INDRA is an AI-powered system for running the CONFLUENCE workflow using a panel of expert AI agents. It provides comprehensive insights and suggestions for improving hydrological modeling through the integration of multiple expert perspectives
- Generates perceptual models for new watersheds
- Provides expert-guided configuration for CONFLUENCE setups
- Performs comprehensive model analysis through multiple expert lenses
- Offers configuration suggestions based on expert consensus
- Creates detailed reports for model decisions and their justification
- Clone the repository:
git clone https://github.com/DarriEy/INDRA.git
cd INDRA
- Set up your environment:
Create and activate a Python virtual environment Install dependencies:
pip install -r requirements.txt
- Set up your API key:
# For Unix-like systems (Linux/Mac)
export ANTHROPIC_API_KEY="your-api-key-here"
# For Windows (via Command Prompt)
set ANTHROPIC_API_KEY=your-api-key-here
INDRA can be used in two main ways:
- New Project Initialization
python INDRA.py
# Select 'n' when asked about existing config
# Follow the interactive prompts
- Existing Project Analysis
python INDRA.py
# Select 'y' when asked about existing config
# Provide path to your CONFLUENCE configuration file
INDRA is designed to work with the CONFLUENCE workflow. See https://github.com/DarriEy/CONFLUENCE for the CONFLUENCE specific dependencies.
We welcome contributions to INDRA! Please follow these steps to contribute:
- Fork the repository
- Create a new branch for your feature
- Commit your changes
- Push to your fork
- Submit a pull request
Please make sure to include tests as appropriate and adhere to the project's coding standards.
This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details.
Darri Eythorsson University of Calgary [email protected]