Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://npmjs.com/package/@llamaindex/server below:

@llamaindex/server - npm

LlamaIndexServer is a Next.js-based application that allows you to quickly launch your LlamaIndex Workflows and Agent Workflows as an API server with an optional chat UI. It provides a complete environment for running LlamaIndex workflows with both API endpoints and a user interface for interaction.

• Add a sophisticated chatbot UI to your LlamaIndex workflow
• Edit code and document artifacts in an OpenAI Canvas-style UI
• Extendable UI components for events and headers
• Built on Next.js for high performance and easy API development
• Human-in-the-loop (HITL) support, check out the Human-in-the-loop documentation for more details.

Create an index.ts file and add the following code:

import { LlamaIndexServer } from '@llamaindex/server'
import { openai } from '@llamaindex/openai'
import { agent } from '@llamaindex/workflow'
import { wiki } from '@llamaindex/tools' // or any other tool

const createWorkflow = () => agent({ tools: [wiki()], llm: openai('gpt-4o') })

new LlamaIndexServer({
  workflow: createWorkflow,
  uiConfig: {
    starterQuestions: ['Who is the first president of the United States?'],
  },
}).start()

The createWorkflow function is a factory function that creates an Agent Workflow with a tool that retrieves information from Wikipedia in this case. For more details, read about the Workflow factory contract.

In the same directory as index.ts, run the following command to start the server:

The server will start at http://localhost:3000

You can also make a request to the server:

curl -X POST "http://localhost:3000/api/chat" -H "Content-Type: application/json" -d '{"message": "Who is the first president of the United States?"}'

The LlamaIndexServer accepts the following configuration options:

• workflow: A callable function that creates a workflow instance for each request. See Workflow factory contract for more details.
• uiConfig: An object to configure the chat UI containing the following properties:
  • starterQuestions: List of starter questions for the chat UI (default: [])
  • enableFileUpload: Whether to enable file upload in the chat UI (default: false). See Upload file example for more details.
  • componentsDir: The directory for custom UI components rendering events emitted by the workflow. The default is undefined, which does not render custom UI components.
  • layoutDir: The directory for custom layout sections. The default value is layout. See Custom Layout for more details.
  • dev_mode: When enabled, you can update workflow code in the UI and see the changes immediately. It's currently in beta and only supports updating workflow code at app/src/workflow.ts. Please start server in dev mode (npm run dev) to use see this reload feature enabled.
• suggestNextQuestions: Whether to suggest next questions after the assistant's response (default: true). You can change the prompt for the next questions by setting the NEXT_QUESTION_PROMPT environment variable.
• llamaCloud: An object to configure the LlamaCloud integration containing the following properties:
  • outputDir: The directory for LlamaCloud output
  • indexSelector: Whether to show the LlamaCloud index selector in the chat UI

LlamaIndexServer accepts all the configuration options from Nextjs Custom Server such as port, hostname, dev, etc. See all Nextjs Custom Server options here.

The workflow provided will be called for each chat request to initialize a new workflow instance. For advanced use cases, you can define workflowFactory with a chatBody which include list of UI messages in the request body.

import { type Message } from "ai";
import { agent } from "@llamaindex/workflow";

const workflowFactory = (chatBody: { messages: Message[] }) => {
  ...
};

The contract of the generated workflow must be the same as for the Agent Workflow. This means that the workflow must handle a startAgentEvent event, which is the entry point of the workflow and contains the following information in it's data property:

{
  userInput: MessageContent;
  chatHistory?: ChatMessage[] | undefined;
};

The userInput is the latest user message and the chatHistory is the list of messages exchanged between the user and the workflow so far.

Furthermore, the workflow must stop with a stopAgentEvent event to mark the end of the workflow. In between, the workflow can emit UI events to render custom UI components and Artifact events to send structured data like generated documents or code snippets to the UI.

import {
  createStatefulMiddleware,
  createWorkflow,
  startAgentEvent,
} from '@llamaindex/workflow'
import { ChatMemoryBuffer, type ChatMessage, Settings } from 'llamaindex'
import { openai } from '@llamaindex/openai'
import { wiki } from '@llamaindex/tools'

Settings.llm = openai('gpt-4o')

export const workflowFactory = async () => {
  const workflow = createWorkflow()

  workflow.handle([startAgentEvent], async ({ data }) => {
    const { state, sendEvent } = getContext()
    const messages = data.chatHistory

    const toolCallResponse = await chatWithTools(
      Settings.llm,
      [wiki()],
      messages
    )

    // using result from tool call and use `sendEvent` to emit the next event...
  })

  // define more workflow handling logic here...

