app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
from io import StringIO
import logging
from pathlib import Path
from prompt_settings import verification_of_final_answer, verification_of_final_answer2, yaml_template, yaml_template2
from duckduckgo_search import DDGS

from llama_index.core import (
    VectorStoreIndex,
    SimpleDirectoryReader,
    Settings,
    set_global_handler
)

from llama_index.core.tools import FunctionTool
from llama_index.agent.openai import OpenAIAgent
from llama_index.llms.openai import OpenAI as LlamaOpenAI

from openai import OpenAI as OpenAIClient

#per i file multimediali
import base64
import json
from PIL import Image
from io import BytesIO
from typing import List
import re
import importlib.metadata
import random
import time


set_global_handler("simple")  # imposta un handler semplice per il logging
logging.getLogger().setLevel(logging.DEBUG)  # imposta il livello di log a DEBUG

class BasicAgent:
    def __init__(self):
        try:
            print("coso Initializing LlamaIndex-based agent...")

            # Leggi la chiave OpenAI dall'ambiente
            openai_api_key = os.getenv("OPENAI_API_KEY")
            if not openai_api_key:
                raise ValueError("OPENAI_API_KEY not set!")
    
            # Imposta il logger
            logging.basicConfig(level=logging.DEBUG)
    
            
    
            # Tool per estrarre ingredienti
            ingredient_tool = FunctionTool.from_defaults(
                name="extract_ingredients",
                fn=extract_ingredients,
                description="Extracts and returns a comma-separated, alphabetized list of ingredients for a pie filling from a transcription string."
            )

            search_tool = FunctionTool.from_defaults(
                name="web_search",
                fn=web_search,
                description="Performs a DuckDuckGo search and returns the top 3 results."
            )

            log_thought_tool = FunctionTool.from_defaults(
                name="log_thought",
                fn=log_thought,
                description="Logs the agent's thought process for debugging purposes."
            )

            sum_list_tool = FunctionTool.from_defaults(
                name="sum_list",
                fn=sum_list,
                description="Takes a list of float numbers and returns their sum."
            )

            final_answer = FunctionTool.from_defaults(
                name="final_answer",
                fn=final_answer_tool,
                description = 
                    '''
                    Use this ONLY at the end. You must pass a string containing ONLY the final answer, with no explanations or formatting. 
                    If the answer is a list, pass it as a plain comma-separated string. 
                    Example: 'cornstarch, granulated sugar, freshly squeezed lemon juice, ripe strawberries, vanilla extract'
                    '''
            )

            is_food_tool = FunctionTool.from_defaults(
                name="is_food",
                fn=is_food,
                description="Takes a list of item names (such as menu categories) and returns a string tagging each item as either food or not. The result is a comma-separated list like 'burgers: True, soda: False'."
            )

            
            # Registra il tool
            #Settings.tools = [ingredient_tool]

            llm = LlamaOpenAI(
                model="gpt-4o",
                temperature=0.0,
                api_key=openai_api_key
            )
            
            
            self.agent = OpenAIAgent.from_tools(
                tools = [ingredient_tool, log_thought_tool, sum_list_tool, search_tool, is_food_tool, final_answer], 
                llm = llm, 
                verbose = True,
                max_steps=30
            )
    
            # Client OpenAI per chiamate esterne (immagini/audio)
           
            self.client = OpenAIClient(api_key=openai_api_key)  # per .chat, .audio, ecc.
            
            Settings.llm = llm
    
            # Carica i documenti
            self.documents = SimpleDirectoryReader("data").load_data()
            self.index = VectorStoreIndex.from_documents(self.documents, settings=Settings)
            self.query_engine = self.index.as_query_engine()
    
            print("coso Agent ready.")


        except Exception as e:
            import traceback
            print_coso(f"Error instantiating agent: {e}")
            traceback.print_exc()



    def __call__(self, question: str, file_info: str = "") -> str:
        print_coso(f"Received question: {question[:100]}")

