update

README.md

@@ -4,7 +4,7 @@ emoji: 💬
 colorFrom: yellow
 colorTo: purple
 sdk: gradio
-sdk_version: 5.0.1
+sdk_version: 5.30.0
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -4,20 +4,17 @@ import json
 import os
 from dotenv import load_dotenv
 
-# 加载.env文件中的环境变量
 load_dotenv()
 
-# 从环境变量中读取配置
 API_URL = os.getenv("API_URL")
 API_TOKEN = os.getenv("API_TOKEN")
 
-# 验证必要的环境变量
 if not API_URL or not API_TOKEN:
-    raise ValueError("make sure API_URL & API_TOKEN")
+    raise ValueError("invalid API_URL | API_TOKEN")
 
 print(f"[INFO] starting:")
 print(f"[INFO] API_URL: {API_URL[:6]}...{API_URL[-12:]}")
-print(f"[INFO] API_TOKEN: {API_TOKEN[:10]}...{API_TOKEN[-10:]}")  # 只显示token的前10位和后10位
+print(f"[INFO] API_TOKEN: {API_TOKEN[:10]}...{API_TOKEN[-10:]}")
 
 """
 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
@@ -25,7 +22,7 @@ For more information on `huggingface_hub` Inference API support, please check th
 
 def respond(
     message,
-    history: list[dict],  # 修改为新的消息格式
+    history: list[dict],
     system_message,
     max_tokens,
     temperature,
@@ -56,22 +53,28 @@ def respond(
     }
 
     print(f"[INFO] process user msg...")
-    print(f"[INFO] sysMsg: {system_message}")
     print(f"[INFO] userMsg: {message}")
-    print(f"[INFO] modelParam: temperature={temperature}, top_p={top_p}")
-    print(f"[INFO] reqData: {data}")
 
     try:
         with requests.post(API_URL, headers=headers, json=data) as r:
+            # print(f"[INFO] response status: {r.status_code}")
             if r.status_code == 200:
                 json_response = r.json()
+                # print(f"[INFO] response json: {json_response}")
                 if 'choices' in json_response and len(json_response['choices']) > 0:
                     content = json_response['choices'][0].get('message', {}).get('content', '')
+                    # print(f"[INFO] response content: {content}")
                     if content:
                         if '<think>' in content and '</think>' in content:
                             content = content.split('</think>')[-1].strip()
-                        print(f"[INFO] response: {content}")
+                        if '**Final Answer**' in content:
+                            content = content.split('**Final Answer**')[-1].strip()
+                        print(f"[INFO] final response: {content}")
                         return content
+                else:
+                    print(f"[ERROR] No choices in response: {json_response}")
+            else:
+                print(f"[ERROR] Bad status code: {r.status_code}, response: {r.text}")
             return "Service temporarily unavailable"
     except Exception as e:
         print(f"[ERROR] Request error: {e}")
@@ -84,7 +87,7 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are DMind AI Assistant, built by DMind.AI. Never present as Qwen, ChatGPT, Tongyi, OpenAI, etc.", label="System message"),
         gr.Slider(minimum=1, maximum=32768, value=16384, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.6, step=0.1, label="Temperature"),
         gr.Slider(
@@ -95,7 +98,7 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
-    type="messages"  # 指定使用新的消息格式
+    type="messages"
 )