Installation - devdattatalele/Krya.ai GitHub Wiki
Installation
Prerequisites
- Python 3.8+
- pip
- Google Gemini API credentials
- Operating System: Windows, macOS, or Linux
Clone & Setup
git clone https://github.com/devdattatalele/Krya.ai.git
cd Krya.ai
python3 -m venv venv
source venv/bin/activate # macOS/Linux
.\venv\Scripts\activate # Windows
pip install --upgrade pip
pip install -r requirements.txt
Dependencies
streamlit — front-end
pyautogui — GUI automation
openai or proprietary Gemini client — LLM access
uvicorn, fastapi (if refactored to API)
pytest, httpx — testing
yaml
Copy
Edit
---
## 🔧 Configuration ( `Configuration.md`)
```markdown
# Configuration
Krya.ai reads settings from `config.json` (or environment variables):
```json
{
"gemini_api_key": "YOUR_API_KEY",
"gemini_model": "gemini-flash-2.0",
"max_retries": 3,
"logging_level": "INFO"
}
gemini_api_key: your API key for LLM calls
gemini_model: model name
max_retries: number of feedback-loop retries
logging_level: DEBUG / INFO / WARNING / ERROR
Alternatively, set env vars:
bash
Copy
Edit
export GEMINI_API_KEY="..."
export GEMINI_MODEL="gemini-flash-2.0"
export MAX_RETRIES=3
export LOGGING_LEVEL="INFO"
yaml
Copy
Edit