mirror of
https://github.com/rowboatlabs/rowboat.git
synced 2026-04-25 08:26:22 +02:00
| .. | ||
| .dockerignore | ||
| .gitignore | ||
| app.py | ||
| copilot.py | ||
| Dockerfile | ||
| lib.py | ||
| README.md | ||
| requirements.txt | ||
AI Workflow Copilot
A Flask-based application that helps design and manage multi-agent AI systems for customer support.
Prerequisites
- Python 3.8+
- OpenAI API key
Installation
- Clone the repository:
- Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows, use: venv\Scripts\activate
- Install required dependencies:
pip install -r requirements.txt
- Set up your OpenAI API key:
export OPENAI_API_KEY='your-api-key-here' # On Windows, use: set OPENAI_API_KEY=your-api-key-here
export API_KEY='test-api-key' # set a shared API key for the application
Running the Application
- Start the Flask server:
python app.py
The server will start on http://localhost:3002
API Usage
The application exposes a single endpoint at /chat that accepts POST requests.
Example Request:
curl -X POST http://localhost:3002/chat \
-H "Content-Type: application/json" \
-H "Authorization: Bearer test-api-key" \
-d '{
"messages": [
{
"role": "user",
"content": "Your message here"
}
],
"workflow_schema": "Your workflow schema here",
"current_workflow_config": "Your current workflow configuration here"
}'
Example Response:
{
"response": "Assistant's response here"
}
Error Handling
The API returns appropriate HTTP status codes:
- 400: Invalid request format or data
- 500: Internal server error
Development
To run the server in debug mode, ensure debug=True is set in app.py (already included).
License
[Add your license information here]