app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd

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

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
import os
from typing import List, Dict, Any, Optional
from smolagents import CodeAgent, Tool, tool, LiteLLMModel
from cool_agent import create_agent
from reformulator import prepare_response

import json
import re
from datetime import datetime

custom_role_conversions = {"tool-call": "assistant", "tool-response": "user"}

from linkup import LinkupClient


def get_image_description(file_name: str, question: str, visual_inspection_tool) -> str:
    prompt = f"""Write a caption of 5 sentences for this image. Pay special attention to any 
    details that might be useful for someone answering the following question:
{question}. But do not try to answer the question directly!
Do not add any information that is not present in the image."""
    return visual_inspection_tool(image_path=file_name, question=prompt)


def get_document_description(file_path: str, question: str, document_inspection_tool) -> str:
    prompt = f"""Write a caption of 5 sentences for this document. Pay special attention to any 
    details that might be useful for someone answering the following question:
{question}. But do not try to answer the question directly!
Do not add any information that is not present in the document."""
    return document_inspection_tool.forward_initial_exam_mode(file_path=file_path, question=prompt)


def get_single_file_description(file_path: str, question: str, visual_inspection_tool,
                                document_inspection_tool):
    file_extension = file_path.split(".")[-1]
    if file_extension in ["png", "jpg", "jpeg"]:
        file_description = f" - Attached image: {file_path}"
        file_description += (
            f"\n     -> Image description: "
            f"{get_image_description(file_path, question, visual_inspection_tool)}"
        )
        return file_description
    elif file_extension in ["pdf", "xls", "xlsx", "docx", "doc", "xml"]:
        file_description = f" - Attached document: {file_path}"
        image_path = file_path.split(".")[0] + ".png"
        if os.path.exists(image_path):
            description = get_image_description(image_path, question, visual_inspection_tool)
        else:
            description = get_document_description(file_path, question, document_inspection_tool)
        file_description += f"\n     -> File description: {description}"
        return file_description
    elif file_extension in ["mp3", "m4a", "wav"]:
        return f" - Attached audio: {file_path}"
    else:
        return f" - Attached file: {file_path}"


class BasicAgent:
    def __init__(self):
        """
        Initialize the GAIA dataset agent with SmoLagents.

        Args:
            api_key: API key for the LLM provider
            model_name: Name of the LLM model to use
        """
        print("BasicAgent initialized.")

        # Initialize the agent
        agent_assets = create_agent()
        self.agent = agent_assets["agent"]
        self.visual_inspection_tool = agent_assets["visualizer"]
        self.document_inspection_tool = agent_assets["text_inspection_tool"]
        self.model = agent_assets["model"]
        self.current_question = None

    def assign_current_question(self, question: str):
        self.current_question = question

    def get_current_question(self):
        return self.current_question

    def __call__(self, question: str, file_name: str = None) -> str:
        """
        Process a question and return an answer.

        Args:
            question: The question to answer

        Returns:
            The answer to the question
        """
        words = question.split()
        joined_words = " ".join(words[:20])
        print(f"Agent received question (first 20 words): {joined_words}...")

        # Create a prompt for the agent

        full_prompt = """You have one question to answer. It is paramount that you provide a 
        correct answer.
        Give it all you can: I know for a fact that you have access to all the relevant tools to 
        solve it and find the correct answer (the answer does exist). Failure or 'I cannot 
        answer' or 'None found' will not be tolerated, success will be rewarded.
        Run verification steps if that's needed, you must make sure you find the correct answer!
        Here is the task:
        """ + question

        if file_name:
            prompt_use_files = ("\n\nTo solve the task above, you will have to use this attached "
                                "file:")
            prompt_use_files += get_single_file_description(
                file_name, question, self.visual_inspection_tool,
                self.document_inspection_tool
            )
            full_prompt += prompt_use_files

        try:
            # Run the agent
            response = self.agent.run(full_prompt)
            self.assign_current_question(full_prompt)
            # Clean up the response
            # Remove any system-prompt-like text at the beginning
            cleaned_response = re.sub(r'^.*?Answer:', '', response, flags=re.DOTALL).strip()

            if not cleaned_response:
                cleaned_response = response  # Fallback to original if cleaning removes everything
            words = cleaned_response.split()
            joined_words = " ".join(words[:20])
            print(f"Agent returning answer (first 20 words): {joined_words}...")
            return cleaned_response
        except Exception as e:
            error_msg = f"Error processing question: {str(e)}"
            print(error_msg)
            return error_msg


def download_file(task_id, base_url, filename="MY_NAME", headers=None):
    """
    Download a file from the API endpoint and save it locally.

    Args:
        task_id (str): The task ID for the file to download
        base_url (str): Base URL of the API (e.g., 'https://api.example.com')
        filename (str): Local filename to save as (default: 'MY_NAME')
        headers (dict): Optional headers for authentication/authorization

    Returns:
        bool: True if download successful, False otherwise
    """
    try:
        # Construct the full URL
        url = f"{base_url}/files/{task_id}"

        # Make the GET request
        response = requests.get(url, headers=headers, stream=True)

        # Check if request was successful
        response.raise_for_status()

        # Save the file locally
        with open(filename, 'wb') as file:
            for chunk in response.iter_content(chunk_size=8192):
                if chunk:
                    file.write(chunk)

        print(f"File downloaded successfully as '{filename}'")
        return True
    except Exception as e:
        print(f"An exception occurred during file download: {e}")
        return False


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 idx, item in enumerate(questions_data):
        print(f"=" * 100)
        print(f"Question {idx + 1}: {item}")
        task_id = item.get("task_id")
        question_text = item.get("question")
        file_name = item.get("file_name")
        if file_name:
            # download and save the file
            download_file(task_id=task_id, base_url=api_url, filename=file_name)
        if not task_id or question_text is None:
            print(f"Skipping item with missing task_id or question: {item}")
            continue
        try:
            _ = agent(question_text, file_name)
            agent_memory = agent.agent.write_memory_to_messages(summary_mode=True)

            final_result = prepare_response(agent.get_current_question(), agent_memory,
                                            reformulation_model=agent.model)

            submitted_answer = str(final_result)
            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 '"
                     f"{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)