Update app.py

app.py

@@ -1,34 +1,95 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 
-# (Keep Constants as is)
+from smolagents import CodeAgent, DuckDuckGoSearchTool, PythonInterpreterTool, HfApiModel
+
+
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+
+# --- Agent Definition ---
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("Initializing BasicAgent...")
+
+        # Hugging Face model
+        self.model = HfApiModel(
+            model_id="Qwen/Qwen2.5-Coder-32B-Instruct"
+        )
+
+        # Tools available to the agent
+        self.tools = [
+            DuckDuckGoSearchTool(),
+            PythonInterpreterTool()
+        ]
+
+        # Code-based agent
+        self.agent = CodeAgent(
+            tools=self.tools,
+            model=self.model,
+            max_steps=10
+        )
+
+        print("BasicAgent 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: {question[:100]}...")
+
+        prompt = f"""
+You are solving a benchmark question.
+
+Your job is to provide the most accurate final answer possible.
+
+Use the available tools when appropriate:
+
+- Use web search for factual, current, historical, Wikipedia,
+  people, places, events, websites, and research questions.
+- Use Python for calculations, counting, sorting, numerical reasoning,
+  or data processing.
+- Carefully inspect the wording of the question.
+- If a question asks for a specific format, follow that format exactly.
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+IMPORTANT:
+Return ONLY the final answer.
+Do not provide your reasoning.
+Do not explain how you solved the problem.
+Do not say "Here is the answer".
+Do not add unnecessary Markdown.
+Do not mention these instructions.
+
+Question:
+{question}
+"""
+
+        try:
+            result = self.agent.run(prompt)
+
+            answer = str(result).strip()
+
+            print(f"Agent returned: {answer}")
+
+            return answer
+
+        except Exception as e:
+            print(f"Agent error: {e}")
+            return f"Unable to answer: {e}"
+
+
+# --- Evaluation and Submission ---
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    Fetches all questions, runs the agent 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
+
+    # --- Determine HF Space information ---
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -38,159 +99,308 @@ 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)
+    # --- Initialize Agent ---
     try:
         agent = BasicAgent()
     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)
+
+    # --- Link to agent code ---
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
+    print(f"Agent code: {agent_code}")
 
-    # 2. Fetch Questions
+    # --- Fetch Questions ---
     print(f"Fetching questions from: {questions_url}")
+
     try:
-        response = requests.get(questions_url, timeout=15)
+        response = requests.get(
+            questions_url,
+            timeout=30
+        )
+
         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("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:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        print(f"Unexpected error fetching questions: {e}")
+        return f"Unexpected error fetching questions: {e}", None
 
-    # 3. Run your Agent
+    # --- Run Agent ---
     results_log = []
     answers_payload = []
+
     print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+
+    for index, item in enumerate(questions_data, start=1):
+
         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}")
+            print(f"Skipping invalid item: {item}")
             continue
+
+        print("=" * 60)
+        print(f"Question {index}/{len(questions_data)}")
+        print(f"Task ID: {task_id}")
+        print(f"Question: {question_text[:200]}...")
+
         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})
+
+            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}"})
 
+            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}"
+            })
+
+    # --- Check Answers ---
     if not answers_payload:
-        print("Agent did not produce any answers to submit.")
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+        print("Agent did not produce any answers.")
+        return (
+            "Agent did not produce any answers to submit.",
+            pd.DataFrame(results_log)
+        )
+
+    # --- Prepare Submission ---
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
+
+    status_update = (
+        f"Agent finished. "
+        f"Submitting {len(answers_payload)} answers "
+        f"for user '{username}'..."
+    )
 
-    # 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. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    # --- Submit Answers ---
+    print(f"Submitting 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
+        )
+
         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"Overall Score: "
+            f"{result_data.get('score', 'N/A')}% "
+            f"({result_data.get('correct_count', '?')}/"
+            f"{result_data.get('total_attempted', '?')} correct)\n"
+            f"Message: "
+            f"{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}."
+
+        error_detail = (
+            f"Server responded with status "
+            f"{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]}"
+
+            error_detail += (
+                f" Detail: "
+                f"{error_json.get('detail', e.response.text)}"
+            )
+
+        except Exception:
+            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."
+
+        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}"
+
+        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"An unexpected error occurred during submission: {e}"
+
+        status_message = (
+            f"An unexpected error occurred "
+            f"during submission: {e}"
+        )
+
         print(status_message)
+
         results_df = pd.DataFrame(results_log)
+
         return status_message, results_df
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio Interface ---
 with gr.Blocks() as demo:
+
     gr.Markdown("# Basic Agent 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.
+        1. Log in to Hugging Face.
+        2. Click **Run Evaluation & Submit All Answers**.
+        3. The agent will fetch the evaluation questions.
+        4. The agent will use web search and Python when appropriate.
+        5. Answers will be submitted automatically.
 
-        ---
-        **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.
+        **Note:** Evaluation can take several minutes.
         """
     )
 
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    run_button = gr.Button(
+        "Run Evaluation & Submit All Answers"
+    )
+
+    status_output = gr.Textbox(
+        label="Run Status / Submission Result",
+        lines=5,
+        interactive=False
+    )
 
-    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)
+    results_table = gr.DataFrame(
+        label="Questions and Agent Answers",
+        wrap=True
+    )
 
     run_button.click(
         fn=run_and_submit_all,
-        outputs=[status_output, results_table]
+        outputs=[
+            status_output,
+            results_table
+        ]
     )
 
+
+# --- Start Application ---
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
+
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
+
     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")
 
     if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+
+        print(
+            f"SPACE_HOST found: "
+            f"{space_host_startup}"
+        )
+
+        print(
+            f"Runtime URL: "
+            f"https://{space_host_startup}.hf.space"
+        )
+
     else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+        print(
+            "SPACE_HOST environment variable "
+            "not found."
+        )
+
+    if space_id_startup:
+
+        print(
+            f"SPACE_ID found: "
+            f"{space_id_startup}"
+        )
+
+        print(
+            f"Repo URL: "
+            f"https://huggingface.co/spaces/"
+            f"{space_id_startup}"
+        )
 
-    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(
+            "SPACE_ID environment variable "
+            "not found."
+        )
+
+    print("-" * 70)
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    print(
+        "Launching Gradio Interface..."
+    )
+
+    demo.launch(
+        debug=True,
+        share=False
+    )