app.py

from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from transformers import AutoModelForCausalLM, AutoTokenizer

app = FastAPI()

# Load your fine-tuned model and tokenizer
model = AutoModelForCausalLM.from_pretrained("Hadeel11/fine-tuned-model")
tokenizer = AutoTokenizer.from_pretrained("Hadeel11/fine-tuned-model")

class Query(BaseModel):
    question: str
    contexts: list

@app.post("/predict/")
async def predict(query: Query):
    inputs = tokenizer(query.question, return_tensors="pt")
    outputs = model.generate(**inputs)
    answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return {"answer": answer}