app.py

import gradio as gr
import pandas as pd
import os
from openai import OpenAI

OPEN_AI_KEY = os.getenv("OPEN_AI_KEY")
client = OpenAI(api_key=OPEN_AI_KEY)



def process_file(file):
    # 读取文件
    if file.name.endswith('.csv'):
        df = pd.read_csv(file)
    else:
        df = pd.read_excel(file)

    # 将 DataFrame 转换为字符串
    df_string = df.to_string()

    # 返回 DataFrame 字符串，以用作聊天机器人的系统提示
    return df_string

def respond(user_message, df_string_output, chat_history):
    print("=== 變數：user_message ===")
    print(user_message)
    print("=== 變數：chat_history ===")
    print(chat_history)

    sys_content = f"你是一個資料分析師，請用 {df_string_output} 為資料進行對話"
    messages = [
        {"role": "system", "content": sys_content},
        {"role": "user", "content": user_message}
    ]

    print("=====messages=====")
    print(messages)
    print("=====messages=====")


    request_payload = {
        "model": "gpt-4-1106-preview",
        "messages": messages,
        "max_tokens": 2000  # 設定一個較大的值，可根據需要調整
    }

    response = client.chat.completions.create(**request_payload)
    print(response)
    
    response_text = response.choices[0].message.content.strip()

    # 更新聊天历史
    new_chat_history = (user_message, response_text)
    if chat_history is None:
        chat_history = [new_chat_history]
    else:
        chat_history.append(new_chat_history)

    # 返回聊天历史和空字符串清空输入框
    return "", chat_history


with gr.Blocks() as demo:
    with gr.Row():
        with gr.Column():
            file_upload = gr.File(label="Upload your file")
        with gr.Column():
            df_string_output = gr.Textbox(label="")

    with gr.Row():
        chatbot = gr.Chatbot()
    
    with gr.Row():
        with gr.Column():
            with gr.Group():
                # password_input = gr.Textbox(label="Password", type="password")
                msg = gr.Textbox(label="請输入對話內容")
                send_button = gr.Button("發送")

    # 当文件上传时，更新 DataFrame 字符串
    file_upload.change(process_file, inputs=file_upload, outputs=df_string_output)

    # 处理聊天机器人的对话
    send_button.click(
        respond, 
        inputs=[msg, df_string_output, chatbot], 
        outputs=[msg, chatbot]
    )

demo.launch()