Saathi MVP

AI Companion for Tier-2/Tier-3 India.

Quick Start (Local)

1. Prerequisites: Docker, Python 3.11, Ollama (optional for local LLM).
2. Run:

   chmod +x scripts/run_local.sh
   ./scripts/run_local.sh

3. Ingest Data:

   python3 scripts/ingest.py

4. Test:

   chmod +x tests/test_endpoints.sh
   ./tests/test_endpoints.sh

Testing without Docker (Local Python)

1. Setup Virtual Env:

   python3 -m venv venv
   source venv/bin/activate
   pip install -r requirements.txt

2. Run Unit Tests (Logic only):

   python tests/test_logic.py

3. Run Integration Tests:

   # Start server in background
   export PYTHONPATH=$PWD/backend
   uvicorn saathi.routes:app --host 0.0.0.0 --port 8000 &
   
   # Run tests
   bash tests/test_endpoints.sh
   
   # Stop server
   pkill -f uvicorn

Configuration

Edit .env or backend/saathi/config.py to switch LLM providers (OLLAMA, VLLM, EXTERNAL).

Operational Mode

See OP_MODE.md for cost optimization details.