import transformers
import torch
import os

from fastapi import FastAPI

from transformers import AutoTokenizer

from llama_cpp import Llama

from huggingface_hub import hf_hub_download

app = FastAPI()
@app.get("/")
def llama():
    llm = Llama(
      model_path="./llama-2-7b-chat.Q4_K_M.gguf",
      # n_gpu_layers=-1, # Uncomment to use GPU acceleration
      # seed=1337, # Uncomment to set a specific seed
      # n_ctx=2048, # Uncomment to increase the context window
    )

    output = llm(
      "Q: Name the planets in the solar system? A: ", # Prompt
      max_tokens=32, # Generate up to 32 tokens, set to None to generate up to the end of the context window
      stop=["Q:", "\n"], # Stop generating just before the model would generate a new question
      echo=True # Echo the prompt back in the output
    ) # Generate a completion, can also call create_completion
    
    return {"output": output}