app.py

import os
import openai
import gradio as gr
import base64
from data4 import strategy_text, description, questions

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") 
openai.api_key = OPENAI_API_KEY

def transcribe_audio(audio_file_path):
    # Use OpenAI's Whisper to transcribe the audio
    audio_file = open(audio_file_path, "rb")
    transcript = openai.Audio.transcribe("whisper-1", audio_file)
    return transcript["text"]

def get_base64_image():
    with open("SBC4.jpg", "rb") as img_file:
        return base64.b64encode(img_file.read()).decode("utf-8")
    
def get_image_html():
    return (
        f"<img src='data:image/jpeg;base64,{get_base64_image()}' style='display: block; margin-left: auto; margin-right: auto; padding-bottom: 15px; width: 300px;'>"
    )

current_question_index = 0
user_input_counter = 0
conversation_history = []

def intelligent_tutor(audio_file, provide_hints=False):
    global current_question_index
    global questions
    global user_input_counter
    global conversation_history

    input_text = transcribe_audio(audio_file)
    current_question = questions[current_question_index]

    if provide_hints:
        hint_message = f"考虑使用 {strategy_text[current_question_index]} 策略来回答这个问题：'{questions[current_question_index]}'。"
        return f"请回答这个问题：{questions[current_question_index]}", hint_message

    conversation = [
        {
            "role": "system",
            "content": f"你是一名专家级的中文老师，正在指导一名学生。学生正在回答这个问题：'{questions[current_question_index]}'。根据他们的回答，为他们提供直接的反馈，以帮助他们提高口语技能。强调他们的优点，建议改进的地方，并指导他们如何使用 {strategy_text[current_question_index]} 策略更好地回答。反馈应该用第二人称，直接向学生发言 请用简单的话给学生建议，帮助他们说得更好。"
        },
        {"role": "user", "content": input_text}
    ]


    # Append the user's response to the conversation history
    conversation_history.append(input_text)

    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=conversation,
        max_tokens=400
    )

    if not response.choices:
        return "No response from the model.", ""

    text_response = response.choices[0]['message']['content'].strip()
    text_response = text_response.replace('\n', '<br>')

    user_input_counter += 1

    if user_input_counter % 2 == 0:
        if current_question_index + 1 < len(questions):
            current_question_index += 1
            next_question = questions[current_question_index]
            text_response += f"\n\nNext question ({current_question_index + 1}): {next_question}"
        else:
            # All questions have been answered, provide a summary
            summary_prompt = {
                "role": "system",
                "content": f"你是一名中文老师，正在帮助新加坡小六的学生。学生正在回答这个问题：'{questions[current_question_index]}'。请用简单的词汇和句子给出反馈，帮助学生改进。" 
            }
            summary_conversation = [summary_prompt, {"role": "user", "content": " ".join(conversation_history)}]
            
            summary_response = openai.ChatCompletion.create(
                model="gpt-3.5-turbo",
                messages=summary_conversation,
                max_tokens=600  # Increased token limit for detailed summary
            )
            
            if not summary_response.choices:
                return "No response from the model.", ""
            
            text_response = summary_response.choices[0]['message']['content'].strip()
            text_response = text_response.replace('\n', '<br>')

    wrapped_output_text = f'<div style="height: 300px; overflow-y: scroll;">{text_response}</div>'
    return f"Current Question: {questions[current_question_index]}", wrapped_output_text

iface = gr.Interface(
    fn=intelligent_tutor,
    inputs=[
        gr.Audio(source="microphone", type="filepath", label="录音", sampling_rate=16000),
        gr.inputs.Checkbox(label="提供对话总结"),  # Checkbox for hints
    ],
    outputs=[
        gr.outputs.HTML(label="问题"),
        gr.outputs.HTML(label="输出文本"),
    ],
    title="口语教练",
    description=(get_image_html() + 
                 "<br> " + questions[0] +
                 "<br>每个问题有两次尝试机会。<br>" +
                 "<b>请在第一个问题后的输出屏幕上回答显示的问题。</b>"),
)
iface.launch(share=False)