app.py

import os
from dotenv import load_dotenv
import gradio as gr
import requests

from typing import List, Dict, Union
import requests
import wikipediaapi
import pandas as pd
import requests
from bs4 import BeautifulSoup
import re
from urllib.parse import quote
import spacy
from googlesearch import search

load_dotenv()

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# --- Basic Agent Definition ---
class BasicAgent:
    def __init__(self):
        print("BasicAgent initialized.")
    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        fixed_answer = WebSearchAgent.run({question})
        print(f"Agent returning fixed answer: {fixed_answer}")
        return fixed_answer

class WebSearchAgent:
    def __init__(self):
        self.nlp = spacy.load("en_core_web_sm")
        self.session = requests.Session()
        self.session.headers.update({
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
        })
        self.cache = {}

    def analyze_query(self, query):
        """Analyze the query to determine intent and extract entities"""
        doc = self.nlp(query)
        
        analysis = {
            'entities': [(ent.text, ent.label_) for ent in doc.ents],
            'intent': self._determine_intent(query.lower()),
            'time_constraints': self._extract_time_constraints(query),
            'quantities': self._extract_quantities(query)
        }
        return analysis

    def _determine_intent(self, query):
        """Determine the intent of the query"""
        if 'how many' in query:
            return 'count'
        elif 'when' in query:
            return 'date'
        elif 'who' in query:
            return 'person'
        elif 'what is' in query or 'define' in query:
            return 'definition'
        elif 'list' in query or 'name all' in query:
            return 'list'
        return 'general'

    def _extract_time_constraints(self, text):
        """Extract time ranges from text"""
        constraints = []
        # Match patterns like "between 2000 and 2009"
        range_match = re.search(r'between (\d{4}) and (\d{4})', text)
        if range_match:
            constraints.append(('range', int(range_match.group(1)), int(range_match.group(2))))
        
        # Match patterns like "in 2005"
        year_match = re.search(r'in (\d{4})', text)
        if year_match:
            constraints.append(('point', int(year_match.group(1))))
        
        return constraints

    def _extract_quantities(self, text):
        """Extract numerical quantities from text"""
        return [int(match) for match in re.findall(r'\b(\d+)\b', text)]

    def search_web(self, query, num_results=3):
        """Search the web using multiple sources"""
        sources = {
            'wikipedia': self._search_wikipedia,
            'google': self._search_google
        }
        
        results = []
        for source_name, search_func in sources.items():
            try:
                results.extend(search_func(query, num_results))
            except Exception as e:
                print(f"Error searching {source_name}: {e}")
        
        return results[:num_results*2]  # Return max of double the requested results

    def _search_wikipedia(self, query, num_results):
        """Search Wikipedia API"""
        url = "https://en.wikipedia.org/w/api.php"
        params = {
            'action': 'query',
            'list': 'search',
            'srsearch': query,
            'format': 'json',
            'srlimit': num_results
        }
        response = self.session.get(url, params=params).json()
        return [{
            'url': f"https://en.wikipedia.org/wiki/{item['title'].replace(' ', '_')}",
            'title': item['title'],
            'snippet': item['snippet'],
            'source': 'wikipedia'
        } for item in response['query']['search']]

    def _search_google(self, query, num_results):
        """Search Google using python-googlesearch"""
        return [{
            'url': url,
            'source': 'google'
        } for url in search(query, num_results=num_results, stop=num_results)]

    def fetch_page(self, url):
        """Fetch and parse a web page with caching"""
        if url in self.cache:
            return self.cache[url]
        
        try:
            response = self.session.get(url, timeout=10)
            soup = BeautifulSoup(response.text, 'html.parser')
            
            # Clean the page content
            for element in soup(['script', 'style', 'nav', 'footer']):
                element.decompose()
            
            page_data = {
                'url': url,
                'title': soup.title.string if soup.title else '',
                'text': ' '.join(soup.stripped_strings),
                'soup': soup
            }
            
            self.cache[url] = page_data
            return page_data
        except Exception as e:
            print(f"Error fetching {url}: {e}")
            return None

    def extract_answer(self, page, analysis):
        """Extract relevant information from a page based on query analysis"""
        if not page:
            return None
        
        if analysis['intent'] == 'count':
            return self._extract_count(page['text'], analysis)
        elif analysis['intent'] == 'date':
            return self._extract_date(page['text'], analysis)
        elif analysis['intent'] == 'list':
            return self._extract_list(page['soup'], analysis)
        else:
            return self._extract_general(page['text'], analysis)

