feat: modularized code

.gitignore

@@ -0,0 +1,6 @@
+.venv
+.env
+.vscode/
+.idea/
+.DS_Store
+.gitattributes

README.md

@@ -1,5 +1,5 @@
 ---
-title: Template Final Assignment
+title: GAIA - Agents Course Assignment
 emoji: 🕵🏻‍♂️
 colorFrom: indigo
 colorTo: indigo
@@ -9,7 +9,7 @@ app_file: app.py
 pinned: false
 hf_oauth: true
 # optional, default duration is 8 hours/480 minutes. Max duration is 30 days/43200 minutes.
-hf_oauth_expiration_minutes: 480
+hf_oauth_expiration_minutes: 567
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,160 +1,96 @@
 import os
+
+import gaia_agent
 import gradio as gr
-import requests
-import inspect
+import logic
 import pandas as pd
+from dotenv import load_dotenv
 
-# (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:
-    def __init__(self):
-        print("BasicAgent initialized.")
-    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,
+load_dotenv()
+
+
+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
 
+    Args:
+        profile: An optional gr.OAuthProfile object containing user information
+            if the user is logged in. If None, the user is not logged in.
+
+    Returns:
+        tuple[str, pd.DataFrame | None]: A tuple containing:
+            - A string representing the status of the run and submission process.
+              This could be a success message, an error message, or a message
+              indicating that no answers were produced.
+            - A pandas DataFrame containing the results log. This DataFrame will
+              be displayed in the Gradio interface. It can be None if an error
+              occurred before the agent was run.
+    """
+    # 0. Get user details
+    space_id = os.getenv("SPACE_ID")
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
     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
 
-    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)
+    # 1. Instantiate Agent
     try:
-        agent = BasicAgent()
+        agent = gaia_agent.GaiaAgent()
     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}")
     try:
-        response = requests.get(questions_url, timeout=15)
-        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
+        questions_data = logic.fetch_all_questions()
     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
-    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}"})
+        return str(e), None
 
+    # 3. Run the Agent
+    results_log, answers_payload = logic.run_agent(agent, questions_data)
     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)
 
-    # 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}")
-    try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
-        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)
-        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
+    # 4. Prepare & Submit Answers
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload,
+    }
+    print(
+        f"Agent finished. Submitting {len(answers_payload)} answers for user '"
+        f"{username}'..."
+    )
+    return logic.submit_answers(submission_data, results_log)
 
 
 # --- Build Gradio Interface using Blocks ---
-with gr.Blocks() as demo:
+with gr.Blocks() as gaia_ui:
     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.  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.
+        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 separate action or even to answer the questions in async.
         """
     )
 
@@ -162,20 +98,21 @@ 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)
+    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(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
+        fn=run_and_submit_all, inputs=None, outputs=[status_output, results_table]
     )
 
 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}")
@@ -183,14 +120,20 @@ 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")
+        print(
+            f"   Repo Tree URL: https://huggingface.co/spaces/"
+            f"{space_id_startup}/tree/main"
+        )
     else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+        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 Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    gaia_ui.launch(debug=True, share=False)

gaia_agent.py

@@ -0,0 +1,33 @@
+class GaiaAgent:
+    """
+    A basic agent that receives a question and returns a fixed answer.
+
+    This class serves as a placeholder or a simple baseline agent for testing
+    and demonstration purposes. It does not perform any sophisticated
+    reasoning or information retrieval.
+    """
+
+    def __init__(self):
+        """
+        Initializes the GaiaAgent.
+
+        Currently, this constructor simply prints a message to the console.
+        In a more complex implementation, this method might load a model,
+        connect to a database, or perform other setup tasks.
+        """
+        print("BasicAgent initialized.")
+
+    def __call__(self, question: str) -> str:
+        """
+        Processes a question and returns a fixed answer.
+
+        Args:
+            question: The question to be processed.
+
+        Returns:
+            A fixed string representing the agent's answer.
+        """
+        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

