Update app.py

app.py

@@ -1,63 +1,80 @@
+# -*- coding: utf-8 -*-
 import gradio as gr
-from huggingface_hub import InferenceClient
+import os
+import re
+import json
+import subprocess
+from openai import OpenAI
+from retry import retry
+from random import choices
+from datetime import datetime
 
-"""
-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")
+os.environ["OPENAI_BASE_URL"] = "http://117.50.185.39:50080/v1"
+os.environ["OPENAI_API_KEY"] = "0"
+client = OpenAI()
+execution_desc = ["运行以上代码，输出会是： ",
+                  "现在将上面的代码复制到Python环境中运行，运行结果为：",
+                  "执行上述Python代码，运行结果将是：",
+                  "上面的Python代码执行结果为：",
+                  "运行上述代码，我们可以得到题目要求的答案。输出结果将是："]
 
+@retry(exceptions=Exception, tries=3, delay=2)
+def question_answer(query):
+    g = open("collect.json", "a", encoding="utf-8")
+    messages = [{"role": "system", "content": "你是一个数学解题大师，请解决以下数学题，务必详细说明解题思路，并在必要时提供Python代码来支持你的推理。答案中的数值应使用\\boxed{}包围，最后的答案以“因此”开头并直接给出结论，不要添加任何多余的内容。"}]
+    messages.append({"role": "user", "content": f"题目：{query}"})
+    result = client.chat.completions.create(messages=messages, 
+                                            model="gpt-3.5-turbo",
+                                            temperature=0.2,
+                                            stream=True)
+    reply_message = ""
+    for chunk in result:
+        if hasattr(chunk, "choices") and chunk.choices[0].delta.content:
+            reply_message += chunk.choices[0].delta.content
+    
+    # find python code and execute the code
+    if '```python' in reply_message:
+        reply_message = '```'.join(reply_message.split('```')[:-1]).replace('```python', '\n```python') + '```'
+        messages.append({"role": "assistant", "content": reply_message})
+        python_code_string = re.findall(r'```python\n(.*?)\n```', reply_message, re.S)[0]
+        python_file_path = 'temp.py'
+        with open(python_file_path, 'w') as f:
+            f.write(python_code_string)
+        python_code_run = subprocess.run(['python3', python_file_path], stdout=subprocess.PIPE, timeout=10)
+        if python_code_run.returncode:
+            print("生成的Python代码无法运行！")
+            raise RuntimeError("生成的Python代码无法运行！")
+        python_code_execution = python_code_run.stdout.decode('utf-8')
+        os.remove(python_file_path)
+        if "``````" in python_code_execution:
+            raise ValueError("执行Python代码结果为空!")
+        code_reply_str = choices(execution_desc, k=1)[0]
+        code_reply = f"\n{code_reply_str}```{python_code_execution.strip()}```\n"
+        reply_message += code_reply
+        # yield reply_message
+        messages.append({"role": "user", "content": code_reply})
+        result = client.chat.completions.create(messages=messages, 
+                                            model="gpt-3.5-turbo",
+                                            temperature=0.2,
+                                            stream=True)
+        
+        for chunk in result:
+            if hasattr(chunk, "choices") and chunk.choices[0].delta.content:
+                reply_message += chunk.choices[0].delta.content
+                # yield reply_message
+    print(reply_message)
+    g.write(json.dumps({"query": query, 
+                        "answer": reply_message, 
+                        "time": datetime.now().strftime('%Y-%m-%d %H:%M:%S %f')
+                        }, ensure_ascii=False)+"\n")
+    g.close()
+    return reply_message
 
-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
-"""
-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)",
-        ),
-    ],
+demo = gr.Interface(
+    fn=question_answer,
+    inputs=gr.Textbox(lines=3, placeholder="题目", label="数学题目"),
+    outputs=gr.Markdown(),
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+demo.launch(server_name="0.0.0.0", server_port=8001, share=True)