chore: bump

.changeset/clean-pots-burn.md

@@ -0,0 +1,9 @@
+---
+"@llamaindex/workflow": minor
+---
+
+refactor!: migrate to llamaflow
+
+- remove `outputs` in workflow. You shuld use TypeScript and define returns type to validate the workflow correctly.
+- remove `timeout` and `verbose` in workflow. Workflow now is a very lightly engine, so you should do this by youself. For example, `abortSignal.timeout`, `console.log`...
+- `workflow.run` now retunrs `ReadableStream | Promise<WorkflowEvent<Result>>`, you shouldn't use steram and promise in both time.

.github/workflows/test.yml

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

.nvmrc

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

apps/next/CHANGELOG.md

@@ -1,31 +1,5 @@
 # @llamaindex/doc
 
-## 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

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.16",
+  "version": "0.2.14",
   "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": "0.0.8",
+    "@llama-flow/docs": "0.0.5",
     "@llamaindex/chat-ui": "0.2.0",
     "@llamaindex/cloud": "workspace:*",
     "@llamaindex/core": "workspace:*",

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/workflow";
+  `import { agent } from "llamaindex";
 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/workflow";
+  `import { agent, multiAgent } from "llamaindex";
 import { openai } from "@llamaindex/openai";
 
 const analyseAgent = agent({
@@ -113,9 +113,8 @@ export default function HomePage() {
           description="Truly powerful retrieval-augmented generation applications use agentic techniques, and LlamaIndex.TS makes it easy to build them."
         >
           <CodeBlock
-            code={`import { SimpleDirectoryReader, VectorStoreIndex } from "llamaindex";
+            code={`import { agent, 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/components/demo/lazy.ts

@@ -11,3 +11,8 @@ 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

@@ -0,0 +1,152 @@
+"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/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 and the Workflow package to use LlamaIndex. For example, to use the OpenAI LLM with agents, you would install the following:
+In most cases, you'll also need an LLM package to use LlamaIndex. For example, to use the OpenAI LLM, you would install the following:
 
 ```package-install
-npm i @llamaindex/openai @llamaindex/workflow
+npm i @llamaindex/openai
 ```
 
 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

@@ -40,7 +40,19 @@ 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.
+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";
+```
 
 ## Enable AsyncIterable for `Web Stream` API
 
@@ -56,8 +68,7 @@ Some modules uses `Web Stream` API like `ReadableStream` and `WritableStream`, y
 ```
 
 ```typescript
-import { tool } from 'llamaindex'
-import { agent } from "@llamaindex/workflow";
+import { agent, tool } from 'llamaindex'
 import { openai } from "@llamaindex/openai";
 
 Settings.llm = openai({

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

@@ -12,8 +12,7 @@ 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 { tool } from "llamaindex";
-import { agent } from "@llamaindex/workflow";
+import { agent, tool } from "llamaindex";
 import { openai } from "@llamaindex/openai";
 
 // Define a joke-telling tool
@@ -41,17 +40,17 @@ 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 { agentToolCallEvent, agentStreamEvent } from "@llamaindex/workflow";
+import { AgentToolCall, AgentStream } from "llamaindex";
 
 // Get the workflow execution context
-const events = workflow.runStream("Tell me something funny");
+const context = workflow.run("Tell me something funny");
 
 // Stream and handle events
-for await (const event of events) {
-  if (agentToolCallEvent.include(event)) {
+for await (const event of context) {
+  if (event instanceof AgentToolCall) {
     console.log(`Tool being called: ${event.data.toolName}`);
   }
-  if (agentStreamEvent.include(event)) {
+  if (event instanceof AgentStream) {
     process.stdout.write(event.data.delta);
   }
 }
@@ -69,8 +68,7 @@ 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 { tool } from "llamaindex";
-import { multiAgent, agent } from "@llamaindex/workflow";
+import { multiAgent, agent, tool } from "llamaindex";
 import { openai } from "@llamaindex/openai";
 import { z } from "zod";
 

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

@@ -17,8 +17,7 @@ The `parameters` field in the tool configuration is defined using `zod`, a TypeS
 
 Example:
 ```ts
-import { tool } from "llamaindex";
-import { agent } from "@llamaindex/workflow";
+import { agent, tool } from "llamaindex";
 import { z } from "zod";
 
 // first arg is LLM input, second is bound arg
@@ -47,7 +46,7 @@ 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/workflow";
+import { agent } from "llamaindex";
 import { wiki } from "@llamaindex/tools";
 
 const researchAgent = agent({
@@ -65,7 +64,7 @@ If you have a MCP server running, you can fetch tools from the server and use th
 ```ts
 // 1. Import MCP tools adapter
 import { mcp } from "@llamaindex/tools";
-import { agent } from "@llamaindex/workflow";
+import { agent } from "llamaindex";
 