        # Prova a decodificare JSON
        try:
            q_data = json.loads(question)
        except json.JSONDecodeError:
            q_data = {"question": question}

        text = q_data.get("question", "")
        #file_info = q_data.get("file_name", "")

        print_coso(f"__call__ q_data: {q_data}")
        print_coso(f"__call__ text: {text}")
        print_coso(f"__call__ file_info: {file_info}")

        text = f"{yaml_template} {verification_of_final_answer2} {text}"
        
        # Se è presente un file, gestiscilo

        risposta = ""
        
        if file_info.endswith((".png", ".jpg", ".jpeg")):
            print("coso Image file detected, processing with GPT-4o")
            image = get_or_download_image(file_info)
            response = self._ask_gpt4o_with_image(image, text)
            risposta = response

        elif file_info.endswith(".wav") or file_info.endswith(".mp3"):
            print("coso Audio file detected, processing with Whisper")
            audio_bytes = get_or_download_audio(file_info)
            if audio_bytes is not None:
                audio_file = BytesIO(audio_bytes) 
                print_coso(f"in mp3 audio_file: {audio_file}")
                audio_file.name = file_info
                transcription = self._transcribe_audio(audio_file)
                prompt_con_audio = (
                    f"The following is the transcription of an audio file related to the question.\n"
                    f"---\n"
                    f"{transcription}\n"
                    f"---\n"
                    f"Now, based on this transcription, answer the following question:\n"
                    f"{question}"
                )
                risposta = self._ask_gpt4o(prompt_con_audio)
            else:
                risposta = "Error loading audio file"

        elif file_info.endswith(".py"):
            print_coso("Python code file detected")
            code_content = get_or_download_code(file_info)
            print_coso(f"Python code before prompt: {code_content}")
            prompt_python = (
                "The following Python code is attached. Please analyze it and provide the final output of the code; your final answer must be only the final output of the code, don not provide any explanation of presentation of the result.\n\n"
                f"{code_content}\n\n"
                f"Question: {question}"
            )
            risposta = self._ask_gpt4o(prompt_python)

        elif file_info.endswith(".xlsx"):
            print_coso("Excel file detected")
            excel_text = _load_excel_as_text(file_info)
            print_coso(f"Excel before prompt: {excel_text}")
            prompt = (
                "The following is the text extracted from an Excel spreadsheet, the symbol `|` is used to separate each column. \n"
                "Please use it to answer the question that follows:\n\n"
                f"{excel_text}\n\n"
                f"Question: {question}\n"
                "Provide only the final answer. If it is a number, format it with two decimal places if relevant. Unless it is specifically requested, return only the final numeric result, as a plain number with no currency symbol, no commas, and no additional text. For example, write '89706.00', not '$89,706.00'. Do not explain."
            )
            risposta = self._ask_gpt4o(prompt)

        elif file_info.endswith(".txt"):
            print("coso Text file detected")
            text_content = self._load_text(file_info)
            risposta = self._ask_gpt4o(text_content)
        else:
            print_coso("nessun file allegato")
            # Altrimenti gestisci solo testo
            risposta = self._ask_gpt4o(text)

        print_coso(f"risposta: {risposta}")
        return risposta


        
    def _ask_gpt4o(self, text: str) -> str:
        response = self.agent.chat(text)
        print_coso("==== Full Agent Response ====")
        print_coso(response)
        print_coso("=============================")
        return str(response)
        '''
        messages = [{"role": "user", "content": text}]
        response = self.client.chat.completions.create(
            model="gpt-4o-mini",
            temperature=0,
            messages=messages
        )
        return response.choices[0].message.content.strip()
        '''

    def _ask_gpt4o_with_image(self, image: Image.Image, question: str) -> str:
        buffered = BytesIO()
        image.save(buffered, format="PNG")
        buffered.seek(0)
        image_bytes = buffered.read()

        response = self.client.chat.completions.create(
            model="gpt-4o",  #ATTENZIONE QUI MODELLO NON MINI
            temperature=0,
            messages=[{
                "role": "user",
                "content": [
                    {"type": "text", "text": question},
                    {"type": "image_url", "image_url": {"url": "data:image/png;base64," + base64.b64encode(image_bytes).decode()}}
                ]
            }]
        )
        return response.choices[0].message.content.strip()

