Upload 3 files

README.md

@@ -16,7 +16,7 @@ A Gradio-based AI-powered web application for querying SEC financial data throug
 
 ## ✨ Features
 
-- 🤖 **Intelligent AI Assistant**: Chat naturally with **Qwen/Qwen2.5-VL-72B-Instruct:nebius** model
+- 🤖 **Intelligent AI Assistant**: Chat naturally with **Qwen/Qwen2.5-72B-Instruct** model (supports tool calling)
 - 🛠️ **Automatic Tool Calling**: AI automatically selects and calls MCP tools based on your questions
 - 🔍 Search companies by name or ticker symbol
 - 📈 View latest financial data
@@ -96,7 +96,7 @@ SEC EDGAR data via MCP Server: https://huggingface.co/spaces/JC321/EasyReportDat
 
 - **Frontend**: Gradio 6.0.1
 - **Backend**: Python with requests
-- **AI Model**: Qwen/Qwen2.5-VL-72B-Instruct:nebius (via Hugging Face Inference API)
+- **AI Model**: Qwen/Qwen2.5-72B-Instruct (via Hugging Face Inference API)
 - **MCP Protocol**: FastMCP with HTTP transport (stateless)
 - **Data Source**: SEC EDGAR via MCP Server
 

app.py

@@ -35,19 +35,22 @@ def create_session_with_retry():
 session = create_session_with_retry()
 
 # 初始化 Hugging Face Inference Client
-# 使用 Qwen/Qwen2.5-VL-72B-Instruct:nebius 模型（更强大的视觉语言模型）
+# 使用 Qwen/Qwen2.5-72B-Instruct 模型（支持 tool calling）
 try:
     # Hugging Face Space 会自动提供 HF_TOKEN 环境变量
-    # 无需手动配置 Secret！
-    hf_token = os.environ.get("HF_TOKEN")
+    # 也支持手动在 Settings > Secrets 中配置 HF_TOKEN
+    hf_token = os.environ.get("HF_TOKEN") or os.environ.get("HUGGING_FACE_HUB_TOKEN")
+    
     if hf_token:
         client = InferenceClient(api_key=hf_token)
-        print(f"✅ Hugging Face client initialized with Qwen/Qwen2.5-VL-72B-Instruct:nebius model")
-        print(f"   Using auto-generated HF Space token")
+        print(f"✅ Hugging Face client initialized with Qwen/Qwen2.5-72B-Instruct model")
+        print(f"   Using authenticated access (HF_TOKEN detected)")
     else:
-        # 如果没有 token，使用无认证模式（免费层，有限制）
+        # 如果没有 token，使用无认证模式（免费层，有速率限制）
         client = InferenceClient()
         print("⚠️ Using Hugging Face Inference API without authentication (rate limited)")
+        print("💡 To remove rate limits, add HF_TOKEN in Space Settings > Repository secrets")
+        print("   Get your token from: https://huggingface.co/settings/tokens")
 except Exception as e:
     print(f"❌ Warning: Failed to initialize Hugging Face client: {e}")
     client = None
@@ -679,11 +682,11 @@ You can handle any financial question - from simple data queries to complex mult
                 
                 response = client.chat_completion(
                     messages=messages,
-                    model="Qwen/Qwen2.5-VL-72B-Instruct:nebius",  # 使用更强大的视觉语言模型
+                    model="Qwen/Qwen2.5-72B-Instruct",  # 支持 tool calling
                     tools=MCP_TOOLS,
                     max_tokens=3000,
                     temperature=0.7,
-                    tool_choice="auto"  # 让模型自动决定是否使用工具
+                    tool_choice="auto"
                 )
                 
                 print(f"✅ LLM response received (iteration {iteration})")
@@ -745,7 +748,7 @@ You can handle any financial question - from simple data queries to complex mult
                     try:
                         response = client.chat_completion(
                             messages=messages,
-                            model="Qwen/Qwen2.5-VL-72B-Instruct:nebius",
+                            model="Qwen/Qwen2.5-72B-Instruct",
                             max_tokens=3000,
                             temperature=0.7
                         )
@@ -760,7 +763,7 @@ You can handle any financial question - from simple data queries to complex mult
         final_response = ""
         
         # 显示调试信息：使用的模型
-        final_response += f"<div style='padding: 8px; background: #e3f2fd; border-left: 3px solid #2196f3; margin-bottom: 10px; font-size: 0.9em;'>🤖 <strong>Model:</strong> Qwen/Qwen2.5-VL-72B-Instruct:nebius | <strong>Iterations:</strong> {iteration}</div>\n\n"
+        final_response += f"<div style='padding: 8px; background: #e3f2fd; border-left: 3px solid #2196f3; margin-bottom: 10px; font-size: 0.9em;'>🤖 <strong>Model:</strong> Qwen/Qwen2.5-72B-Instruct | <strong>Iterations:</strong> {iteration}</div>\n\n"
         
         # 如果有工具调用，显示调用日志
         if tool_calls_log:
@@ -844,7 +847,7 @@ with gr.Blocks(title="SEC Financial Data Query Assistant") as demo:
     # 显示 AI 功能说明
     gr.Markdown("""
     <div style='padding: 15px; background: #d4edda; border-left: 4px solid #28a745; margin: 10px 0; border-radius: 4px;'>
-        <strong>✅ AI Assistant Enabled:</strong> Powered by Qwen/Qwen2.5-VL-72B-Instruct:nebius model with automatic MCP tool calling.
+        <strong>✅ AI Assistant Enabled:</strong> Powered by Qwen/Qwen2.5-72B-Instruct model with automatic MCP tool calling.
         <br>
         <strong>💬 Ask me anything:</strong> I can understand natural language and automatically fetch financial data when needed!
     </div>
@@ -924,5 +927,6 @@ if __name__ == "__main__":
     demo.launch(
         server_name="0.0.0.0",
         server_port=7860,
-        show_error=True
+        show_error=True,
+        ssr_mode=False  # 禁用 SSR 模式，避免 asyncio 文件描述符错误
     )