app_old.py

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

import asyncio
import nest_asyncio
from typing import List, Dict, Any
from llama_index.core.agent import ReActAgent
from llama_index.core.agent.workflow import AgentWorkflow
from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI
from youtube_tool import youtube_transcript_tool, youtube_transcript_snippet_tool
#from multiple_tools import round_to_two_decimals_tool, text_inverter_tool, google_web_search_tool, wikipedia_search_tool
from multiple_tools import round_to_two_decimals_tool, text_inverter_tool, google_web_search_tool, wikipedia_search_tool, transcribe_audio_tool, excel_food_sales_sum_tool, parse_file_and_summarize_tool, solve_chess_image_tool, vegetable_classifier_tool
from agent import smart_agent
from llama_index.llms.openai import OpenAI
import re
#-----------------------------------------------------------------


# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
HF_key = os.getenv("HF_TOKEN")
OpenAI_key = os.getenv("OPEN_AI_TOKEN")

# --- Basic Agent Definition ---

# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
    def __init__(self):
        print("BasicAgent initialized. . . .")
        
        #self.llm = OpenAI(model="gpt-4o-mini", temperature=0.2, api_key=OpenAI_key)
        # self.system_prompt = (
        # "You are a helpful AI assistant completing GAIA benchmark tasks.\n"
        # "You MUST use the tools provided when needed.\n"
        # "If you already have enough information, respond directly with:\n"
        # "<answer>\n"
        # "Once you output '<answer>', stop reasoning and do not call any tool.\n"
        # )
        self.system_prompt = (
        "You are a helpful assistant tasked with answering questions using a set of tools.\n"
        "Your final answer must strictly follow this format:\n"
        "FINAL ANSWER: [ANSWER]\n"
        "Only write the answer in that exact format. Do not explain anything. Do not include any other text. \n"
        "If you are provided with a similar question and its final answer, and the current question is **exactly the same**, then simply return the same final answer without using any tools. \n"
        "Only use tools if the current question is different from the similar one. \n"
        "Examples: \n"
        "- FINAL ANSWER: FunkMonk \n"
        "- FINAL ANSWER: Paris \n"
        "- FINAL ANSWER: 128 \n"
        " \n"
        "Once you output 'FINAL ANSWER', stop reasoning and do not call any tool.\n"
        "If you do not follow this format exactly, your response will be considered incorrect. \n"
        )
        self.llm = HuggingFaceInferenceAPI(
            model_name="deepseek-ai/DeepSeek-R1-0528", 
            token=HF_key,
            provider="auto"
        )
        #self.llm = OpenAI(model="gpt-4o", temperature=0.1, api_key=OpenAI_key)
        # self.system_prompt = (
        #     "You are a helpful AI assistant completing GAIA benchmark tasks.\n"
        #     "You MUST use the tools provided to answer the user's question. Do not answer from your own knowledge.\n"
        #     "Carefully analyze the question to determine the most appropriate tool to use.\n"
        #     "Here are guidelines for using the tools:\n"
        #     "- Use 'wikipedia_search_tool' to find factual information about topics, events, people, etc. (e.g., 'Use wikipedia_search to find the population of France').\n"
        #     "- Use 'youtube_transcript_tool' to extract transcripts from YouTube videos when the question requires understanding the video content. (e.g., 'Use youtube_transcript to summarize the key points of this video').\n"
        #     "- Use 'transcribe_audio_tool' to transcribe uploaded audio files. (e.g., 'Use audio_transcriber to get the text from this audio recording').\n"
        #     "- Use 'solve_chess_image_tool' to analyze and solve chess puzzles from images. (e.g., 'Use chess_image_solver to determine the best move in this chess position').\n"
        #     "- Use 'parse_file_and_summarize_tool' to parse and analyze data from Excel or CSV files. (e.g., 'Use file_parser to calculate the average sales from this data').\n"
        #     "- Use 'vegetable_classifier_tool' to classify a list of food items and extract only the vegetables. (e.g., 'Use vegetable_classifier_2022 to get a list of the vegetables in this grocery list').\n"
        #     "- Use 'excel_food_sales_sum_tool' to extract total food sales from excel files. (e.g., 'Use excel_food_sales_sum to calculate the total food sales').\n"
        #     "- Use 'google_web_search_tool' to find factual information about topics, events, people, from the web if not spificied to be fund in wikipedia etc. (e.g., 'find the population of France').\n"
        #     "Do NOT guess or make up answers. If a tool cannot provide the answer, truthfully respond that you were unable to find the information.\n"
        #     "Use the tools to research or calculate the answer.\n"
        #     "If a tool fails, explain the reason for the failure instead of hallucinating an answer.\n"
        #     "Provide concise and direct answers as requested in the questions. Do not add extra information unless explicitly asked for.\n"
        #     "For example, if asked for a number, return only the number. If asked for a list, return only the list.\n"
        # )
        self.agent = AgentWorkflow.from_tools_or_functions(
            [
                wikipedia_search_tool, youtube_transcript_tool, youtube_transcript_snippet_tool, round_to_two_decimals_tool, text_inverter_tool, google_web_search_tool,transcribe_audio_tool, excel_food_sales_sum_tool, parse_file_and_summarize_tool, solve_chess_image_tool, vegetable_classifier_tool
             ],
            llm=self.llm,
            system_prompt=self.system_prompt,
        )
    def extract_answer(self, text: str) -> str:
        match = re.search(r"(?<=<answer>)(.*?)(?=</answer>)", text)
        return match.group(1) if match else ""
    
    async def run(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        # answer = await self.agent.run(question)
        answer = await self.agent.run(
            f"{question}\n\nIf you have enough information, respond with a concise final answer.",
            max_iterations=10
        )
        return str(answer)
        #return self.extract_answer(str(answer));
        # if hasattr(answer, "output"):
        #     print(f"Agent returning answer: {answer}")
        #     return str(answer.output)
        # else:
        #     print(f"Agent returning answer: {answer}")
        #     return str(answer)
        
    def __call__(self, question: str) -> str:
        return asyncio.run(self.run(question))




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)

    #3A

    async def run_all_questions(questions_data):
        answers_payload = []
        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:
                answer = await agent.run(question_text)  # await coroutine
                answers_payload.append({"task_id": task_id, "submitted_answer": answer})
                print(f"Answered Task {task_id}:: {answer}")
            except Exception as e:
                answers_payload.append({"task_id": task_id, "submitted_answer": f"AGENT ERROR: {e}"})
                print(f"Error on Task {task_id}: {e}")
        return answers_payload

    answers_payload = asyncio.run(run_all_questions(questions_data))
    #answers_payload = run_all_questions(questions_data)
    
    #3B

    # 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)