 // 2. Initialize a MCP client
 // by npx
@@ -115,8 +114,7 @@ Note: calling the `bind` method will return a new `FunctionTool` instance, witho
 
 Example to pass a `userToken` as additional argument:
 ```ts
-import { tool } from "llamaindex";
-import { agent } from "@llamaindex/workflow";
+import { agent, tool } from "llamaindex";
 
 // first arg is LLM input, second is bound arg
 const queryKnowledgeBase = async ({ question }, { userToken }) => {

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

@@ -6,13 +6,256 @@ A `Workflow` in LlamaIndex is a lightweight, event-driven abstraction used to ch
 
 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
+npm i @llama-flow/core @llamaindex/openai
 ```
 
-This package is a stable, production-ready version of our [llama-flow](../../../llamaflow) project. 
+## Getting Started
 
-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.
+Let's explore a simple workflow example where a joke is generated and then critiqued and iterated on:
 
+```typescript
+import { OpenAI } from "@llamaindex/openai";
+import { createWorkflow, workflowEvent } from "@llama-flow/core";
+import { withStore } from "@llama-flow/core/middleware/store";
+
+// Create LLM instance
+const llm = new OpenAI({ model: "gpt-4.1-mini", apiKey: "..."});
+
+// 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 jokeFlow = withStore(
+    () => ({
+        numIterations: 0,
+        maxIterations: 3,
+    }),
+    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 store = jokeFlow.getStore();
+  store.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 (store.numIterations < store.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);
+```
+
+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 Store Middleware
+
+```typescript
+const jokeFlow = withStore(
+    () => ({
+        numIterations: 0,
+        maxIterations: 3,
+    }),
+    createWorkflow()
+);
+```
+
+Our workflow is implemented using the `createWorkflow()` function, enhanced with the `withStore` middleware. The store 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 store will be accesible within workflows by using the `jokeFlow.getStore()` 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 store = jokeFlow.getStore();
+  store.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 (store.numIterations < store.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
+
+Workflows provide utility functions to make working with event streams easier:
+
+```typescript
+import { collect } from "@llama-flow/core/stream/consumer";
+import { until } from "@llama-flow/core/stream/until";
+
+// 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 collect(until(stream, resultEvent));
+
+// The last event will be the resultEvent
+const finalEvent = allEvents[allEvents.length - 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:
+- `collect`: 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 documentation in the tutorial section](../../../llamaflow).

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

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 @llamaindex/workflow
+npm i llamaindex @llamaindex/openai @llamaindex/readers @llamaindex/huggingface
 ```
 
 ## Choose your model

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

@@ -35,16 +35,11 @@ First we'll need to pull in our dependencies. These are:
 import "dotenv/config";
 import {
   agent,
-  agentStreamEvent,
-  openai,
-} from "@llamaindex/workflow";
-import {
+  AgentStream,
   tool,
+  openai,
   Settings,
 } from "llamaindex";
-import {
-  openai,
-} from "@llamaindex/openai";
 import { z } from "zod";
 ```
 
@@ -113,10 +108,11 @@ const myAgent = agent({ tools });
 
 ### Ask the agent a question
 
-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.
+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.
 
 ```javascript
-const result = await myAgent.run("Sum 101 and 303");
+const context = myAgent.run("Sum 101 and 303");
+const result = await context;
 console.log(result.data);
 ```
 You will see the following output:
@@ -127,13 +123,12 @@ You will see the following output:
 { result: 'The sum of 101 and 303 is 404.' }
 ```
 
-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:
+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:
 
 ```javascript
-const events = myAgent.runStream("Add 101 and 303");
-for await (const event of events) {
-  if (agentStreamEvent.include(event)) {
+const context = myAgent.run("Add 101 and 303");
+for await (const event of context) {
+  if (event instanceof AgentStream) {
     process.stdout.write(event.data.delta);
   }
 }
@@ -145,18 +140,18 @@ for await (const event of events) {
 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 events = myAgent.runStream("Sum 202 and 404");
-for await (const event of events) {
-  if (agentStreamEvent.include(event)) {
+const context = myAgent.run("Sum 202 and 404");
+for await (const event of context) {
+  if (event instanceof AgentStream) {
     // Stream the response
-    process.stdout.write(event.data.delta);
+    for (const chunk of event.data.delta) {
+      process.stdout.write(chunk);
+    }
   } 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/workflow`.
+You can also create local agent by importing `agent` from `llamaindex`.
 
 ```javascript
-import { agent } from "@llamaindex/workflow";
+import { agent } from "llamaindex";
 
 const workflow = agent({
   tools: [getWeatherTool],
 });
 
-const resutl = workflow.run(
+const workflowContext = workflow.run(
   "What's the weather like in San Francisco?",
 );
 ```

