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

model_name = "meta-llama/Llama-3.1-8B-Instruct"

# Use the Hugging Face token from the environment variable
hf_token = os.getenv("HF_TOKEN")
tokenizer = AutoTokenizer.from_pretrained(model_name, token=hf_token)
model = AutoModelForCausalLM.from_pretrained(model_name, token=hf_token)

app = FastAPI()

class Prompt(BaseModel):
    text: str

@app.post("/generate")
def generate_text(prompt: Prompt):
    inputs = tokenizer(prompt.text, return_tensors="pt")
    outputs = model.generate(**inputs, max_length=100)
    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return {"generated_text": generated_text}