from fastapi import FastAPI from transformers import pipeline import crawl_archive import GenerateAIPodcast from llama_cpp import Llama app = FastAPI() llm = Llama.from_pretrained( repo_id="hugging-quants/Llama-3.2-1B-Instruct-Q8_0-GGUF", filename="llama-3.2-1b-instruct-q8_0.gguf", ) @app.get("/") def home(): return {"message":"Hello World"} # Define a function to handle the GET request at `/generate` @app.get("/generate") def generate(link:str): ## use the pipeline to generate text from given input text output= llm.create_chat_completion( messages = [ {"role": "system", "content": "Always answer short and most detailled and dont use * in your answers. It should be good to hear as a Podcast"}, {"role": "user", "content": f"Please summarize this website: {link}."} ] ) ## return the generate text in Json reposnfe return output['choices'][0]['message']['content'] crawl_archive.run_tldr_crawler()