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

@@ -25,8 +25,7 @@ We'll be bringing in `SimpleDirectoryReader`, `HuggingFaceEmbedding`, `VectorSto
 
 ```javascript
 import { QueryEngineTool, Settings, VectorStoreIndex } from "llamaindex";
-import { agent } from "@llamaindex/workflow";
-import { openai } from "@llamaindex/openai";
+import { OpenAI, OpenAIAgent } from "@llamaindex/openai";
 import { HuggingFaceEmbedding } from "@llamaindex/huggingface";
 import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
 ```

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

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

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

@@ -4,7 +4,7 @@
     "basic_agent",
     "rag",
     "agents",
-    "workflows",
+    "../../llamaflow",
     "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

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

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

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

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

@@ -1,176 +0,0 @@
----
-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", "api", "llamaflow"]
+  "pages": ["llamaindex", "api"]
 }

apps/next/src/deps/type.ts

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

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

@@ -1,21 +1,5 @@
 # @llamaindex/cloudflare-worker-agent-test
 
-## 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": "0.0.158",
+  "version": "0.0.156",
   "type": "module",
   "private": true,
   "scripts": {

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

@@ -1,18 +1,5 @@
 # @llamaindex/llama-parse-browser-test
 
-## 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": "0.0.60",
+  "version": "0.0.58",
   "type": "module",
   "scripts": {
     "dev": "vite",

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,21 +1,5 @@
 # @llamaindex/next-agent-test
 
-## 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": "0.1.158",
+  "version": "0.1.156",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,21 +1,5 @@
 # test-edge-runtime
 
-## 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": "0.1.157",
+  "version": "0.1.155",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,23 +1,5 @@
 # @llamaindex/next-node-runtime
 
-## 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

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.25",
+  "version": "0.1.23",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,21 +1,5 @@
 # vite-import-llamaindex
 
-## 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": "0.0.24",
+  "version": "0.0.22",
   "type": "module",
   "scripts": {
     "build": "vite build",

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

@@ -1,21 +1,5 @@
 # @llamaindex/waku-query-engine-test
 
-## 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": "0.0.158",
+  "version": "0.0.156",
   "type": "module",
   "private": true,
   "scripts": {

examples/CHANGELOG.md

@@ -1,55 +1,5 @@
 # examples
 
-## 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

examples/agent/large_toolcall.ts

@@ -1,6 +1,5 @@
 import { OpenAI } from "@llamaindex/openai";
-import { agent } from "@llamaindex/workflow";
-import { tool } from "llamaindex";
+import { FunctionTool, agent } from "llamaindex";
 import { z } from "zod";
 
 const csvData =
@@ -12,22 +11,24 @@ 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 = 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 }) => {
+  const interpreterTool = FunctionTool.from(
+    ({ 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/agent/mcp_tools.ts

@@ -1,6 +1,6 @@
 import { openai } from "@llamaindex/openai";
 import { mcp } from "@llamaindex/tools";
-import { agent } from "@llamaindex/workflow";
+import { agent } from "llamaindex";
 
 async function main() {
   // Create an MCP server for filesystem tools

examples/agent/openai.ts

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

examples/agent/query_tool.ts

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

examples/agent/wiki.ts

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

examples/agents/workflow/joke.ts

@@ -1,94 +0,0 @@
-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/agentworkflow/blog-writer.ts

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

examples/agentworkflow/multiple-agents.ts

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

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

examples/agentworkflow/with-anthropic.ts

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

examples/agentworkflow/with-ollama.ts

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

examples/anthropic/agent.ts

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

examples/anthropic/chat-with-file.ts

@@ -1,39 +0,0 @@
-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: fs.readFileSync("./data/manga.pdf"),
-            mimeType: "application/pdf",
-          },
-        ],
-      },
-    ],
-  });
-
-  console.log(result.message);
-}
-
-void main().catch(console.error);

examples/gemini/agent.ts

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

examples/gemini/chat.ts

@@ -1,12 +1,11 @@
 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_1_5,
+    model: GEMINI_MODEL.GEMINI_PRO,
   });
   const result = await gemini.chat({
     messages: [
@@ -19,26 +18,4 @@ import fs from "fs";
     ],
   });
   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: fs.readFileSync("./data/manga.pdf"),
-            mimeType: "application/pdf",
-          },
-        ],
-      },
-    ],
-  });
-
-  console.log(resultWithFile);
 })();