    def _transcribe_audio(self, audio_bytes: BytesIO) -> str:
        #audio_file = BytesIO(audio_bytes)
        #transcription = self.client.audio.transcriptions.create(model="whisper-1", file=audio_bytes)
        transcription = self.client.audio.transcriptions.create(
            file=audio_bytes,
            model="whisper-1",
            #api_key=os.getenv(openai_api_key)
        )
        print_coso(f"usato _transcribe_audio: {transcription}")
        return transcription.text.strip()

    def _load_image(self, data: str) -> Image.Image:
        print_coso(f"_load_image: {data}")
        try:
            coso = Image.open(BytesIO(base64.b64decode(data)))
            return coso
        except Exception as e:
            print_coso(f"_load_image error: {e}")
            return None            

    def _load_bytes(self, file_name: str) -> bytes:
        file_path = os.path.join("/data", file_name)
        try:
            with open(file_path, "rb") as f:
                return f.read()
        except Exception as e:
            print_coso(f"Error loading file {file_path}: {e}")
            return None
    
    def _load_text(self, data: str) -> str:
        return base64.b64decode(data).decode("utf-8")



def get_or_download_image(file_name: str) -> Image.Image:
    import os
    import requests
    from PIL import Image
    from io import BytesIO

    file_path = os.path.join("data", file_name)
    hf_token = os.getenv("HF_TOKEN_READ")

    if not hf_token:
        print("[ERRORE] HF_TOKEN_READ non trovato. Imposta la variabile d'ambiente HF_TOKEN_READ.")
        return None

    if not os.path.exists(file_path):
        print(f"[INFO] File {file_name} non trovato in /data, lo scarico...")

        url = f"https://huggingface.co/datasets/gaia-benchmark/GAIA/resolve/main/2023/validation/{file_name}"
        headers = {"Authorization": f"Bearer {hf_token}"}

        try:
            response = requests.get(url, headers=headers)
            response.raise_for_status()
            with open(file_path, "wb") as f:
                f.write(response.content)
            print(f"[INFO] Scaricato e salvato in {file_path}")
        except Exception as e:
            print(f"[ERRORE] Impossibile scaricare l'immagine: {e}")
            return None

    try:
        return Image.open(file_path)
    except Exception as e:
        print(f"[ERRORE] Impossibile aprire l'immagine {file_path}: {e}")
        return None


def get_or_download_audio(file_name: str) -> bytes:
    import os
    import requests

    file_path = os.path.join("data", file_name)
    hf_token = os.getenv("HF_TOKEN_READ")

    if not hf_token:
        print("[ERRORE] HF_TOKEN_READ non trovato. Imposta la variabile d'ambiente HF_TOKEN_READ.")
        return None

    if not os.path.exists(file_path):
        print(f"[INFO] File {file_name} non trovato in /data, lo scarico...")

        url = f"https://huggingface.co/datasets/gaia-benchmark/GAIA/resolve/main/2023/validation/{file_name}"
        headers = {"Authorization": f"Bearer {hf_token}"}

        try:
            response = requests.get(url, headers=headers)
            response.raise_for_status()
            with open(file_path, "wb") as f:
                f.write(response.content)
            print(f"[INFO] Scaricato e salvato in {file_path}")
        except Exception as e:
            print(f"[ERRORE] Impossibile scaricare il file audio: {e}")
            return None

    try:
        with open(file_path, "rb") as f:
            return f.read()
    except Exception as e:
        print(f"[ERRORE] Impossibile leggere il file audio {file_path}: {e}")
        return None

def get_or_download_code(file_name: str) -> str:
    import os
    import requests

    file_path = os.path.join("data", file_name)
    hf_token = os.getenv("HF_TOKEN_READ")

    if not os.path.exists(file_path):
        print(f"[INFO] File {file_name} non trovato. Scarico...")
        url = f"https://huggingface.co/datasets/gaia-benchmark/GAIA/resolve/main/2023/validation/{file_name}"
        headers = {"Authorization": f"Bearer {hf_token}"}
        response = requests.get(url, headers=headers)
        response.raise_for_status()
        with open(file_path, "wb") as f:
            f.write(response.content)
        print(f"[INFO] Scaricato in {file_path}")

    with open(file_path, "r") as f:
        return f.read()

def _load_excel_as_text(file_name: str) -> str:
    import pandas as pd
    import os
    import requests

    from io import StringIO

    file_path = os.path.join("data", file_name)
    hf_token = os.getenv("HF_TOKEN_READ")
    
