getting_started.md

Getting started

The fastest way to start and try Rico Lebot is using Docker

🛠️ Configuration

Pre-requisites:

• LiveKit Account: Sign up for LiveKit to obtain API credentials. LiveKit Realtime API Quickstart
• OpenAI API Key: Obtain your API key from OpenAI.

Clone the Repository

git clone https://github.com/xbasset/rico-lebot.git
cd rico-lebot

Configure Environment Variables

Create a .env file in the root directory based on the provided .env.example:

cp .env.example .env

Open the .env file and populate it with your credentials:

# .env

# OpenAI Credentials
OPENAI_API_KEY=your_openai_api_key

# LiveKit Credentials
LIVEKIT_API_KEY=your_livekit_api_key
LIVEKIT_API_SECRET=your_livekit_api_secret
LIVEKIT_URL=your_livekit_server_url

🚀 Run with Docker

You can build the Docker image named rico and run it using the following commands.

Build the Docker Image

docker build -t rico .

Run the Docker Container

docker run -p 5001:5001 --name rico rico

Congratz. 🎉 You're all set! Start using Rico Lebot: 👉 http://localhost:5001

🧑‍💻 As a developer

If you want to start each component and dive deeper, use the following.

Setup Virtual Environment

It's recommended to use a virtual environment to manage dependencies.

python3 -m venv .venv
source .venv/bin/activate  # On Windows, use .venv\Scripts\activate

Python Dependencies

pip install -r requirements.txt

Run each component

Running the Application

Start the Flask application with SocketIO enabled.

python app.py

The application will be accessible at http://localhost:5001.

Running the Agent

In a separate terminal window, ensure your virtual environment is activated and run the agent script.

python agent.py dev

The agent connects to the LiveKit room and starts interacting based on the defined role.