examples/llamaindex-server/README.md

@@ -0,0 +1,17 @@
+# Run LlamaIndex Server with simple steps
+
+1. Setup environment variables
+
+```bash
+export OPENAI_API_KEY=<your-openai-api-key>
+```
+
+2. Run the server
+
+```bash
+npx tsx llamaindex-server/simple-workflow/index.ts
+```
+
+3. Open the app at `http://localhost:4000` and start chatting with the agent
+
+![Screenshot](./screenshot.png)

examples/llamaindex-server/simple-workflow/index.ts

@@ -0,0 +1,19 @@
+import { OpenAI } from "@llamaindex/openai";
+import { LlamaIndexServer } from "@llamaindex/server";
+import { weather } from "@llamaindex/tools";
+import "dotenv/config";
+import { agent } from "llamaindex";
+
+const weatherAgent = agent({
+  tools: [weather()],
+  llm: new OpenAI({ model: "gpt-4o-mini" }),
+});
+
+new LlamaIndexServer({
+  workflow: () => weatherAgent,
+  uiConfig: {
+    appTitle: "Weather Agent",
+    starterQuestions: ["Ho Chi Minh city weather", "New York weather"],
+  },
+  port: 4000,
+}).start();

examples/mistral/agent.ts

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

examples/node/workflow/basic.ts

@@ -0,0 +1,32 @@
+import { StartEvent, StopEvent, Workflow } from "llamaindex";
+
+type ContextData = {
+  counter: number;
+};
+
+const contextData: ContextData = { counter: 0 };
+
+const workflow = new Workflow<ContextData, string, string>();
+
+workflow.addStep(
+  {
+    inputs: [StartEvent<string>],
+  },
+  async (context, startEvent) => {
+    const input = startEvent.data;
+    context.data.counter++;
+    return new StopEvent(`Hello, ${input}!`);
+  },
+);
+
+{
+  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!
+}
+
+console.log(contextData.counter); // 2

examples/openai/openai.ts

@@ -1,8 +1,7 @@
 import { OpenAI, OpenAIEmbedding } from "@llamaindex/openai";
-import fs from "fs";
 
 (async () => {
-  const llm = new OpenAI({ model: "gpt-4o" });
+  const llm = new OpenAI({ model: "gpt-4.5-preview", temperature: 0.1 });
 
   // complete api
   const response1 = await llm.complete({ prompt: "How are you?" });
@@ -14,51 +13,7 @@ import fs from "fs";
   });
   console.log(response2.message.content);
 
-  // chat with file
-  const response3 = await llm.chat({
-    messages: [
-      {
-        role: "user",
-        content: [
-          {
-            type: "text",
-            text: "What's in this document? Describe it in detail.",
-          },
-          {
-            type: "file",
-            data: fs.readFileSync("./data/manga.pdf"),
-            mimeType: "application/pdf",
-          },
-        ],
-      },
-    ],
-  });
-  console.log(response3.message.content);
-
-  // chat with image
-  const response4 = await llm.chat({
-    messages: [
-      {
-        role: "user",
-        content: [
-          {
-            type: "text",
-            text: "What's in this image? Describe it in detail.",
-          },
-          {
-            type: "image_url",
-            image_url: {
-              url: "https://storage.googleapis.com/cloud-samples-data/vision/face/faces.jpeg",
-            },
-          },
-        ],
-      },
-    ],
-  });
-
-  console.log("Single Image Analysis:", response4.message.content);
-
-  // // embeddings
+  // embeddings
   const embedModel = new OpenAIEmbedding();
   const texts = ["hello", "world"];
   const embeddings = await embedModel.getTextEmbeddingsBatch(texts);

examples/openai/responses/agent.ts

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

examples/openai/responses/chat-with-file.ts

@@ -1,35 +0,0 @@
-import { openaiResponses } from "@llamaindex/openai";
-import fs from "fs";
-
-async function main() {
-  if (!process.env.OPENAI_API_KEY) {
-    throw new Error("Please set the OPENAI_API_KEY environment variable.");
-  }
-
-  const llm = openaiResponses({
-    apiKey: process.env.OPENAI_API_KEY,
-  });
-
-  const result = await llm.chat({
-    messages: [
-      {
-        role: "user",
-        content: [
-          {
-            type: "text",
-            text: "What's in this document? Describe it in detail.",
-          },
-          {
-            type: "file",
-            data: fs.readFileSync("./data/manga.pdf"),
-            mimeType: "application/pdf",
-          },
-        ],
-      },
-    ],
-  });
-
-  console.log(result);
-}
-
-void main().catch(console.error);

