patch Changes
+
+- @llamaindex/cloud@4.0.6
+
+## 0.0.60
+
+### Patch Changes
+
+- Updated dependencies [2225ffd]
+  - @llamaindex/cloud@4.0.5
+
+## 0.0.59
+
+### Patch Changes
+
+- @llamaindex/cloud@4.0.4
+
 ## 0.0.58
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llama-parse-browser-test",
   "private": true,
-  "version": "0.0.58",
+  "version": "0.0.61",
   "type": "module",
   "scripts": {
     "dev": "vite",
@@ -10,8 +10,8 @@
   },
   "devDependencies": {
     "typescript": "^5.7.3",
-    "vite": "^5.4.16",
-    "vite-plugin-wasm": "^3.3.0"
+    "vite": "^6.3.3",
+    "vite-plugin-wasm": "^3.4.1"
   },
   "dependencies": {
     "@llamaindex/cloud": "workspace:*"

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,27 @@
 # @llamaindex/next-agent-test
 
+## 0.1.159
+
+### Patch Changes
+
+- llamaindex@0.10.5
+
+## 0.1.158
+
+### Patch Changes
+
+- Updated dependencies [2225ffd]
+- Updated dependencies [6ddf1c1]
+- Updated dependencies [41953a3]
+  - llamaindex@0.10.4
+
+## 0.1.157
+
+### Patch Changes
+
+- Updated dependencies [3ee8c83]
+  - llamaindex@0.10.3
+
 ## 0.1.156
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.156",
+  "version": "0.1.159",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,27 @@
 # test-edge-runtime
 
+## 0.1.158
+
+### Patch Changes
+
+- llamaindex@0.10.5
+
+## 0.1.157
+
+### Patch Changes
+
+- Updated dependencies [2225ffd]
+- Updated dependencies [6ddf1c1]
+- Updated dependencies [41953a3]
+  - llamaindex@0.10.4
+
+## 0.1.156
+
+### Patch Changes
+
+- Updated dependencies [3ee8c83]
+  - llamaindex@0.10.3
+
 ## 0.1.155
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.155",
+  "version": "0.1.158",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,38 @@
 # @llamaindex/next-node-runtime
 
+## 0.1.26
+
+### Patch Changes
+
+- llamaindex@0.10.5
+- @llamaindex/huggingface@0.1.8
+- @llamaindex/readers@3.1.2
+
+## 0.1.25
+
+### Patch Changes
+
+- Updated dependencies [2225ffd]
+- Updated dependencies [6ddf1c1]
+- Updated dependencies [41953a3]
+  - llamaindex@0.10.4
+
+## 0.1.24
+
+### Patch Changes
+
+- Updated dependencies [3ee8c83]
+  - llamaindex@0.10.3
+  - @llamaindex/huggingface@0.1.7
+  - @llamaindex/readers@3.1.1
+
+## 0.1.23
+
+### Patch Changes
+
+- Updated dependencies [1e59695]
+  - @llamaindex/readers@3.1.0
+
 ## 0.1.22
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.22",
+  "version": "0.1.26",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,27 @@
 # vite-import-llamaindex
 
+## 0.0.25
+
+### Patch Changes
+
+- llamaindex@0.10.5
+
+## 0.0.24
+
+### Patch Changes
+
+- Updated dependencies [2225ffd]
+- Updated dependencies [6ddf1c1]
+- Updated dependencies [41953a3]
+  - llamaindex@0.10.4
+
+## 0.0.23
+
+### Patch Changes
+
+- Updated dependencies [3ee8c83]
+  - llamaindex@0.10.3
+
 ## 0.0.22
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.22",
+  "version": "0.0.25",
   "type": "module",
   "scripts": {
     "build": "vite build",
@@ -16,7 +16,7 @@
     "@size-limit/preset-big-lib": "^11.1.6",
     "size-limit": "^11.1.6",
     "typescript": "^5.7.3",
-    "vite": "^5.4.16"
+    "vite": "^6.3.3"
   },
   "dependencies": {
     "llamaindex": "workspace:*"

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

@@ -1,5 +1,29 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.159
+
+### Patch Changes
+
+- Updated dependencies [9b2e25a]
+  - @llamaindex/env@0.1.30
+  - llamaindex@0.10.5
+
+## 0.0.158
+
+### Patch Changes
+
+- Updated dependencies [2225ffd]
+- Updated dependencies [6ddf1c1]
+- Updated dependencies [41953a3]
+  - llamaindex@0.10.4
+
+## 0.0.157
+
+### Patch Changes
+
+- Updated dependencies [3ee8c83]
+  - llamaindex@0.10.3
+
 ## 0.0.156
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.156",
+  "version": "0.0.159",
   "type": "module",
   "private": true,
   "scripts": {

