Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| import logging | |
| from typing import Optional, List | |
| from smolagents import ( | |
| MCPClient, | |
| CodeAgent, InferenceClientModel, DuckDuckGoSearchTool, GoogleSearchTool, | |
| VisitWebpageTool, | |
| LiteLLMModel,AzureOpenAIServerModel, WikipediaSearchTool,PythonInterpreterTool) | |
| from mcp import StdioServerParameters | |
| # (Keep Constants as is) | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| GAIA_SYSTEM_PROMPT = """ | |
| Tu es un assistant expert spécialisé dans la résolution de questions GAIA. | |
| RÈGLES ABSOLUES: | |
| 1. Lis la question 3 fois avant de commencer | |
| 2. Décompose TOUJOURS la question en sous-problèmes identifiables | |
| 3. Vérifie CHAQUE information avec au moins 2 sources différentes | |
| 4. Pour les calculs: utilise OBLIGATOIREMENT Python pour tous les calculs numériques | |
| 5. Pour les dates: vérifie l'année actuelle (nous sommes en 2025) | |
| 6. JAMAIS de réponse approximative - sois précis au maximum | |
| PROCESSUS OBLIGATOIRE: | |
| 1. ANALYSE: Que demande exactement la question? Quel type de réponse? | |
| 2. RECHERCHE: Quelles informations spécifiques me manquent? | |
| 3. VÉRIFICATION: Les sources sont-elles cohérentes entre elles? | |
| 4. CALCUL: Si nécessaire, utilise Python pour calculs précis | |
| 5. SYNTHÈSE: Donne une réponse finale précise et concise | |
| FORMAT DE RÉPONSE FINAL: | |
| - Si c'est un nombre: donne UNIQUEMENT le nombre (ex: "42") | |
| - Si c'est un nom: donne UNIQUEMENT le nom (ex: "Paris") | |
| - Si c'est une date: format précis demandé | |
| - Pas d'explication supplémentaire dans la réponse finale | |
| OUTILS DISPONIBLES: | |
| - DuckDuckGoSearchTool: pour informations récentes et générales | |
| - WikipediaSearchTool: pour faits établis et données encyclopédiques | |
| - PythonInterpreterTool: pour calculs, manipulations de données, dates""" | |
| # Configure logging | |
| logging.basicConfig(level=logging.INFO) | |
| logger = logging.getLogger(__name__) | |
| class BasicAgent: | |
| def __init__(self, model_id: Optional[str] = None, api_key: Optional[str] = None): | |
| """ | |
| Initialize BasicAgent with model and tools. | |
| Args: | |
| model_id: Optional model ID to use | |
| api_key: Optional API key (will use environment variable if not provided) | |
| """ | |
| # Initialize model | |
| self.model = AzureOpenAIServerModel( | |
| model_id = "o3-mini", | |
| azure_endpoint=os.environ.get("AZURE_OPENAI_ENDPOINT"), | |
| api_key=os.environ.get("AZURE_OPENAI_API_KEY"), | |
| api_version="2024-12-01-preview" #2024-02-15-preview | |
| ) | |
| server_parameters = StdioServerParameters( | |
| command="uvx", # Using uvx ensures dependencies are available | |
| args=["--quiet", "pubmedmcp@0.1.3"], | |
| env={"UV_PYTHON": "3.12", **os.environ}, | |
| ) | |
| self.mcp_client = MCPClient(server_parameters) | |
| # Initialize tools | |
| self.tools = [ | |
| WikipediaSearchTool(), | |
| self.mcp_client.get_tools() | |
| # DuckDuckGoSearchTool(), | |
| # PythonInterpreterTool(), | |
| # VisitWebpageTool() | |
| ] | |
| # Create CodeAgent | |
| self.agent = CodeAgent( | |
| tools=self.tools, | |
| model=self.model, | |
| max_steps=2, | |
| add_base_tools=True, | |
| additional_authorized_imports=["pandas","requests"], | |
| name="gaia_nureyni", | |
| description="Agent designed to solve GAIA benchmark level 1 questions using tools like DuckDuckGo and LLM for reasoning." | |
| ) | |
| # logger.info(f"BasicAgent initialized with model: {self.default_model_id}") | |
| def __call__(self, question: str) -> str: | |
| """ | |
| Make the agent callable directly. | |
| Args: | |
| question: The question to ask the agent | |
| Returns: | |
| Agent's response | |
| """ | |
| logger.info(f"Agent received question (first 50 chars): {question[:50]}...") | |
| try: | |
| question = f"""{GAIA_SYSTEM_PROMPT}\n | |
| QUESTION GAIA: | |
| {question} | |
| APPLIQUE LES RÈGLES CI-DESSUS ET RÉSOUS: | |
| """ | |
| answer = self.agent.run(question) | |
| logger.info("Agent successfully generated response") | |
| return answer | |
| except Exception as e: | |
| logger.error(f"Agent failed to generate response: {e}") | |
| raise | |
| 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": str(submitted_answer)}) | |
| results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": str(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) | |
| # se deconnecter du serveur mcp | |
| agent.mcp_client.disconnect() | |
| # 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) |