Upload 2 files

README.md

@@ -12,28 +12,88 @@ license: mit
 
 # SEC Financial Data Query Assistant
 
-A Gradio-based web application for querying SEC financial data through MCP Server.
+A Gradio-based AI-powered web application for querying SEC financial data through MCP Server.
 
-## Features
+## ✨ Features
 
+- 🤖 **Intelligent AI Assistant**: Chat naturally with Qwen/Qwen2.5-72B-Instruct model
+- 🛠️ **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
 - 📊 Analyze 3-year and 5-year financial trends
 - 💰 Display revenue, net income, EPS, operating expenses, and cash flow metrics
+- 📝 List company SEC filings
 
-## Usage
+## 🚀 Quick Start
 
-Simply enter a company name or ticker symbol (e.g., NVIDIA, AAPL, Microsoft) and select the query type:
-- **Latest Financial Data**: Shows the most recent fiscal year data
-- **3-Year Trend**: Displays financial trends over 3 years
-- **5-Year Trend**: Displays financial trends over 5 years
+No configuration needed! Just start asking questions:
 
-## Data Source
+### AI Assistant Tab
+
+Ask natural language questions:
+- "Show me Apple's latest financial data"
+- "What's NVIDIA's 3-year trend?"
+- "Compare Tesla's revenue with expenses"
+- "How is Microsoft performing?"
+- "Give me Alibaba's financial overview"
+
+The AI will automatically:
+1. 🧠 Understand your question
+2. 🔧 Call the appropriate MCP tools
+3. 📊 Analyze the data
+4. 💬 Provide a comprehensive answer
+
+### Direct Query Tab
+
+For structured queries:
+- Enter company name or ticker symbol (e.g., NVIDIA, AAPL, Microsoft)
+- Select query type:
+  - **Latest Financial Data**: Most recent fiscal year data
+  - **3-Year Trends**: Financial trends over 3 years
+  - **5-Year Trends**: Financial trends over 5 years
+  - **Company Filings**: List of SEC filings
+
+## 📊 Example Questions
+
+**General inquiries:**
+- "What can you tell me about Apple?"
+- "How is Tesla doing financially?"
+
+**Specific data:**
+- "Show me NVIDIA's revenue for the last 3 years"
+- "What's Microsoft's latest EPS?"
+
+**Comparisons:**
+- "Compare Amazon's revenue and expenses"
+- "How does Google's cash flow look?"
+
+**Trends:**
+- "Give me a 5-year financial overview of Alibaba"
+- "Show me Meta's financial trends"
+
+## 💾 Data Source
 
 SEC EDGAR data via MCP Server: https://huggingface.co/spaces/JC321/EasyReportDateMCP
 
-## Technology Stack
+## 🛠️ Technology Stack
 
-- **Frontend**: Gradio 4.0+
+- **Frontend**: Gradio 6.0.1
 - **Backend**: Python with requests
+- **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
+
+## 💡 Tips
+
+- The AI understands context, so you can ask follow-up questions
+- You can ask about multiple companies in one conversation
+- Both company names and ticker symbols work (e.g., "Apple" or "AAPL")
+- The AI will show which tools it used to answer your question
+
+## 👍 Supported Companies
+
+All US-listed companies in SEC EDGAR database, including:
+- Tech: Apple, Microsoft, NVIDIA, Google, Meta, Amazon, Tesla
+- Finance: JPMorgan, Bank of America, Goldman Sachs
+- Retail: Walmart, Target, Costco
+- And many more...

app.py

@@ -35,25 +35,13 @@ def create_session_with_retry():
 session = create_session_with_retry()
 
 # 初始化 Hugging Face Inference Client
-# 使用环境变量或者免费的公开模型
-HF_TOKEN = os.getenv("HF_TOKEN", None)  # 可选：如果需要访问私有模型
-
-# 尝试初始化 client
-if HF_TOKEN:
-    try:
-        client = InferenceClient(token=HF_TOKEN)
-        print("✅ Hugging Face client initialized successfully with token")
-    except Exception as e:
-        print(f"⚠️ Warning: Failed to initialize Hugging Face client with token: {e}")
-        client = None
-else:
-    # 没有 token，使用公开访问（有速率限制）
-    try:
-        client = InferenceClient()
-        print("⚠️ Using Hugging Face client without token (rate limited)")
-    except Exception as e:
-        print(f"❌ Warning: Failed to initialize Hugging Face client: {e}")
-        client = None
+# 直接使用免费的公开 API，无需 token
+try:
+    client = InferenceClient()
+    print("✅ Hugging Face client initialized (free tier)")
+except Exception as e:
+    print(f"❌ Warning: Failed to initialize Hugging Face client: {e}")
+    client = None
 
 # 定义可用的 MCP 工具
 MCP_TOOLS = [
@@ -733,17 +721,17 @@ Always be helpful, accurate, and cite the data sources when providing financial
                     break
                     
             except ValueError as ve:
-                # API Key 相关错误
+                # API Key 相关错误（虽然我们不使用 token，但仍然可能出现）
                 error_msg = str(ve)
                 if "api_key" in error_msg.lower() or "token" in error_msg.lower():
-                    print(f"❌ LLM API authentication error: {ve}")
+                    print(f"⚠️ LLM API rate limit or authentication issue: {ve}")
                     print("ℹ️ Falling back to simple response logic")
                     return fallback_chatbot_response(message)
                 else:
                     raise
             except Exception as e:
-                # 其他 LLM API 错误
-                print(f"❌ LLM API error: {e}")
+                # 其他 LLM API 错误（如速率限制）
+                print(f"⚠️ LLM API error (possibly rate limited): {e}")
                 print("ℹ️ Falling back to simple response logic")
                 return fallback_chatbot_response(message)
         
@@ -826,29 +814,14 @@ def query_with_status(company, query_type):
 with gr.Blocks(title="SEC Financial Data Query Assistant") as demo:
     gr.Markdown("# 🤖 SEC Financial Data Query Assistant")
     
-    # 显示 HF_TOKEN 状态提示
-    if not HF_TOKEN:
-        gr.Markdown("""
-        <div style='padding: 15px; background: #fff3cd; border-left: 4px solid #ffc107; margin: 10px 0; border-radius: 4px;'>
-            <strong>⚠️ Note:</strong> AI Assistant is running in <strong>rate-limited mode</strong> without HF_TOKEN. 
-            For better performance, set the <code>HF_TOKEN</code> environment variable in your Space settings.
-            <br><br>
-            <strong>How to get your token:</strong>
-            <ol>
-                <li>Go to <a href="https://huggingface.co/settings/tokens" target="_blank">Hugging Face Tokens</a></li>
-                <li>Create a new token (Read access is sufficient)</li>
-                <li>Add it as a Secret in your Space settings: Settings → Repository secrets → New secret</li>
-                <li>Name: <code>HF_TOKEN</code>, Value: <code>your_token_here</code></li>
-                <li>Restart the Space</li>
-            </ol>
-        </div>
-        """)
-    else:
-        gr.Markdown("""
-        <div style='padding: 15px; background: #d4edda; border-left: 4px solid #28a745; margin: 10px 0; border-radius: 4px;'>
-            <strong>✅ AI Mode Active:</strong> Full LLM capabilities enabled with Qwen/Qwen2.5-72B-Instruct model.
-        </div>
-        """)
+    # 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/Qwen2.5-72B-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>
+    """)
     
     with gr.Tab("AI Assistant"):
         # 使用 Gradio ChatInterface（兼容 4.44.1）