examples/CHANGELOG.md

@@ -1,5 +1,141 @@
 # examples
 
+## 0.3.14
+
+### Patch Changes
+
+- 9b2e25a: Use Uint8Array instead of Buffer for file type messages (works with non-NodeJS)
+- 206b491: Add support for google live api
+- Updated dependencies [9b2e25a]
+- Updated dependencies [206b491]
+  - @llamaindex/anthropic@0.3.5
+  - @llamaindex/google@0.3.0
+  - @llamaindex/openai@0.3.6
+  - @llamaindex/core@0.6.4
+  - @llamaindex/env@0.1.30
+  - llamaindex@0.10.5
+  - @llamaindex/clip@0.0.54
+  - @llamaindex/deepinfra@0.0.54
+  - @llamaindex/deepseek@0.0.14
+  - @llamaindex/fireworks@0.0.14
+  - @llamaindex/groq@0.0.69
+  - @llamaindex/huggingface@0.1.8
+  - @llamaindex/jinaai@0.0.14
+  - @llamaindex/perplexity@0.0.11
+  - @llamaindex/azure@0.1.14
+  - @llamaindex/elastic-search@0.1.4
+  - @llamaindex/milvus@0.1.13
+  - @llamaindex/qdrant@0.1.13
+  - @llamaindex/supabase@0.1.3
+  - @llamaindex/together@0.0.14
+  - @llamaindex/vllm@0.0.40
+  - @llamaindex/cloud@4.0.6
+  - @llamaindex/node-parser@2.0.4
+  - @llamaindex/assemblyai@0.1.3
+  - @llamaindex/cohere@0.0.18
+  - @llamaindex/discord@0.1.3
+  - @llamaindex/mistral@0.1.4
+  - @llamaindex/mixedbread@0.0.18
+  - @llamaindex/notion@0.1.3
+  - @llamaindex/ollama@0.1.4
+  - @llamaindex/portkey-ai@0.0.46
+  - @llamaindex/replicate@0.0.46
+  - @llamaindex/astra@0.0.18
+  - @llamaindex/chroma@0.0.18
+  - @llamaindex/firestore@1.0.11
+  - @llamaindex/mongodb@0.0.19
+  - @llamaindex/pinecone@0.1.4
+  - @llamaindex/postgres@0.0.47
+  - @llamaindex/upstash@0.0.18
+  - @llamaindex/weaviate@0.0.18
+  - @llamaindex/vercel@0.1.4
+  - @llamaindex/voyage-ai@1.0.10
+  - @llamaindex/readers@3.1.2
+  - @llamaindex/tools@0.0.9
+  - @llamaindex/workflow@1.1.1
+
+## 0.3.13
+
+### Patch Changes
+
+- Updated dependencies [3ee8c83]
+  - @llamaindex/core@0.6.3
+  - llamaindex@0.10.3
+  - @llamaindex/anthropic@0.3.4
+  - @llamaindex/google@0.2.5
+  - @llamaindex/openai@0.3.5
+  - @llamaindex/vercel@0.1.3
+  - @llamaindex/cloud@4.0.4
+  - @llamaindex/node-parser@2.0.3
+  - @llamaindex/assemblyai@0.1.2
+  - @llamaindex/clip@0.0.53
+  - @llamaindex/cohere@0.0.17
+  - @llamaindex/deepinfra@0.0.53
+  - @llamaindex/discord@0.1.2
+  - @llamaindex/huggingface@0.1.7
+  - @llamaindex/jinaai@0.0.13
+  - @llamaindex/mistral@0.1.3
+  - @llamaindex/mixedbread@0.0.17
+  - @llamaindex/notion@0.1.2
+  - @llamaindex/ollama@0.1.3
+  - @llamaindex/perplexity@0.0.10
+  - @llamaindex/portkey-ai@0.0.45
+  - @llamaindex/replicate@0.0.45
+  - @llamaindex/astra@0.0.17
+  - @llamaindex/azure@0.1.13
+  - @llamaindex/chroma@0.0.17
+  - @llamaindex/elastic-search@0.1.3
+  - @llamaindex/firestore@1.0.10
+  - @llamaindex/milvus@0.1.12
+  - @llamaindex/mongodb@0.0.18
+  - @llamaindex/pinecone@0.1.3
+  - @llamaindex/postgres@0.0.46
+  - @llamaindex/qdrant@0.1.12
+  - @llamaindex/supabase@0.1.2
+  - @llamaindex/upstash@0.0.17
+  - @llamaindex/weaviate@0.0.17
+  - @llamaindex/voyage-ai@1.0.9
+  - @llamaindex/readers@3.1.1
+  - @llamaindex/tools@0.0.8
+  - @llamaindex/workflow@1.0.4
+  - @llamaindex/deepseek@0.0.13
+  - @llamaindex/fireworks@0.0.13
+  - @llamaindex/groq@0.0.68
+  - @llamaindex/together@0.0.13
+  - @llamaindex/vllm@0.0.39
+
+## 0.3.12
+
+### Patch Changes
+
+- Updated dependencies [82d4b46]
+  - @llamaindex/server@0.1.6
+  - @llamaindex/tools@0.0.7
+
+## 0.3.11
+
+### Patch Changes
+
+- Updated dependencies [294f502]
+  - @llamaindex/tools@0.0.6
+
+## 0.3.10
+
+### Patch Changes
+
+- Updated dependencies [1e59695]
+- Updated dependencies [1e59695]
+- Updated dependencies [1e59695]
+- Updated dependencies [1e59695]
+- Updated dependencies [1e59695]
+- Updated dependencies [1e59695]
+  - @llamaindex/assemblyai@0.1.1
+  - @llamaindex/mongodb@0.0.17
+  - @llamaindex/azure@0.1.12
+  - @llamaindex/readers@3.1.0
+  - @llamaindex/notion@0.1.1
+  - @llamaindex/discord@0.1.1
+
 ## 0.3.9
 
