./start_server.sh# Activate virtual environment
source venv/bin/activate
# Start server
uvicorn app.main:app --reloadsource venv/bin/activate
python -m uvicorn app.main:app --reloadOnce the server is running:
- Frontend: http://localhost:8000
- API Docs (Swagger): http://localhost:8000/docs
- API Docs (ReDoc): http://localhost:8000/redoc
- Health Check: http://localhost:8000/api/v1/health
Solution: Make sure you're using the virtual environment:
source venv/bin/activate
pip install -r requirements.txtIf you see Python 3.12 errors but venv has 3.8:
# Deactivate and reactivate
deactivate
source venv/bin/activate
which python # Should show venv/bin/python# Use a different port
uvicorn app.main:app --port 8001 --reloadMake sure .env file has:
OPENAI_API_KEY- Your OpenAI API keyQDRANT_URL- Your Qdrant Cloud URL (optional)QDRANT_API_KEY- Your Qdrant API key (optional)
# Health check
curl http://localhost:8000/api/v1/health
# Get estimate
curl -X POST http://localhost:8000/api/v1/estimate \
-H "Content-Type: application/json" \
-d '{"requirements": "User authentication and dashboard"}'- Start the server
- Open browser to http://localhost:8000
- Enter requirements and click "Get Estimate"
- Or try "Chat Mode" for conversational interaction