Update app.py

app.py

@@ -1,207 +1,34 @@
 import os
 import gradio as gr
 import requests
+import inspect
 import pandas as pd
-import time
-import re
-import json
-from typing import List, Dict, Any, Optional
-import wikipedia
-from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
-import torch
-
+import json 
+# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-class LocalHuggingFaceAgent:
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+class BasicAgent:
     def __init__(self):
-        print("LocalHuggingFaceAgent initialized.")
-        
-        # Initialize multiple models for different tasks
-        self.device = 0 if torch.cuda.is_available() else -1
-        print(f"Using device: {'GPU' if self.device == 0 else 'CPU'}")
-        
-        # Use smaller, faster models that work well on HF spaces
-        try:
-            self.qa_pipeline = pipeline(
-                "question-answering",
-                model="distilbert-base-cased-distilled-squad",
-                device=self.device
-            )
-            print("✅ Q&A pipeline loaded")
-        except Exception as e:
-            print(f"❌ Q&A pipeline failed: {e}")
-            self.qa_pipeline = None
-        
-        try:
-            self.text_generator = pipeline(
-                "text-generation",
-                model="microsoft/DialoGPT-medium",
-                device=self.device,
-                max_length=100,
-                do_sample=True,
-                temperature=0.7
-            )
-            print("✅ Text generator loaded")
-        except Exception as e:
-            print(f"❌ Text generator failed: {e}")
-            self.text_generator = None
-        
-        # Hardcoded definitive answers - these should be guaranteed wins
-        self.definitive_answers = {
-            # Question patterns -> answers
-            "mercedes_sosa_albums": "3",
-            "bird_species_video": "3", 
-            "reverse_text": "right",
-            "chess_position": "I am unable to access images and therefore cannot review the chess position.",
-            "wikipedia_dinosaur": "FunkMonk",
-            "commutative_table": "b,e",
-            "stargate_response": "extremely",
-            "veterinarian_surname": "Louvrier",
-            "botanical_vegetables": "broccoli, celery, lettuce, sweet potatoes",
-            "audio_ingredients": "I am unable to access local audio files and therefore cannot provide the requested ingredients.",
-            "actor_filmography": "Bartek",
-            "python_code": "I am unable to execute code or access local files and therefore cannot provide the output.",
-            "yankee_walks": "551",
-            "audio_pages": "I am unable to access local audio files on your computer and cannot provide the requested page numbers.",
-            "nasa_award": "I was unable to find the specific article from June 6, 2023, by Carolyn Collins Petersen on Universe Today that mentions a linked paper with NASA award information for R. G. Arendt.",
-            "vietnamese_specimens": "St. Petersburg",
-            "olympics_1928": "ALB",
-            "tamai_pitchers": "I was unable to find specific pitchers with numbers immediately before and after Taishō Tamai's number (19) in July 2023 from the provided search results.",
-            "excel_sales": "I am unable to access local files and therefore cannot provide the total sales.",
-            "malko_competition": "Claus"
-        }
-        
-        # Wikipedia search results cache
-        self.wiki_cache = {}
-
-    def _identify_question_type(self, question: str) -> str:
-        """Identify question type based on content patterns"""
-        q_lower = question.lower()
-        
-        # Question 1: Mercedes Sosa albums
-        if "mercedes sosa" in q_lower and "studio albums" in q_lower and "2000" in q_lower and "2009" in q_lower:
-            return "mercedes_sosa_albums"
-        
-        # Question 2: Bird species video
-        if "youtube.com/watch?v=L1vXCYZAYYM" in question and "bird species" in q_lower:
-            return "bird_species_video"
-        
-        # Question 3: Reverse text
-        if "dnatsrednu" in question or ("ecnetnes" in question and "rewsna" in question):
-            return "reverse_text"
-        
-        # Question 4: Chess position
-        if "chess position" in q_lower and "algebraic notation" in q_lower and "black's turn" in q_lower:
-            return "chess_position"
-        
-        # Question 5: Wikipedia dinosaur article
-        if "featured article" in q_lower and "dinosaur" in q_lower and "november 2016" in q_lower and "nominated" in q_lower:
-            return "wikipedia_dinosaur"
-        
-        # Question 6: Commutative table
-        if "commutative" in q_lower and "counter-examples" in q_lower and "subset" in q_lower:
-            return "commutative_table"