 ### Patch Changes

examples/agents/agent/blog-writer.ts

@@ -1,12 +1,12 @@
+import { tool } from "@llamaindex/core/tools";
 import { openai } from "@llamaindex/openai";
-import fs from "fs";
 import {
   agent,
-  AgentToolCall,
-  AgentToolCallResult,
+  agentToolCallEvent,
+  agentToolCallResultEvent,
   multiAgent,
-  tool,
-} from "llamaindex";
+} from "@llamaindex/workflow";
+import fs from "fs";
 import os from "os";
 import { z } from "zod";
 
@@ -56,19 +56,19 @@ async function main() {
     rootAgent: researchAgent,
   });
 
-  const context = workflow.run("Write a blog post about history of LLM");
+  const events = workflow.runStream("Write a blog post about history of LLM");
 
   let finalResult;
-  for await (const event of context) {
-    if (event instanceof AgentToolCall) {
+  for await (const event of events) {
+    if (agentToolCallEvent.include(event)) {
       console.log(
-        `[Agent ${event.displayName}] executing tool ${event.data.toolName} with parameters ${JSON.stringify(
+        `[Agent ${event.data.agentName}] executing tool ${event.data.toolName} with parameters ${JSON.stringify(
           event.data.toolKwargs,
         )}`,
       );
-    } else if (event instanceof AgentToolCallResult) {
+    } else if (agentToolCallResultEvent.include(event)) {
       console.log(
-        `[Agent ${event.displayName}] executed tool ${event.data.toolName} with result ${event.data.toolOutput.result}`,
+        `[Tool ${event.data.toolName}] executed with result ${event.data.toolOutput.result}`,
       );
     }
     finalResult = event;

examples/agents/agent/large-toolcall.ts

@@ -1,5 +1,6 @@
 import { OpenAI } from "@llamaindex/openai";
-import { FunctionTool, agent } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
+import { tool } from "llamaindex";
 import { z } from "zod";
 
 const csvData =
@@ -11,24 +12,22 @@ const userQuestion = "which are the best comedies after 2010?";
   // The agent will succeed if we increase `maxTokens` to 1024
   const llm = new OpenAI({ model: "gpt-4-turbo", maxTokens: 1024 });
 
-  const interpreterTool = FunctionTool.from(
-    ({ code }) => {
+  const interpreterTool = tool({
+    name: "interpreter",
+    description:
+      "Execute python code in a Jupyter notebook cell and return any result, stdout, stderr, display_data, and error.",
+    parameters: z.object({
+      code: z.string({
+        description: "The python code to execute in a single cell.",
+      }),
+    }),
+    execute: ({ code }) => {
       console.log(
         `To answer the user's question, call the following code:\n${code}`,
       );
       return code;
     },
-    {
-      name: "interpreter",
-      description:
-        "Execute python code in a Jupyter notebook cell and return any result, stdout, stderr, display_data, and error.",
-      parameters: z.object({
-        code: z.string({
-          description: "The python code to execute in a single cell.",
-        }),
-      }),
-    },
-  );
+  });
 
   const systemPrompt =
     "You are a Python interpreter.\n        - You are given tasks to complete and you run python code to solve them.\n        - The python code runs in a Jupyter notebook. Every time you call $(interpreter) tool, the python code is executed in a separate cell. It's okay to make multiple calls to $(interpreter).\n        - Display visualizations using matplotlib or any other visualization library directly in the notebook. Shouldn't save the visualizations to a file, just return the base64 encoded data.\n        - You can install any pip package (if it exists) if you need to but the usual packages for data analysis are already preinstalled.\n        - You can run any python code you want in a secure environment.";

examples/agents/agent/mcp-tools.ts

@@ -1,6 +1,6 @@
 import { openai } from "@llamaindex/openai";
 import { mcp } from "@llamaindex/tools";
-import { agent } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
 
 async function main() {
   // Create an MCP server for filesystem tools
@@ -9,6 +9,12 @@ async function main() {
     args: ["-y", "@modelcontextprotocol/server-filesystem", "."],
     verbose: true,
   });
+  // You can also connect to the MCP server using SSE
+  // See: https://modelcontextprotocol.io/docs/concepts/transports#server-sent-events-sse
+  // const server = mcp({
+  //   url: "http://localhost:8000/mcp",
+  //   verbose: true,
+  // });
 
   try {
     // Create an agent that uses the MCP tools
@@ -21,9 +27,7 @@ async function main() {
     });
 
     // Run a task
-    const response = await myAgent.run(
-      "what are the files in the current directory?",
-    );
+    const response = await myAgent.run("What are the available tools?");
 
     console.log("Agent response:", response.data);
   } finally {

examples/agents/agent/multiple-agents.ts

@@ -6,15 +6,15 @@
 import { openai } from "@llamaindex/openai";
 import {
   agent,
-  AgentInput,
-  AgentOutput,
-  AgentStream,
-  AgentToolCall,
-  AgentToolCallResult,
+  agentInputEvent,
+  agentOutputEvent,
+  agentStreamEvent,
+  agentToolCallEvent,
+  agentToolCallResultEvent,
   multiAgent,
-  StopEvent,
-  tool,
-} from "llamaindex";
+  stopAgentEvent,
+} from "@llamaindex/workflow";
+import { tool } from "llamaindex";
 import { z } from "zod";
 
 const llm = openai({
@@ -79,21 +79,21 @@ async function multiWeatherAgent() {
   });
 
