app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
import logging
from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel, OpenAIServerModel
from pathlib import Path
from prompt_settings import verification_of_final_answer, yaml_template

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


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."
            )
            
            # Registra il tool
            Settings.tools = [ingredient_tool, chess_tool]

            llm = LlamaOpenAI(
                model="gpt-4o",
                temperature=0.0,
                api_key=openai_api_key
            )
    
            # Prepara l'agente
            self.agent = OpenAIAgent.from_tools([ingredient_tool], llm=llm, verbose=True)
    
            # 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"{text} {verification_of_final_answer} {yaml_template}"
        
        # 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 only the final output:\n\n"
                f"{code_content}\n\n"
                f"Question: {question}"
            )
            risposta = self._ask_gpt4o(prompt_python)

        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)
        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 _ask_gpt4o_with_mp3(self, audio: 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
            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()
    
    '''
    base_url = "https://huggingface.co/datasets/gaia-benchmark/GAIA/resolve"
    commit_hash = "86620fe7a265fdd074ea8d8c8b7a556a1058b0af"
    full_url = f"{base_url}/{commit_hash}/2023/validation/{file_name}"
    '''

DOMANDE_MOCKATE = True
def create_mock_questions():

    '''
    {    
      "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': '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': '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": "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 [  
       {
          "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"
       }
    ]




#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 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:
            response = requests.get(questions_url, timeout=15)
            response.raise_for_status()
            total_questions = response.json()
        
        print("\n\n")
        print(f"total_questions: {total_questions}")
        print("\n\n")
        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)
            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
        
        #return "mock1", None

        
    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)