""" Basic Agent Evaluation Runner""" import os import inspect import gradio as gr import requests import pandas as pd from langchain_core.messages import HumanMessage from agents.agent import build_graph from api_integration import GAIAApiClient import tempfile import mimetypes # Added for MIME type detection import base64 # Added for base64 encoding images # (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: """A langgraph agent.""" def __init__(self): print("BasicAgent initialized.") self.graph = build_graph() def __call__(self, messages: list) -> str: # Modified to accept a list of messages print(f"Agent received messages: {messages}") # Ensure messages are in the correct format for the graph processed_messages = self.graph.invoke({"messages": messages}) # The final answer should be in the 'content' of the last message raw_answer = processed_messages['messages'][-1].content # Attempt to find "FINAL ANSWER:" and extract text after it final_answer_marker = "FINAL ANSWER:" marker_index = raw_answer.rfind(final_answer_marker) # Use rfind to get the last occurrence if marker_index != -1: # Extract the text after "FINAL ANSWER: " extracted_answer = raw_answer[marker_index + len(final_answer_marker):].strip() # If there's a newline after the extracted answer, take only the first line # This handles cases where the LLM might add extra explanations after the marker on a new line first_line_of_extracted_answer = extracted_answer.split('\\n')[0].strip() if first_line_of_extracted_answer: # Ensure it's not empty after stripping print(f"Extracted answer: {first_line_of_extracted_answer}") return first_line_of_extracted_answer else: # If the first line is empty, it might be that the answer is just the marker itself (unlikely but handle) print(f"Warning: Extracted answer after '{final_answer_marker}' is empty. Returning raw answer part after marker if any, or full raw answer.") # Fallback to extracted_answer if first_line was empty but extracted_answer was not return extracted_answer if extracted_answer else raw_answer # Fallback if "FINAL ANSWER:" is not found or extraction results in empty string print(f"Warning: '{final_answer_marker}' not found in agent's output or extraction failed. Returning raw answer: {raw_answer}") return raw_answer 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 submit_url = f"{api_url}/submit" gaia_client = GAIAApiClient(api_url=api_url) # 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 using GAIAApiClient from: {api_url}") try: questions_data = gaia_client.get_questions() 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 via GAIAApiClient: {e}") return f"Error fetching questions: {e}", None except Exception as e: print(f"An unexpected error occurred fetching questions via GAIAApiClient: {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") original_file_name = item.get("file_name") content_parts = [{"type": "text", "text": question_text}] downloaded_file_path_for_log = None # For logging purposes if task_id and original_file_name: print(f"Question {task_id} has an associated file: {original_file_name}. Attempting to download.") try: file_bytes = gaia_client.get_file(task_id) if file_bytes: temp_dir = tempfile.gettempdir() safe_original_filename = "".join(c if c.isalnum() or c in ('.', '_', '-') else '_' for c in original_file_name) temp_file_name = f"task_{task_id}_{safe_original_filename}" downloaded_file_path = os.path.join(temp_dir, temp_file_name) downloaded_file_path_for_log = downloaded_file_path with open(downloaded_file_path, "wb") as f_out: f_out.write(file_bytes) print(f"File for task {task_id} downloaded to: {downloaded_file_path}") # Determine MIME type and construct message part mime_type, _ = mimetypes.guess_type(downloaded_file_path) if mime_type and mime_type.startswith("image/"): base64_image = base64.b64encode(file_bytes).decode('utf-8') content_parts.append({ "type": "image_url", "image_url": { "url": f"data:{mime_type};base64,{base64_image}" } }) current_question_for_log = f"{question_text}\n\n[System Note: Image file {original_file_name} ({mime_type}) was processed and included directly in the message.]" # elif mime_type and mime_type.startswith("audio/"): # # For audio, tools might expect a path or raw bytes. # # For now, let's add a note with the path, assuming tools can handle it. # # This part might need adjustment based on specific audio tool capabilities. # content_parts.append({ # "type": "text", # Or a custom type if LangGraph/tools support it # "text": f"[System Note: An audio file '{original_file_name}' is available at: {downloaded_file_path}]" # }) # current_question_for_log = f"{question_text}\n\n[System Note: Audio file {original_file_name} available at {downloaded_file_path}]" else: # For other file types (text, csv, py, etc.) # Add a system note with the file path. Tools will need to be able # to read the file from this path. content_parts.append({ "type": "text", "text": f"[System Note: An associated file '{original_file_name}' ({mime_type if mime_type else 'unknown type'}) has been downloaded. It is available at: {downloaded_file_path}]" }) current_question_for_log = f"{question_text}\n\n[System Note: File {original_file_name} ({mime_type if mime_type else 'unknown type'}) available at {downloaded_file_path}]" else: print(f"Warning: File indicated for task {task_id} ('{original_file_name}'), but download returned no content.") content_parts.append({"type": "text", "text": f"[System Note: A file ('{original_file_name}') was indicated for this question, but the download attempt returned no content.]"}) current_question_for_log = f"{question_text}\n\n[System Note: File {original_file_name} download returned no content.]" except Exception as e_file: print(f"Error downloading or processing file '{original_file_name}' for task {task_id}: {e_file}") content_parts.append({"type": "text", "text": f"[System Note: An error occurred while trying to download/process the associated file ('{original_file_name}') for this question: {e_file}]"}) current_question_for_log = f"{question_text}\n\n[System Note: Error with file {original_file_name}: {e_file}]" else: current_question_for_log = question_text # No file associated if not task_id or question_text is None: print(f"Skipping item with missing task_id or question: {item}") continue try: # The agent now expects a list of content parts human_message = HumanMessage(content=content_parts) submitted_answer = agent([human_message]) # Pass as a list of messages answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer}) results_log.append({"Task ID": task_id, "Question": current_question_for_log, "File Path": downloaded_file_path_for_log if downloaded_file_path_for_log else "N/A", "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": current_question_for_log, "File Path": downloaded_file_path_for_log if downloaded_file_path_for_log else "N/A", "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)