app.py

from threading import Thread
import gradio as gr
import inspect
from gradio import routes
from typing import List, Type

import requests, os, re, asyncio, queue
import math
import time
import datetime
import requests, json

loop = asyncio.get_event_loop()
# Monkey patch
def get_types(cls_set: List[Type], component: str):
    docset = []
    types = []
    if component == "input":
        for cls in cls_set:
            doc = inspect.getdoc(cls)
            doc_lines = doc.split("\n")
            docset.append(doc_lines[1].split(":")[-1])
            types.append(doc_lines[1].split(")")[0].split("(")[-1])
    else:
        for cls in cls_set:
            doc = inspect.getdoc(cls)
            doc_lines = doc.split("\n")
            docset.append(doc_lines[-1].split(":")[-1])
            types.append(doc_lines[-1].split(")")[0].split("(")[-1])
    return docset, types
routes.get_types = get_types


q = queue.Queue()

arrr = []

from huggingface_hub import hf_hub_download
hf_hub_download(repo_id='StarFox7/Llama-2-ko-7B-chat-gguf', filename='Llama-2-ko-7B-chat-gguf-q4_0.bin', local_dir='./')

# App code
def res(x, id, cdata, url):    
    global q

    arr = [x, id, str(cdata.split(",", 1)[0]), url]
    q.put(arr)

    arrr.append(x)
    print("\n_Done\n\n")
    return "Done"

def rese(x):    

    print(f"{arrr}")
    return "Done"
    
with gr.Blocks() as demo:
    count = 0
    aa = gr.Interface(
      fn=res,
      inputs=["text","text", "text", "text"],
      outputs="text",
      description="call",
    )

    bb = gr.Interface(
      fn=rese,
      inputs=["text"],
      outputs="text",
      description="call",
    )
    demo.queue(max_size=32).launch(enable_queue=True)