Integrate ModularGAIAAgent into evaluation runner architecture

app.py

@@ -19,100 +19,85 @@ agent = ModularGAIAAgent()
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+# --- Advanced Modular Agent Integration ---
 class BasicAgent:
     def __init__(self):
         print("BasicAgent (GAIA Modular Agent) initialized.")
         self.agent = ModularGAIAAgent()
-    def __call__(self, question: str) -> str:
+    def __call__(self, question: str, file_name: str = "") -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
         try:
-            answer, trace = self.agent.answer_question({"task_id": "manual", "question": question, "file_name": ""})
+            answer, trace = self.agent.answer_question({"task_id": "manual", "question": question, "file_name": file_name})
             print(f"Agent returning answer: {answer}")
             return answer
         except Exception as e:
             print(f"Agent error: {e}")
             return f"AGENT ERROR: {e}"
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+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
-
+    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
-
     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)
     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}")
     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("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"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
     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")
+        file_name = item.get("file_name", "")
         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)
+            submitted_answer = agent(question_text, file_name)
             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}"})
     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)
@@ -123,8 +108,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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"Message: {result_data.get('message', 'No message received.')}")
         print("Submission successful.")
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
@@ -155,75 +139,44 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
-def show_help():
-    return (
-        "# Agent Capabilities\n"
-        "- Multi-modal QA (text, audio, image, code, table, YouTube/video)\n"
-        "- File download and analysis from API\n"
-        "- Advanced video QA: object detection, captioning, ASR\n"
-        "- Secure code execution\n"
-        "- Robust error handling and logging\n"
-        "- GAIA-compliant output\n"
-        "\nSee README.md for full details."
+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.
+        ---
+        **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.LoginButton()
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+    run_button.click(
+        fn=run_and_submit_all,
+        outputs=[status_output, results_table]
     )
-
-def submit_answers(username, agent_code_url):
-    # Placeholder for submission logic
-    return f"Submission for {username} with code {agent_code_url} (not implemented in demo)"
-
-def show_leaderboard():
-    # Placeholder for leaderboard logic
-    return "Leaderboard feature coming soon."
-
-demo = gr.Blocks(title="GAIA Benchmark Agent", theme=gr.themes.Soft())
-with demo:
-    gr.Markdown("""
-    # 🤖 GAIA Benchmark Agent
-    Multi-modal, multi-step reasoning agent for the Hugging Face GAIA benchmark.
-    """)
-    with gr.Tabs():
-        with gr.TabItem("API Q&A"):
-            api_btn = gr.Button("Run on API Questions", variant="primary")
-            api_output = gr.Textbox(label="Answers and Reasoning Trace", lines=20)
-            api_btn.click(run_api_questions, outputs=api_output)
-        with gr.TabItem("Manual Input"):
-            manual_q = gr.Textbox(label="Enter your question", lines=3)
-            manual_btn = gr.Button("Answer", variant="primary")
-            manual_a = gr.Textbox(label="Answer")
-            manual_trace = gr.Textbox(label="Reasoning Trace", lines=5)
-            manual_btn.click(run_manual_question, inputs=manual_q, outputs=[manual_a, manual_trace])
-        with gr.TabItem("Submission/Leaderboard"):
-            username = gr.Textbox(label="Hugging Face Username")
-            code_url = gr.Textbox(label="Agent Code URL")
-            submit_btn = gr.Button("Submit Answers", variant="primary")
-            submit_out = gr.Textbox(label="Submission Result")
-            submit_btn.click(submit_answers, inputs=[username, code_url], outputs=submit_out)
-            leaderboard_btn = gr.Button("Show Leaderboard")
-            leaderboard_out = gr.Textbox(label="Leaderboard")
-            leaderboard_btn.click(show_leaderboard, outputs=leaderboard_out)
-        with gr.TabItem("Agent Help"):
-            help_md = gr.Markdown(show_help())
 
 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
-
+    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")
     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.")
-
     print("-"*(60 + len(" App Starting ")) + "\n")
-
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)