Update app.py

app.py

@@ -1,247 +1,117 @@
 import os
 import gradio as gr
 import requests
+import inspect
 import pandas as pd
-import re
-from typing import Optional, Dict, Any
-import json
-import logging
-
-# --- Setup Logging ---
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
-logger = logging.getLogger(__name__)
 
+# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Mock Smolagents Agent Class ---
-class SmolAgent:
-    def __init__(self):
-        self.tools = {
-            "web_search": self.web_search_tool,
-            "file_processor": self.file_processor_tool
-        }
-        self.answer_cache = {}
-        logger.info("SmolAgent initialized.")
-
-    def web_search_tool(self, query: str) -> Dict[str, str]:
-        """Simulates a web search tool (e.g., SerpAPI, Wikipedia)."""
-        logger.info(f"Web search tool called with query: {query}")
-        mock_results = {
-            "1928 summer olympics least athletes": {"result": "Malta (MLT) had the fewest athletes (1)."},
-            "taishō tamai pitcher numbers july 2023": {"result": "Pitchers before and after Taishō Tamai (18): Tanaka (17), Yamamoto (19)."},
-            "malko competition winners after 1977 defunct country": {"result": "Igor Lassov, USSR, won in 1986."},
-            "mercedes sosa studio albums 2000-2009": {"result": "3 albums: Misa Criolla (2000), Corazón Libre (2005), Cantora (2009)."},
-            "opposite of left": {"result": "right"},
-            "youtube video camera count": {"result": "3 cameras used simultaneously."},  # Hypothetical
-            "pasta shapes starting with c": {"result": "Campanelle, Cavatappi, Conchiglie"},
-            "highest mountain southern hemisphere": {"result": "Aconcagua"},
-            "elements atomic number less than 10": {"result": "Hydrogen, Helium, Lithium, Beryllium, Boron, Carbon, Nitrogen, Oxygen, Fluorine"},
-            "nobel peace prize 2009": {"result": "Barack Obama"},
-            "first human in space": {"result": "Yuri Gagarin"},
-            "capital of bhutan": {"result": "Thimphu"},
-            "longest river south america": {"result": "Amazon River"},
-            "oscar best picture 2010": {"result": "The Hurt Locker"},
-            "noble gases": {"result": "Helium, Neon, Argon, Krypton, Xenon, Radon"},
-            "largest desert": {"result": "Antarctic Desert"},
-            "world cup 2014 winner": {"result": "Germany"},
-            "shakespeare othello": {"result": "Othello"},
-            "currency japan": {"result": "Yen"},
-            "smallest country land area": {"result": "Vatican City"}
-        }
-        for key, value in mock_results.items():
-            if key.lower() in query.lower():
-                return value
-        return {"result": "No data found."}
-
-    def file_processor_tool(self, file_path: str, query: str) -> Dict[str, str]:
-        """Simulates processing of files (e.g., Excel for sales)."""
-        logger.info(f"File processor tool called with file: {file_path}, query: {query}")
-        if "fast-food chain" in query.lower() and "excel" in query.lower():
-            return {"result": "10423.75"}  # Hardcoded from submitted answer
-        return {"result": "Unable to process file."}
-
-    def run(self, question: str, files: Optional[list] = None) -> str:
-        """Processes a question using tools and mock LLM logic."""
-        logger.info(f"Processing question (first 50 chars): {question[:50]}...")
-        question_lower = question.lower().strip()
-
-        # Check cache
-        if question in self.answer_cache:
-            logger.info(f"Returning cached answer: {self.answer_cache[question]}")
-            return self.answer_cache[question]
-
-        # Question 1: Grocery list vegetable categorization
-        if "grocery list" in question_lower and "botany" in question_lower:
-            vegetables = ["acorns", "basil", "broccoli", "celery", "lettuce", "sweet potatoes"]
-            answer = ", ".join(sorted(vegetables)).strip()
-            self.answer_cache[question] = answer
-            logger.info(f"Returning vegetable list: {answer}")
-            return answer
-
-        # Question 2: 1928 Summer Olympics
-        elif "1928 summer olympics" in question_lower:
-            result = self.tools["web_search"]("1928 summer olympics least athletes")
-            answer = "MLT" if result["result"] != "No data found." else "MLT"
-            self.answer_cache[question] = answer
-            logger.info(f"Returning IOC code: {answer}")
-            return answer
-
-        # Question 3: Taishō Tamai pitchers
-        elif "taishō tamai" in question_lower:
-            result = self.tools["web_search"]("taishō tamai pitcher numbers july 2023")
-            answer = "Tanaka, Yamamoto" if result["result"] != "No data found." else "Tanaka, Yamamoto"
-            self.answer_cache[question] = answer
-            logger.info(f"Returning pitchers: {answer}")
-            return answer
-
-        # Question 4: Fast-food sales (Excel)
-        elif "fast-food chain" in question_lower and "excel file" in question_lower:
-            if files:
-                result = self.tools["file_processor"](files[0], question)
-                answer = result["result"]
-            else:
-                answer = "10423.75"  # Fallback
-            self.answer_cache[question] = answer
-            logger.info(f"Returning total sales: {answer}")
-            return answer
-
-        # Question 5: Malko Competition
-        elif "malko competition" in question_lower:
-            result = self.tools["web_search"]("malko competition winners after 1977 defunct country")
-            if result["result"] != "No data found.":
-                match = re.search(r"(\w+)\s+\w+,", result["result"])
-                answer = match.group(1) if match else "Igor"
-            else:
-                answer = "Igor"
-            self.answer_cache[question] = answer
-            logger.info(f"Returning Malko recipient: {answer}")
-            return answer
-
-        # Additional GAIA Questions
-        elif "mercedes sosa" in question_lower and "studio albums" in question_lower:
-            result = self.tools["web_search"]("mercedes sosa studio albums 2000-2009")
-            answer = "3" if result["result"] != "No data found." else "3"
-            self.answer_cache[question] = answer
-            logger.info(f"Returning album count: {answer}")
-            return answer
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+from transformers import pipeline
 
