first

.env

@@ -0,0 +1 @@
+OPENAI_API_KEY=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

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.py text eol=lf
+*.txt text eol=lf
+*.md text eol=lf
+.env text eol=lf

app.py

@@ -1,64 +1,121 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+import easyocr
+from dotenv import load_dotenv
+from openai import OpenAI
+from PIL import Image
+import numpy as np
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# 加载环境变量
+load_dotenv()
 
+# 初始化 OpenAI 客户端
+client = OpenAI(api_key=os.getenv('OPENAI_API_KEY'))
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# 初始化 EasyOCR
+reader = easyocr.Reader(['ch_sim', 'en'])
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def extract_text_from_image(image):
+    """从图片中提取文字"""
+    if isinstance(image, str):
+        image_path = image
+    else:
+        # 将 numpy array 转换为 PIL Image
+        if isinstance(image, np.ndarray):
+            image = Image.fromarray(image)
+        # 保存临时文件
+        image_path = "temp_image.png"
+        image.save(image_path)
+    
+    # 使用 EasyOCR 识别文字
+    result = reader.readtext(image_path)
+    
+    # 如果是临时文件，删除它
+    if image_path == "temp_image.png":
+        os.remove(image_path)
+    
+    # 提取文字内容
+    text = ' '.join([item[1] for item in result])
+    return text
 
-    messages.append({"role": "user", "content": message})
+def analyze_slide(text):
+    """使用 GPT-4 分析幻灯片内容"""
+    prompt = f"""请分析以下幻灯片内容，并提供详细的讲解：
 
-    response = ""
+{text}
 
-    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
+请从以下几个方面进行分析：
+1. 主要内容概述
+2. 重点概念解释
+3. 与其他知识的联系
+4. 实际应用场景
 
-        response += token
-        yield response
+请用中文回答。"""
 
+    response = client.chat.completions.create(
+        model="gpt-4",
+        messages=[{"role": "user", "content": prompt}]
+    )
+    
+    return response.choices[0].message.content
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", 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 (nucleus sampling)",
-        ),
-    ],
-)
+def chat_with_assistant(message, history):
+    """与 AI 助手对话"""
+    messages = [
+        {"role": "system", "content": "你是一位专业的课程助教，负责帮助学生理解课程内容。请用中文回答问题。"}
+    ]
+    
+    # 添加历史对话
+    for human, assistant in history:
+        messages.append({"role": "user", "content": human})
+        messages.append({"role": "assistant", "content": assistant})
+    
+    # 添加当前问题
+    messages.append({"role": "user", "content": message})
+    
+    response = client.chat.completions.create(
+        model="gpt-4",
+        messages=messages
+    )
+    
+    return response.choices[0].message.content
 
+# 创建 Gradio 界面
+with gr.Blocks(title="课程幻灯片理解助手") as demo:
+    gr.Markdown("# 课程幻灯片理解助手")
+    gr.Markdown("上传幻灯片图片，AI 将帮助你理解内容并回答问题。")
+    
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Image(label="上传幻灯片图片")
+            analyze_button = gr.Button("分析幻灯片")
+        
+        with gr.Column():
+            text_output = gr.Textbox(label="识别的文字内容", lines=5)
+            analysis_output = gr.Textbox(label="AI 分析结果", lines=10)
+    
+    gr.Markdown("---")
+    gr.Markdown("### 与 AI 助手对话")
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(label="输入你的问题")
+    clear = gr.Button("清除对话历史")
+    
+    # 设置事件处理
+    analyze_button.click(
+        fn=lambda img: (extract_text_from_image(img), analyze_slide(extract_text_from_image(img))),
+        inputs=[image_input],
+        outputs=[text_output, analysis_output]
+    )
+    
+    msg.submit(
+        fn=chat_with_assistant,
+        inputs=[msg, chatbot],
+        outputs=[chatbot],
+        clear_input=True
+    )
+    
+    clear.click(lambda: None, None, chatbot, queue=False)
 
+# 启动应用
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

requirements.txt

@@ -1 +1,7 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+gradio>=4.0.0
+easyocr>=1.7.1
+python-dotenv>=1.0.0
+openai>=1.0.0
+Pillow>=10.0.0
+numpy>=1.24.0