logic.py

@@ -0,0 +1,163 @@
+from typing import Dict, List, Tuple
+
+import pandas as pd
+import requests
+from gaia_agent import GaiaAgent
+from pandas import DataFrame
+
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+QUESTIONS_URL = f"{DEFAULT_API_URL}/questions"
+SUBMIT_URL = f"{DEFAULT_API_URL}/submit"
+
+
+# --- Helper Methods ---
+def fetch_all_questions() -> Dict:
+    """Fetches all questions from the specified API endpoint.
+
+    This function retrieves a list of questions from the API, handles potential errors
+    such as network issues, invalid responses, or empty question lists, and returns
+    the questions as a dictionary.
+
+    Returns:
+        Dict: A dictionary containing the questions data retrieved from the API.
+
+    Raises:
+        UserWarning: If there is an error fetching the questions, such as network issues,
+            invalid JSON response, or an empty question list.  The exception message
+            provides details about the specific error encountered.
+    """
+    print(f"Fetching questions from: {QUESTIONS_URL}")
+    response = requests.get(QUESTIONS_URL, timeout=15)
+    try:
+        response.raise_for_status()
+        questions_data = response.json()
+        if not questions_data:
+            print("Fetched questions list is empty.")
+            raise UserWarning("Fetched questions list is empty or invalid format.")
+        print(f"Fetched {len(questions_data)} questions.")
+        return questions_data
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching questions: {e}")
+        raise UserWarning(f"Error fetching questions: {e}")
+    except requests.exceptions.JSONDecodeError as e:
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        print(f"Response text: {response.text[:500]}")
+        raise UserWarning(f"Error decoding server response for questions: {e}")
+    except Exception as e:
+        print(f"An unexpected error occurred fetching questions: {e}")
+        raise UserWarning(f"An unexpected error occurred fetching questions: {e}")
+
+
+def submit_answers(submission_data: dict, results_log: list) -> Tuple[str, DataFrame]:
+    """Submits answers to the scoring API and returns the submission status and results.
+
+    This function sends the provided answers to the scoring API, handles potential errors
+    such as network issues, server errors, or invalid responses, and returns a status
+    message indicating the success or failure of the submission, along with a DataFrame
+    containing the results log.
+
+    Args:
+        submission_data (dict): A dictionary containing the answers to be submitted.
+            Expected to have a structure compatible with the scoring API.
+        results_log (list): A list of dictionaries containing the results log.
+            This log is converted to a Pandas DataFrame and returned.
+
+    Returns:
+        Tuple[str, DataFrame]: A tuple containing:
+            - A status message (str) indicating the submission status and any relevant
+              information or error messages.
+            - A Pandas DataFrame containing the results log.
+
+    """
+    try:
+        response = requests.post(SUBMIT_URL, json=submission_data, timeout=60)
+        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', '?')}/"
+            f"{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"An unexpected error occurred during submission: {e}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+
+
+def run_agent(agent: GaiaAgent, 
+              questions_data: List[Dict]) -> Tuple[List[Dict], List[Dict]]:
+    """Runs the agent on a list of questions and returns the results and answers.
+
+    This function iterates through a list of questions, runs the provided agent on each
+    question, and collects the results and answers. It handles potential errors during
+    agent execution and returns the results log and the answers payload.
+
+    Args:
+        agent (GaiaAgent): An instance of the GaiaAgent class, which is responsible for
+            generating answers to the questions.
+        questions_data (List[Dict]): A list of dictionaries, where each dictionary
+            represents a question and contains at least the 'task_id' and 'question' keys.
+
+    Returns:
+        Tuple[List[Dict], List[Dict]]: A tuple containing:
+            - A list of dictionaries representing the results log, where each dictionary
+              contains the 'Task ID', 'Question', and 'Submitted Answer'.
+            - A list of dictionaries representing the answers payload, where each dictionary
+              contains the 'task_id' and 'submitted_answer'.
+    """
+    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 invalid item (missing task_id or question): {item}")
+            continue
+        try:
+            submitted_answer = agent(question_text)
+            answers_payload.append(
+                {"task_id": task_id, "submitted_answer": submitted_answer}
+            )
+        except Exception as e:
+            print(f"❌ Error running agent on task {task_id}: {e}")
+            submitted_answer = f"AGENT ERROR: {e}"
+
+        results_log.append(
+            {
+                "Task ID": task_id,
+                "Question": question_text,
+                "Submitted Answer": submitted_answer,
+            }
+        )
+    return results_log, answers_payload

requirements.txt

@@ -1,2 +1,5 @@
 gradio
-requests
+gradio[oauth]
+requests
+python-dotenv
+pandas