import os import gradio as gr import requests import inspect import pandas as pd from agents.agent import BaseAgent # (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): self.agent = BaseAgent() def __call__(self, question: str, extra_details: str | None = None) -> str: print(f"Agent received question (first 50 chars): {question[:50]}...") answer = self.agent(question, extra_details) print(f"Agent returning fixed answer: {answer}") return answer.formatted_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.") yield "Please Login to Hugging Face with the button.", None return 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}") yield f"Error initializing agent: {e}", None return # 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 status_message = f"Fetching questions from: {questions_url}" print(status_message) yield status_message, None try: response = requests.get(questions_url, timeout=15) print(response) response.raise_for_status() questions_data = response.json() print(questions_data) if not questions_data: status_message = "Fetched questions list is empty or invalid format." print(status_message) yield status_message, None return status_message = f"Fetched {len(questions_data)} questions." print(status_message) yield status_message, None except requests.exceptions.RequestException as e: status_message = f"Error fetching questions: {e}" print(status_message) yield status_message, None return except requests.exceptions.JSONDecodeError as e: status_message = f"Error decoding JSON response from questions endpoint: {e}\nResponse text: {response.text[:500]}" print(status_message) yield status_message, None return except Exception as e: status_message = f"An unexpected error occurred fetching questions: {e}" print(status_message) yield status_message, None return # 3. Run your Agent results_log = [] answers_payload = [] status_message = f"Running agent on {len(questions_data)} questions..." print(status_message) yield status_message, pd.DataFrame(results_log) for i, item in enumerate(questions_data): print(item) task_id = item.get("task_id") question_text = item.get("question") if item.get("file_name"): file_url = f"{api_url}/files/{task_id}" print(file_url) file_name = item.get("file_name") file_response = requests.get(file_url, stream=True) file_response.raise_for_status() # Write the file content to a file with the specified name with open(file_name, 'wb') as f: for chunk in file_response.iter_content(chunk_size=8192): f.write(chunk) print(f"File saved as: {file_name}") if not task_id or question_text is None: print(f"Skipping item with missing task_id or question: {item}") results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": "SKIPPED - Missing Data"}) yield f"Processing question {i+1}/{len(questions_data)} (Skipped)", pd.DataFrame(results_log) continue try: status_message = f"Processing question {i+1}/{len(questions_data)}: {question_text[:100]}..." print(status_message) yield status_message, pd.DataFrame(results_log) if item.get("file_name"): extra_details = "You can find the file in: " + file_name else: extra_details = None submitted_answer = agent(question_text, extra_details) 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}) yield f"Processed question {i+1}/{len(questions_data)}. Answer: {submitted_answer[:100]}...", pd.DataFrame(results_log) except Exception as e: error_message = f"AGENT ERROR on task {task_id}: {e}" print(f"Error running agent on task {task_id}: {e}") results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": error_message}) yield f"Error on question {i+1}/{len(questions_data)}", pd.DataFrame(results_log) if not answers_payload: status_message = "Agent did not produce any answers to submit." print(status_message) yield status_message, pd.DataFrame(results_log) return # 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) yield status_update, pd.DataFrame(results_log) # 5. Submit submit_status = f"Submitting {len(answers_payload)} answers to: {submit_url}" print(submit_status) yield submit_status, pd.DataFrame(results_log) 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) yield 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) yield 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) yield 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) yield 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) yield 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)