examples/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/examples",
-  "version": "0.3.13",
+  "version": "0.3.12",
   "private": true,
   "scripts": {
     "lint": "eslint .",
@@ -11,59 +11,60 @@
     "@azure/cosmos": "^4.1.1",
     "@azure/identity": "^4.4.1",
     "@azure/search-documents": "^12.1.0",
-    "@llamaindex/anthropic": "^0.3.4",
-    "@llamaindex/astra": "^0.0.17",
-    "@llamaindex/azure": "^0.1.13",
-    "@llamaindex/chroma": "^0.0.17",
-    "@llamaindex/clip": "^0.0.53",
-    "@llamaindex/cloud": "^4.0.4",
-    "@llamaindex/cohere": "^0.0.17",
-    "@llamaindex/core": "^0.6.3",
-    "@llamaindex/deepinfra": "^0.0.53",
+    "@llamaindex/anthropic": "^0.3.3",
+    "@llamaindex/astra": "^0.0.16",
+    "@llamaindex/azure": "^0.1.12",
+    "@llamaindex/chroma": "^0.0.16",
+    "@llamaindex/clip": "^0.0.52",
+    "@llamaindex/cloud": "^4.0.3",
+    "@llamaindex/cohere": "^0.0.16",
+    "@llamaindex/core": "^0.6.2",
+    "@llamaindex/deepinfra": "^0.0.52",
     "@llamaindex/env": "^0.1.29",
-    "@llamaindex/firestore": "^1.0.10",
-    "@llamaindex/google": "^0.2.5",
-    "@llamaindex/groq": "^0.0.68",
-    "@llamaindex/huggingface": "^0.1.7",
-    "@llamaindex/milvus": "^0.1.12",
-    "@llamaindex/mistral": "^0.1.3",
-    "@llamaindex/mixedbread": "^0.0.17",
-    "@llamaindex/mongodb": "^0.0.18",
-    "@llamaindex/elastic-search": "^0.1.3",
-    "@llamaindex/node-parser": "^2.0.3",
-    "@llamaindex/ollama": "^0.1.3",
-    "@llamaindex/openai": "^0.3.5",
-    "@llamaindex/pinecone": "^0.1.3",
-    "@llamaindex/portkey-ai": "^0.0.45",
-    "@llamaindex/postgres": "^0.0.46",
-    "@llamaindex/qdrant": "^0.1.12",
-    "@llamaindex/readers": "^3.1.1",
-    "@llamaindex/replicate": "^0.0.45",
-    "@llamaindex/upstash": "^0.0.17",
-    "@llamaindex/vercel": "^0.1.3",
-    "@llamaindex/vllm": "^0.0.39",
-    "@llamaindex/voyage-ai": "^1.0.9",
-    "@llamaindex/weaviate": "^0.0.17",
-    "@llamaindex/workflow": "^1.0.4",
-    "@llamaindex/deepseek": "^0.0.13",
-    "@llamaindex/fireworks": "^0.0.13",
-    "@llamaindex/together": "^0.0.13",
-    "@llamaindex/jinaai": "^0.0.13",
-    "@llamaindex/perplexity": "^0.0.10",
-    "@llamaindex/supabase": "^0.1.2",
-    "@llamaindex/tools": "^0.0.8",
+    "@llamaindex/firestore": "^1.0.9",
+    "@llamaindex/google": "^0.2.4",
+    "@llamaindex/groq": "^0.0.67",
+    "@llamaindex/huggingface": "^0.1.6",
+    "@llamaindex/milvus": "^0.1.11",
+    "@llamaindex/mistral": "^0.1.2",
+    "@llamaindex/mixedbread": "^0.0.16",
+    "@llamaindex/mongodb": "^0.0.17",
+    "@llamaindex/elastic-search": "^0.1.2",
+    "@llamaindex/node-parser": "^2.0.2",
+    "@llamaindex/ollama": "^0.1.2",
+    "@llamaindex/openai": "^0.3.4",
+    "@llamaindex/pinecone": "^0.1.2",
+    "@llamaindex/portkey-ai": "^0.0.44",
+    "@llamaindex/postgres": "^0.0.45",
+    "@llamaindex/qdrant": "^0.1.11",
+    "@llamaindex/readers": "^3.1.0",
+    "@llamaindex/replicate": "^0.0.44",
+    "@llamaindex/upstash": "^0.0.16",
+    "@llamaindex/vercel": "^0.1.2",
+    "@llamaindex/vllm": "^0.0.38",
+    "@llamaindex/voyage-ai": "^1.0.8",
+    "@llamaindex/weaviate": "^0.0.16",
+    "@llamaindex/workflow": "^1.0.3",
+    "@llamaindex/deepseek": "^0.0.12",
+    "@llamaindex/fireworks": "^0.0.12",
+    "@llamaindex/together": "^0.0.12",
+    "@llamaindex/jinaai": "^0.0.12",
+    "@llamaindex/perplexity": "^0.0.9",
+    "@llamaindex/server": "^0.1.6",
+    "@llamaindex/supabase": "^0.1.1",
+    "@llamaindex/tools": "^0.0.7",
     "@notionhq/client": "^2.2.15",
     "@pinecone-database/pinecone": "^4.0.0",
-    "@llamaindex/assemblyai": "^0.1.2",
-    "@llamaindex/discord": "^0.1.2",
-    "@llamaindex/notion": "^0.1.2",
+    "@llamaindex/assemblyai": "^0.1.1",
+    "@llamaindex/discord": "^0.1.1",
+    "@llamaindex/notion": "^0.1.1",
     "@vercel/postgres": "^0.10.0",
     "ai": "^4.0.0",
     "ajv": "^8.17.1",
     "commander": "^12.1.0",
     "dotenv": "^16.4.5",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.10.3",
+    "llamaindex": "^0.10.2",
     "mongodb": "6.7.0",
     "postgres": "^3.4.4",
     "wikipedia": "^2.1.2",

