app.py

import gradio as gr

from load_model_type_a import load_Auto
from load_push import all_files
from retriever import *
from retrieve_docs import *
from make_chain_model import make_chain_llm
from make_answer import *

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response

"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
TITLE = "FUT FUT Chatbot"

DESCRIPTION = """
'해요'체를 사용하며 친절하게 답하는 풋풋이 챗봇.
A rag pipeline with a chatbot feature
Resources used to build this project :
* embedding model : https://huggingface.co/BM-K/KoSimCSE-roberta-multitask
* dataset : https://huggingface.co/datasets/Dongwookss/q_a_korean_futsal
* vector DB : PINECONE
* chatbot : https://huggingface.co/Dongwookss/small_fut_final
"""

Examples = [['시흥 풋살 구장 추천해줘'],['풋살 경기 규칙 설명해줘'], ['풋살 경기 시간 알려줘']]

demo = gr.ChatInterface(
    fn=talk,
    chatbot=gr.Chatbot(
        show_label=True,
        show_share_button=True,
        show_copy_button=True,
        likeable=True,
        layout="bubble",
        bubble_full_width=False,
    ),
    theme="Soft",
    examples=[["what's anarchy ? "]],
    title=TITLE,
    description=DESCRIPTION,
    examples=Examples
    
)
demo.launch(debug=True)

# if __name__ == "__main__":
#     demo.launch()