    # Scarica il file se non esiste localmente
    if not os.path.exists(file_path):
        print_coso(f"[INFO] File {file_name} non trovato. Scarico...")
        url = f"https://huggingface.co/datasets/gaia-benchmark/GAIA/resolve/main/2023/validation/{file_name}"
        headers = {"Authorization": f"Bearer {hf_token}"}
        try:
            response = requests.get(url, headers=headers)
            response.raise_for_status()
            with open(file_path, "wb") as f:
                f.write(response.content)
            print(f"[INFO] Scaricato e salvato in {file_path}")
        except Exception as e:
            print(f"[ERRORE] Impossibile scaricare il file Excel: {e}")
            return "ERROR: Could not download Excel file."

    try:
        df = pd.read_excel(file_path)
        df = df.applymap(lambda x: f"{x:.2f}" if isinstance(x, float) else x)

        # Costruzione della tabella markdown-style
        header = "| " + " | ".join(df.columns) + " |"
        separator = "| " + " | ".join(["---"] * len(df.columns)) + " |"
        rows = df.astype(str).apply(lambda row: "| " + " | ".join(row) + " |", axis=1).tolist()

        table_text = "\n".join([header, separator] + rows)
        return table_text

    except Exception as e:
        print(f"[ERRORE] Impossibile leggere il file Excel: {e}")
        return "ERROR: Could not read Excel file."

def _load_excel_as_text2(file_name: str) -> str:
    import pandas as pd
    import os
    import requests

    file_path = os.path.join("data", file_name)
    hf_token = os.getenv("HF_TOKEN_READ")
    
    # Scarica il file se non esiste localmente
    if not os.path.exists(file_path):
        print_coso(f"[INFO] File {file_name} non trovato. Scarico...")
        url = f"https://huggingface.co/datasets/gaia-benchmark/GAIA/resolve/main/2023/validation/{file_name}"
        headers = {"Authorization": f"Bearer {hf_token}"}
        try:
            response = requests.get(url, headers=headers)
            response.raise_for_status()
            with open(file_path, "wb") as f:
                f.write(response.content)
            print(f"[INFO] Scaricato e salvato in {file_path}")
        except Exception as e:
            print(f"[ERRORE] Impossibile scaricare il file Excel: {e}")
            return "ERROR: Could not download Excel file."

    # Leggi il contenuto
    try:
        #xl = pd.ExcelFile(file_path)
        xl = pd.read_excel(file_path)
        print_coso(f"excel: {xl}")
        #sheets = xl.sheet_names

        xl = xl.applymap(lambda x: f"{x:.2f}" if isinstance(x, float) else x)

        # Esporta in formato CSV con separatore "pipe" per chiarezza (| colonna |)
        csv_buffer = StringIO()
        xl.to_csv(csv_buffer, index=False)
        xl_string = csv_buffer.getvalue()
        csv_buffer.close()
        return xl_string
        
        '''
        all_text = ""
        for sheet in sheets:
            df = xl.parse(sheet)
            all_text += f"\nSheet: {sheet}\n"
            all_text += df.to_string(index=False)
        return all_text
        '''
    except Exception as e:
        print(f"[ERRORE] Impossibile leggere il file Excel: {e}")
        return "ERROR: Could not read Excel file."