package.json

@@ -15,10 +15,9 @@
     "circular-check": "madge --circular ./packages/**/**/dist/index.js",
     "release": "pnpm run build && changeset publish",
     "release-snapshot": "pnpm run build && changeset publish --tag snapshot",
-    "new-version": "changeset version && pnpm postversion && pnpm format:write && pnpm run build",
+    "new-version": "changeset version && pnpm format:write && pnpm run build",
     "new-snapshot": "pnpm run build && changeset version --snapshot",
-    "lint-staged": "lint-staged",
-    "postversion": "node scripts/repin-workflow.mjs"
+    "lint-staged": "lint-staged"
   },
   "devDependencies": {
     "@changesets/cli": "^2.27.5",

packages/autotool/CHANGELOG.md

@@ -1,21 +1,5 @@
 # @llamaindex/autotool
 
-## 7.0.4
-
-### Patch Changes
-
-- Updated dependencies [2225ffd]
-- Updated dependencies [6ddf1c1]
-- Updated dependencies [41953a3]
-  - llamaindex@0.10.4
-
-## 7.0.3
-
-### Patch Changes
-
-- Updated dependencies [3ee8c83]
-  - llamaindex@0.10.3
-
 ## 7.0.2
 
 ### Patch Changes

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

@@ -1,23 +1,5 @@
 # @llamaindex/autotool-01-node-example
 
-## 0.0.105
-
-### Patch Changes
-
-- Updated dependencies [2225ffd]
-- Updated dependencies [6ddf1c1]
-- Updated dependencies [41953a3]
-  - llamaindex@0.10.4
-  - @llamaindex/autotool@7.0.4
-
-## 0.0.104
-
-### Patch Changes
-
-- Updated dependencies [3ee8c83]
-  - llamaindex@0.10.3
-  - @llamaindex/autotool@7.0.3
-
 ## 0.0.103
 
 ### Patch Changes

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

@@ -13,5 +13,5 @@
   "scripts": {
     "start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
   },
-  "version": "0.0.105"
+  "version": "0.0.103"
 }

packages/autotool/package.json

@@ -6,7 +6,7 @@
     "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
     "directory": "packages/autotool"
   },
-  "version": "7.0.4",
+  "version": "7.0.2",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",

packages/cloud/CHANGELOG.md

@@ -1,18 +1,5 @@
 # @llamaindex/cloud
 
-## 4.0.5
-
-### Patch Changes
-
-- 2225ffd: feat: bump llama cloud sdk
-
-## 4.0.4
-
-### Patch Changes
-
-- Updated dependencies [3ee8c83]
-  - @llamaindex/core@0.6.3
-
 ## 4.0.3
 
 ### Patch Changes

packages/cloud/README.md

@@ -2,6 +2,15 @@
 
 > 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.
 
+## Usage
+
+```ts
+import { OpenAPI } from "@llamaindex/cloud/api";
+OpenAPI.TOKEN = "YOUR_API_KEY";
+OpenAPI.BASE = "https://api.cloud.llamaindex.ai/";
+// ...
+```
+
 For more information, see the [API documentation](https://docs.cloud.llamaindex.ai/).
 
