Update app.py

app.py

@@ -3,32 +3,87 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from smolagents import CodeAgent, HfApiModel
+from smolagents.tools import PythonInterpreterTool, DuckDuckGoSearchTool
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
+# --- SmolAgents Agent Definition ---
+class SmolAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("SmolAgent initializing...")
+        
+        # 初始化模型 - 使用 HuggingFace API
+        # 你需要设置你的 HF token
+        hf_token = os.getenv("HF_TOKEN")
+        if not hf_token:
+            print("Warning: HF_TOKEN not found. Please set your HuggingFace token.")
+        
+        # 使用一个强大的模型，比如 Qwen2.5-72B-Instruct
+        self.model = HfApiModel(
+            model_id="Qwen/Qwen2.5-72B-Instruct",
+            token=hf_token
+        )
+        
+        # 初始化工具
+        self.tools = [
+            PythonInterpreterTool(),
+            DuckDuckGoSearchTool(),
+        ]
+        
+        # 创建代理
+        self.agent = CodeAgent(
+            tools=self.tools,
+            model=self.model,
+            max_steps=10,
+            verbosity_level=2
+        )
+        
+        print("SmolAgent initialized successfully.")
+    
     def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        print(f"Agent received question (first 100 chars): {question[:100]}...")
+        
+        try:
+            # 构建提示，强调需要精确答案
+            enhanced_prompt = f"""
+Please answer the following question accurately and precisely. 
+Provide only the final answer without any additional text or explanation.
+If the question requires calculations, use the Python tool to ensure accuracy.
+If you need to search for information, use the search tool.
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+Question: {question}
+
+Important: Your response should contain ONLY the final answer, nothing else.
+"""
+            
+            # 运行代理
+            result = self.agent.run(enhanced_prompt)
+            
+            # 提取最终答案
+            if hasattr(result, 'content'):
+                answer = result.content.strip()
+            else:
+                answer = str(result).strip()
+            
+            print(f"Agent returning answer: {answer}")
+            return answer
+            
+        except Exception as e:
+            print(f"Error in agent execution: {e}")
+            return f"Error: {str(e)}"
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    Fetches all questions, runs the SmolAgent on them, submits all answers,
     and displays the results.
     """
     # --- Determine HF Space Runtime URL and Repo URL ---
     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:
         print("User not logged in.")
@@ -38,15 +93,16 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate Agent
     try:
-        agent = BasicAgent()
+        agent = SmolAgent()
     except Exception as e:
         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)
+        
+    # In the case of an app running as a hugging Face space, this link points toward your codebase
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
+    print(f"Agent code link: {agent_code}")
 
     # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
@@ -72,20 +128,34 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     # 3. Run your Agent
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    print(f"Running SmolAgent on {len(questions_data)} questions...")
+    
+    for i, item in enumerate(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
+            
+        print(f"Processing question {i+1}/{len(questions_data)} (Task ID: {task_id})")
+        
         try:
             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})
+            results_log.append({
+                "Task ID": task_id, 
+                "Question": question_text[:100] + "..." if len(question_text) > 100 else 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}"})
+             error_answer = f"AGENT ERROR: {e}"
+             answers_payload.append({"task_id": task_id, "submitted_answer": error_answer})
+             results_log.append({
+                 "Task ID": task_id, 
+                 "Question": question_text[:100] + "..." if len(question_text) > 100 else question_text, 
+                 "Submitted Answer": error_answer
+             })
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
@@ -93,13 +163,13 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     # 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}'..."
+    status_update = f"SmolAgent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
     print(status_update)
 
     # 5. Submit
     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
+        response = requests.post(submit_url, json=submission_data, timeout=120)  # 增加超时时间
         response.raise_for_status()
         result_data = response.json()
         final_status = (
@@ -142,28 +212,29 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# SmolAgents GAIA Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
-
-        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:**
-        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        1. Make sure you have set your HF_TOKEN environment variable in your Space settings
+        2. Log in to your Hugging Face account using the button below
+        3. Click 'Run Evaluation & Submit All Answers' to start the evaluation
+        
+        **SmolAgent Features:**
+        - Uses Qwen2.5-72B-Instruct model for reasoning
+        - Python interpreter for calculations
+        - DuckDuckGo search for information retrieval
+        - Multi-step reasoning capabilities
+        
+        **Note:** This process may take several minutes as the agent processes each question thoroughly.
         """
     )
 
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
 
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=8, interactive=False)
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
@@ -172,10 +243,12 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
+    print("\n" + "-"*30 + " SmolAgent App Starting " + "-"*30)
+    
+    # Check for required environment variables
     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")
+    hf_token = os.getenv("HF_TOKEN")
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -183,14 +256,19 @@ 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(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.")
+    
+    if hf_token:
+        print("✅ HF_TOKEN found.")
+    else:
+        print("⚠️  HF_TOKEN environment variable not found. Please set it in your Space settings.")
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    print("-"*(60 + len(" SmolAgent App Starting ")) + "\n")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    print("Launching Gradio Interface for SmolAgent GAIA Evaluation...")
     demo.launch(debug=True, share=False)