Update app.py

app.py

@@ -1,25 +1,13 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from agent import BasicAgent
 
-# (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):
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
@@ -28,7 +16,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -38,20 +26,21 @@ 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)
+    # 1. Instantiate 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)
+    
+    # In the case of an app running as a hugging Face space, this link points toward your codebase
     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 = requests.get(questions_url, timeout=30)
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
@@ -73,12 +62,22 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
+    
+    # Progress tracking
+    progress_count = 0
+    total_questions = len(questions_data)
+    
     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
+            
+        # Update progress
+        progress_count += 1
+        print(f"Processing question {progress_count}/{total_questions}")
+        
         try:
             submitted_answer = agent(question_text)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
@@ -99,11 +98,11 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     # 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"
             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"
@@ -119,78 +118,112 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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}"
+        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. Please try again."
         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 during submission: {e}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
+def test_agent(question: str, provider: str):
+    """Test the agent with a single question."""
+    try:
+        agent = BasicAgent(provider=provider)
+        answer = agent(question)
+        return f"Question: {question}\nAnswer: {answer}"
+    except Exception as e:
+        return f"Error testing agent: {e}"
 
 # --- Build Gradio Interface using Blocks ---
-with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+with gr.Blocks(title="GAIA Agent Evaluator") as demo:
+    gr.Markdown("# 🤖 GAIA Agent Evaluator")
     gr.Markdown(
         """
+        This interface allows you to evaluate your agent against the GAIA benchmark questions.
+        
         **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.
+        1. Log in to your Hugging Face account using the button below
+        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, and submit answers
+        3. View your results and score in the output panel
+        
+        **For Testing:**
+        Use the test section below to verify your agent works correctly with sample questions.
         """
     )
-
-    gr.LoginButton()
-
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-
-    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]
-    )
+    
+    with gr.Tab("Evaluation"):
+        gr.Markdown("## 🚀 Run Full Evaluation")
+        gr.LoginButton()
+        
+        with gr.Row():
+            run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
+        
+        status_output = gr.Textbox(label="📊 Status / Submission Result", lines=8, 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]
+        )
+    
+    with gr.Tab("Testing"):
+        gr.Markdown("## 🧪 Test Your Agent")
+        with gr.Row():
+            with gr.Column():
+                test_question = gr.Textbox(
+                    label="Question",
+                    placeholder="Enter a test question...",
+                    value="What is 2+2?"
+                )
+                provider_choice = gr.Radio(
+                    choices=["groq", "hf"],
+                    value="groq",
+                    label="Provider"
+                )
+                test_button = gr.Button("Test Agent")
+            with gr.Column():
+                test_output = gr.Textbox(label="Agent Response", lines=10, interactive=False)
+        
+        test_button.click(
+            fn=test_agent,
+            inputs=[test_question, provider_choice],
+            outputs=test_output
+        )
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    print("\n" + "="*50)
+    print("🚀 GAIA Agent Evaluator Starting")
+    print("="*50)
+    
     # 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")
+        print(f"   Runtime URL: 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("ℹ️  Running locally (SPACE_HOST not 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...")
+        print("ℹ️  SPACE_ID not found (Repo URL cannot be determined)")
+    
+    print("="*50)
+    print("Launching Gradio Interface...")
     demo.launch(debug=True, share=False)