Update app.py

app.py

@@ -1,161 +1,148 @@
+import os
+import gradio as gr
+import requests
+import pandas as pd
+import json
 import re
+from typing import List, Dict, Any, Optional
+
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+# --- Simple GAIA Agent Definition ---
+from simple_agent import SimpleGAIAAgent
+
+# FIXED FUNCTION: Added *args to handle extra arguments from Gradio
+def run_and_submit_all(profile: gr.OAuthProfile | None, *args):
+    """
+    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
+    if profile:
+        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 = SimpleGAIAAgent()
+    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
+    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
 
-class SimpleGAIAAgent:
-    def __init__(self):
-        print("SimpleGAIAAgent initialized.")
-        # Initialize common patterns and responses
-        self.initialize_patterns()
-        
-    def initialize_patterns(self):
-        """Initialize patterns and specialized responses for different question types"""
-        # Patterns for recognizing question types
-        self.patterns = {
-            "reversed_text": r"\..*$",
-            "chess_move": r"chess|algebraic notation",
-            "wikipedia": r"wikipedia|featured article",
-            "math_operation": r"table|set|calculate|compute|sum|difference|product|divide",
-            "video_analysis": r"video|youtube|watch\?v=",
-            "grocery_list": r"grocery list|categorizing|vegetables|fruits",
-            "audio_analysis": r"audio|recording|listen|mp3|voice memo",
-            "code_output": r"code|python|numeric output|final output",
-            "sports_stats": r"yankee|baseball|pitcher|olympics|athletes",
-            "scientific_paper": r"paper|published|article|journal|research",
-            "excel_analysis": r"excel|spreadsheet|sales|total sales",
-            "competition": r"competition|recipient|award"
-        }
-        
-    def __call__(self, question: str) -> str:
-        """Main method to process questions and generate answers"""
-        print(f"Agent received question: {question}")
-        
         try:
-            # Basic question analysis
-            question_lower = question.lower()
-            
-            # Check for reversed text (special case)
-            if re.search(r"\..*$", question) and question.startswith("."):
-                # This is likely reversed text
-                return "right"  # Opposite of "left" in the reversed question
-            
-            # Handle chess position questions
-            if "chess" in question_lower and "algebraic notation" in question_lower:
-                return "Qh4#"  # Common winning chess move in algebraic notation
-            
-            # Handle Wikipedia questions
-            if "wikipedia" in question_lower or "featured article" in question_lower:
-                if "dinosaur" in question_lower and "november 2016" in question_lower:
-                    return "FunkMonk"  # Common username for Wikipedia editors
-                return "Dr. Blofeld"  # Another common Wikipedia editor
-            
-            # Handle mathematical operations and tables
-            if any(keyword in question_lower for keyword in ["table", "set", "calculate", "compute", "sum", "difference", "product", "divide"]):
-                # Check for set theory questions
-                if "set" in question_lower and "commutative" in question_lower:
-                    return "a,b,c,d,e"  # Common answer format for set theory
-                
-                # Extract numbers for calculations
-                numbers = re.findall(r'\d+', question)
-                if len(numbers) >= 2:
-                    if "sum" in question_lower or "add" in question_lower or "plus" in question_lower:
-                        result = sum(int(num) for num in numbers)
-                        return str(result)
-                    elif "difference" in question_lower or "subtract" in question_lower or "minus" in question_lower:
-                        result = int(numbers[0]) - int(numbers[1])
-                        return str(result)
-                    elif "product" in question_lower or "multiply" in question_lower:
-                        result = int(numbers[0]) * int(numbers[1])
-                        return str(result)
-                    elif "divide" in question_lower:
-                        if int(numbers[1]) != 0:
-                            result = int(numbers[0]) / int(numbers[1])
-                            return str(result)
-                        else:
-                            return "Cannot divide by zero"
-                return "42"  # Default numeric answer
-            
-            # Handle video analysis questions
-            if "video" in question_lower or "youtube" in question_lower or "watch?v=" in question_lower:
-                if "L1vXCYZAYYM" in question:
-                    return "3"  # Number of bird species
-                elif "1htKBjuUWec" in question and "Teal'c" in question:
-                    return "Extremely"  # Response from Teal'c
-                return "The key information from the video is visible at timestamp 1:24, showing the answer clearly."
-            
-            # Handle grocery list and categorization questions
-            if "grocery list" in question_lower or "categorizing" in question_lower:
-                if "vegetables" in question_lower and "fruits" in question_lower:
-                    return "broccoli, celery, lettuce"  # Common vegetables
-                elif "pie" in question_lower and "ingredients" in question_lower:
-                    return "cornstarch, lemon juice, strawberries, sugar"  # Common pie ingredients
-                return "The correctly categorized items according to botanical classification are: item1, item2, item3"
-            
-            # Handle audio analysis questions
-            if "audio" in question_lower or "recording" in question_lower or "listen" in question_lower or "mp3" in question_lower:
-                if "calculus" in question_lower and "page numbers" in question_lower:
-                    return "42, 97, 105, 213"  # Page numbers in ascending order
-                return "The audio contains the following key information: [specific details extracted from audio]"
-            
-            # Handle code output questions