-        elif "opposite of left" in question_lower:
-            result = self.tools["web_search"]("opposite of left")
-            answer = "right" if result["result"] != "No data found." else "right"
-            self.answer_cache[question] = answer
-            logger.info(f"Returning opposite word: {answer}")
-            return answer
+class BasicAgent:
+    def __init__(self):
+        print("✅ AI Agent with transformers + PyTorch initialized")
+        self.generator = pipeline(
+            "text-generation", 
+            model="sshleifer/tiny-gpt2",  # or use "distilgpt2"
+            framework="pt"  # Explicitly use PyTorch
+        )
 
-        elif "youtube video" in question_lower and "camera" in question_lower:
-            result = self.tools["web_search"]("youtube video camera count")
-            answer = result["result"] if result["result"] != "No data found." else "3"  # Hypothetical
-            self.answer_cache[question] = answer
-            logger.info(f"Returning video camera count: {answer}")
+    def __call__(self, question: str) -> str:
+        print(f"⚙️ Generating answer for: {question[:60]}...")
+        try:
+            response = self.generator(question, max_length=50, num_return_sequences=1)
+            answer = response[0]['generated_text'].strip()
+            print(f"🧠 Answer: {answer}")
             return answer
+        except Exception as e:
+            print(f"❌ Error in model inference: {e}")
+            return "Model error"
 
-        # Generic GAIA Tasks
-        for query_key in [
-            "pasta shapes starting with c",
-            "highest mountain southern hemisphere",
-            "elements atomic number less than 10",
-            "nobel peace prize 2009",
-            "first human in space",
-            "capital of bhutan",
-            "longest river south america",
-            "oscar best picture 2010",
-            "noble gases",
-            "largest desert",
-            "world cup 2014 winner",
-            "shakespeare othello",
-            "currency japan",
-            "smallest country land area"
-        ]:
-            if query_key in question_lower:
-                result = self.tools["web_search"](query_key)
-                answer = result["result"] if result["result"] != "No data found." else "Unable to process question."
-                self.answer_cache[question] = answer
-                logger.info(f"Returning answer for {query_key}: {answer}")
-                return answer
-
-        # Default fallback
-        logger.info("Question not recognized. Using web search...")
-        result = self.tools["web_search"](question[:100])
-        answer = result["result"] if result["result"] != "No data found." else "Unable to process question."
-        self.answer_cache[question] = answer
-        logger.info(f"Returning default answer: {answer}")
-        return answer
 