    
    '''
    base_url = "https://huggingface.co/datasets/gaia-benchmark/GAIA/resolve"
    commit_hash = "86620fe7a265fdd074ea8d8c8b7a556a1058b0af"
    full_url = f"{base_url}/{commit_hash}/2023/validation/{file_name}"
    '''



whiteList = [
    {
        'task_id': '99c9cc74-fdc8-46c6-8f8d-3ce2d3bfeea3',
        'question': 'Hi, I\'m making a pie but I could use some help with my shopping list. I have everything I need for the crust, but I\'m not sure about the filling. I got the recipe from my friend Aditi, but she left it as a voice memo and the speaker on my phone is buzzing so I can\'t quite make out what she\'s saying. Could you please listen to the recipe and list all of the ingredients that my friend described? I only want the ingredients for the filling, as I have everything I need to make my favorite pie crust. I\'ve attached the recipe as Strawberry pie.mp3.\n\nIn your response, please only list the ingredients, not any measurements. So if the recipe calls for "a pinch of salt" or "two cups of ripe strawberries" the ingredients on the list would be "salt" and "ripe strawberries".\n\nPlease format your response as a comma separated list of ingredients. Also, please alphabetize the ingredients.', 
        'Level': '1', 
        'file_name': '99c9cc74-fdc8-46c6-8f8d-3ce2d3bfeea3.mp3'
    },
    {
        "task_id":"f918266a-b3e0-4914-865d-4faa564f1aef",
        "question":"What is the final numeric output from the attached Python code?",
        "Level":"1",
        "file_name":"f918266a-b3e0-4914-865d-4faa564f1aef.py"
    },
    {
        "task_id":"7bd855d8-463d-4ed5-93ca-5fe35145f733",
        "question":"The attached Excel file contains the sales of menu items for a local fast-food chain. What were the total sales that the chain made from food (not including drinks)? Express your answer in USD with two decimal places.",
        "Level":"1",
        "file_name":"7bd855d8-463d-4ed5-93ca-5fe35145f733.xlsx"
    }, 
    {
        "task_id":"1f975693-876d-457b-a649-393859e79bf3",
        "question":"Hi, I was out sick from my classes on Friday, so I'm trying to figure out what I need to study for my Calculus mid-term next week. My friend from class sent me an audio recording of Professor Willowbrook giving out the recommended reading for the test, but my headphones are broken :(\n\nCould you please listen to the recording for me and tell me the page numbers I'm supposed to go over? I've attached a file called Homework.mp3 that has the recording. Please provide just the page numbers as a comma-delimited list. And please provide the list in ascending order.",
        "Level":"1",
        "file_name":"1f975693-876d-457b-a649-393859e79bf3.mp3"
    },
    {
        "task_id":"4fc2f1ae-8625-45b5-ab34-ad4433bc21f8",
        "question":"Who nominated the only Featured Article on English Wikipedia about a dinosaur that was promoted in November 2016?",
        "Level":"1",
        "file_name":""
    },
    {
        "task_id":"2d83110e-a098-4ebb-9987-066c06fa42d0",
        "question":".rewsna eht sa \"tfel\" drow eht fo etisoppo eht etirw ,ecnetnes siht dnatsrednu uoy fI",
        "Level":"1",
        "file_name":""
    }  
]

blackList = [
     "cca530fc-4052-43b2-b130-b30968d8aa44"
]
    
'''
    {    
      "task_id":"cca530fc-4052-43b2-b130-b30968d8aa44",
      "question":"Review the chess position provided in the image. It is black's turn. Provide the correct next move for black which guarantees a win. Please provide your response in algebraic notation.",
      "Level":"1",
      "file_name":"cca530fc-4052-43b2-b130-b30968d8aa44.png" 
    },
'''
    





DOMANDE_MOCKATE = False
def create_mock_questions():

    '''
  

    {'task_id': '8e867cd7-cff9-4e6c-867a-ff5ddc2550be', 
         'question': 'How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia.', 
         'Level': '1',
         'file_name': ''
        },
       
         {
            "task_id": "5a0c1adf-205e-4841-a666-7c3ef95def9d",
            "question": "What is the first name of the only Malko Competition recipient from the 20th Century (after 1977) whose nationality on record is a country that no longer exists?",
            "Level": "1",
            "file_name": ""
        } 
    '''  
    return whiteList


