LlamaIndex 发布 AG-UI 官方集成,一行代码构建智能体前端
AG-UI Agentic Frontends: Quick Start Guide | LlamaIndex
LlamaIndex 推出 AG-UI 协议官方集成,pip 安装后可用一行代码创建兼容 AG-UI 的 FastAPI router,为智能体提供前端或后端工具。前端可引入 CopilotChat React 组件直接访问智能体,CopilotKit 负责将用户请求路由到相应工具。
正文
当前显示原文,中文全文译文尚未就绪。
It’s been a big month for CopilotKit’s AG-UI project since it launched a little over a month ago! They’ve seen a lot of adoption and are celebrating today with a raft of updates and new features. We’re joining in the celebration by launching the official LlamaIndex integration to AG-UI!
If you’re just tuning in, AG-UI is a protocol that makes it easy to bring agents out of the backend and into direct interaction with users. The protocol can work with any end-user facing UI – a web app, a desktop application, or any existing chat application. CopilotKit is a first-class client to the protocol, focusing on bringing agents into interaction with users through modern web frontends in React.
Getting started is easy, just pip install the integration:
sh
Then you can create an AG-UI compatible FastAPI router in one line of code! This creates an agent, and provides it with tools that it can use on the frontend or the backend to complete user tasks.
python
(See the full documentation or starter example for how to define these tools.)
On the frontend, this will allow you to include the CopilotChat React component:
javascript
Which can then be instantiated to give you simple access to your agent:
javascript
CopilotKit works seamlessly with the AG-UI protocol to route user requests to frontend or backend tools to achieve their goals. A lot of messy boilerplate is abstracted away, letting you focus on your business logic and user experience.
Explore our free and paid plans today.
Learn more
We’re delighted to add to AG-UI’s already impressive momentum. If you want to build your own agentic frontend using LlamaIndex and CopilotKit, check out these resources:
Official LlamaIndex integration; LlamaIndex CopilotKit documentation; LlamaIndex example in AG-UI documentation