Skip to content

SumanMadipeddi/voice-agent

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Voice Agent

Real-time voice agent application with React frontend and Python backend, built on LiveKit with RAG capabilities.

Prerequisites

  • Node.js 18+ and npm
  • Python 3.10+
  • uv package manager
  • LiveKit CLI: winget install LiveKit.LiveKitCLI
  • LiveKit Cloud, Pinecone, and Azure OpenAI accounts

Installation

Frontend

cd agent-react
npm install

Backend

cd backend
uv sync

Configuration

Create a .env file in the project root:

VITE_LIVEKIT_URL=wss://your-project.livekit.cloud
VITE_LIVEKIT_API_KEY=your-api-key
VITE_LIVEKIT_API_SECRET=your-api-secret
PINECONE_API_KEY=your-pinecone-api-key
AZURE_OPENAI_API_KEY=your-azure-openai-key
AZURE_OPENAI_ENDPOINT=your-azure-endpoint
AZURE_OPENAI_API_VERSION=2024-02-15-preview

Get LiveKit credentials from LiveKit Cloud Dashboard → Project Settings → Keys.

Running

Frontend

cd agent-react
npm run dev

Access at http://localhost:3000

Backend

cd backend
uv run agent.py dev

lk agent create
lk agent delete

Project Structure

voice-agent/
├── agent-react/          # React frontend
├── backend/              # Python agent
│   ├── agent.py         # Agent entrypoint
│   └── rag/             # RAG implementation
└── README.md

Documentation

About

RAG Enabled Multi Agent Voice Assistant with LiveKit audio and video streaming with <200ms latency

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors