---
title: Patient Virtuel · Français en médecine dentaire
emoji: 🦷
colorFrom: red
colorTo: gray
sdk: gradio
sdk_version: 6.16.0
app_file: src/server_app.py
pinned: false
license: apache-2.0
tags:
  - hackathon
  - build-small-hackathon
  - backyard-ai
  - voice-ai
  - french-learning
  - dental
  - gradio
  - modal
  - llama-cpp
  - gemma
  - track:backyard
  - sponsor:modal
  - achievement:offgrid
  - achievement:offbrand
  - achievement:llama
  - achievement:sharing
  - achievement:fieldnotes
---

# Patient Virtuel · Français en médecine dentaire

Hackathon submission for [build-small-hackathon](https://huggingface.co/build-small-hackathon).

**Track**: Backyard AI — a real tool for a real learner: a dental hygienist training professional French.

Uses `gradio.Server` with a custom HTML/CSS/JS frontend (Off-Brand Award entry).

**Llama Champion badge**: Model runs through the llama.cpp runtime via `llama-cpp-python` with flash attention and L4 GPU optimizations.

**Off the Grid badge**: Zero cloud APIs. STT → faster-whisper (local), LLM → Gemma 4 (local), TTS → piper-tts (local neural, `fr_FR-siwis-medium` voice).

See [`space_README.md`](space_README.md) for the full description.

📖 [Field Notes](FIELD_NOTES.md) — architecture decisions, lessons learned, and the story behind the app.
📡 [Agent Trace](https://huggingface.co/datasets/build-small-hackathon/patient-virtuel-trace) — curated build log on HF Hub (Sharing is Caring badge).

[Demo video](https://youtu.be/oP3KrlZFUPk) · [LinkedIn post](https://www.linkedin.com/posts/carlosduplar_my-wife-is-a-dentist-re-entering-the-workforce-activity-7471897489332289536-p5Ne)

## Architecture

```
src/
  server_app.py       → gr.Server backend (API endpoints)
  core.py             → Shared session logic
  llm_engine.py       → Gemma 4 26B-A4B via Modal (llama.cpp runtime)
  stt_engine.py       → faster-whisper via Modal
  tts_engine.py       → piper-tts (local neural, fr_FR-siwis-medium)
  prompts.py          → System prompts
  parse_feedback.py   → Feedback parsing
frontend/
  custom_index.html   → Custom vanilla HTML/CSS/JS frontend
  style.css           → Styles
modal/
  modal_app.py        → Modal deployments (llama.cpp + CUDA)
```

## Running locally

```bash
pip install -r requirements.txt
python src/server_app.py
```

## Deploying to HF Spaces

The Space uses `space_README.md` as its README and `src/server_app.py` as the entry point.