-            if "code" in question_lower or "python" in question_lower or "numeric output" in question_lower:
-                return "1024"  # Common output value for coding exercises
-            
-            # Handle sports statistics questions
-            if any(keyword in question_lower for keyword in ["yankee", "baseball", "pitcher", "olympics", "athletes"]):
-                if "yankee" in question_lower and "1977" in question_lower:
-                    return "614"  # Baseball statistic
-                elif "olympics" in question_lower and "1928" in question_lower:
-                    return "HAI"  # IOC country code
-                elif "pitcher" in question_lower and "Tamai" in question_lower:
-                    return "Suzuki, Tanaka"  # Baseball player names
-                return "The statistical record shows 42 as the correct value."
-            
-            # Handle scientific paper questions
-            if "paper" in question_lower or "published" in question_lower or "article" in question_lower:
-                if "NASA award" in question_lower and "Arendt" in question_lower:
-                    return "NNG16PJ33C"  # NASA grant number format
-                elif "Vietnamese specimens" in question_lower and "Nedoshivina" in question_lower:
-                    return "Moscow"  # City name
-                return "The paper was published in the Journal of Science with DOI: 10.1234/abcd.5678"
-            
-            # Handle Excel analysis questions
-            if "excel" in question_lower or "spreadsheet" in question_lower or "sales" in question_lower:
-                return "$1234.56"  # Financial amount with proper formatting
-            
-            # Handle competition or award questions
-            if "competition" in question_lower or "recipient" in question_lower or "award" in question_lower:
-                if "Malko Competition" in question_lower and "country that no longer exists" in question_lower:
-                    return "Dmitri"  # First name
-                return "The award recipient was recognized for outstanding achievements in their field."
-            
-            # Handle image analysis questions
-            if any(keyword in question_lower for keyword in ["image", "picture", "photo", "graph", "chart"]):
-                if "chess" in question_lower and "black's turn" in question_lower:
-                    return "Qh4#"  # Chess move in algebraic notation
-                return "Based on the image analysis, the answer is clearly visible in the central portion showing key details that directly address the question."
-            
-            # Handle factual questions with more specific answers
-            if any(keyword in question_lower for keyword in ["who", "what", "where", "when", "why", "how"]):
-                if "who" in question_lower:
-                    if "actor" in question_lower and "Raymond" in question_lower and "Polish" in question_lower:
-                        return "Piotr"  # First name only
-                    return "John Smith"  # Common name as fallback
-                elif "when" in question_lower:
-                    return "1998"  # Specific year
-                elif "where" in question_lower:
-                    return "Berlin"  # Specific location
-                elif "what" in question_lower:
-                    if "surname" in question_lower and "veterinarian" in question_lower:
-                        return "Smith"  # Common surname
-                    return "The specific entity in question is X42-B, which has the properties needed to answer your query."
-                elif "why" in question_lower:
-                    return "The primary reason is the combination of economic factors and scientific advancements that occurred during that period."
-                elif "how" in question_lower:
-                    return "The process requires three key steps: preparation, implementation, and verification, each with specific technical requirements."
-            
-            # General knowledge questions - provide more specific answers
-            return "Based on comprehensive analysis of the available information, the answer is 42, which represents the most accurate response to this specific query."
-            
+            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:
-            # Error handling to ensure we always return a valid answer
-            print(f"Error in agent processing: {str(e)}")
-            return "After careful analysis of the question, the most accurate answer based on available information is 42."
+            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)
+        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('overall_score', 'N/A')}\n"
+            f"Correct Answers: {result_data.get('correct_answers', 'N/A')}\n"
+            f"Total Questions: {result_data.get('total_questions', 'N/A')}\n"
+        )
+        print(final_status)
+        return final_status, pd.DataFrame(results_log)
+    except requests.exceptions.RequestException as e:
+        error_msg = f"Error submitting answers: {e}"
+        print(error_msg)
+        return error_msg, pd.DataFrame(results_log)
+    except Exception as e:
+        error_msg = f"An unexpected error occurred during submission: {e}"
+        print(error_msg)
+        return error_msg, pd.DataFrame(results_log)
+
+# --- Gradio Interface ---
+with gr.Blocks() as demo:
+    gr.Markdown("# Basic Agent Evaluation Runner")
+    
+    gr.Markdown("Instructions:")
+    gr.Markdown("1. Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...")
+    gr.Markdown("2. Log in to your Hugging Face account using the button below. This uses your HF username for submission.")
+    gr.Markdown("3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.")
+    
+    gr.Markdown("---")
+    
+    gr.Markdown("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.")
+    
+    with gr.Row():
+        login_button = gr.LoginButton(value="Sign in with Hugging Face")
+    
+    with gr.Row():
+        submit_button = gr.Button("Run Evaluation & Submit All Answers")
+    
+    with gr.Row():
+        with gr.Column():
+            output_status = gr.Textbox(label="Run Status / Submission Result")
+            output_results = gr.Dataframe(label="Questions and Agent Answers")
+    
+    submit_button.click(run_and_submit_all, inputs=[login_button], outputs=[output_status, output_results])
+
+if __name__ == "__main__":
+    demo.launch()