-# --- Submission Logic ---
-def run_and_submit_all(profile: gr.OAuthProfile | None):
+def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the SmolAgent 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", "unknown_space")
+    # --- 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}"
-        logger.info(f"User logged in: {username}")
+        username= f"{profile.username}"
+        print(f"User logged in: {username}")
     else:
-        logger.error("User not logged in.")
+        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"
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
 
+    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = SmolAgent()
+        agent = BasicAgent()
     except Exception as e:
-        logger.error(f"Error instantiating agent: {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)
 
-    logger.info(f"Agent code URL: {agent_code}")
-    logger.info(f"Fetching questions from: {questions_url}")
+    # 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:
-            logger.error("Fetched questions list is empty.")
-            return "Fetched questions list is empty or invalid format.", None
-        logger.info(f"Fetched {len(questions_data)} questions.")
+             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:
-        logger.error(f"Error fetching questions: {e}")
+        print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
     except requests.exceptions.JSONDecodeError as e:
-        logger.error(f"Error decoding JSON response: {e}")
-        return f"Error decoding server response: {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:
-        logger.error(f"An unexpected error occurred fetching questions: {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 = []
-    logger.info(f"Running agent on {len(questions_data)} questions...")
+    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")
-        files = item.get("files", [])
         if not task_id or question_text is None:
-            logger.warning(f"Skipping item with missing task_id or question: {item}")
+            print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent.run(question_text, files)
-            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer.strip()})
+            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})
-            logger.info(f"Task {task_id} answer: {submitted_answer}")
         except Exception as e:
-            logger.error(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:
-        logger.error("Agent did not produce any answers to submit.")
+        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}
-    logger.info(f"Submitting {len(answers_payload)} answers for user '{username}' to: {submit_url}")
+    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()
@@ -253,7 +123,7 @@ 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.')}"
         )
-        logger.info("Submission successful.")
+        print("Submission successful.")
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
     except requests.exceptions.HTTPError as e:
@@ -263,36 +133,42 @@ 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]}"
-        logger.error(f"Submission Failed: {error_detail}")
+        status_message = f"Submission Failed: {error_detail}"
+        print(status_message)
         results_df = pd.DataFrame(results_log)
-        return f"Submission Failed: {error_detail}", results_df
+        return status_message, results_df
     except requests.exceptions.Timeout:
-        logger.error("Submission Failed: The request timed out.")
+        status_message = "Submission Failed: The request timed out."
+        print(status_message)
         results_df = pd.DataFrame(results_log)
-        return "Submission Failed: The request timed out.", results_df
+        return status_message, results_df
     except requests.exceptions.RequestException as e:
-        logger.error(f"Submission Failed: Network error - {e}")
+        status_message = f"Submission Failed: Network error - {e}"
+        print(status_message)
         results_df = pd.DataFrame(results_log)
-        return f"Submission Failed: Network error - {e}", results_df
+        return status_message, results_df
     except Exception as e:
-        logger.error(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 f"An unexpected error occurred during submission: {e}", results_df
+        return status_message, results_df
+
 
-# --- Build Gradio Interface ---
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# AI Agent Evaluation Runner")
+    gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
 
-        1. Clone this space and update the agent logic using smolagents or other tools.
-        2. Log in to Hugging Face to submit answers under your username.
-        3. Click 'Run Evaluation & Submit All Answers' to process questions and submit.
+        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:**
-        Submission may take time due to processing 20 questions. Consider caching answers or using async processing for optimization.
+        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.
         """
     )
 
@@ -301,6 +177,7 @@ with gr.Blocks() as demo:
     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(
@@ -309,22 +186,25 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    logger.info("\n" + "-"*30 + " App Starting " + "-"*30)
+    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")
+    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
 
     if space_host_startup:
-        logger.info(f"SPACE_HOST found: {space_host_startup}")
-        logger.info(f"Runtime URL: https://{space_host_startup}.hf.space")
+        print(f"✅ SPACE_HOST found: {space_host_startup}")
+        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
     else:
-        logger.info("SPACE_HOST not found (running locally?).")
+        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup:
-        logger.info(f"SPACE_ID found: {space_id_startup}")
-        logger.info(f"Repo URL: https://huggingface.co/spaces/{space_id_startup}")
+    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:
-        logger.info("SPACE_ID not found (running locally?).")
+        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+
+    print("-"*(60 + len(" App Starting ")) + "\n")
 
-    logger.info("-"*(60 + len(" App Starting ")))
-    logger.info("Launching Gradio Interface...")
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)