Update app.py

app.py

@@ -1,196 +1,254 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 
-# (Keep Constants as is)
-# --- Constants ---
+from smolagents import (
+    CodeAgent,
+    DuckDuckGoSearchTool,
+    InferenceClientModel
+)
+
+# -----------------------------
+# Constants
+# -----------------------------
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+
+# -----------------------------
+# Smart Agent
+# -----------------------------
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+
+        print("Initializing Smart Agent...")
+
+        # Web Search Tool
+        search_tool = DuckDuckGoSearchTool()
+
+        # Free Hugging Face Model
+        model = InferenceClientModel(
+            model_id="meta-llama/Llama-3.1-8B-Instruct"
+        )
+
+        # Main Agent
+        self.agent = CodeAgent(
+            tools=[search_tool],
+            model=model,
+            add_base_tools=True,
+            max_steps=5
+        )
+
     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
-
-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") # Get the SPACE_ID for sending link to the code
+
+        print(f"Question: {question}")
+
+        prompt = f"""
+You are a GAIA benchmark assistant.
+
+IMPORTANT RULES:
+- Return ONLY the final answer
+- Do NOT explain your reasoning
+- Do NOT write 'FINAL ANSWER'
+- Keep answers short and exact
+- If the answer is a number, return only the number
+- If the answer is text, return only the text
+
+Question:
+{question}
+"""
+
+        try:
+            response = self.agent.run(prompt)
+
+            answer = str(response).strip()
+
+            print(f"Agent answer: {answer}")
+
+            return answer
+
+        except Exception as e:
+            print(f"Error while solving question: {e}")
+
+            return "Error"
+
+
+# -----------------------------
+# Main Evaluation Function
+# -----------------------------
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+
+    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.")
-        return "Please Login to Hugging Face with the button.", None
+        return "Please login with Hugging Face first.", None
 
     api_url = DEFAULT_API_URL
+
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # -----------------------------
+    # Create 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)
+
+    # -----------------------------
+    # Space Code URL
+    # -----------------------------
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+
     print(agent_code)
 
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+    # -----------------------------
+    # Fetch Questions
+    # -----------------------------
     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(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
+
+        print(f"Fetched {len(questions_data)} questions")
+
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        return f"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:
+
         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)
-            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:
-        print("Agent did not produce any answers to submit.")
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+            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:
 
-    # 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)
+            results_log.append({
+                "Task ID": task_id,
+                "Question": question_text,
+                "Submitted Answer": f"ERROR: {e}"
+            })
+
+    # -----------------------------
+    # Submit Answers
+    # -----------------------------
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
 
-    # 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
+        )
+
         response.raise_for_status()
+
         result_data = response.json()
+
         final_status = (
-            f"Submission Successful!\n"
+            f"Submission Successful!\n\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"Score: {result_data.get('score')}%\n"
+            f"Correct: {result_data.get('correct_count')}/"
+            f"{result_data.get('total_attempted')}\n\n"
+            f"Message: {result_data.get('message')}"
         )
-        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"An unexpected error occurred during submission: {e}"
-        print(status_message)
+
         results_df = pd.DataFrame(results_log)
-        return status_message, results_df
 
+        return f"Submission Failed: {e}", results_df
 
-# --- Build Gradio Interface using Blocks ---
+
+# -----------------------------
+# Gradio UI
+# -----------------------------
 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.
+    gr.Markdown("# GAIA Agent Evaluation")
 
-        ---
-        **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.
+    gr.Markdown(
         """
+Login with Hugging Face and run your AI agent on GAIA questions.
+"""
     )
 
     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="Status",
+        lines=8
+    )
 
-    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="Agent Results"
+    )
 
     run_button.click(
         fn=run_and_submit_all,
-        outputs=[status_output, results_table]
+        outputs=[
+            status_output,
+            results_table
+        ]
     )
 
-if __name__ == "__main__":
-    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
-
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    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.")
+# -----------------------------
+# Launch App
+# -----------------------------
+if __name__ == "__main__":
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    print("Starting GAIA Agent App...")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(
+        debug=True,
+        share=False
+    )