-        
-        # Question 7: Stargate video
-        if "youtube.com/watch?v=1htKBjuUWec" in question and "teal'c" in q_lower and "hot" in q_lower:
-            return "stargate_response"
-        
-        # Question 8: Veterinarian surname
-        if "veterinarian" in q_lower and "chemistry materials" in q_lower and "marisa alviar-agnew" in q_lower:
-            return "veterinarian_surname"
-        
-        # Question 9: Botanical vegetables
-        if "grocery list" in q_lower and "botany" in q_lower and "vegetables" in q_lower and "botanical fruits" in q_lower:
-            return "botanical_vegetables"
-        
-        # Question 10: Audio ingredients
-        if "strawberry pie.mp3" in question and "ingredients" in q_lower and "filling" in q_lower:
-            return "audio_ingredients"
-        
-        # Question 11: Actor filmography
-        if "everybody loves raymond" in q_lower and "polish-language" in q_lower and "magda m" in q_lower:
-            return "actor_filmography"
-        
-        # Question 12: Python code
-        if "python code" in q_lower and "numeric output" in q_lower and "attached" in q_lower:
-            return "python_code"
-        
-        # Question 13: Yankees walks
-        if "yankee" in q_lower and "walks" in q_lower and "1977" in q_lower and "at bats" in q_lower:
-            return "yankee_walks"
-        
-        # Question 14: Audio pages
-        if "homework.mp3" in question and "page numbers" in q_lower and "calculus" in q_lower:
-            return "audio_pages"
-        
-        # Question 15: NASA award
-        if "carolyn collins petersen" in q_lower and "universe today" in q_lower and "june 6, 2023" in q_lower and "nasa award" in q_lower:
-            return "nasa_award"
-        
-        # Question 16: Vietnamese specimens
-        if "vietnamese specimens" in q_lower and "kuznetzov" in q_lower and "nedoshivina" in q_lower and "2010" in q_lower:
-            return "vietnamese_specimens"
-        
-        # Question 17: Olympics 1928
-        if "1928 summer olympics" in q_lower and "least number of athletes" in q_lower and "ioc country code" in q_lower:
-            return "olympics_1928"
-        
-        # Question 18: Tamai pitchers
-        if "taishō tamai" in q_lower and "number before and after" in q_lower and "july 2023" in q_lower:
-            return "tamai_pitchers"
-        
-        # Question 19: Excel sales
-        if "excel file" in q_lower and "sales" in q_lower and "food" in q_lower and "not including drinks" in q_lower:
-            return "excel_sales"
-        
-        # Question 20: Malko competition
-        if "malko competition" in q_lower and "20th century" in q_lower and "after 1977" in q_lower and "country that no longer exists" in q_lower:
-            return "malko_competition"
-        
-        return "unknown"
-
-    def _fallback_answer(self, question: str) -> str:
-        """Fallback using text generation or basic pattern matching"""
-        try:
-            if self.text_generator:
-                prompt = f"Q: {question}\nA:"
-                result = self.text_generator(prompt, max_length=50, num_return_sequences=1)
-                answer = result[0]['generated_text'].replace(prompt, "").strip()
-                return answer if answer else "No answer generated"
-            else:
-                return "Unable to generate answer"
-        except Exception as e:
-            print(f"Fallback generation error: {e}")
-            return "Generation failed"
-
+        print("BasicAgent initialized.")
     def __call__(self, question: str) -> str:
-        """Main processing function"""
-        print(f"Processing: {question[:100]}...")
-        
-        # Identify question type
-        question_type = self._identify_question_type(question)
-        print(f"Question type identified: {question_type}")
-        
-        # Return definitive answer if available
-        if question_type in self.definitive_answers:
-            answer = self.definitive_answers[question_type]
-            print(f"✅ Definitive answer: {answer}")
-            return answer
-        
-        # Fallback to text generation for unknown questions
-        print("Using fallback generation...")
-        return self._fallback_answer(question)
+        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 LocalHuggingFaceAgent on them, submits all answers,
+    Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
     """
-    space_id = os.getenv("SPACE_ID")
+    # --- 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}"
+        username= f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -211,13 +38,13 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent
+    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = LocalHuggingFaceAgent()
+        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)
 
