from ctransformers import AutoModelForCausalLM
from fastapi import FastAPI, Form
from pydantic import BaseModel

#Model loading
llm = AutoModelForCausalLM.from_pretrained("TheBloke/CodeLlama-7B-Python-GGUF",
model_file="Meta-Llama-3-8B-Instruct-Q4_K_M.gguf",
model_type='llama',
# max_new_tokens = 1096,
threads = 3,
)
   

#Pydantic object
class validation(BaseModel):
    prompt: str
    
#Fast API
app = FastAPI()

#Zephyr completion
@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.'
    prompt = f'''
    <|begin_of_text|><|start_header_id|>system<|end_header_id|>

    {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

    {item.prompt.strip()}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
    '''
    return llm(prompt)