app.py

import os
import gradio as gr
import requests
import base64
import time
import pandas as pd
from dotenv import load_dotenv
from llama_index.readers.web import SimpleWebPageReader
from llama_index.llms.gemini import Gemini
from llama_index.tools.wikipedia import WikipediaToolSpec
from llama_index.readers.youtube_transcript import YoutubeTranscriptReader
from llama_index.core.tools import FunctionTool
from llama_index.tools.duckduckgo import DuckDuckGoSearchToolSpec
from llama_index.tools.arxiv import ArxivToolSpec
from llama_index.core.agent.workflow import AgentWorkflow

# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# --- Basic Agent Definition ---
class BasicAgent:
    def __init__(self):
        # Initialize LLM
        load_dotenv()
        self.llm = Gemini(
            model_name="models/gemini-2.0-flash",
            temperature=0.1,
            max_tokens=4096
        )
        
        # Define tools
        def load_video_transcript(video_url: str) -> dict:
            """Get the transcript of a YouTube video."""
            try:
                loader = YoutubeTranscriptReader()
                documents = loader.load_data(ytlinks=[video_url])
                
                if documents and len(documents) > 0:
                    return {"video_transcript": documents[0].text}
                else:
                    return {"video_transcript": "No transcript available for this video."}
            except Exception as e:
                return {"video_transcript": f"Error obtaining transcript: {str(e)}"}

        load_video_transcript_tool = FunctionTool.from_defaults(
            load_video_transcript,
            name="load_video_transcript",
            description="Load the transcript of the given video using the link. If some calls fail, we can still use this tool for others."
        )

        def web_page_reader(url: str) -> dict:
            """Read and extract content from a web page."""
            try:
                documents = SimpleWebPageReader(html_to_text=True).load_data([url])
                return {"webpage_content": "\n".join([doc.text for doc in documents])}
            except Exception as e:
                return {"webpage_content": f"Error reading the web page: {str(e)}"}
        
        web_page_reader_tool = FunctionTool.from_defaults(
            web_page_reader,
            name="web_page_reader",
            description="Visit a web page at the given URL and return its textual content."
        )

        def duck_duck_go_search_tool(query: str) -> dict:
            """Search the web using DuckDuckGo."""
            try:
                raw_results = DuckDuckGoSearchToolSpec().duckduckgo_full_search(query, max_results=5)
                texts = [f"Title: {res['title']}\nURL: {res['link']}\nContent: {res['body']}" for res in raw_results]
                full_text = "\n\n".join(texts)
                return {"web_search_results": full_text}
            except Exception as e:
                return {"web_search_results": f"Error searching the web: {str(e)}"}
        
        duckduckgo_search_tool = FunctionTool.from_defaults(
            duck_duck_go_search_tool,
            name="duck_duck_go_search_tool",
            description="Search the web and refine the result into a high-quality response. Use this tool when others don't seem appropriate."
        )
        
        def wikipedia_search(page_title: str, query: str) -> dict:
            """Search information on Wikipedia."""
            try:
                text = WikipediaToolSpec().load_data(page=page_title)

                if not text:
                    text = WikipediaToolSpec().search_data(query)
                
                return {"wiki_search_results": text}
            except Exception as e:
                return {"wiki_search_results": f"Error searching Wikipedia: {str(e)}"}
        
        wikipedia_search_tool = FunctionTool.from_defaults(
            wikipedia_search,
            name="wikipedia_search",
            description="Search Wikipedia and convert the results into a high-quality response."
        )
        
        # Create a list of all tools
        tools = [
            duckduckgo_search_tool,
            load_video_transcript_tool, 
            wikipedia_search_tool, 
            web_page_reader_tool
        ]
        
        # Create system prompt
        system_prompt = """
        You're an AI agent designed for question answering. Keep your answers concise or even one word when possible. 
        You have access to a bunch of tools, utilize them well to reach answers.
        """
        
        # Initialize the agent workflow
        self.agent = AgentWorkflow.from_tools_or_functions(tools, llm=self.llm, system_prompt=system_prompt)
        print("BasicAgent initialized.")

    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        
        try:
            # Process file data if present
            if "file_data:" in question:
                parts = question.split("file_data:", 1)
                question_text = parts[0].strip()
                question = f"{question_text}\n[This question includes attached file data]"
            
            # Run the agent
            response = self.agent.run(question)
            
            # Extract final answer
            final_answer = response.response
            
            print(f"Agent returning answer: {final_answer[:50]}...")
            return final_answer
        except Exception as e:
            error_message = f"Error processing question: {str(e)}"
            print(error_message)
            return error_message

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"
    files_url = f"{api_url}/files/"

    # 1. Instantiate 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
    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=30)
        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:
        time.sleep(20)  # Added delay between questions
        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:
            encoded = None
            if item.get("file_name") != "":
                response = requests.get(files_url + task_id)
                response.raise_for_status()

                data = response.content

                encoded = base64.b64encode(data).decode('utf-8')
            
            if encoded is not None:
                submitted_answer = agent(question_text + "\nfile_data: " + encoded)
            else:
                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. Log in to your Hugging Face account using the button below. This uses your HF username for submission.
        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
        ---
        **Disclaimer:**
        Once you click the "Submit" button, it may take some time for the agent to process all questions.
        """
    )

    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)

    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)