app.py

import gradio as gr
from huggingface_hub import InferenceClient
from PyPDF2 import PdfReader
import os

# PDF 텍스트 미리 읽어오기
def extract_pdf_text(pdf_paths):
    full_text = ""
    for path in pdf_paths:
        reader = PdfReader(path)
        for page in reader.pages:
            text = page.extract_text()
            if text:
                full_text += text + "\n"
    return full_text.strip()

# 미리 지정된 PDF 문서들
pdf_context = extract_pdf_text([
    "assets/Programming-Fundamentals-1570222270.pdf",
    "assets/1분파이썬_강의자료_전체.pdf"
])

# Inference Client 설정 - 모델 변경됨
client = InferenceClient(
    model="mistralai/Mistral-7B-Instruct-v0.1",
    token=os.getenv("HUGGINGFACEHUB_API_TOKEN")  # 반드시 등록 필요
)

def respond(message, history, system_message, max_tokens, temperature, top_p):
    messages = [{"role": "system", "content": system_message}]
    
    # history 기반 message 구성
    for user_msg, bot_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if bot_msg:
            messages.append({"role": "assistant", "content": bot_msg})

    # 문서 기반 질문 구성
    messages.append({
        "role": "user",
        "content": f"다음은 파이썬 프로그래밍 문서입니다:\n\n{pdf_context}\n\n질문: {message}"
    })

    response = ""
    for chunk in client.chat_completion(
        messages=messages,
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        stream=True,
    ):
        delta = chunk.choices[0].delta.content
        if delta:
            response += delta
            yield response

demo = gr.ChatInterface(
    fn=respond,
    additional_inputs=[
        gr.Textbox(value="You are a helpful assistant answering based on the programming reference.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p"),
    ],
    title="📘 파이썬 API 레퍼런스 챗봇 (Mistral 기반)",
    description="한국공대 수업자료 기반으로 질문에 답변하는 챗봇입니다."
)

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