   // Ask the agent to get the weather in a city
-  const context = workflow.run(
+  const events = workflow.runStream(
     "What is the weather in San Francisco in Celsius?",
   );
   // Stream the events
-  for await (const event of context) {
-    // These events might be useful for UI
+  for await (const event of events) {
+    // These events are useful for reporting the current state to the user in the UI
     if (
-      event instanceof AgentToolCall ||
-      event instanceof AgentToolCallResult ||
-      event instanceof AgentOutput ||
-      event instanceof AgentInput ||
-      event instanceof StopEvent
+      agentToolCallEvent.include(event) ||
+      agentToolCallResultEvent.include(event) ||
+      agentOutputEvent.include(event) ||
+      agentInputEvent.include(event) ||
+      stopAgentEvent.include(event)
     ) {
       console.log(event);
-    } else if (event instanceof AgentStream) {
+    } else if (agentStreamEvent.include(event)) {
       for (const chunk of event.data.delta) {
         process.stdout.write(chunk);
       }

examples/agents/agent/openai.ts

@@ -1,5 +1,6 @@
 import { openai } from "@llamaindex/openai";
-import { agent, tool } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
+import { tool } from "llamaindex";
 import { z } from "zod";
 
 const sumNumbers = tool({
@@ -25,7 +26,7 @@ const divideNumbers = tool({
 async function main() {
   const mathAgent = agent({
     tools: [sumNumbers, divideNumbers],
-    llm: openai({ model: "gpt-4o-mini" }),
+    llm: openai({ model: "gpt-4.1-mini" }),
     verbose: false,
   });
 

examples/agents/agent/query-tool.ts

@@ -1,11 +1,9 @@
 import {
-  AgentStream,
-  AgentToolCallResult,
-  Document,
-  VectorStoreIndex,
   agent,
-  openai,
-} from "llamaindex";
+  agentStreamEvent,
+  agentToolCallResultEvent,
+} from "@llamaindex/workflow";
+import { Document, VectorStoreIndex, openai } from "llamaindex";
 
 async function main() {
   const index = await VectorStoreIndex.fromDocuments([
@@ -30,15 +28,15 @@ async function main() {
     ],
   });
 
-  const context = myAgent.run("The fact about cats");
+  const events = myAgent.runStream("The fact about cats");
 
-  for await (const event of context) {
-    if (event instanceof AgentToolCallResult) {
+  for await (const event of events) {
+    if (agentToolCallResultEvent.include(event)) {
       console.log(
         "Using these retrieved information to answer the question:\n",
         event.data.toolOutput.result,
       );
-    } else if (event instanceof AgentStream) {
+    } else if (agentStreamEvent.include(event)) {
       for (const chunk of event.data.delta) {
         process.stdout.write(chunk);
       }

examples/agents/agent/single-agent.ts

@@ -2,8 +2,8 @@
  * This example shows how to use a single agent with a tool
  */
 import { openai } from "@llamaindex/openai";
-import { agent } from "llamaindex";
-import { getWeatherTool } from "../agent/utils/tools";
+import { agent } from "@llamaindex/workflow";
+import { getWeatherTool } from "../deprecated/utils/tools";
 
 async function main() {
   const weatherAgent = agent({
@@ -14,14 +14,14 @@ async function main() {
     verbose: false,
   });
 
-  // Run the agent and keep the context
-  const context = weatherAgent.run("What's the weather like in San Francisco?");
-  const result = await context;
+  const result = await weatherAgent.run(
+    "What's the weather like in San Francisco?",
+  );
   console.log(`${JSON.stringify(result, null, 2)}`);
 
-  // Reuse the context from the previous run
+  // Reuse the state from the previous run
   const caResult = await weatherAgent.run("Compare it with California?", {
-    context: context.data,
+    state: result.data.state,
   });
   console.log(`${JSON.stringify(caResult, null, 2)}`);
 }

examples/agents/agent/wiki.ts

@@ -1,6 +1,6 @@
 import { OpenAI } from "@llamaindex/openai";
 import { wiki } from "@llamaindex/tools";
-import { AgentStream, agent } from "llamaindex";
+import { agent, agentStreamEvent } from "@llamaindex/workflow";
 
 async function main() {
   const llm = new OpenAI({ model: "gpt-4-turbo" });
@@ -12,10 +12,10 @@ async function main() {
   });
 
   // Chat with the agent
-  const context = workflow.run("Who was Goethe?");
+  const events = workflow.runStream("Who was Goethe?");
 
-  for await (const event of context) {
-    if (event instanceof AgentStream) {
+  for await (const event of events) {
+    if (agentStreamEvent.include(event)) {
       for (const chunk of event.data.delta) {
         process.stdout.write(chunk);
       }

examples/agents/agent/with-anthropic.ts

@@ -1,11 +1,11 @@
-import fs from "fs";
 import {
   agent,
-  AgentToolCall,
-  AgentToolCallResult,
+  agentToolCallEvent,
+  agentToolCallResultEvent,
   multiAgent,
-  tool,
-} from "llamaindex";
+} from "@llamaindex/workflow";
+import fs from "fs";
+import { tool } from "llamaindex";
 import { z } from "zod";
 
 import { anthropic } from "@llamaindex/anthropic";
@@ -81,21 +81,21 @@ async function main() {
     rootAgent: researchAgent,
   });
 