tempMock = [{"task_id":"8e867cd7-cff9-4e6c-867a-ff5ddc2550be","question":"How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia.","Level":"1","file_name":""},{"task_id":"a1e91b78-d3d8-4675-bb8d-62741b4b68a6","question":"In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?","Level":"1","file_name":""},{"task_id":"2d83110e-a098-4ebb-9987-066c06fa42d0","question":".rewsna eht sa \"tfel\" drow eht fo etisoppo eht etirw ,ecnetnes siht dnatsrednu uoy fI","Level":"1","file_name":""},{"task_id":"cca530fc-4052-43b2-b130-b30968d8aa44","question":"Review the chess position provided in the image. It is black's turn. Provide the correct next move for black which guarantees a win. Please provide your response in algebraic notation.","Level":"1","file_name":"cca530fc-4052-43b2-b130-b30968d8aa44.png"},{"task_id":"4fc2f1ae-8625-45b5-ab34-ad4433bc21f8","question":"Who nominated the only Featured Article on English Wikipedia about a dinosaur that was promoted in November 2016?","Level":"1","file_name":""},{"task_id":"6f37996b-2ac7-44b0-8e68-6d28256631b4","question":"Given this table defining * on the set S = {a, b, c, d, e}\n\n|*|a|b|c|d|e|\n|---|---|---|---|---|---|\n|a|a|b|c|b|d|\n|b|b|c|a|e|c|\n|c|c|a|b|b|a|\n|d|b|e|b|e|d|\n|e|d|b|a|d|c|\n\nprovide the subset of S involved in any possible counter-examples that prove * is not commutative. Provide your answer as a comma separated list of the elements in the set in alphabetical order.","Level":"1","file_name":""},{"task_id":"9d191bce-651d-4746-be2d-7ef8ecadb9c2","question":"Examine the video at https://www.youtube.com/watch?v=1htKBjuUWec.\n\nWhat does Teal'c say in response to the question \"Isn't that hot?\"","Level":"1","file_name":""},{"task_id":"cabe07ed-9eca-40ea-8ead-410ef5e83f91","question":"What is the surname of the equine veterinarian mentioned in 1.E Exercises from the chemistry materials licensed by Marisa Alviar-Agnew & Henry Agnew under the CK-12 license in LibreText's Introductory Chemistry materials as compiled 08/21/2023?","Level":"1","file_name":""},{"task_id":"3cef3a44-215e-4aed-8e3b-b1e3f08063b7","question":"I'm making a grocery list for my mom, but she's a professor of botany and she's a real stickler when it comes to categorizing things. I need to add different foods to different categories on the grocery list, but if I make a mistake, she won't buy anything inserted in the wrong category. Here's the list I have so far:\n\nmilk, eggs, flour, whole bean coffee, Oreos, sweet potatoes, fresh basil, plums, green beans, rice, corn, bell pepper, whole allspice, acorns, broccoli, celery, zucchini, lettuce, peanuts\n\nI need to make headings for the fruits and vegetables. Could you please create a list of just the vegetables from my list? If you could do that, then I can figure out how to categorize the rest of the list into the appropriate categories. But remember that my mom is a real stickler, so make sure that no botanical fruits end up on the vegetable list, or she won't get them when she's at the store. Please alphabetize the list of vegetables, and place each item in a comma separated list.","Level":"1","file_name":""},{"task_id":"99c9cc74-fdc8-46c6-8f8d-3ce2d3bfeea3","question":"Hi, I'm making a pie but I could use some help with my shopping list. I have everything I need for the crust, but I'm not sure about the filling. I got the recipe from my friend Aditi, but she left it as a voice memo and the speaker on my phone is buzzing so I can't quite make out what she's saying. Could you please listen to the recipe and list all of the ingredients that my friend described? I only want the ingredients for the filling, as I have everything I need to make my favorite pie crust. I've attached the recipe as Strawberry pie.mp3.