app.py

import asyncio
import os
from pathlib import Path
import gradio as gr
import mimetypes
import requests
import pandas as pd
from llama_index.core.llms import ChatMessage, TextBlock, ImageBlock, AudioBlock
from llama_index.llms.gemini import Gemini
from llama_index.core.agent.workflow import ReActAgent, AgentOutput
from llama_index.core.tools import FunctionTool
from llama_index.tools.duckduckgo import DuckDuckGoSearchToolSpec
from llama_index.tools.wikipedia import WikipediaToolSpec
from dotenv import load_dotenv
from pydantic import ValidationError

try:
    import mlflow
    mlflow.set_experiment("final_handson")
    mlflow.llama_index.autolog()
except ImportError:
    pass


load_dotenv()

# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
SYSTEM_PROMPT = (Path(__file__).parent / 'system_prompt.txt').read_text()
GOOGLE_API_KEY = os.environ['GOOGLE_API_KEY']

# --- Basic Agent Definition ---
class BasicAgent:
    def __init__(self, max_calls_per_minute=15):
        search_tool = FunctionTool.from_defaults(DuckDuckGoSearchToolSpec().duckduckgo_full_search)
        wikipedia_load_tool = FunctionTool.from_defaults(WikipediaToolSpec().load_data)
        wikipedia_search_tool = FunctionTool.from_defaults(WikipediaToolSpec().search_data)
        self._tools = [search_tool, wikipedia_load_tool, wikipedia_search_tool]

        self._llm = Gemini(api_key=GOOGLE_API_KEY, model="models/gemini-2.0-flash-lite", max_tokens=1600)
        self._agent = ReActAgent(tools=self._tools, llm=self._llm)
        # Modify the react prompt.
        self._agent.update_prompts({"react_header": SYSTEM_PROMPT})
        print("BasicAgent initialized.")
        self._min_call_interval = 1/max_calls_per_minute

    async def __call__(self, question: ChatMessage) -> str:
        question.blocks[0].text
        print(f"Agent received question (first 50 chars): {question.blocks[0].text[:50]}...")
        # Here, we need to rate limit
        agent_output = await self._agent.run(user_msg=question)
        print(f"Agent returning answer: {agent_output}")
        response_parts = str(agent_output).split('FINAL ANSWER: ')
        if len(response_parts) > 1:
            response = response_parts[-1]
        else:
            response = str(agent_output)
        return response.strip()


def fetch_questions(api_url: str = DEFAULT_API_URL):
    questions_url = f"{api_url}/questions"
    print(f"Fetching questions from: {questions_url}")
    response = requests.get(questions_url, timeout=15)
    try:
        response.raise_for_status()
    except Exception:
        print(f"Response text: {response.text[:500]}")
        raise
    questions_data = response.json()
    return questions_data


def get_media_type(filename: str):
    media_type = mimetypes.guess_type(filename)[0]
    if media_type is not None:
        return media_type.split('/')[0]


def get_media_content(item):
    if item.get('file_name'):
        file_response = requests.get(f"{DEFAULT_API_URL}/files/{item.get('task_id')}")
        if file_response:
            media_type = get_media_type(item.get('file_name'))
            if media_type == 'image':
                return ImageBlock(image=file_response.content)
            elif media_type == 'text':
                return TextBlock(text=file_response.content)
            # Audio currently not supported
            #elif media_type == 'audio':
            #    return AudioBlock(audio=file_response.content)


def create_question_message(item):
    question_text = item.get("question")
    msg_blocks = [TextBlock(text=question_text)]
    media_block = get_media_content(item)
    if media_block is not None:
        msg_blocks.append(media_block)
    question_message = ChatMessage(role="user", blocks=msg_blocks)
    return question_message


async def answer_question(agent, item, answers_payload, results_log):
    task_id = item.get("task_id")
    question_text = item.get("question")
    try:
        question_message = create_question_message(item)
    except ValidationError:
        print(f"Skipping item for which the question could not be processed: {item}")
        return
    if not task_id:
        print(f"Skipping item with missing task_id: {item}")
        return
    try:
        submitted_answer = await agent(question_message)

        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}"})


async 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
    submit_url = f"{api_url}/submit"

    # 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 ( 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
    try:
        questions_data = fetch_questions()
        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.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 requests.exceptions.RequestException as e:
        print(f"Error fetching questions: {e}")
        return f"Error fetching 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:
        await answer_question(agent, item, answers_payload, results_log)

    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)