Update app.py

app.py

@@ -2,160 +2,120 @@ import os
 import gradio as gr
 import requests
 import pandas as pd
-from smolagents import CodeAgent, HfApiModel, DuckDuckGoSearchTool, LiteLLMModel
+from smolagents import CodeAgent, HfApiModel, DuckDuckGoSearchTool
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 # --- Basic Agent Definition ---
-# ----- 這裡我們使用 smolagents 來打造強力 Agent ------
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
         
-        # 1. 設定模型：使用 Hugging Face 的免費 Inference API
-        # Qwen2.5-Coder 是目前免費 API 中寫程式和邏輯最強的模型之一
+        # 1. 設定模型：不設定 Token，嘗試使用匿名存取
+        # 注意：沒有 Token 比較容易遇到 Rate Limit (429 Error)
         model_id = "Qwen/Qwen2.5-Coder-32B-Instruct"
         
-        self.model = HfApiModel(
-            model_id=model_id,
-            token=os.getenv("HF_TOKEN") # 確保你的 Space Settings 裡有設定 HF_TOKEN
-        )
+        try:
+            # 這裡移除了 token=os.getenv("HF_TOKEN")
+            self.model = HfApiModel(model_id=model_id)
+        except Exception as e:
+            print(f"Model init warning: {e}")
+            self.model = None
         
-        # 2. 設定工具：加入搜尋工具 (DuckDuckGo)
-        # 這能幫助解決 Wikipedia 和 影片內容的問題
+        # 2. 設定工具
         search_tool = DuckDuckGoSearchTool()
         
         # 3. 建立 Agent
-        # CodeAgent 會嘗試寫 Python 程式碼來解決問題，這對數學/集合論題目非常有效
-        self.agent = CodeAgent(
-            tools=[search_tool], 
-            model=self.model,
-            add_base_tools=True, # 加入基本工具 (如 Python 解譯器)
-            max_steps=4 # 限制步數避免超時
-        )
+        if self.model:
+            self.agent = CodeAgent(
+                tools=[search_tool], 
+                model=self.model,
+                add_base_tools=True,
+                max_steps=4 # 步數少一點以避免超時
+            )
+        else:
+            self.agent = None
 
     def __call__(self, question: str) -> str:
         print(f"Agent received question: {question}")
+        
+        # 防呆機制：如果 Agent 初始化失敗，或是跑的過程出錯，回傳預設答案
+        if not self.agent:
+            return "Agent not initialized correctly."
+
         try:
-            # 讓 Agent 思考並執行
-            # 我們加入提示讓它知道可以使用工具
+            # 嘗試讓 Agent 思考並執行
             answer = self.agent.run(question)
             print(f"Agent answer: {answer}")
             return str(answer)
         except Exception as e:
-            print(f"Error during agent run: {e}")
-            return "I could not answer the question due to an internal error."
+            print(f"Error during agent run (Likely Rate Limit or Auth): {e}")
+            # 如果因為沒 Token 導致失敗，回傳一個安全答案，而不是讓程式崩潰
+            return "I could not answer due to anonymous rate limits. Please set HF_TOKEN for better results."
 
-# --- 下面是原本的評估邏輯，基本保持不變 ---
+# --- 以下是評測跑分邏輯 (不用動) ---
 
 def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
-    # --- Determine HF Space Runtime URL and Repo URL ---
     space_id = os.getenv("SPACE_ID")
-
     if profile:
         username= f"{profile.username}"
-        print(f"User logged in: {username}")
     else:
-        print("User not logged in.")
         return "Please Login to Hugging Face with the button.", None
 
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent
     try:
         agent = BasicAgent()
     except Exception as e:
-        print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
         
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
 
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
-        response.raise_for_status()
         questions_data = response.json()
-        if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
-        print(f"Fetched {len(questions_data)} questions.")
     except Exception as e:
-        print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
 
-    # 3. Run your Agent
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
     
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
-        
-        if not task_id or question_text is None:
-            continue
+        if not task_id or question_text is None: continue
             
         try:
-            print(f"Processing Task: {task_id}")
             submitted_answer = agent(question_text)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
         except Exception as e:
-             print(f"Error running agent on task {task_id}: {e}")
              results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
 
-    if not answers_payload:
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
-
-    # 4. Prepare Submission 
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    print(f"Submitting {len(answers_payload)} answers...")
 
-    # 5. Submit
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
-        response.raise_for_status()
         result_data = response.json()
         final_status = (
-            f"Submission Successful!\n"
-            f"User: {result_data.get('username')}\n"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
-            f"Message: {result_data.get('message', 'No message received.')}"
+            f"Submission Successful! Score: {result_data.get('score', 'N/A')}%\n"
+            f"Message: {result_data.get('message', 'No message.')}"
         )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
+        return final_status, pd.DataFrame(results_log)
     except Exception as e:
-        status_message = f"Submission Failed: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
 
-
-# --- Build Gradio Interface ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Agent Evaluation Runner (SmolAgents Powered)")
-    gr.Markdown("**Note:** This agent uses Qwen2.5-Coder and DuckDuckGo Search to solve the tasks.")
-    
+    gr.Markdown("# Agent Evaluation (No Token Version)")
     gr.LoginButton()
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+    run_button = gr.Button("Run Evaluation")
+    status_output = gr.Textbox(label="Status", lines=4)
+    results_table = gr.DataFrame(label="Results")
 
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 if __name__ == "__main__":
-    demo.launch(debug=True)
+    demo.launch()