\n\nIn your response, please only list the ingredients, not any measurements. So if the recipe calls for \"a pinch of salt\" or \"two cups of ripe strawberries\" the ingredients on the list would be \"salt\" and \"ripe strawberries\".\n\nPlease format your response as a comma separated list of ingredients. Also, please alphabetize the ingredients.","Level":"1","file_name":"99c9cc74-fdc8-46c6-8f8d-3ce2d3bfeea3.mp3"},{"task_id":"305ac316-eef6-4446-960a-92d80d542f82","question":"Who did the actor who played Ray in the Polish-language version of Everybody Loves Raymond play in Magda M.? Give only the first name.","Level":"1","file_name":""},{"task_id":"f918266a-b3e0-4914-865d-4faa564f1aef","question":"What is the final numeric output from the attached Python code?","Level":"1","file_name":"f918266a-b3e0-4914-865d-4faa564f1aef.py"},{"task_id":"3f57289b-8c60-48be-bd80-01f8099ca449","question":"How many at bats did the Yankee with the most walks in the 1977 regular season have that same season?","Level":"1","file_name":""},{"task_id":"1f975693-876d-457b-a649-393859e79bf3","question":"Hi, I was out sick from my classes on Friday, so I'm trying to figure out what I need to study for my Calculus mid-term next week. My friend from class sent me an audio recording of Professor Willowbrook giving out the recommended reading for the test, but my headphones are broken :(\n\nCould you please listen to the recording for me and tell me the page numbers I'm supposed to go over? I've attached a file called Homework.mp3 that has the recording. Please provide just the page numbers as a comma-delimited list. And please provide the list in ascending order.","Level":"1","file_name":"1f975693-876d-457b-a649-393859e79bf3.mp3"},{"task_id":"840bfca7-4f7b-481a-8794-c560c340185d","question":"On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This article mentions a team that produced a paper about their observations, linked at the bottom of the article. Find this paper. Under what NASA award number was the work performed by R. G. Arendt supported by?","Level":"1","file_name":""},{"task_id":"bda648d7-d618-4883-88f4-3466eabd860e","question":"Where were the Vietnamese specimens described by Kuznetzov in Nedoshivina's 2010 paper eventually deposited? Just give me the city name without abbreviations.","Level":"1","file_name":""},{"task_id":"cf106601-ab4f-4af9-b045-5295fe67b37d","question":"What country had the least number of athletes at the 1928 Summer Olympics? If there's a tie for a number of athletes, return the first in alphabetical order. Give the IOC country code as your answer.","Level":"1","file_name":""},{"task_id":"a0c07678-e491-4bbc-8f0b-07405144218f","question":"Who are the pitchers with the number before and after Taishō Tamai's number as of July 2023? Give them to me in the form Pitcher Before, Pitcher After, use their last names only, in Roman characters.","Level":"1","file_name":""},{"task_id":"7bd855d8-463d-4ed5-93ca-5fe35145f733","question":"The attached Excel file contains the sales of menu items for a local fast-food chain. What were the total sales that the chain made from food (not including drinks)? Express your answer in USD with two decimal places.","Level":"1","file_name":"7bd855d8-463d-4ed5-93ca-5fe35145f733.xlsx"},{"task_id":"5a0c1adf-205e-4841-a666-7c3ef95def9d","question":"What is the first name of the only Malko Competition recipient from the 20th Century (after 1977) whose nationality on record is a country that no longer exists?","Level":"1","file_name":""}]



