import time
import copy
import asyncio
import requests
import transformers
import torch

from fastapi import FastAPI, Request
from sse_starlette import EventSourceResponse

from transformers import AutoTokenizer

# Load the model

app = FastAPI()
model = "meta-llama/Llama-2-70b"
@app.get("/llama")
def llama():
    tokenizer = AutoTokenizer.from_pretrained(model)

    pipeline = transformers.pipeline("text-generation" ,model=model ,torch_dtype=torch.float16 ,device_map="auto" , )

    sequences = pipeline(
        'I liked "Breaking Bad" and "Band of Brothers". Do you have any recommendations of other shows I might like?\n',
        do_sample=True,
        top_k=10,
        num_return_sequences=1,
        eos_token_id=tokenizer.eos_token_id,
        max_length=200,
    )

    for seq in sequences:
        print(f"Result: {seq['generated_text']}")
    
    return sequences