---
title: LexGuard Backend
emoji: ⚖️
colorFrom: indigo
colorTo: purple
sdk: docker
app_port: 7860
pinned: false
license: mit
short_description: Multi-agent contract intelligence API — 5-agent pipeline
---

# LexGuard Backend

FastAPI service powering the LexGuard 5-agent contract analysis pipeline.

## Endpoints

| Method | Path | Purpose |
|---|---|---|
| GET | `/api/health` | Liveness probe |
| POST | `/api/analyze` | Upload PDF/DOCX/TXT → `{job_id}` |
| GET | `/api/stream/{job_id}` | SSE stream of agent events + `report_complete` |
| POST | `/api/negotiate/{clause_id}?job_id=...` | On-demand Negotiator agent |
| POST | `/api/compare` | Compare clause against benchmark store |

## Environment (set as HF Space secrets)

| Variable | Required | Description |
|---|---|---|
| `GROQ_API_KEY` | Yes | Groq API key (free tier works) |
| `CORS_ORIGINS` | Yes | Your Vercel frontend URL, e.g. `https://lexguard.vercel.app` |
| `GCP_PROJECT` | No | If set, switches to Vertex AI Gemini instead of Groq |
| `GROQ_MODEL` | No | Default: `llama-3.3-70b-versatile` |

## Local Development

```bash
cp .env.example .env   # fill in GROQ_API_KEY
pip install -e ".[dev]"
uvicorn app.main:app --reload --port 8000
```