 ## License

packages/cloud/openapi-ts.config.ts

@@ -1,19 +1,22 @@
-import { defaultPlugins, defineConfig } from "@hey-api/openapi-ts";
+import { defineConfig } from "@hey-api/openapi-ts";
 
 export default defineConfig({
   // you can download this file to get the latest version of the OpenAPI document
   // @link https://api.cloud.llamaindex.ai/api/openapi.json
   input: "./openapi.json",
+  client: "@hey-api/client-fetch",
   output: {
     path: "./src/client",
     format: "prettier",
     lint: "eslint",
   },
   plugins: [
-    ...defaultPlugins,
-    "@hey-api/client-fetch",
+    "@hey-api/schemas",
+    "@hey-api/sdk",
     {
-      name: "@hey-api/sdk",
+      enums: "javascript",
+      identifierCase: "preserve",
+      name: "@hey-api/typescript",
     },
   ],
 });

packages/cloud/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloud",
-  "version": "4.0.5",
+  "version": "4.0.3",
   "type": "module",
   "license": "MIT",
   "scripts": {
@@ -55,8 +55,8 @@
     "directory": "packages/cloud"
   },
   "devDependencies": {
-    "@hey-api/client-fetch": "^0.10.0",
-    "@hey-api/openapi-ts": "^0.66.7",
+    "@hey-api/client-fetch": "^0.6.0",
+    "@hey-api/openapi-ts": "^0.61.0",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*"
   },

packages/cloud/src/api.ts

@@ -1,11 +1 @@
-import { client } from "./client/client.gen";
-
-client.setConfig({
-  baseUrl: "https://api.cloud.llamaindex.ai/",
-  headers: {
-    "X-SDK-Name": "llamaindex-ts",
-  },
-});
-
 export * from "./client";
-export { client };

packages/cloud/src/reader.ts

@@ -4,8 +4,7 @@ import { Document, FileReader } from "@llamaindex/core/schema";
 import { fs, getEnv, path } from "@llamaindex/env";
 import pRetry from "p-retry";
 import {
-  type BodyUploadFileApiParsingUploadPost,
-  type FailPageMode,
+  type Body_upload_file_api_v1_parsing_upload_post,
   type ParserLanguages,
   type ParsingMode,
   getJobApiV1ParsingJobJobIdGet,
@@ -163,15 +162,6 @@ export class LlamaParseReader extends FileReader {
   content_guideline_instruction?: string | undefined;
   adaptive_long_table?: boolean | undefined;
   model?: string | undefined;
-  auto_mode_configuration_json?: string | undefined;
-  compact_markdown_table?: boolean | undefined;
-  markdown_table_multiline_header_separator?: string | undefined;
-  page_error_tolerance?: number | undefined;
-  replace_failed_page_mode?: FailPageMode | undefined;
-  replace_failed_page_with_error_message_prefix?: string | undefined;
-  replace_failed_page_with_error_message_suffix?: string | undefined;
-  save_images?: boolean | undefined;
-  preset?: string | undefined;
 
   constructor(
     params: Partial<Omit<LlamaParseReader, "language" | "apiKey">> & {
@@ -341,23 +331,11 @@ export class LlamaParseReader extends FileReader {
       content_guideline_instruction: this.content_guideline_instruction,
       adaptive_long_table: this.adaptive_long_table,
       model: this.model,
-      auto_mode_configuration_json: this.auto_mode_configuration_json,
-      compact_markdown_table: this.compact_markdown_table,
-      markdown_table_multiline_header_separator:
-        this.markdown_table_multiline_header_separator,
-      page_error_tolerance: this.page_error_tolerance,
-      replace_failed_page_mode: this.replace_failed_page_mode,
-      replace_failed_page_with_error_message_prefix:
-        this.replace_failed_page_with_error_message_prefix,
-      replace_failed_page_with_error_message_suffix:
-        this.replace_failed_page_with_error_message_suffix,
-      save_images: this.save_images,
-      preset: this.preset,
     } satisfies {
-      [Key in keyof BodyUploadFileApiParsingUploadPost]-?:
-        | BodyUploadFileApiParsingUploadPost[Key]
+      [Key in keyof Body_upload_file_api_v1_parsing_upload_post]-?:
+        | Body_upload_file_api_v1_parsing_upload_post[Key]
         | undefined;
-    } as unknown as BodyUploadFileApiParsingUploadPost;
+    } as unknown as Body_upload_file_api_v1_parsing_upload_post;
 
