app.py

from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

app = FastAPI()

# Allow frontend requests
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

# Load model
model_name = "openai/gpt-oss-20b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)

class ChatRequest(BaseModel):
    message: str

@app.post("/chat")
async def chat(req: ChatRequest):
    messages = [{"role": "user", "content": req.message}]
    inputs = tokenizer.apply_chat_template(
        messages,
        add_generation_prompt=True,
        tokenize=True,
        return_dict=True,
        return_tensors="pt",
    ).to(model.device)

    outputs = model.generate(**inputs, max_new_tokens=100)
    reply = tokenizer.decode(
        outputs[0][inputs["input_ids"].shape[-1]:],
        skip_special_tokens=True
    )
    return {"reply": reply}