Update app.py

app.py

@@ -1,137 +1,192 @@
 import os
+import traceback
 import gradio as gr
 import requests
+import inspect
 import pandas as pd
+from smolagents import CodeAgent, DuckDuckGoSearchTool, PythonInterpreterTool, HfApiModel, LiteLLMModel, WikipediaSearchTool
+from huggingface_hub import login
+import time
 
-from smolagents import (
-    ToolCallingAgent, 
-    CodeAgent,
-    DuckDuckGoSearchTool, 
-    OpenAIServerModel
-)
-
+# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+#HF_TOKEN = os.getenv("HF_TOKEN")
+#login(HF_TOKEN)
+model = LiteLLMModel(model_id="deepseek-chat",
+                     api_key=os.getenv("DEEPSEEK_API_KEY"),
+                     base_url="https://api.deepseek.com")
 
 # --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
-        self.model = OpenAIServerModel(
-            model_id='deepseek-chat',
-            api_base="https://api.deepseek.com",
-            api_key=os.environ["DEEPSEEK_API_KEY"],
-        )
-        self.agent = ToolCallingAgent(
-            tools=[DuckDuckGoSearchTool()], 
+        print("BasicAgent initialized.")
+        # Set up model
+        self.model = model
+
+        # Initialize custom tools
+        self.tools = [
+            PythonInterpreterTool(),
+            DuckDuckGoSearchTool(),
+            WikipediaSearchTool(),
+        ]
+
+        # Create agent
+        self.agent = CodeAgent(
             model=self.model,
+            tools=self.tools,
             add_base_tools=True
         )
+        
+    def answer_question(self, question: str) -> str:
+        """Process a question and return the answer"""
+        print(f"Processing question: {question[:50]}..." if len(question) > 50 else question)
 
-        # 修改系统提示词，允许更详细的回答
-        self.agent.prompt_templates['system_prompt'] = """You are a general AI assistant. I will ask you a question.
-Your primary goal is to answer the question accurately and thoroughly.
-The 'content' field of your response message, even if it's just your thought process before a tool call, MUST be a single string or null. It MUST NOT be a list or any other sequence.
-If you are providing a direct answer without using any tools, your response content MUST be a single string.
-
-For complex questions that require detailed explanations (like describing benchmarks, datasets, or technical concepts), provide a comprehensive answer with all relevant details.
-
-Finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER].
-YOUR FINAL ANSWER can be detailed and comprehensive when the question requires it, especially for questions about technical topics, benchmarks, datasets, or concepts that need thorough explanation.
-"""
-    
-    def __call__(self, question: str) -> str:
-        # 移除所有打印语句，直接返回答案
-        return self.agent.run(question)
+        try:
+            result = self.agent.run(question)
+            # Ensure result is always a string
+            if not isinstance(result, str):
+                result = str(result)
+            return result
+        except Exception as e:
+            print(traceback.format_exc())
+            error_msg = f"Error running agent: {str(e)}"
+            return f"I encountered an issue while processing your question: {str(e)}"
 
-def run_and_submit_all(profile: gr.OAuthProfile | None):
+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")
+    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
 
     if profile:
-        username = f"{profile.username}"
+        username= f"{profile.username}"
+        print(f"User logged in: {username}")
     else:
-        return "请使用下方按钮登录Hugging Face。", None
+        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. 实例化代理
+    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
         agent = BasicAgent()
     except Exception as e:
-        return f"初始化代理时出错: {e}", None
-    
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
+    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
 
-    # 2. 获取问题
+    # 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:
-            return "获取的问题列表为空或格式无效。", None
+             print("Fetched questions list is empty.")
+             return "Fetched questions list is empty or invalid format.", None
+        print(f"Fetched {len(questions_data)} questions.")
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching questions: {e}")
+        return f"Error fetching questions: {e}", None
+    except requests.exceptions.JSONDecodeError as e:
+         print(f"Error decoding JSON response from questions endpoint: {e}")
+         print(f"Response text: {response.text[:500]}")
+         return f"Error decoding server response for questions: {e}", None
     except Exception as e:
-        return f"获取问题时出错: {e}", None
+        print(f"An unexpected error occurred fetching questions: {e}")
+        return f"An unexpected error occurred fetching questions: {e}", None
 
-    # 3. 运行代理
+    # 3. Run your Agent
     results_log = []
     answers_payload = []
-    
-    for i, item in enumerate(questions_data):
+    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:
+            print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = agent.answer_question(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:
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {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}"})
+
+        time.sleep(45)
 
     if not answers_payload:
-        return "代理未能生成任何答案。", pd.DataFrame(results_log)
+        print("Agent did not produce any answers to submit.")
+        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-    # 4. 准备提交 
+    # 4. Prepare Submission 
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
+    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    print(status_update)
 
-    # 5. 提交
+    # 5. Submit
+    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
         result_data = response.json()
         final_status = (
-            f"提交成功!\n"
-            f"用户: {result_data.get('username')}\n"
-            f"总分: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} 正确)\n"
-            f"消息: {result_data.get('message', '未收到消息。')}"
+            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.')}"
         )
+        print("Submission successful.")
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
+    except requests.exceptions.HTTPError as e:
+        error_detail = f"Server responded with status {e.response.status_code}."
+        try:
+            error_json = e.response.json()
+            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
+        except requests.exceptions.JSONDecodeError:
+            error_detail += f" Response: {e.response.text[:500]}"
+        status_message = f"Submission Failed: {error_detail}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+    except requests.exceptions.Timeout:
+        status_message = "Submission Failed: The request timed out."
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+    except requests.exceptions.RequestException as e:
+        status_message = f"Submission Failed: Network error - {e}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
     except Exception as e:
-        status_message = f"提交失败: {e}"
+        status_message = f"An unexpected error occurred during submission: {e}"
+        print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
 
-
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# LangGraph Agent Evaluation Runner")  # Updated title
+    gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
 
-        1.  Please clone this space, then modify the code in `agent.py` and `app.py` to define your agent's logic, the tools, the necessary packages, etc ...
-        2.  **Make sure you have your `DEEPSEEK_API_KEY` set as a Space Secret.**
-        3.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        4.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
+        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
+        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
 
         ---
         **Disclaimers:**
@@ -145,6 +200,7 @@ with gr.Blocks() as demo:
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
@@ -153,10 +209,10 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
+    print("\n" + "-"*30 + " App Starting " + "-"*30)
     # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID")  # Get SPACE_ID at startup
+    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -164,14 +220,14 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup:  # Print repo URLs if SPACE_ID is found
+    if space_id_startup: # Print repo URLs if SPACE_ID is found
         print(f"✅ SPACE_ID found: {space_id_startup}")
         print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
         print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
     else:
         print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
 
-    print("-" * (60 + len(" App Starting ")) + "\n")
+    print("-"*(60 + len(" App Starting ")) + "\n")
 
-    print("Launching Gradio Interface for LangGraph Agent Evaluation...")  # Updated message
-    demo.launch(debug=True, share=False, auth=None)
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    demo.launch(debug=True, share=False)