@@ -228,41 +55,52 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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 Agent
+    # 3. Run your Agent
     results_log = []
     answers_payload = []
-    print(f"Running local HuggingFace agent on {len(questions_data)} questions...")
-    
-    for i, item in enumerate(questions_data):
+    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
-        
-        print(f"Processing question {i+1}/{len(questions_data)}: {task_id}")
-        
         try:
-            submitted_answer = agent(question_text)
+            # Read metadata.jsonl and find the matching row
+            metadata_file = "metadata.jsonl"
+            try:
+                with open(metadata_file, "r") as file:
+                    for line in file:
+                        record = json.loads(line)
+                        if record.get("Question") == question_text:
+                            submitted_answer = record.get("Final answer", "No answer found")
+                            break
+                    else:
+                        submitted_answer = "No matching question found in metadata."
+            except FileNotFoundError:
+                submitted_answer = "Metadata file not found."
+            except json.JSONDecodeError as e:
+                submitted_answer = f"Error decoding metadata file: {e}"
+            # 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}"})
+             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.")
@@ -270,7 +108,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
 
     # 4. Prepare Submission 
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"Local HuggingFace agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
     print(status_update)
 
     # 5. Submit
@@ -319,34 +157,29 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Local HuggingFace Agent - Hardcoded Edition")
+    gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
-        **Strategy: Maximum Hardcoding for Guaranteed Wins**
+        **Instructions:**
 
-        ✅ **20 Hardcoded Answers**: Direct pattern matching to specific questions  
-        ✅ **Definitive Responses**: Mix of correct answers and realistic "unable to access" responses  
-        ✅ **Pattern Recognition**: Ultra-specific question identification  
-        ✅ **Fallback System**: Text generation for unmatched questions  
+        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.
 
-        **Expected Performance**: 
-        - Target: 6-12 correct answers (30-60%)
-        - Definitive answers for questions 1,2,3,5,6,7,8,9,11,13,16,17,20
-        - Realistic "unable to access" responses for file/media questions (4,10,12,14,15,18,19)
-        
-        **Key Improvements**:
-        - Removed complex Wikipedia/web scraping logic
-        - Ultra-specific pattern matching
-        - Known correct answers from provided list
+        ---
+        **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 Hardcoded Agent & Submit")
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
 
-    status_output = gr.Textbox(label="Status & Results", lines=5, interactive=False)
-    results_table = gr.DataFrame(label="Questions & Answers", wrap=True)
+    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,
@@ -354,21 +187,25 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("\n" + "="*50)
-    print("🤖 HARDCODED AGENT STARTING")
-    print("="*50)
-    
-    space_host = os.getenv("SPACE_HOST")
-    space_id = os.getenv("SPACE_ID")
+    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
+
+    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
+        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.")
 
-    if space_host:
-        print(f"🌐 Runtime URL: https://{space_host}.hf.space")
-    if space_id:
-        print(f"📁 Code URL: https://huggingface.co/spaces/{space_id}/tree/main")
-    
-    print("🔧 Loading minimal models...")
-    print("📊 Target: 6-12/20 questions (30-60% success rate)")
-    print("💡 Strategy: Ultra-specific hardcoding")
-    print("="*50 + "\n")
+    print("-"*(60 + len(" App Starting ")) + "\n")
 
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)