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 llama_index.core import ( VectorStoreIndex, SimpleDirectoryReader, Settings, set_global_handler ) from llama_index.llms.openai import OpenAI from openai import OpenAI as OpenAIClient #per i file multimediali import base64 import json from PIL import Image from io import BytesIO NUMERO_DOMANDE_TOTALE = 1 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): 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!") # Crea un'istanza di OpenAI llm = OpenAI( model="gpt-4o-mini", temperature=0, api_key=openai_api_key, verbose = True ) # Imposta le impostazioni tramite Settings Settings.llm=llm self.client = OpenAIClient(api_key=openai_api_key) # Carica i documenti dalla cartella 'data' self.documents = SimpleDirectoryReader("data").load_data() # Crea l'indice con la configurazione self.index = VectorStoreIndex.from_documents(self.documents, settings=Settings) # Prepara il query engine self.query_engine = self.index.as_query_engine() print("coso Agent ready.") ''' def __call__(self, question: str) -> str: print(f"Received question: {question[:50]}...") response = self.query_engine.query(question) # Stampa ragionamento interno print("Query response object:", response) print("Response text:", str(response)) return str(response) ''' def __call__(self, question: 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"q_data: {q_data}") print_coso(f"text: {text}") print_coso(f"file_info: {file_info}") # Se è presente un file, gestiscilo if file_info: file_name = file_info.get("name", "") file_data = file_info.get("data", "") if file_name.endswith((".png", ".jpg", ".jpeg")): print("coso Image file detected, processing with GPT-4o") image = self._load_image(file_data) response = self._ask_gpt4o_with_image(image, text) return response elif file_name.endswith(".wav") or file_name.endswith(".mp3"): print("coso Audio file detected, processing with Whisper") audio_bytes = self._load_bytes(file_data) transcription = self._transcribe_audio(audio_bytes) return self._ask_gpt4o(transcription) elif file_name.endswith(".txt"): print("coso Text file detected") text_content = self._load_text(file_data) return self._ask_gpt4o(text_content) print("coso nessun file allegato") # Altrimenti gestisci solo testo return self._ask_gpt4o(text) def _ask_gpt4o(self, text: str) -> str: messages = [{"role": "user", "content": text}] response = self.client.chat.completions.create(model="gpt-4o-mini", 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 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: bytes) -> str: audio_file = BytesIO(audio_bytes) transcription = self.client.audio.transcriptions.create(model="whisper-1", file=audio_file) return transcription.text.strip() def _load_image(self, data: str) -> Image.Image: return Image.open(BytesIO(base64.b64decode(data))) def _load_bytes(self, data: str) -> bytes: return base64.b64decode(data) def _load_text(self, data: str) -> str: return base64.b64decode(data).decode("utf-8") def create_mock_questions(): #with open("data/A_photograph_captures_a_domestic_kitchen_scene_dur.png", "rb") as img_file: # img_bytes = img_file.read() # img_base64 = base64.b64encode(img_bytes).decode("utf-8") return [{ "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" }] def print_coso(scritta: str): return 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: ''' 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") ''' total_questions = create_mock_questions() print_coso(f"total_questions: {total_questions}") questions_data = total_questions[:NUMERO_DOMANDE_TOTALE] 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: 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) # 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) print(f"coso final_status: {final_status} - results_df: {results_df}") return final_status, results_df #return "mock1", "mock2" 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)