-  const context = workflow.run(
+  const events = workflow.runStream(
     "Write a report about New York weather and inflation",
   );
 
   let finalResult;
-  for await (const event of context) {
-    if (event instanceof AgentToolCall) {
+  for await (const event of events) {
+    if (agentToolCallEvent.include(event)) {
       console.log(
-        `[Agent ${event.displayName}] executing tool ${event.data.toolName} with parameters ${JSON.stringify(
+        `[Agent ${event.data.agentName}] executing tool ${event.data.toolName} with parameters ${JSON.stringify(
           event.data.toolKwargs,
         )}`,
       );
-    } else if (event instanceof AgentToolCallResult) {
+    } else if (agentToolCallResultEvent.include(event)) {
       console.log(
-        `[Agent ${event.displayName}] executed tool ${event.data.toolName} with result ${event.data.toolOutput.result}`,
+        `[Agent executed tool ${event.data.toolName} with result ${event.data.toolOutput.result}`,
       );
     }
     finalResult = event;

examples/agents/agent/with-ollama.ts

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

examples/agents/workflow/joke.ts

@@ -0,0 +1,94 @@
+import { openai } from "@llamaindex/openai";
+import {
+  createStatefulMiddleware,
+  createWorkflow,
+  workflowEvent,
+} from "@llamaindex/workflow";
+
+// Create LLM instance
+const llm = openai({ model: "gpt-4.1-mini" });
+
+// Define our workflow events
+const startEvent = workflowEvent<string>(); // Input topic for joke
+const jokeEvent = workflowEvent<{ joke: string }>(); // Intermediate joke
+const critiqueEvent = workflowEvent<{ joke: string; critique: string }>(); // Intermediate critique
+const resultEvent = workflowEvent<{ joke: string; critique: string }>(); // Final joke + critique
+
+// Create our workflow
+const { withState, getContext } = createStatefulMiddleware(() => ({
+  numIterations: 0,
+  maxIterations: 3,
+}));
+const jokeFlow = withState(createWorkflow());
+
+// Define handlers for each step
+jokeFlow.handle([startEvent], async (event) => {
+  // Prompt the LLM to write a joke
+  const prompt = `Write your best joke about ${event.data}. Write the joke between <joke> and </joke> tags.`;
+  const response = await llm.complete({ prompt });
+
+  // Parse the joke from the response
+  const joke =
+    response.text.match(/<joke>([\s\S]*?)<\/joke>/)?.[1]?.trim() ??
+    response.text;
+  return jokeEvent.with({ joke: joke });
+});
+
+jokeFlow.handle([jokeEvent], async (event) => {
+  // Prompt the LLM to critique the joke
+  const prompt = `Give a thorough critique of the following joke. If the joke needs improvement, put "IMPROVE" somewhere in the critique: ${event.data.joke}`;
+  const response = await llm.complete({ prompt });
+
+  // If the critique includes "IMPROVE", keep iterating, else, return the result
+  if (response.text.includes("IMPROVE")) {
+    return critiqueEvent.with({
+      joke: event.data.joke,
+      critique: response.text,
+    });
+  }
+
+  return resultEvent.with({ joke: event.data.joke, critique: response.text });
+});
+
+jokeFlow.handle([critiqueEvent], async (event) => {
+  // Keep track of the number of iterations
+  const state = getContext().state;
+  state.numIterations++;
+
+  // Write a new joke based on the previous joke and critique
+  const prompt = `Write a new joke based on the following critique and the original joke. Write the joke between <joke> and </joke> tags.\n\nJoke: ${event.data.joke}\n\nCritique: ${event.data.critique}`;
+  const response = await llm.complete({ prompt });
+
+  // Parse the joke from the response
+  const joke =
+    response.text.match(/<joke>([\s\S]*?)<\/joke>/)?.[1]?.trim() ??
+    response.text;
+
+  // If we've done less than the max number of iterations, keep iterating
+  // else, return the result
+  if (state.numIterations < state.maxIterations) {
+    return jokeEvent.with({ joke: joke });
+  }
+
+  return resultEvent.with({ joke: joke, critique: event.data.critique });
+});
+
+// Usage
+async function main() {
+  const { stream, sendEvent } = jokeFlow.createContext();
+  sendEvent(startEvent.with("pirates"));
+
+  let result: { joke: string; critique: string } | undefined;
+
+  for await (const event of stream) {
+    // console.log(event.data);  optionally log the event data
+    if (resultEvent.include(event)) {
+      result = event.data;
+      break; // Stop when we get the final result
+    }
+  }
+
+  console.log(result);
+}
+
+main().catch(console.error);

examples/anthropic/agent.ts

@@ -1,6 +1,7 @@
 import { anthropic } from "@llamaindex/anthropic";
 import { wiki } from "@llamaindex/tools";
-import { agent, tool } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
+import { tool } from "llamaindex";
 import { z } from "zod";
 
