app.py

from fastapi import FastAPI
from llama_cpp import Llama

## create a new FASTAPI app instance
app=FastAPI()

# Initialize the text generation pipeline
#pipe = pipeline("text2text-generation", model="lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF",token=os.getenv('HF_KEY'))
llm = Llama(
    model_path="Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf",
)

@app.get("/")
def home():
    print("helloe here")
    output= llm("What is the difference btw RAG and Fine tunning", max_tokens=1000)
    print(output["choices"][0]["text"])
    ## return the generate text in Json reposne
    return {"output":output["choices"][0]["text"]}

# Define a function to handle the GET request at `/generate`


@app.get("/generate")
def generate(text:str):
    ## use the pipeline to generate text from given input text
    print("Recieved prompt "+str(text))
    output= llm(text, max_tokens=1000)
    print(output["choices"][0]["text"])
    ## return the generate text in Json reposne
    return {"output":output["choices"][0]["text"]}