    def _extract_count(self, text, analysis):
        """Extract a count/number from text"""
        entities = [e[0] for e in analysis['entities']]
        pattern = r'(\b\d+\b)[^\.]*\b(' + '|'.join(re.escape(e) for e in entities) + r')\b'
        matches = re.finditer(pattern, text, re.IGNORECASE)
        
        counts = [int(match.group(1)) for match in matches]
        return max(counts) if counts else None

    def _extract_date(self, text, analysis):
        """Extract dates from text"""
        date_pattern = r'\b(\d{1,2}(?:st|nd|rd|th)?\s+(?:\w+)\s+\d{4}|\d{4})\b'
        dates = [match.group(0) for match in re.finditer(date_pattern, text)]
        
        entities = [e[0] for e in analysis['entities']]
        return next((d for d in dates if any(e.lower() in text.lower() for e in entities)), None)

    def _extract_list(self, soup, analysis):
        """Extract list items from page"""
        entities = [e[0] for e in analysis['entities']]
        items = []
        
        for list_tag in soup.find_all(['ul', 'ol']):
            list_items = [li.get_text().strip() for li in list_tag.find_all('li')]
            if any(e.lower() in ' '.join(list_items).lower() for e in entities):
                items.extend(list_items)
        
        return items if items else None

    def _extract_general(self, text, analysis):
        """Extract general information from text"""
        entities = [e[0] for e in analysis['entities']]
        sentences = re.split(r'(?<!\w\.\w.)(?<![A-Z][a-z]\.)(?<=\.|\?)\s', text)
        
        relevant = [s for s in sentences if any(e.lower() in s.lower() for e in entities)]
        return ' '.join(relevant) if relevant else None

    def answer_question(self, question, num_sources=3):
        """Main method to answer a question"""
        print(f"Processing question: {question}")
        
        # Step 1: Analyze the question
        analysis = self.analyze_query(question)
        print(f"Analysis: {analysis}")
        
        # Step 2: Search the web
        search_results = self.search_web(question, num_sources)
        print(f"Found {len(search_results)} potential sources")
        
        # Step 3: Fetch and analyze pages
        answers = []
        for result in search_results:
            page = self.fetch_page(result['url'])
            if page:
                answer = self.extract_answer(page, analysis)
                if answer:
                    answers.append({
                        'answer': answer,
                        'source': result['url'],
                        'confidence': self._calculate_confidence(answer, analysis)
                    })
        
        # Step 4: Return the best answer
        if not answers:
            return {"status": "No answers found"}
        
        answers.sort(key=lambda x: x['confidence'], reverse=True)
        return {
            "question": question,
            "best_answer": answers[0]['answer'],
            "source": answers[0]['source'],
            "confidence": answers[0]['confidence'],
            "all_answers": answers
        }

    def _calculate_confidence(self, answer, analysis):
        """Calculate confidence score for an answer"""
        confidence = 0.5  # Base confidence
        
        # Type matching
        if analysis['intent'] == 'count' and isinstance(answer, int):
            confidence += 0.3
        elif analysis['intent'] == 'date' and re.match(r'.*\d{4}.*', str(answer)):
            confidence += 0.3
        elif analysis['intent'] == 'list' and isinstance(answer, list):
            confidence += 0.3
        
        # Time constraints
        if analysis['time_constraints'] and str(answer):
            for constraint in analysis['time_constraints']:
                if constraint[0] == 'range':
                    years = re.findall(r'\b(19|20)\d{2}\b', str(answer))
                    if any(constraint[1] <= int(y) <= constraint[2] for y in years):
                        confidence += 0.2
        
        return min(0.99, max(0.1, confidence))  # Keep within bounds

# Example usage ?
if __name__ == "__main__":
    agent = WebSearchAgent()
    
    questions = [
        "How many studio albums were published by Taylor Swift between 2010 and 2015?",
        "When was Albert Einstein born?",
        "What is the capital of Australia?",
        "List the members of The Beatles"
    ]
    
    for question in questions:
        print("\n" + "="*50)
        print(f"Question: {question}")
        result = agent.answer_question(question)
        
        print("\nBest Answer:")
        if isinstance(result['best_answer'], list):
            for item in result['best_answer']:
                print(f"- {item}")
        else:
            print(result['best_answer'])
        
        print(f"\nSource: {result['source']}")
        print(f"Confidence: {result['confidence']:.0%}")



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:
        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 = 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)

    # 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
        try:
            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}"})

    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('score', 'N/A')}% "
            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)
        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(
        """
        **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 seperate action or even to answer the questions in async.
        """
    )

    gr.LoginButton()

    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(
        fn=run_and_submit_all,
        outputs=[status_output, results_table]
    )

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)