 const workflow = agent({

examples/anthropic/chat-with-file.ts

@@ -0,0 +1,39 @@
+import { Anthropic } from "@llamaindex/anthropic";
+import fs from "fs";
+
+// Note that: Anthropic only supports PDF files for now with limited models
+// See: https://docs.anthropic.com/en/docs/build-with-claude/pdf-support?q=pdf#supported-platforms-and-models
+
+async function main() {
+  if (!process.env.ANTHROPIC_API_KEY) {
+    throw new Error("Please set the ANTHROPIC_API_KEY environment variable.");
+  }
+
+  const llm = new Anthropic({
+    apiKey: process.env.ANTHROPIC_API_KEY,
+    model: "claude-3-7-sonnet",
+  });
+
+  const result = await llm.chat({
+    messages: [
+      {
+        role: "user",
+        content: [
+          {
+            type: "text",
+            text: "What's in this document? Describe it in detail.",
+          },
+          {
+            type: "file",
+            data: Uint8Array.from(fs.readFileSync("./data/manga.pdf")),
+            mimeType: "application/pdf",
+          },
+        ],
+      },
+    ],
+  });
+
+  console.log(result.message);
+}
+
+void main().catch(console.error);

examples/assemblyai/reader.ts

@@ -1,7 +1,7 @@
 import {
   AudioTranscriptReader,
   TranscribeParams,
-} from "@llamaindex/readers/assembly-ai";
+} from "@llamaindex/assemblyai";
 import { program } from "commander";
 import { VectorStoreIndex } from "llamaindex";
 import { stdin as input, stdout as output } from "node:process";

examples/cosmosdb/loadVectorData.ts

@@ -1,11 +1,11 @@
 import { CosmosClient } from "@azure/cosmos";
 import { DefaultAzureCredential } from "@azure/identity";
-import { AzureCosmosDBNoSQLConfig } from "@llamaindex/azure";
-import { OpenAI, OpenAIEmbedding } from "@llamaindex/openai";
 import {
+  AzureCosmosDBNoSQLConfig,
   SimpleCosmosDBReader,
   SimpleCosmosDBReaderLoaderConfig,
-} from "@llamaindex/readers/cosmosdb";
+} from "@llamaindex/azure";
+import { OpenAI, OpenAIEmbedding } from "@llamaindex/openai";
 import * as dotenv from "dotenv";
 import {
   Settings,

examples/discord/reader.ts

@@ -1,4 +1,4 @@
-import { DiscordReader } from "@llamaindex/readers/discord";
+import { DiscordReader } from "@llamaindex/discord";
 
 async function main() {
   // Create an instance of the DiscordReader. Set token here or DISCORD_TOKEN environment variable

examples/gemini/agent.ts

@@ -1,5 +1,6 @@
 import { gemini, GEMINI_MODEL } from "@llamaindex/google";
-import { agent, tool } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
+import { tool } from "llamaindex";
 import { z } from "zod";
 
 const sumNumbers = tool({

examples/gemini/chat.ts

@@ -1,11 +1,12 @@
 import { Gemini, GEMINI_MODEL } from "@llamaindex/google";
+import fs from "fs";
 
 (async () => {
   if (!process.env.GOOGLE_API_KEY) {
     throw new Error("Please set the GOOGLE_API_KEY environment variable.");
   }
   const gemini = new Gemini({
-    model: GEMINI_MODEL.GEMINI_PRO,
+    model: GEMINI_MODEL.GEMINI_PRO_1_5,
   });
   const result = await gemini.chat({
     messages: [
@@ -18,4 +19,26 @@ import { Gemini, GEMINI_MODEL } from "@llamaindex/google";
     ],
   });
   console.log(result);
+
+  // chat with file
+  const resultWithFile = await gemini.chat({
+    messages: [
+      {
+        role: "user",
+        content: [
+          {
+            type: "text",
+            text: "What's in this document? Describe it in detail.",
+          },
+          {
+            type: "file",
+            data: Uint8Array.from(fs.readFileSync("./data/manga.pdf")),
+            mimeType: "application/pdf",
+          },
+        ],
+      },
+    ],
+  });
+
+  console.log(resultWithFile);
 })();

