modal_app.py

import base64
import os
import tempfile

import modal

app = modal.App("patient-virtuel")

# ---- Shared volumes ----
qwen_vol = modal.Volume.from_name("qwen-cache", create_if_missing=True)
whisper_vol = modal.Volume.from_name("whisper-cache", create_if_missing=True)
CACHE_DIR = "/root/.cache/huggingface"

# ---- 1. Qwen/Qwen3.6-27B LLM ----
qwen_image = (
    modal.Image.debian_slim(python_version="3.12")
    .pip_install("vllm>=0.6.0", "bitsandbytes>=0.43", "huggingface-hub", "torch>=2.5", "fastapi[standard]")
)


@app.function(
    image=qwen_image,
    gpu="A100:1",
    volumes={CACHE_DIR: qwen_vol},
    secrets=[modal.Secret.from_name("hf-token"), modal.Secret.from_name("app-tokens")],
    timeout=600,
    scaledown_window=600,
)
@modal.asgi_app()
def qwen_web():
    from fastapi import FastAPI, HTTPException, Request

    fastapi_app = FastAPI()

    @fastapi_app.post("/")
    async def handler(request: Request):
        body = await request.json()
        token = body.get("token", "")
        expected = os.environ.get("EXPECTED_TOKEN", "")
        if not token or token != expected:
            raise HTTPException(401, "Unauthorized")

        messages = body["messages"]

        from vllm import LLM, SamplingParams

        llm = LLM(
            model="Qwen/Qwen3.6-27B",
            dtype="bfloat16",
            quantization="bitsandbytes",
            load_format="bitsandbytes",
            max_model_len=16384,
            trust_remote_code=True,
        )

        sp = SamplingParams(temperature=0.7, top_p=0.8, top_k=20, max_tokens=512)
        outputs = llm.chat(messages=messages, sampling_params=sp, use_tqdm=False)

        text = outputs[0].outputs[0].text.strip()
        if "<think>" in text:
            text = text.split("</think>")[-1].strip()
        return {"text": text}

    return fastapi_app


# ---- 2. Whisper STT (JSON input — base64-encoded WAV) ----
whisper_image = (
    modal.Image.debian_slim(python_version="3.12")
    .pip_install("faster-whisper", "numpy", "fastapi[standard]")
)


@app.function(
    image=whisper_image,
    gpu="A10G:1",
    volumes={CACHE_DIR: whisper_vol},
    timeout=120,
    scaledown_window=300,
)
@modal.asgi_app()
def whisper_web():
    from fastapi import FastAPI, HTTPException, Request

    fastapi_app = FastAPI()

    @fastapi_app.post("/")
    async def handler(request: Request):
        body = await request.json()
        token = body.get("token", "")
        expected = os.environ.get("EXPECTED_TOKEN", "")
        if not token or token != expected:
            raise HTTPException(401, "Unauthorized")

        audio_base64 = body["audio_base64"]

        from faster_whisper import WhisperModel

        model = WhisperModel(
            "large-v3-turbo", device="cuda", compute_type="float16", download_root=CACHE_DIR,
        )

        raw = base64.b64decode(audio_base64)
        with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as f:
            f.write(raw)
            path = f.name

        segments, _ = model.transcribe(path, language="fr", beam_size=5, vad_filter=True)
        os.unlink(path)

        return {"text": " ".join(s.text for s in segments)}

    return fastapi_app