import os import time import gradio as gr import requests import inspect import pandas as pd import json from logging_config import logger # Import the shared logger from dotenv import load_dotenv from agent import MODEL_PROVIDER load_dotenv(".env") # (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 ------ # --- Basic Agent Definition --- # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ class BasicAgent: def __init__(self): print("BasicAgent initialized.") from agent import graph self.graph = graph def __call__(self, item: dict) -> str: """Process the input item and return a response. Args: item (dict): Input dictionary containing the question. """ question = item.get("question", "") task_id = item.get("task_id", "") file_name = item.get("file_name", "") if file_name: # file_name provided, adding task_id to question for context question += f"\nTask ID: {task_id}" logger.info(f"Agent received question (first 50 chars): {question[:50]}...") # fixed_answer = "This is a default answer." # print(f"Agent returning fixed answer: {fixed_answer}") answer = self.graph.invoke({"question": question, "task_id": task_id}) return answer.get("final_answer", "No answer generated.") # type: ignore def run_all(profile: gr.OAuthProfile | None): """ Fetches all questions, runs the BasicAgent on them caching 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" # 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: # type: ignore print(f"Error decoding JSON response from questions endpoint: {e}") print(f"Response text: {response.text[:500]}") # type: ignore 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(item) 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}"}) time.sleep(15) # To avoid hitting rate limits or overwhelming the system 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) # save results log to a json file for debugging with open(f"results_log_{MODEL_PROVIDER}.json", "w") as fh: json.dump(results_log, fh, indent=2) logger.info(f"Results log saved to results_log_{MODEL_PROVIDER}.json") # save answers payload to a json file. Caching the answers to be able to submit them later with open(f"answers_payload_{MODEL_PROVIDER}.json", "w") as fh: json.dump(answers_payload, fh, indent=2) logger.info(f"Answers payload saved to answers_payload_{MODEL_PROVIDER}.json") message = f"Agent run completed. {len(answers_payload)} answers ready for submission." results_df = pd.DataFrame(results_log) # type: ignore return message, results_df def submit_all(profile: gr.OAuthProfile | None): # --- Determine HF Space Runtime URL and Repo URL --- space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" 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 # 4. Prepare Submission try: with open(f"answers_payload.json", "r") as fh: answers_payload = json.load(fh) except Exception as e: print(f"Error loading answers payload: {e}") try: with open(f"results_log.json", "r") as fh: results_log = json.load(fh) except Exception as e: print(f"Error loading results log: {e}") submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload} # type: ignore status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..." # type: ignore print(status_update) api_url = DEFAULT_API_URL submit_url = f"{api_url}/submit" print(f"Submitting {len(answers_payload)} answers to: {submit_url}") # type: ignore # 5. Submit 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) # type: ignore 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) # type: ignore 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) # type: ignore 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) # type: ignore 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) # type: ignore 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 & Cache Answers") # Renamed for clarity submit_button = gr.Button("Submit Cached Answers") # New button for submission 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_all, outputs=[status_output, results_table] ) # Add the click event for the new submit_button submit_button.click( fn=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)