Skip to content

README.md

Latest commit

 

History

History
71 lines (46 loc) · 1.6 KB

README.md

File metadata and controls

71 lines (46 loc) · 1.6 KB
Raw

AI Research Copilot

This project demonstrates an AI research copilot built with Pipecat for voice interactions, integrated with Langfuse for conversation tracing and analysis.

AI Research Copilot demo video

Prerequisites

  • Python 3+
  • Node.js 20+
  • Langfuse stack (Cloud or Self-Hosted)
  • Langfuse API key
  • Gemini API key
  • Daily.co API key

How to run

Running the server

  1. Configure environment variables

    Create a .env file:

    cd server
cp env.example .env

    Then fill in the values.

  2. Install dependencies, uses uv

    uv sync

  3. Run the AI research copilot:

    uv run bot.py --transport daily # we're using daily.co for Real-Time communications

Running the client

  1. Configure environment variables

    Create a .env file:

    cd client
cp env.example .env

    Then fill in the values.

  2. Install dependencies

    npm install

  3. Run the client

    npm run dev

Open http://localhost:3000 with your browser to access the AI research copilot interface.

Deploying to production

Follow the instructions to deploying the server and deploying the frontend app.