from llama_cpp import LlamaModel
from fastapi import FastAPI
from pydantic import BaseModel

# Charger le modèle LLaMA
llm = LlamaModel(model_path="phi-2.Q5_K_M.gguf")

# Pydantic object
class Validation(BaseModel):
    prompt: str

# Fast API
app = FastAPI()

@app.post("/llm_on_cpu")
async def stream(item: Validation):
    system_prompt = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.'
    E_INST = "</s>"
    user, assistant = "<|user|>", "<|assistant|>"
    prompt = f"{system_prompt}{E_INST}\n{user}\n{item.prompt}{E_INST}\n{assistant}\n"
    response = llm.generate(prompt, max_new_tokens=1096, num_threads=3)
    return response