  // Finally stop with a `stopAgentEvent` event to mark the end of the workflow.
  // return stopAgentEvent.with({
  //   result: "This is the end!",
  // });

  return workflow
}

To generate sophisticated examples of workflows, you best use the create-llama project.

The ServerMessage class is a central utility for handling messages in the LlamaIndex Server. It provides convenient methods to extract and process different types of content from Vercel AI SDK messages, including artifacts, file attachments, and human responses.

• Extract artifacts: Get code artifacts, documents, and other generated content
• Access attachments: Retrieve file attachments from messages
• Convert to LlamaIndex format: Transform messages for use with LlamaIndex workflows
• Type-safe filtering: Built-in type guards for different message part types

Import and create a ServerMessage instance:

import { toServerMessage } from '@llamaindex/server'
import { UIMessage } from '@ai-sdk/react'

// Convert Vercel AI SDK messages to ServerMessage instances
const messages: UIMessage[] = ...
const serverMessages = messages.map(toServerMessage)

// Get all artifacts from all messages
const artifacts = serverMessages.flatMap(message => message.artifacts)

// Get the last artifact of any type
const lastArtifact = artifacts[artifacts.length - 1]

// Get the last artifact of a specific type
const lastCodeArtifact = serverMessage.getLastArtifact('code')
const lastDocumentArtifact = serverMessage.getLastArtifact('document')

const attachments = serverMessage.attachments

const llamaindexMessage = serverMessage.llamaindexMessage

The LlamaIndex server provides support for rendering workflow events using custom UI components, allowing you to extend and customize the chat interface. These components can be auto-generated using an LLM by providing a JSON schema of the workflow event.

To display custom UI components, your workflow needs to emit UI events that have an event type for identification and a data object:

class UIEvent extends WorkflowEvent<{
  type: 'data-ui_event'
  data: UIEventData
}> {}

The data object can be any JSON object. To enable AI generation of the UI component, you need to provide a schema for that data (here we're using Zod):

const MyEventDataSchema = z
  .object({
    stage: z
      .enum(['retrieve', 'analyze', 'answer'])
      .describe('The current stage the workflow process is in.'),
    progress: z
      .number()
      .min(0)
      .max(1)
      .describe('The progress in percent of the current stage'),
  })
  .describe('WorkflowStageProgress')

type UIEventData = z.infer<typeof MyEventDataSchema>

The generateEventComponent function uses an LLM to generate a custom UI component based on the JSON schema of a workflow event. The schema should contain accurate descriptions of each field so that the LLM can generate matching components for your use case. We've done this for you in the example above using the describe function from Zod:

import { OpenAI } from 'llamaindex'
import { generateEventComponent } from '@llamaindex/server'
import { MyEventDataSchema } from './your-workflow'

// Also works well with Claude 3.5 Sonnet and Google Gemini 2.5 Pro
const llm = new OpenAI({ model: 'gpt-4.1' })
const code = generateEventComponent(MyEventDataSchema, llm)

After generating the code, we need to save it to a file. The file name must match the event type from your workflow (e.g., ui_event.jsx for handling events with ui_event type):

fs.writeFileSync('components/ui_event.jsx', code)

Feel free to modify the generated code to match your needs. If you're not satisfied with the generated code, we suggest improving the provided JSON schema first or trying another LLM.

Note that generateEventComponent is generating JSX code, but you can also provide a TSX file.

LlamaIndex Server supports custom layout for header and footer. To use custom layout, you need to initialize the LlamaIndex server with the layoutDir that contains your custom layout files.

new LlamaIndexServer({
  workflow: createWorkflow,
  uiConfig: {
    layoutDir: 'layout',
  },
}).start()

layout/
  header.tsx
  footer.tsx

We currently support custom header and footer for the chat interface. The syntax for these files is the same as events components in components directory. Note that by default, we are still rendering the default LlamaIndex Header. It's also the fallback when having errors rendering the custom header. Example layout files will be generated in the layout directory of your project when creating a new project with create-llama.