     const response = await uploadFileApiV1ParsingUploadPost({
       client: this.#client,
@@ -404,6 +382,10 @@ export class LlamaParseReader extends FileReader {
               client: this.#client,
               throwOnError: true,
               path: { job_id: jobId },
+              query: {
+                project_id: this.project_id ?? null,
+                organization_id: this.organization_id ?? null,
+              },
               signal: AbortSignal.timeout(this.maxTimeout * 1000),
             }),
           {
@@ -449,6 +431,7 @@ export class LlamaParseReader extends FileReader {
                 throwOnError: true,
                 path: { job_id: jobId },
                 query: {
+                  project_id: this.project_id ?? null,
                   organization_id: this.organization_id ?? null,
                 },
                 signal: AbortSignal.timeout(this.maxTimeout * 1000),
@@ -462,6 +445,7 @@ export class LlamaParseReader extends FileReader {
                 throwOnError: true,
                 path: { job_id: jobId },
                 query: {
+                  project_id: this.project_id ?? null,
                   organization_id: this.organization_id ?? null,
                 },
                 signal: AbortSignal.timeout(this.maxTimeout * 1000),
@@ -475,6 +459,7 @@ export class LlamaParseReader extends FileReader {
                 throwOnError: true,
                 path: { job_id: jobId },
                 query: {
+                  project_id: this.project_id ?? null,
                   organization_id: this.organization_id ?? null,
                 },
                 signal: AbortSignal.timeout(this.maxTimeout * 1000),
@@ -704,6 +689,10 @@ export class LlamaParseReader extends FileReader {
           job_id: jobId,
           name: imageName,
         },
+        query: {
+          project_id: this.project_id ?? null,
+          organization_id: this.organization_id ?? null,
+        },
       });
     if (response.error) {
       throw new Error(`Failed to download image: ${response.error.detail}`);

packages/community/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/community
 
-## 0.0.97
-
-### Patch Changes
-
-- Updated dependencies [3ee8c83]
-  - @llamaindex/core@0.6.3
-
 ## 0.0.96
 
 ### Patch Changes

packages/community/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/community",
   "description": "Community package for LlamaIndexTS",
-  "version": "0.0.97",
+  "version": "0.0.96",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/core/CHANGELOG.md

@@ -1,11 +1,5 @@
 # @llamaindex/core
 
-## 0.6.3
-
-### Patch Changes
-
-- 3ee8c83: feat: support file content type in message content
-
 ## 0.6.2
 
 ### Patch Changes

packages/core/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/core",
   "type": "module",
-  "version": "0.6.3",
+  "version": "0.6.2",
   "description": "LlamaIndex Core Module",
   "exports": {
     "./agent": {

packages/core/src/llms/index.ts

@@ -17,7 +17,6 @@ export type {
   LLMMetadata,
   MessageContent,
   MessageContentDetail,
-  MessageContentFileDetail,
   MessageContentImageDetail,
   MessageContentTextDetail,
   MessageType,

packages/core/src/llms/type.ts

@@ -163,16 +163,9 @@ export type MessageContentImageDetail = {
   detail?: "high" | "low" | "auto";
 };
 
-export type MessageContentFileDetail = {
-  type: "file";
-  data: Buffer;
-  mimeType: string;
-};
-
 export type MessageContentDetail =
   | MessageContentTextDetail
-  | MessageContentImageDetail
-  | MessageContentFileDetail;
+  | MessageContentImageDetail;
 
 /**
  * Extended type for the content of a message that allows for multi-modal messages.

packages/experimental/CHANGELOG.md

@@ -1,21 +1,5 @@
 # @llamaindex/experimental
 
-## 0.0.174
-
-### Patch Changes
-
-- Updated dependencies [2225ffd]
-- Updated dependencies [6ddf1c1]
-- Updated dependencies [41953a3]
-  - llamaindex@0.10.4
-
-## 0.0.173
-
-### Patch Changes
-
-- Updated dependencies [3ee8c83]
-  - llamaindex@0.10.3
-
 ## 0.0.172
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.174",
+  "version": "0.0.172",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/llamaindex/CHANGELOG.md

@@ -1,30 +1,5 @@
 # llamaindex
 
-## 0.10.4
-
-### Patch Changes
-
-- 2225ffd: feat: bump llama cloud sdk
-- 6ddf1c1: Show warning to use @llamaindex/workflow when using depracted workflows
-- 41953a3: fix: node10 module resolution fail in sub llamaindex packages
-- Updated dependencies [7e8e454]
-- Updated dependencies [2225ffd]
-- Updated dependencies [bc53342]
-  - @llamaindex/workflow@1.1.0
-  - @llamaindex/cloud@4.0.5
-
-## 0.10.3
-
-### Patch Changes
-
-- 3ee8c83: feat: support file content type in message content
-- Updated dependencies [3ee8c83]
-  - @llamaindex/core@0.6.3
-  - @llamaindex/openai@0.3.5
-  - @llamaindex/cloud@4.0.4
-  - @llamaindex/node-parser@2.0.3
-  - @llamaindex/workflow@1.0.4
-
 ## 0.10.2
 
 ### Patch Changes

packages/llamaindex/agent/package.json

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

packages/llamaindex/cloud/package.json

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