app.py

import os
from fastapi import FastAPI, Request, HTTPException, Header
from pydantic import BaseModel
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

app = FastAPI()

# Récupérer le token depuis les variables d’environnement
API_TOKEN = "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"

# Charger le modèle
model_name = "google/medgemma-4b-pt"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")

# Modèle de requête
class GenerationRequest(BaseModel):
    prompt: str

@app.post("/generate")
async def generate(request_data: GenerationRequest, authorization: str = Header(None)):
    if authorization != f"Bearer {API_TOKEN}":
        raise HTTPException(status_code=401, detail="Unauthorized")

    inputs = tokenizer(request_data.prompt, return_tensors="pt").to(model.device)
    with torch.no_grad():
        outputs = model.generate(**inputs, max_new_tokens=100)
    result = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return {"response": result}