To use the generated UI components, you need to initialize the LlamaIndex server with the componentsDir that contains your custom UI components:

new LlamaIndexServer({
  workflow: createWorkflow,
  uiConfig: {
    componentsDir: 'components',
  },
}).start()

LlamaIndex Server allows your workflows to send various types of events to the frontend UI. These events can include custom UI components, structured data artifacts, or any other information you want to display to users.

Important Note: The server filters events from the backend to only allow specific types to reach the frontend:

• Text parts: text-delta, text-start, text-end events for streaming text content
• Data parts: Any event with a type that starts with data- (e.g., data-artifact, data-chart, data-table)

All other events are filtered out to ensure compatibility with the Vercel AI SDK and maintain a stable frontend experience.

One common use case is sending structured data artifacts like generated documents or code snippets to the UI. These artifacts are displayed in a dedicated "Canvas" panel in the chat interface.

To send an artifact, your workflow needs to emit an event with type: "data-artifact". The data payload of this event should include:

• type: A string indicating the type of artifact (e.g., "document", "code").
• created_at: A timestamp (e.g., Date.now()) indicating when the artifact was created.
• data: An object containing the specific details of the artifact. The structure of this object depends on the artifact type.

First, define your artifact event using workflowEvent from @llamaindex/workflow:

import { workflowEvent } from '@llamaindex/workflow'

// Example for a document artifact
const artifactEvent = workflowEvent<{
  type: 'data-artifact' // Must start with "data-"
  data: {
    type: 'document' // Custom type for your artifact (e.g., "document", "code")
    created_at: number
    data: {
      // Specific data for the document artifact type
      title: string
      content: string
      type: 'markdown' | 'html' // document format
    }
  }
}>()

Then, within your workflow logic, use sendEvent (obtained from getContext()) to emit the event:

// Assuming 'sendEvent' is available in your workflow handler
// and 'documentDetails' contains the content for the artifact.

sendEvent(
  artifactEvent.with({
    type: "data-artifact", // This top-level type must start with "data-"
    data: {
      type: "document", // This is your specific artifact type
      created_at: Date.now(),
      data: {
        title: "My Generated Document",
        content: "# Hello World
This is a markdown document.",
        type: "markdown",
      },
    },
  }),
);

This will send the artifact to the LlamaIndex Server UI, where it will be rendered in the ChatCanvasPanel by a renderer depending on the artifact type. For type document this is using the DocumentArtifactViewer.

You can send any event type that starts with data- to create custom UI experiences. For example:

• data-file for file content
• data-image for image content
• data-* for your own custom components

The key requirement is that the event type must start with data- to pass through the server's event filter.

When you send events from your workflow, they flow through the system as follows:

1. Workflow Stream: Your workflow emits events using sendEvent()
2. Server Processing: The server transforms events to Server-Sent Events (SSE) format
3. Frontend Parsing: Vercel AI SDK parses the stream and converts events back to message parts
4. UI Rendering: Chat UI renders each part using built-in or custom components

The server includes a default chat endpoint at /api/chat for handling chat interactions.

The server always provides a chat interface at the root path (/) with:

• Configurable starter questions
• Real-time chat interface
• API endpoint integration

• The server automatically mounts the data and output folders at {server_url}{api_prefix}/files/data (default: /api/files/data) and {server_url}{api_prefix}/files/output (default: /api/files/output) respectively.
• Your workflows can use both folders to store and access files. By convention, the data folder is used for documents that are ingested, and the output folder is used for documents generated by the workflow.

If you want to fully customize the server UI and routes, you can use npm eject. It will create a normal Next.js project with the same functionality as @llamaindex/server. By default, the ejected project will be in the next directory in the current working directory. You can change the output directory by providing custom path after eject command:

npm eject <path-to-output-directory>

How eject works:

1. Init nextjs project with eslint, prettier, postcss, tailwindcss, shadcn components, etc.
2. Copy your workflow definition and setting files in src/app/* to the ejected project in app/api/chat
3. Copy your components, data, output, storage folders to the ejected project
4. Copy your current .env file to the ejected project
5. Clean up files that are no longer needed and update imports

• LlamaIndexServer

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4