Update app.py

app.py

@@ -3,32 +3,127 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+import json
+from typing import Dict, List, Optional, Any
 
 # (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:
+# --- Enhanced Agent Definition ---
+# ----- THIS IS WHERE YOU CAN BUILD WHAT YOU WANT ------
+class GIAIAAgent:
+    """
+    Agent designed to answer GIAIA questions.
+    Modify this class to implement your own logic for answering questions.
+    """
+    
     def __init__(self):
-        print("BasicAgent initialized.")
+        """Initialize your agent with any necessary tools, models, or resources."""
+        print("GIAIA Agent initialized.")
+        
+        # TODO: Initialize your tools, models, or APIs here
+        # Example:
+        # self.model = load_your_model()
+        # self.tools = load_your_tools()
+        
+        # You can store a cache of answers if needed
+        self.answer_cache = {}
+        
     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
+        """
+        Process a question and return an answer.
+        
+        Args:
+            question: The question text to answer
+            
+        Returns:
+            The answer as a string
+        """
+        print(f"Processing question (first 100 chars): {question[:100]}...")
+        
+        # TODO: Implement your actual question-answering logic here
+        # This is where you should put your agent's intelligence
+        
+        # For now, let's do some basic processing to show the structure
+        try:
+            # You might want to:
+            # 1. Parse the question
+            # 2. Use tools to gather information
+            # 3. Process with a model
+            # 4. Format the answer
+            
+            # Example structure (replace with your actual logic):
+            answer = self._generate_answer(question)
+            
+            print(f"Generated answer: {answer[:50]}...")
+            return answer
+            
+        except Exception as e:
+            print(f"Error processing question: {e}")
+            return f"Error generating answer: {str(e)}"
+    
+    def _generate_answer(self, question: str) -> str:
+        """
+        Internal method to generate answers.
+        Replace this with your actual implementation.
+        
+        This is a placeholder - you should implement your own logic!
+        """
+        
+        # TODO: IMPLEMENT YOUR ACTUAL ANSWER GENERATION LOGIC HERE
+        # 
+        # Some ideas:
+        # - Use a language model via API
+        # - Use retrieval augmented generation
+        # - Use web search tools
+        # - Use a knowledge base
+        # - Implement specific logic for each type of question
+        
+        # For demonstration, I'll categorize questions based on keywords
+        # BUT YOU SHOULD REPLACE THIS WITH YOUR ACTUAL IMPLEMENTATION
+        
+        question_lower = question.lower()
+        
+        # This is just a simple example - REPLACE WITH REAL LOGIC!
+        if "what is" in question_lower:
+            return f"Based on the context, {question.replace('What is', '').strip()} refers to a concept in the field."
+        elif "how to" in question_lower:
+            return f"To {question.replace('How to', '').strip()}, you should follow these steps: [Your solution here]"
+        elif "explain" in question_lower:
+            return f"Here's an explanation of {question.replace('Explain', '').strip()}: [Your explanation here]"
+        elif "difference between" in question_lower:
+            return f"The main differences are: [Your comparison here]"
+        else:
+            # For questions without clear keywords, you might want to use a default approach
+            return f"Answer: [Your answer for: {question[:50]}...]"
+    
+    def batch_answer(self, questions: List[str]) -> List[str]:
+        """
+        Optional: Process multiple questions at once for efficiency.
+        
+        Args:
+            questions: List of question strings
+            
+        Returns:
+            List of answer strings
+        """
+        answers = []
+        for question in questions:
+            answers.append(self(question))
+        return answers
 
-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,
+    Fetches all questions, runs the GIAIAAgent 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")  # 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.")
@@ -38,15 +133,18 @@ 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 (modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        # Use the enhanced GIAIA agent instead of BasicAgent
+        agent = GIAIAAgent()
+        print("Agent instantiated successfully")
     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)
+    
+    # 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" if space_id else "Local development"
+    print(f"Agent code URL: {agent_code}")
 
     # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
@@ -54,54 +152,96 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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.")
+        
+        # Optional: Display the first few questions to see what we're dealing with
+        print("\n--- First 3 questions (preview) ---")
+        for i, item in enumerate(questions_data[:3]):
+            print(f"Q{i+1}: {item.get('question', 'No question')[:100]}...")
+        print("--- End preview ---\n")
+        
     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
+    # 3. Run your Agent on all questions
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    
+    print(f"\nRunning GIAIA agent on {len(questions_data)} questions...")
+    print("This may take a while depending on your implementation...")
+    
+    # Process questions one by one (or in batches if you implement batch_answer)
+    for i, item in enumerate(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
+        
+        print(f"Processing question {i+1}/{len(questions_data)} (Task ID: {task_id})")
+        
         try:
+            # Run your agent on the question
             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})
+            
+            # Add to payload for submission
+            answers_payload.append({
+                "task_id": task_id, 
+                "submitted_answer": submitted_answer
+            })
+            
+            # Log for display
+            results_log.append({
+                "Task ID": task_id, 
+                "Question": question_text[:100] + "..." if len(question_text) > 100 else question_text,
+                "Submitted Answer": submitted_answer[:100] + "..." if len(submitted_answer) > 100 else submitted_answer
+            })
+            
+            print(f"✓ Question {i+1} answered")
+            
         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[:100] + "..." if len(question_text) > 100 else question_text,
+                "Submitted Answer": f"AGENT ERROR: {str(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}
+    # 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
+    # 5. Submit answers to scoring server
     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"
@@ -109,9 +249,23 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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)
+        print(f"Score: {result_data.get('score', 'N/A')}%")
+        
+        # Create full results DataFrame with complete answers for download
+        full_results_log = []
+        for i, item in enumerate(questions_data):
+            if i < len(answers_payload):
+                full_results_log.append({
+                    "Task ID": item.get("task_id"),
+                    "Question": item.get("question"),
+                    "Submitted Answer": answers_payload[i].get("submitted_answer")
+                })
+        
+        results_df = pd.DataFrame(full_results_log if full_results_log else 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:
@@ -123,16 +277,19 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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)
@@ -141,30 +298,69 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
 
 # --- Build Gradio Interface using Blocks ---
-with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# GIAIA Agent Evaluation Runner")
     gr.Markdown(
         """
+        **Welcome to the GIAIA Agent Evaluation!**
+        
+        This space evaluates your agent on 20 GIAIA 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.
-
-        ---
+        1.  **Fork/Clone** this space to your own account
+        2.  **Modify the `GIAIAAgent` class** in `app.py` to implement your agent's logic
+        3.  Add any required **dependencies** to `requirements.txt`
+        4.  Log in with your Hugging Face account below
+        5.  Click 'Run Evaluation' to test your agent on all 20 questions
+        6.  View your score and detailed results
+        
+        **Tips for Implementation:**
+        - The agent will be called once for each question
+        - You can add tools, use APIs, or implement any logic you want
+        - Consider performance - all 20 questions will be processed sequentially
+        - You can implement caching if needed
+        
         **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.
+        - This evaluation may take some time depending on your implementation
+        - Make sure to keep your space public so others can see your solution
         """
     )
 
-    gr.LoginButton()
+    with gr.Row():
+        with gr.Column(scale=1):
+            gr.LoginButton()
+            
+        with gr.Column(scale=2):
+            run_button = gr.Button("🚀 Run Evaluation on 20 Questions", variant="primary", size="lg")
 
-    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)
+    with gr.Row():
+        with gr.Column():
+            status_output = gr.Textbox(
+                label="Run Status / Submission Result", 
+                lines=6, 
+                interactive=False,
+                placeholder="Status will appear here..."
+            )
+    
+    with gr.Row():
+        with gr.Column():
+            results_table = gr.DataFrame(
+                label="Questions and Agent Answers (Preview)", 
+                wrap=True,
+                height=400
+            )
+    
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown(
+                """
+                ---
+                **Need Help?**
+                - Check the [documentation](https://huggingface.co/docs)
+                - Modify the `GIAIAAgent._generate_answer` method with your logic
+                - Add any required packages to `requirements.txt`
+                """
+            )
 
     run_button.click(
         fn=run_and_submit_all,
@@ -172,25 +368,30 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
+    print("\n" + "="*70)
+    print(" GIAIA Agent Evaluation App Starting")
+    print("="*70)
+    
+    # Check for SPACE_HOST and SPACE_ID at startup
     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?).")
+        print("ℹ️  SPACE_HOST 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("ℹ️  SPACE_ID not found (running locally)")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    print("="*70 + "\n")
+    print("Launching Gradio Interface...")
+    print("NOTE: The agent in this template uses placeholder logic.")
+    print("You MUST modify the GIAIAAgent class to implement actual answers!")
+    print("-"*70 + "\n")
+    
     demo.launch(debug=True, share=False)