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

@@ -0,0 +1,104 @@
+import { ModalityType } from "@llamaindex/core/schema";
+import { tool } from "@llamaindex/core/tools";
+import { gemini, GEMINI_MODEL } from "@llamaindex/google";
+
+import { liveEvents } from "llamaindex";
+import { z } from "zod";
+
+const weatherTool = tool({
+  name: "weather",
+  description: "Get the weather",
+  parameters: z.object({
+    location: z.string({
+      description: "The location to get the weather for",
+    }),
+  }),
+  execute: ({ location }) => {
+    return `The weather in ${location} is rainy`;
+  },
+});
+
+const divideNumbers = tool({
+  name: "divideNumbers",
+  description: "Use this function to divide two numbers",
+  parameters: z.object({
+    a: z.number().describe("The dividend a to divide"),
+    b: z.number().describe("The divisor b to divide by"),
+  }),
+  execute: ({ a, b }) => `${a / b}`,
+});
+
+async function main() {
+  const apiKey = process.env.GOOGLE_API_KEY;
+  if (!apiKey) {
+    console.error(
+      "Please set GOOGLE_API_KEY in your environment variables or .env file",
+    );
+    process.exit(1);
+  }
+
+  console.log("🚀 Initializing Gemini Live API with tools example...");
+
+  const llm = gemini({
+    apiKey: apiKey,
+    model: GEMINI_MODEL.GEMINI_2_0_FLASH_LIVE, // Must use a live-compatible model
+  });
+
+  console.log("📡 Connecting to Gemini Live session...");
+
+  // Connect to a live session with tools
+  const session = await llm.live.connect({
+    // Specify response modalities (text response is required for tools)
+    responseModality: [ModalityType.TEXT],
+    // Register our tools with the session
+    tools: [weatherTool, divideNumbers],
+    // Optional system instruction
+    systemInstruction:
+      "You are a helpful assistant that can use tools. When answering questions about weather or divide numbers, always use the appropriate tool.",
+  });
+
+  (async () => {
+    console.log("🎧 Listening for events...");
+
+    for await (const event of session.streamEvents()) {
+      if (liveEvents.open.include(event)) {
+        console.log("✅ Connected to Gemini Live session");
+
+        console.log(
+          "💬 Sending message: 'What's the weather in San Francisco and what is 100 / 2?'",
+        );
+        session.sendMessage({
+          content: "What's the weather in San Francisco and what is 100 / 2?",
+          role: "user",
+        });
+      } else if (liveEvents.text.include(event)) {
+        process.stdout.write(event.text);
+      } else if (liveEvents.error.include(event)) {
+        console.error("❌ Error:", event.error);
+      } else if (liveEvents.close.include(event)) {
+        console.log("👋 Session closed");
+        process.exit(0);
+      } else if (liveEvents.setupComplete.include(event)) {
+        console.log("🔧 Setup complete");
+      }
+    }
+  })();
+
+  process.on("SIGINT", async () => {
+    console.log("\n👋 Interrupted by user. Closing session...");
+    await session.disconnect();
+    process.exit(0);
+  });
+
+  // Timeout after 2 minutes if no interaction
+  setTimeout(async () => {
+    console.log("\n⏱️ Session timeout. Closing session...");
+    await session.disconnect();
+    process.exit(0);
+  }, 120000);
+}
+
+main().catch((error) => {
+  console.error("❌ Fatal error:", error);
+  process.exit(1);
+});

examples/gemini/gemini-live.ts

@@ -0,0 +1,221 @@
+import { fs } from "@llamaindex/env";
+import { gemini, GEMINI_MODEL, GeminiLiveSession } from "@llamaindex/google";
+import { liveEvents } from "llamaindex";
+
+import path from "path";
+
+function createWavHeader(
+  sampleRate = 16000,
+  bitsPerSample = 16,
+  channels = 1,
+  dataLength: number,
+) {
+  const buffer = Buffer.alloc(44);
+
+  // RIFF chunk descriptor
+  buffer.write("RIFF", 0);
+  buffer.writeUInt32LE(36 + dataLength, 4); // File size - 8
+  buffer.write("WAVE", 8);
+
+  // fmt sub-chunk
+  buffer.write("fmt ", 12);
+  buffer.writeUInt32LE(16, 16); // Subchunk1Size (16 for PCM)
+  buffer.writeUInt16LE(1, 20); // AudioFormat (1 for PCM)
+  buffer.writeUInt16LE(channels, 22); // NumChannels
+  buffer.writeUInt32LE(sampleRate, 24); // SampleRate
+  buffer.writeUInt32LE((sampleRate * channels * bitsPerSample) / 8, 28); // ByteRate
+  buffer.writeUInt16LE((channels * bitsPerSample) / 8, 32); // BlockAlign
+  buffer.writeUInt16LE(bitsPerSample, 34); // BitsPerSample
+
+  // data sub-chunk
+  buffer.write("data", 36);
+  buffer.writeUInt32LE(dataLength, 40); // Subchunk2Size
+
+  return buffer;
+}
+
+async function saveWavFile(
+  audioChunks: Buffer[],
+  filePath: string,
+  sampleRate = 16000,
+  bitsPerSample = 16,
+  channels = 1,
+): Promise<void> {
+  if (audioChunks.length === 0) {
+    throw new Error("No audio data to save");
+  }
+
+  try {
+    const combinedAudioData = Buffer.concat(audioChunks);
+    console.log(`Total audio data: ${combinedAudioData.length} bytes`);
+
+    const wavHeader = createWavHeader(
+      sampleRate,
+      bitsPerSample,
+      channels,
+      combinedAudioData.length,
+    );
+    const wavFile = Buffer.concat([wavHeader, combinedAudioData]);
+
+    await fs.writeFile(filePath, wavFile);
+    console.log(`💾 Saved audio to ${filePath}`);
+    return;
+  } catch (error) {
+    console.error("❌ Error saving audio file:", error);
+    throw error;
+  }
+}
+
+async function main() {
+  const apiKey = process.env.GOOGLE_API_KEY;
+  if (!apiKey) {
+    console.error(
+      "Please set GOOGLE_API_KEY in your environment variables or .env file",
+    );
+    process.exit(1);
+  }
+
+  console.log("🚀 Initializing Gemini Live API example...");
+
+  const llm = gemini({
+    model: GEMINI_MODEL.GEMINI_2_0_FLASH_LIVE,
+    voiceName: "Zephyr",
+  });
+
+  console.log("📡 Connecting to Gemini Live session...");
+
+  const session = await llm.live.connect();
+
+  let isRunning = true;
+
+  const audioChunks: Buffer[] = [];
+  let audioResponse = false;
+
+  (async () => {
+    try {
+      console.log("🎧 Listening for events...");
+
+      for await (const event of session.streamEvents()) {
+        if (liveEvents.open.include(event)) {
+          console.log("✅ Connected to Gemini Live session");
+
+          console.log(
+            "💬 Sending text message: 'Say something about you for 10 seconds'",
+          );
+          session.sendMessage({
+            content: "Say something about you for 10 seconds",
+            role: "user",
+          });
+
+          setTimeout(() => {
+            sendPcmAudioFile(session);
+          }, 3000);
+        } else if (liveEvents.setupComplete.include(event)) {
+          console.log("✅ Setup complete");
+        } else if (liveEvents.text.include(event)) {
+          process.stdout.write(event.text);
+        } else if (liveEvents.audio.include(event)) {
+          console.log("\n🔊 Received audio chunk");
+          audioResponse = true;
+
+          try {
+            const chunk = Buffer.from(event.data as string, "base64");
+            audioChunks.push(chunk);
+            console.log(`Received audio chunk: ${chunk.length} bytes`);
+          } catch (error) {
+            console.error("❌ Error processing audio chunk:", error);
+          }
+        } else if (liveEvents.error.include(event)) {
+          console.error("❌ Error:", event.error);
+        } else if (liveEvents.close.include(event)) {
+          console.log("👋 Session closed");
+
+          if (audioResponse && audioChunks.length > 0) {
+            try {
+              await saveWavFile(audioChunks, "gemini-response.wav");
+            } catch (error) {
+              console.error("❌ Error saving final audio file:", error);
+            }
+          }
+
+          isRunning = false;
+          break;
+        }
+      }
+    } catch (error) {
+      console.error("❌ Error processing stream:", error);
+    }
+  })();
+
+  async function sendPcmAudioFile(session: GeminiLiveSession) {
+    try {
+      console.log("🎤 Reading PCM audio file...");
+
+      const filePath = path.join(__dirname, "hello_are_you_there.pcm");
+      console.log(`Reading file from: ${filePath}`);
+
+      const audioBuffer = await fs.readFile(filePath);
+
+      const base64Audio = audioBuffer.toString("base64");
+
+      session.sendMessage({
+        content: [
+          {
+            type: "audio",
+            data: base64Audio,
+            mimeType: "audio/pcm;rate=16000",
+          },
+        ],
+        role: "user",
+      });
+
+      console.log("🎤 PCM audio file sent! Waiting for response...");
+    } catch (error) {
+      console.error("❌ Error sending audio file:", error);
+    }
+  }
+
+  setTimeout(async () => {
+    console.log("\n⏱️ Time's up! Closing session...");
+
+    if (audioResponse && audioChunks.length > 0) {
+      try {
+        await saveWavFile(audioChunks, "gemini-response.wav");
+      } catch (error) {
+        console.error("❌ Error saving final audio file:", error);
+      }
+    }
+
+    await session.disconnect();
+    isRunning = false;
+  }, 60000);
+
+  process.on("SIGINT", async () => {
+    console.log("\n👋 Interrupted by user. Closing session...");
+
+    if (audioResponse && audioChunks.length > 0) {
+      try {
+        await saveWavFile(audioChunks, "gemini-response.wav");
+      } catch (error) {
+        console.error("❌ Error saving final audio file:", error);
+      }
+    }
+
+    await session.disconnect();
+    isRunning = false;
+  });
+
+  const waitForClose = () => {
+    if (isRunning) {
+      setTimeout(waitForClose, 1000);
+    } else {
+      process.exit(0);
+    }
+  };
+  waitForClose();
+}
+
+main().catch((error) => {
+  console.error("❌ Fatal error:", error);
+  process.exit(1);
+});