def process_questions(serviceList, whiteList, blackList):
    # 1. Estrai tutti i task_id da escludere (da whiteList e blackList)
    exclude_ids = {q["task_id"] for q in whiteList + blackList}

    # 2. Rimuovi da serviceList tutte le domande con task_id in exclude_ids
    serviceList = [q for q in serviceList if q["task_id"] not in exclude_ids]

    # 3. Calcola la somma delle domande rimanenti + quelle in whiteList
    total = len(serviceList) + len(whiteList)

    # 4. Se la somma supera 20, rimuovi a caso da serviceList
    removed = []
    if total > 20:
        excess = total - 20
        removed = random.sample(serviceList, excess)
        serviceList = [q for q in serviceList if q not in removed]

    # 5. Stampa le domande rimosse
    print("Domande rimosse:")
    for q in removed:
        print(f"- {q['task_id']}: {q['question'][:80]}")

    # 6. Stampa la serviceList aggiornata
    print("\nService list aggiornata:")
    for q in serviceList:
        print(f"- {q['task_id']}: {q['question'][:80]}")

    # 7. Aggiungi le domande della whiteList
    final_list = serviceList + whiteList

    return final_list

    
def generate_tool_descriptions(tools):
    lines = []
    for tool in tools:
        name = tool.metadata.name
        desc = tool.metadata.description
        inputs = tool.metadata.fn.__annotations__
        return_type = inputs.get('return', 'unknown')

        arg_list = [
            f"{k}: {v.__name__ if hasattr(v, '__name__') else str(v)}"
            for k, v in inputs.items() if k != "return"
        ]
        inputs_str = ", ".join(arg_list)
        lines.append(f"- {name}: {desc}\n    Takes inputs: {inputs_str}\n    Returns an output of type: {return_type}")
    return "\n".join(lines)

#Tools

def transcribe_audio(file_name: str) -> str:
    print_coso(f"usato transcribe_audio tool: {result['text']}")
    file_path = os.path.join("/data", file_name)
    if not os.path.isfile(file_path):
        return f"File not found: {file_path}"

    model = whisper.load_model("base")
    result = model.transcribe(file_path)

    print_coso(f"transcribe_audio tool result: {result['text']}")
    return result["text"]


def extract_ingredients(transcription: str) -> str:
    """
    Estrae una lista alfabetica, separata da virgole, di ingredienti dal testo fornito,
    mantenendo le descrizioni (es. 'freshly squeezed lemon juice').
    """
    print_coso("tool extract_ingredients")
    # pattern semplice per ingredienti comuni e le loro descrizioni
    pattern = r"\b(?:a dash of |a pinch of |freshly squeezed |pure )?[a-zA-Z ]+?(?:strawberries|sugar|lemon juice|cornstarch|vanilla extract)\b"
    matches = re.findall(pattern, transcription.lower())

    # normalizza, rimuove duplicati e ordina
    unique_ingredients = sorted(set(match.strip() for match in matches))
    return ", ".join(unique_ingredients)

def web_search(query: str) -> str:
    print_coso(f"tool web_search con query: {query}")
    with DDGS() as ddgs:
        results = []#ddgs.text(keywords = query, max_results=3)
        #formattedResult = "\n".join([f"{res['title']} - {res['href']}" for res in results])
        for r in ddgs.text(query, region="wt-wt", safesearch="off", max_results=3):
            results.append(r)
            time.sleep(1.5) 
        print_coso(f"tool web_search formattedResult: {results}")
        return results
'''
def web_search(query: str) -> str:
    print_coso(f"tool web_search con query: {query}")
    try:
        with DDGS() as ddgs:
            results = ddgs.text(query)
            if not results:
                return "No results found."
            return "\n".join([r["body"] for r in results[:3]])
    except Exception as e:
        return f"Error: {e}"
'''

def log_thought(thought: str) -> str:
    print_coso(f"Tool log_thought: {thought}")
    return "Thought logged."

def sum_list(numbers: list[float]) -> float:
    total = sum(numbers)
    print_coso(f"[TOOL] sum_list called with: {numbers}")
    print_coso(f"[TOOL] Result: {total}")
    return total

def is_food(items: list[str]) -> str:
    food_items = {"burgers", "hot dogs", "salads", "fries", "ice cream"}
    tags = {item: (item.lower() in food_items) for item in items}
    result = ", ".join([f"{item}: {tags[item]}" for item in items])
    print(f"tag_food_items({items}) -> {result}")
    return result
    
def final_answer_tool(answer: str) -> str:
    print_coso(f"Final answer: {answer}")
    return answer

def print_coso(scritta: str):
    print(f"coso {scritta}")
    


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

##Roba per la valutazione        

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:
        #qui per servizio get domande
        if DOMANDE_MOCKATE:
            total_questions = create_mock_questions()
        else:
            print_coso("lancio servizio questions")
            responseFromService = tempMock #requests.get(questions_url, timeout=30)
            response = process_questions(responseFromService)       
            response.raise_for_status()
            total_questions = response.json()
        
        questions_data = total_questions[:min(20, len(total_questions))]
        print_coso(f"questions_data: {questions_data}")
        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:
            file_name = item.get("file_name")
            print_coso(f"file_name riga in 3. Run your Agent: {file_name}")
            submitted_answer = agent(question_text, file_name) #mock
            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()
        print_coso(result_data)
        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)

        print(f"coso final_status: {final_status} - results_df: {results_df}")
        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)