import os import gradio as gr import requests import inspect import pandas as pd from core_agent import GAIAAgent # Debug function to show available environment variables def debug_environment(): """Print available environment variables related to API keys (with values hidden)""" debug_vars = [ "HF_API_TOKEN", "HUGGINGFACEHUB_API_TOKEN", "OPENAI_API_KEY", "XAI_API_KEY", "AGENT_MODEL_TYPE", "AGENT_MODEL_ID", "AGENT_TEMPERATURE", "AGENT_VERBOSE" ] print("=== DEBUG: Environment Variables ===") for var in debug_vars: if os.environ.get(var): # Hide actual values for security print(f"{var}: [SET]") else: print(f"{var}: [NOT SET]") print("===================================") # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- Basic Agent Definition --- # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ class BasicAgent: def __init__(self): print("BasicAgent initialized.") # Call debug function to show available environment variables debug_environment() # Initialize the GAIAAgent with local execution try: # Load environment variables if dotenv is available try: import dotenv dotenv.load_dotenv() print("Loaded environment variables from .env file") except ImportError: print("python-dotenv not installed, continuing with environment as is") # Try to load API keys from environment # Check both HF_API_TOKEN and HUGGINGFACEHUB_API_TOKEN (HF Spaces uses HF_API_TOKEN) hf_token = os.environ.get("HF_API_TOKEN") or os.environ.get("HUGGINGFACEHUB_API_TOKEN") openai_key = os.environ.get("OPENAI_API_KEY") xai_key = os.environ.get("XAI_API_KEY") # If we have at least one API key, use a model-based approach if hf_token or openai_key or xai_key: # Default model parameters - read directly from environment model_type = os.environ.get("AGENT_MODEL_TYPE", "OpenAIServerModel") model_id = os.environ.get("AGENT_MODEL_ID", "gpt-4o") temperature = float(os.environ.get("AGENT_TEMPERATURE", "0.2")) verbose = os.environ.get("AGENT_VERBOSE", "false").lower() == "true" print(f"Agent config - Model Type: {model_type}, Model ID: {model_id}") try: if xai_key: # Use X.AI API with OpenAIServerModel api_base = os.environ.get("XAI_API_BASE", "https://api.x.ai/v1") self.gaia_agent = GAIAAgent( model_type="OpenAIServerModel", model_id="grok-3-latest", # X.AI's model api_key=xai_key, api_base=api_base, temperature=temperature, executor_type="local", verbose=verbose ) print(f"Using OpenAIServerModel with X.AI API at {api_base}") elif model_type == "HfApiModel" and hf_token: # Use Hugging Face API self.gaia_agent = GAIAAgent( model_type="HfApiModel", model_id=model_id, api_key=hf_token, temperature=temperature, executor_type="local", verbose=verbose ) print(f"Using HfApiModel with model_id: {model_id}") elif openai_key: # Default to OpenAI API api_base = os.environ.get("AGENT_API_BASE") kwargs = { "model_type": "OpenAIServerModel", "model_id": model_id, "api_key": openai_key, "temperature": temperature, "executor_type": "local", "verbose": verbose } if api_base: kwargs["api_base"] = api_base print(f"Using custom API base: {api_base}") self.gaia_agent = GAIAAgent(**kwargs) print(f"Using OpenAIServerModel with model_id: {model_id}") else: # Fallback to using whatever token we have print("WARNING: Using fallback initialization with available token") if hf_token: self.gaia_agent = GAIAAgent( model_type="HfApiModel", model_id="mistralai/Mistral-7B-Instruct-v0.2", api_key=hf_token, temperature=temperature, executor_type="local", verbose=verbose ) elif openai_key: self.gaia_agent = GAIAAgent( model_type="OpenAIServerModel", model_id="gpt-3.5-turbo", api_key=openai_key, temperature=temperature, executor_type="local", verbose=verbose ) else: self.gaia_agent = GAIAAgent( model_type="OpenAIServerModel", model_id="grok-3-latest", api_key=xai_key, api_base=os.environ.get("XAI_API_BASE", "https://api.x.ai/v1"), temperature=temperature, executor_type="local", verbose=verbose ) except ImportError as ie: # Handle OpenAI module errors specifically if "openai" in str(ie).lower() and hf_token: print(f"OpenAI module error: {ie}. Falling back to HfApiModel.") self.gaia_agent = GAIAAgent( model_type="HfApiModel", model_id="mistralai/Mistral-7B-Instruct-v0.2", api_key=hf_token, temperature=temperature, executor_type="local", verbose=verbose ) print(f"Using HfApiModel with model_id: mistralai/Mistral-7B-Instruct-v0.2 (fallback)") else: raise else: # No API keys available, log the error print("ERROR: No API keys found. Please set at least one of these environment variables:") print("- HUGGINGFACEHUB_API_TOKEN or HF_API_TOKEN") print("- OPENAI_API_KEY") print("- XAI_API_KEY") self.gaia_agent = None print("WARNING: No API keys found. Agent will not be able to answer questions.") except Exception as e: print(f"Error initializing GAIAAgent: {e}") self.gaia_agent = None print("WARNING: Failed to initialize agent. Falling back to basic responses.") def __call__(self, question: str) -> str: print(f"Agent received question (first 50 chars): {question[:50]}...") # Check if we have a functioning GAIA agent if self.gaia_agent: try: # Process the question using the GAIA agent answer = self.gaia_agent.answer_question(question) print(f"Agent generated answer: {answer[:50]}..." if len(answer) > 50 else f"Agent generated answer: {answer}") return answer except Exception as e: print(f"Error processing question: {e}") # Fall back to a simple response on error return "An error occurred while processing your question. Please check the agent logs for details." else: # We don't have a valid agent, provide a basic response return "The agent is not properly initialized. Please check your API keys and configuration." 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() # Check if agent is properly initialized if not agent.gaia_agent: print("ERROR: Agent was not properly initialized") return "ERROR: Agent was not properly initialized. Check the logs for details on missing API keys or configuration.", None except Exception as e: print(f"Error instantiating agent: {e}") return f"Error initializing agent: {e}", None # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public) agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" print(agent_code) # 2. Fetch Questions print(f"Fetching questions from: {questions_url}") try: response = requests.get(questions_url, timeout=15) response.raise_for_status() questions_data = response.json() if not questions_data: print("Fetched questions list is empty.") return "Fetched questions list is empty or invalid format.", None print(f"Fetched {len(questions_data)} questions.") except requests.exceptions.RequestException as e: print(f"Error fetching questions: {e}") return f"Error fetching questions: {e}", None except requests.exceptions.JSONDecodeError as e: print(f"Error decoding JSON response from questions endpoint: {e}") print(f"Response text: {response.text[:500]}") return f"Error decoding server response for questions: {e}", None except Exception as e: print(f"An unexpected error occurred fetching questions: {e}") return f"An unexpected error occurred fetching questions: {e}", None # 3. Run your Agent results_log = [] answers_payload = [] print(f"Running agent on {len(questions_data)} questions...") for item in questions_data: task_id = item.get("task_id") question_text = item.get("question") if not task_id or question_text is None: print(f"Skipping item with missing task_id or question: {item}") continue try: submitted_answer = agent(question_text) answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer}) results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer}) except Exception as e: print(f"Error running agent on task {task_id}: {e}") results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"}) if not answers_payload: print("Agent did not produce any answers to submit.") return "Agent did not produce any answers to submit.", pd.DataFrame(results_log) # 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)