from fastapi import FastAPI, Request
from transformers import AutoTokenizer, AutoModelForCausalLM

app = FastAPI()

model_path = "tinyllama-finetuned-skin"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path)

@app.post("/generate")
async def generate(request: Request):
    data = await request.json()
    prompt = data["prompt"]
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=100)
    result = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return {"response": result}