examples/mistral/agent.ts

@@ -1,6 +1,8 @@
 import { mistral } from "@llamaindex/mistral";
 import { wiki } from "@llamaindex/tools";
-import { agent, tool } from "llamaindex";
+import { agent } from "@llamaindex/workflow";
+import { tool } from "llamaindex";
+
 import { z } from "zod";
 
 const workflow = agent({

examples/mongo.ts

@@ -1,4 +1,4 @@
-import { SimpleMongoReader } from "@llamaindex/readers/mongo";
+import { SimpleMongoReader } from "@llamaindex/mongodb";
 import { Document, VectorStoreIndex } from "llamaindex";
 import { MongoClient } from "mongodb";
 

examples/mongodb/2_load_and_index.ts

@@ -1,5 +1,7 @@
-import { MongoDBAtlasVectorSearch } from "@llamaindex/mongodb";
-import { SimpleMongoReader } from "@llamaindex/readers/mongo";
+import {
+  MongoDBAtlasVectorSearch,
+  SimpleMongoReader,
+} from "@llamaindex/mongodb";
 import * as dotenv from "dotenv";
 import { storageContextFromDefaults, VectorStoreIndex } from "llamaindex";
 import { MongoClient } from "mongodb";

examples/multimodal/context.ts

@@ -37,8 +37,10 @@ async function main() {
   const index = await VectorStoreIndex.init({
     storageContext,
   });
-  // topK for text is 0 and for image 1 => we only retrieve one image and no text based on the query
-  const retriever = index.asRetriever({ topK: { TEXT: 0, IMAGE: 1 } });
+  // topK for text is 0, for image 1, for audio 0  => we only retrieve one image and no text based on the query
+  const retriever = index.asRetriever({
+    topK: { TEXT: 0, IMAGE: 1, AUDIO: 0 },
+  });
   // NOTE: we set the contextRole to "user" (default is "system"). The reason is that GPT-4 does not support
   // images in a system message
   const chatEngine = new ContextChatEngine({ retriever, contextRole: "user" });