Update app.py

app.py

@@ -1,196 +1,404 @@
 import os
+import re
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 
-# (Keep Constants as is)
-# --- Constants ---
+from smolagents import CodeAgent, InferenceClientModel, WebSearchTool
+
+
+# ---------------------------------------------------------
+# Configuration
+# ---------------------------------------------------------
+
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+MODEL_ID = "Qwen/Qwen2.5-Coder-32B-Instruct"
+
+
+# ---------------------------------------------------------
+# GAIA Agent
+# ---------------------------------------------------------
+
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("Initializing GAIA agent...")
+
+        hf_token = os.getenv("HF_TOKEN")
+
+        if not hf_token:
+            raise ValueError(
+                "HF_TOKEN is missing. Add it in "
+                "Settings → Variables and secrets."
+            )
+
+        self.model = InferenceClientModel(
+            model_id=MODEL_ID,
+            token=hf_token,
+        )
+
+        self.agent = CodeAgent(
+            tools=[
+                WebSearchTool(),
+            ],
+            model=self.model,
+            max_steps=12,
+            additional_authorized_imports=[
+                "math",
+                "statistics",
+                "datetime",
+                "re",
+                "json",
+            ],
+            instructions="""
+You are an AI agent solving Level 1 GAIA benchmark questions.
+
+Carefully solve each question using web search and Python when needed.
+
+Important rules:
+
+1. Search the web for factual or obscure information.
+2. Verify important facts before answering.
+3. Use Python for calculations when useful.
+4. Follow the answer format requested in the question exactly.
+5. Return only the final requested answer.
+6. Do not include explanations, reasoning, citations, or introductions.
+7. Do not write "FINAL ANSWER".
+8. Do not write "The answer is".
+9. Preserve requested capitalization, ordering, punctuation, units,
+   separators, singular/plural forms, and date formats.
+""",
+        )
+
+        print("GAIA agent initialized successfully.")
+
+    @staticmethod
+    def clean_answer(answer) -> str:
+        """
+        Remove common prefixes that can cause exact-match failure.
+        """
+
+        text = str(answer).strip()
+
+        unwanted_prefixes = [
+            r"^final answer\s*:\s*",
+            r"^answer\s*:\s*",
+            r"^the answer is\s*",
+        ]
+
+        for pattern in unwanted_prefixes:
+            text = re.sub(
+                pattern,
+                "",
+                text,
+                flags=re.IGNORECASE,
+            ).strip()
+
+        # Remove accidental surrounding quotation marks.
+        if (
+            len(text) >= 2
+            and text[0] == text[-1]
+            and text[0] in {"'", '"'}
+        ):
+            text = text[1:-1].strip()
+
+        return text
+
     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"Question received: {question[:100]}...")
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+        prompt = f"""
+Solve this GAIA benchmark question carefully.
+
+Question:
+{question}
+
+Use web search and Python tools when necessary.
+
+Return only the exact answer requested by the question.
+Do not include an explanation.
+Do not include citations.
+Do not write FINAL ANSWER.
+Do not write "The answer is".
+"""
+
+        result = self.agent.run(prompt)
+
+        cleaned_answer = self.clean_answer(result)
+
+        print(f"Agent answer: {cleaned_answer}")
+
+        return cleaned_answer
+
+
+# ---------------------------------------------------------
+# 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.
+    Fetch all GAIA questions, run the agent, submit the answers,
+    and display the score.
     """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
+        username = profile.username
+        print(f"Logged-in user: {username}")
     else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+        return (
+            "Please log in to Hugging Face using the login button.",
+            None,
+        )
+
+    if not space_id:
+        return (
+            "SPACE_ID was not found. Make sure this app is running "
+            "inside a Hugging Face Space.",
+            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)
+    # 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)
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
-
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+    except Exception as error:
+        print(f"Agent initialization error: {error}")
+
+        return (
+            f"Error initializing agent: {error}",
+            None,
+        )
+
+    agent_code = (
+        f"https://huggingface.co/spaces/"
+        f"{space_id}/tree/main"
+    )
+
+    print(f"Agent code URL: {agent_code}")
+
+    # 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
+            return (
+                "The questions list is empty.",
+                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
-
-    # 3. Run your Agent
+
+    except requests.exceptions.RequestException as error:
+        return (
+            f"Error fetching questions: {error}",
+            None,
+        )
+
+    except ValueError as error:
+        return (
+            f"Invalid response from questions API: {error}",
+            None,
+        )
+
+    # Run the agent.
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+
+    for question_number, 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}")
+
+        if not task_id or not question_text:
+            print(f"Skipping invalid question item: {item}")
             continue
+
+        print(
+            f"Processing question "
+            f"{question_number}/{len(questions_data)}"
+        )
+
         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}"})
+
+        except Exception as error:
+            print(
+                f"Error on task {task_id}: {error}"
+            )
+
+            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,
+            }
+        )
+
+    results_df = pd.DataFrame(results_log)
 
     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)
+        return (
+            "The agent did not produce any answers.",
+            results_df,
+        )
+
+    # Prepare submission.
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload,
+    }
 
-    # 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)
+    print(
+        f"Submitting {len(answers_payload)} answers "
+        f"for {username}."
+    )
 
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    # Submit answers.
     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.')}"
-        )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
+            "Submission Successful!\n\n"
+            f"User: {result_data.get('username', username)}\n"
+            f"Overall Score: "
+            f"{result_data.get('score', 'N/A')}%\n"
+            f"Correct Answers: "
+            f"{result_data.get('correct_count', '?')}/"
+            f"{result_data.get('total_attempted', '?')}\n"
+            f"Message: "
+            f"{result_data.get('message', 'No message received.')}"
+        )
+
         return final_status, results_df
-    except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
+
+    except requests.exceptions.HTTPError as error:
+        error_detail = (
+            f"Server returned status "
+            f"{error.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
+            error_json = error.response.json()
+            error_detail += (
+                f"\nDetails: "
+                f"{error_json.get('detail', error.response.text)}"
+            )
+
+        except ValueError:
+            error_detail += (
+                f"\nResponse: "
+                f"{error.response.text[:500]}"
+            )
+
+        return (
+            f"Submission failed.\n{error_detail}",
+            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
-
-
-# --- Build Gradio Interface using Blocks ---
+        return (
+            "Submission failed because the request timed out.",
+            results_df,
+        )
+
+    except requests.exceptions.RequestException as error:
+        return (
+            f"Submission failed because of a network error: {error}",
+            results_df,
+        )
+
+    except Exception as error:
+        return (
+            f"Unexpected submission error: {error}",
+            results_df,
+        )
+
+
+# ---------------------------------------------------------
+# Gradio interface
+# ---------------------------------------------------------
+
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# GAIA Agent Evaluation Runner")
+
     gr.Markdown(
         """
-        **Instructions:**
+        ### 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 using your Hugging Face account.
+        2. Click **Run Evaluation & Submit All Answers**.
+        3. The agent will solve all 20 GAIA questions.
+        4. Your 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.
+        The target score for the course certificate is **30% or higher**.
         """
     )
 
     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=8,
+        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,
+        ],
     )
 
-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.")
+# ---------------------------------------------------------
+# Start application
+# ---------------------------------------------------------
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+if __name__ == "__main__":
+    print("Starting GAIA Agent Evaluation Runner...")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(
+        debug=True,
+        share=False,
+    )