app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
import smolagents
from smolagents import DuckDuckGoSearchTool, VisitWebpageTool
import time  # Added: For sleep functionality
from functools import lru_cache  # Added: For caching search results

from youtube_transcript_api import YouTubeTranscriptApi
import re


class YouTubeVideoTool:
    def __init__(self):
        self.name = "youtube_video_tool"
        
    def __call__(self, query):
        """
        Extract information from a YouTube video.
        
        Args:
            query: Either a YouTube URL or video ID
        
        Returns:
            String with the transcript of the video
        """
        try:
            # Extract video ID from URL if needed
            video_id = self._extract_video_id(query)
            if not video_id:
                return "Could not extract a valid YouTube video ID"
                
            # Get the transcript
            transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
            
            # Combine the transcript text
            transcript_text = " ".join([item['text'] for item in transcript_list])
            
            return f"Transcript from YouTube video {video_id}:\n{transcript_text}"
        except Exception as e:
            return f"Error processing YouTube video: {str(e)}"
    
    
    
    def _extract_video_id(self, url_or_id):
        """Extract YouTube video ID from various URL formats or return the ID if already provided."""
        # Handle direct video ID
        if len(url_or_id) == 11 and re.match(r'^[A-Za-z0-9_-]{11}$', url_or_id):
            return url_or_id
            
        # Common YouTube URL patterns
        patterns = [
            r'(?:youtube\.com\/watch\?v=|youtu\.be\/|youtube\.com\/embed\/|youtube\.com\/v\/)([A-Za-z0-9_-]{11})',
            r'youtube\.com\/watch\?.*v=([A-Za-z0-9_-]{11})',
            r'youtube\.com\/shorts\/([A-Za-z0-9_-]{11})'
        ]
        
        for pattern in patterns:
            match = re.search(pattern, url_or_id)
            if match:
                return match.group(1)
                
        return None        


# TOOLS
search_tool = DuckDuckGoSearchTool()
visit_webpage = VisitWebpageTool()
youtube_tool = YouTubeVideoTool()

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

# Cache Wrapper
@lru_cache(maxsize=100)
def cached_search(query):
    return search_tool(query)

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------


class BasicAgent:
    
    
    def __init__(self, model=None, tools=None):
        self.model = model
        self.tools = tools if tools is not None else []
        self.history = []
        print(f"BasicAgent initialized with model: {model} and {len(self.tools)} tools.")
        
    
    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        # Implement your agent logic here using self.model and self.tools
        final_answer = self.process_question(question)
        print(f"Agent returning answer: {final_answer[:50]}...")
        return final_answer

    
    
    def process_question(self, question:str) -> str:
        try:
            # Check if this is a request about a YouTube video
            youtube_patterns = ["youtube.com", "youtu.be", "watch youtube", "youtube video"]
            use_youtube_tool = any(pattern in question.lower() for pattern in youtube_patterns)
            
            if use_youtube_tool and any(isinstance(tool, YouTubeVideoTool) for tool in self.tools):
                # Extract potential YouTube URL or ID
                url_match = re.search(r'(?:https?:\/\/)?(?:www\.)?(?:youtube\.com|youtu\.be)\/[^\s]+', question)
                youtube_url = url_match.group(0) if url_match else question
                
                # Use YouTube tool
                youtube_info = next(tool for tool in self.tools 
                                   if isinstance(tool, YouTubeVideoTool))(youtube_url)
                
                relevant_info = self._extract_key_info(youtube_info, question)
                return self._formulate_direct_answer(relevant_info, question)
            else:
                # Use regular search
                search_results = cached_search(question) if any(isinstance(tool, DuckDuckGoSearchTool) for tool in self.tools) else "No search results available."
                relevant_info = self._extract_key_info(search_results, question)
                return self._formulate_direct_answer(relevant_info, question)
        except Exception as e:
            if "too many requests" in str(e).lower():
                time.sleep(2)
                try:
                    search_results = cached_search(question)
                    relevant_info = self._extract_key_info(search_results, question)
                    return self._formulate_direct_answer(relevant_info, question)
                except:
                    return self._get_fallback_answer(question)
            return self._get_fallback_answer(question)
    
    
    
    def _extract_key_info(self, search_results, question):
        # Split results into sentences and find most relevant
        sentences = search_results.split('. ')
        if len(sentences) <= 3:
            return search_results[:250]  # If few sentences, return first portion
        
        # Try to find sentence with keywords from question
        keywords = [w for w in question.lower().split() if len(w) > 3]
        for sentence in sentences:
            sentence_lower = sentence.lower()
            if any(keyword in sentence_lower for keyword in keywords):
                return sentence
        
        # Fallback to first few sentences
        return '. '.join(sentences[:2])

    
    
    def _formulate_direct_answer(self, relevant_info, question):
        if self.model:
            return f"Based on the search: {relevant_info}"
        return relevant_info
    
    
    
    def _get_fallback_answer(self, question):
        return f"Based on the information available, I cannot provide a specific answer to your question about {question.split()[0:3]}..."



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(model= 'gemini/gemini-2.0-flash-exp', tools=[search_tool, visit_webpage, youtube_tool])
    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 idx, item in enumerate(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})
            if idx % 5 == 0 and idx > 0:  # Added: Add delay every 5 questions
                time.sleep(1)  # Wait 1 second between batches to avoid rate limiting
        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)