Update app.py

app.py

@@ -3,53 +3,96 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from bs4 import BeautifulSoup
+import re
 
-# --- Constants ---
+# Constants
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Tools Definitions ---
-def add_numbers(a, b):
-    return a + b
-
-def reverse_text(text):
-    return text[::-1]
-
-# --- Basic Agent Definition ---
-# ----- THIS IS WHERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
-    def __init__(self, tools=None):
-        self.tools = tools or []
-        print("BasicAgent initialized with tools.")
+# --- Generalized Tools ---
+class KnowledgeExtractionTool:
+    def __init__(self):
+        self.api_url = DEFAULT_API_URL
+    
+    def fetch_data(self, url):
+        """Fetches data from a URL (Wikipedia or other sources)"""
+        response = requests.get(url)
+        if response.status_code == 200:
+            return response.text
+        return None
+    
+    def extract_winners_from_wikipedia(self, url):
+        """Extracts competition winners from a Wikipedia page"""
+        page_content = self.fetch_data(url)
+        if not page_content:
+            return []
         
-    def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        soup = BeautifulSoup(page_content, 'html.parser')
+        winners_data = []
         
-        # Implement a basic logic to process tools
-        if 'add' in question.lower():
-            try:
-                a, b = map(int, question.split()[-2:])
-                answer = sum([a, b])
-                print(f"Agent returning answer: {answer}")
-                return str(answer)
-            except Exception as e:
-                return f"Error processing question: {e}"
+        # Look for the table of winners
+        winners_table = soup.find('table', {'class': 'wikitable'})
+        if winners_table:
+            for row in winners_table.find_all('tr')[1:]:  # Skipping the header row
+                cells = row.find_all('td')
+                if len(cells) > 3:
+                    name = cells[0].text.strip()  # Winner's name
+                    year = int(cells[1].text.strip())  # Year
+                    nationality = cells[3].text.strip()  # Nationality
+                    winners_data.append({"name": name, "year": year, "nationality": nationality})
+        return winners_data
+    
+    def filter_winners(self, winners_data, year_threshold=1977, countries_to_check=None):
+        """Filters winners by year and nationality (if country no longer exists)"""
+        if not countries_to_check:
+            countries_to_check = ["Yugoslavia", "Soviet Union", "East Germany"]  # Example list
         
-        elif 'reverse' in question.lower():
-            answer = question[::-1]
-            print(f"Agent returning reversed answer: {answer}")
-            return answer
+        filtered_winners = []
+        for winner in winners_data:
+            if winner["year"] > year_threshold and any(country in winner["nationality"] for country in countries_to_check):
+                filtered_winners.append(winner)
+        return filtered_winners
+
+    def extract_first_name(self, full_name):
+        """Extract the first name from a full name string"""
+        return full_name.split()[0] if full_name else None
+
+    def process_question(self, question):
+        """Generalized function to process a wide variety of questions"""
+        if "Malko Competition" in question and "first name" in question:
+            print("Processing Malko Competition query...")
+
+            # Fetch data from Wikipedia (or other sources)
+            winners_data = self.extract_winners_from_wikipedia("https://en.wikipedia.org/wiki/Malko_Competition")
+            
+            # Filter by year and nationality of winners
+            filtered_winners = self.filter_winners(winners_data)
+
+            # Extract and return the first name
+            if filtered_winners:
+                first_name = self.extract_first_name(filtered_winners[0]["name"])
+                return f"The first name of the winner is: {first_name}"
+            else:
+                return "No winners found with the specified conditions."
         
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        # Add other types of questions and their handling here as needed
+        return "Question could not be processed."
 
-# --- Function to run the agent ---
+# --- Basic Agent Definition ---
+class BasicAgent:
+    def __init__(self):
+        self.knowledge_tool = KnowledgeExtractionTool()
+    
+    def __call__(self, question: str) -> str:
+        print(f"Processing question: {question}")
+        return self.knowledge_tool.process_question(question)
+
+# --- Run and Submit All Function ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
     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:
@@ -63,17 +106,14 @@ 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)
+    # Instantiate Agent
     try:
-        agent = BasicAgent(tools=[add_numbers, reverse_text])  # Adding tools here
+        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 (useful for others so please keep it public)
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
 
-    # 2. Fetch Questions
+    # Fetch Questions
     print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
@@ -86,15 +126,8 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     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
+    # Run agent on each question
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -116,12 +149,8 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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
+    # Prepare and submit answers
+    submission_data = {"username": username.strip(), "agent_code": f"https://huggingface.co/spaces/{os.getenv('SPACE_ID')}/tree/main", "answers": answers_payload}
     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
@@ -137,56 +166,28 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         print("Submission successful.")
         results_df = pd.DataFrame(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:
-            error_json = e.response.json()
-            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}"
-        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)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Generalized Agent Evaluation Runner")
     gr.Markdown(
         """
         **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 separate action or even to answer the questions in async.
+        1. Clone this space and modify the code to define your agent's logic, tools, and packages.
+        2. Log in to your Hugging Face account using the button below.
+        3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
         """
     )
 
     gr.LoginButton()
 
     run_button = gr.Button("Run Evaluation & Submit All Answers")
-
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
@@ -196,25 +197,4 @@ 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
-    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.")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
-
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)