| import os |
| import gradio as gr |
| import requests |
| import pandas as pd |
| from my_agent import GeminiAgentContainer |
| from markdownify import markdownify as to_markdown |
| import time |
| import json |
|
|
| |
| |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" |
|
|
|
|
| |
| questions = None |
| results_log = [] |
| answers_by_task = {} |
|
|
| def load_questions(questions_url): |
| 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 or invalid.") |
| return None |
| print(f"Fetched {len(questions_data)} questions.") |
| except requests.exceptions.RequestException as e: |
| print(f"Error fetching questions: {e}") |
| return 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 None |
| except Exception as e: |
| print(f"An unexpected error occurred fetching questions: {e}") |
| return None |
| return questions_data |
|
|
| def answer_one(agent, question_data): |
| """ |
| Runs the agent on a single question and returns the result. |
| """ |
| task_id = question_data.get("task_id") |
| question_text = question_data.get("question") |
| filename = question_data.get("file_name") |
| payload = None |
| submitted_answer = None |
| agent_error = None |
|
|
| try: |
| if not task_id or question_text is None: |
| raise ValueError(f"Missing task_id or question in item: {question_data}") |
| if filename: |
| file_prompt = f"\nThere is an attached file with task id `{task_id}` available.\n" |
| question_text = file_prompt + question_text |
| submitted_answer = agent(question_text) |
| payload = {"task_id": task_id, "submitted_answer": submitted_answer} |
| except Exception as e: |
| print(agent) |
| print(f"Error running agent on task {task_id}: {e}") |
| agent_error = f"AGENT ERROR: {e}" |
| finally: |
| log_entry = { |
| "Task ID": task_id, |
| "Question": question_text, |
| "Submitted Answer": submitted_answer or agent_error, |
| } |
| return payload, log_entry |
| |
| def _submit_all(username, agent_code, answers_payload, submit_url): |
| |
| submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload} |
| status_update = f"Submitting {len(answers_payload)} answers for user '{username}'..." |
| print(status_update) |
|
|
| |
| 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(final_status) |
| return final_status |
| 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) |
| return status_message |
| except requests.exceptions.Timeout: |
| status_message = "Submission Failed: The request timed out." |
| print(status_message) |
| return status_message |
| except requests.exceptions.RequestException as e: |
| status_message = f"Submission Failed: Network error - {e}" |
| print(status_message) |
| return status_message |
| except Exception as e: |
| status_message = f"An unexpected error occurred during submission: {e}" |
| print(status_message) |
| return status_message |
|
|
| |
| def prepare_agent(api_key=None): |
| |
| try: |
| agent = GeminiAgentContainer(api_key=api_key) |
| print(agent.system_prompt) |
| except Exception as e: |
| print(f"Error instantiating agent: {e}") |
| return None |
| |
| return agent |
|
|
| def save_answers_to_file(): |
| """ |
| Submits the answers to a local file named with the current epoch time. |
| """ |
| if not answers_by_task: |
| return ("Nothing to save, no answers found.") |
| answers_payload = list(answers_by_task.values()) |
|
|
| file_path = f"answers-{int(time.time())}.json" |
| print(f"Saving answers to file: {file_path}") |
| try: |
| with open(file_path, "w") as file: |
| json.dump(answers_payload, file, indent=4) |
| submit_status = (f"Answers successfully written to {file_path}") |
| except Exception as e: |
| submit_status = (f"Error writing answers to file: {e}") |
| print(submit_status) |
| return submit_status |
|
|
|
|
| def run_all(api_key: str | None = None): |
| """ |
| Fetches all questions, runs the BasicAgent on them, |
| """ |
| |
| questions_url = f"{DEFAULT_API_URL}/questions" |
|
|
| agent = prepare_agent(api_key) |
|
|
| questions_data = load_questions(questions_url) |
| |
| |
| print(f"Running agent on {len(questions_data)} questions...") |
| for item in questions_data: |
| payload_data, log_entry = answer_one(agent, item) |
| if payload_data: |
| task_id = payload_data.get("task_id") |
| answers_by_task[task_id] = payload_data |
| results_log.append(log_entry) |
| time.sleep(1) |
| if not answers_by_task: |
| final_status = "Agent did not produce any answers to submit." |
| else: |
| final_status = f"Agent finished, {len(answers_by_task)} answers produced." |
| print(final_status) |
| return final_status, pd.DataFrame(results_log) |
|
|
| def submit_all( profile: gr.OAuthProfile | None): |
| """ |
| Submits all answers and displays the results. |
| """ |
| submit_url = f"{DEFAULT_API_URL}/submit" |
|
|
| 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." |
| |
| space_id = os.getenv("SPACE_ID") |
|
|
| if not answers_by_task: |
| submit_status = "No answers to submit." |
| else: |
| |
| |
| agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" |
|
|
| submit_status = _submit_all(username, agent_code, list(answers_by_task.values()), submit_url) |
|
|
| return submit_status |
|
|
|
|
| |
| with gr.Blocks() as demo: |
| gr.Markdown("# Basic Agent Evaluation Runner") |
| gr.Markdown( |
| """ |
| **Instructions:** |
| |
| 1. Please use your own Gemini API key to run the agent. You can find your API key in your [Gemini account settings](https://gemini.com/account/settings). |
| 2. Click 'Run Evaluation' to fetch questions, run the agent, and see the answers. |
| 3. Click 'Submit All Answers' to submit the answers to the server. |
| """ |
| ) |
|
|
| gr.LoginButton() |
|
|
| api_key_input = gr.Textbox( |
| label="Gemini API Key", |
| placeholder="Enter your Gemini API key here", |
| type="password", |
| lines=1, |
| visible=True |
| ) |
|
|
| run_button = gr.Button("Run Evaluation") |
| save_button = gr.Button("Save Answers to File") |
| submit_button = gr.Button("Submit All Answers") |
|
|
| status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False) |
| results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True) |
|
|
| run_button.click( |
| fn=run_all, |
| inputs=[api_key_input], |
| outputs=[status_output, results_table] |
| ) |
|
|
| save_button.click( |
| fn=save_answers_to_file, |
| outputs=[status_output] |
| ) |
|
|
| submit_button.click( |
| fn=submit_all, |
| outputs=[status_output] |
| ) |
|
|
| if __name__ == "__main__": |
| print("\n" + "-"*30 + " App Starting " + "-"*30) |
| |
| space_host_startup = os.getenv("SPACE_HOST") |
| space_id_startup = os.getenv("SPACE_ID") |
|
|
| 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(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(f"API KEY: {os.getenv('GOOGLE_API_KEY')}") |
|
|
| print("-"*(60 + len(" App Starting ")) + "\n") |
|
|
| print("Launching Gradio Interface for Basic Agent Evaluation...") |
| demo.launch(debug=True, share=False) |