rowboat/apps/copilot
2025-01-14 12:28:44 +05:30
..
.dockerignore add copilot dockerfile 2025-01-14 11:21:03 +05:30
.gitignore add copilot app 2025-01-13 17:57:37 +05:30
app.py add docker-compose and readme 2025-01-14 12:28:44 +05:30
copilot.py add copilot app 2025-01-13 17:57:37 +05:30
Dockerfile add docker-compose and readme 2025-01-14 12:28:44 +05:30
lib.py add copilot app 2025-01-13 17:57:37 +05:30
README.md add copilot app 2025-01-13 17:57:37 +05:30
requirements.txt add copilot app 2025-01-13 17:57:37 +05:30

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

  1. Clone the repository:
  2. Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate  # On Windows, use: venv\Scripts\activate
  1. Install required dependencies:
pip install -r requirements.txt
  1. 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

Running the Application

  1. Start the Flask server:
python app.py

The server will start on http://localhost:5000

API Usage

The application exposes a single endpoint at /chat that accepts POST requests.

Example Request:

{
  "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]