api.py

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

app = FastAPI()

# ✅ Load Model
model_path = "fine_tuned_medical_llama2"
model = AutoModelForCausalLM.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)

@app.post("/predict")
def predict(query: str):
    inputs = tokenizer(query, return_tensors="pt", padding=True, truncation=True)
    with torch.no_grad():
        outputs = model.generate(**inputs, max_length=200)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return {"response": response}