Download app.py from andrei-sferdian/Agents_Course_Final_Assignment: direct link, hf CLI and curl.
- Browser
- Download file 15.2 kB
-
https://huggingface.co/spaces/andrei-sferdian/Agents_Course_Final_Assignment/resolve/main/app.py
- Command line
-
hf download hf://spaces/andrei-sferdian/Agents_Course_Final_Assignment/app.py
-
curl -L -o app.py https://huggingface.co/spaces/andrei-sferdian/Agents_Course_Final_Assignment/resolve/main/app.py
15.2 kB
| import os | |
| import queue | |
| from concurrent.futures import ThreadPoolExecutor | |
| import gradio as gr | |
| import pandas as pd | |
| import requests | |
| from langchain_core.runnables import RunnableConfig | |
| from agent import agent | |
| from langfuse_handler import create_langfuse_handler | |
| from questions import Answer, Question | |
| # (Keep Constants as is) | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| langfuse_handler = ( | |
| create_langfuse_handler() if os.getenv("USE_LANGFUSE") is not None else None | |
| ) | |
| def run_and_submit_all(profile: gr.OAuthProfile | None): | |
| """ | |
| Fetches all questions, runs the BasicAgent on them, submits all answers, | |
| and displays the results. | |
| """ | |
| 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 = os.getenv("API_URL") or DEFAULT_API_URL | |
| questions_url = f"{api_url}/questions" | |
| submit_url = f"{api_url}/submit" | |
| space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code | |
| agent_code = f"https://huggingface.co/spaces/{username}/{space_id}/tree/main" | |
| print(agent_code) | |
| # 1. Fetch Tasks | |
| print(f"Fetching questions from: {questions_url}") | |
| response = None | |
| 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.JSONDecodeError as e: | |
| print(f"Error decoding JSON response from questions endpoint: {e}") | |
| if response: | |
| print(f"Response text: {response.text[:500]}") | |
| return f"Error decoding server response for questions: {e}", None | |
| except requests.exceptions.RequestException as e: | |
| print(f"Error fetching questions: {e}") | |
| return f"Error fetching 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 = queue.Queue() | |
| answers = queue.Queue() | |
| def _process_question(question: Question): | |
| print(f"Processing question: {question}") | |
| task_id = question["task_id"] | |
| question_text = question["question"] | |
| try: | |
| response = agent.invoke( | |
| {"question": question}, | |
| RunnableConfig( | |
| callbacks=[langfuse_handler] if langfuse_handler else None, | |
| ), | |
| ) | |
| submitted_answer = ( | |
| response["messages"][-1].content | |
| if response | |
| and response.get("messages") | |
| and len(response["messages"]) > 0 | |
| else None | |
| ) | |
| if submitted_answer is None: | |
| raise Exception( | |
| f"Agent did not produce a valid answer for question {task_id}." | |
| ) | |
| print(f"Agent response: {submitted_answer}") | |
| answers.put( | |
| { | |
| "task_id": task_id, | |
| "submitted_answer": submitted_answer, | |
| } | |
| ) | |
| results.put( | |
| { | |
| "Task ID": task_id, | |
| "Question": question_text, | |
| "Submitted Answer": submitted_answer, | |
| } | |
| ) | |
| except Exception as e: | |
| print(f"Error running agent on question {task_id}: {e}") | |
| results.put( | |
| { | |
| "Task ID": task_id, | |
| "Question": question_text, | |
| "Submitted Answer": f"AGENT ERROR: {e}", | |
| } | |
| ) | |
| max_concurrency = int(os.getenv("MAX_CONCURRENCY", 1)) | |
| with ThreadPoolExecutor(max_workers=max_concurrency) as executor: | |
| print(f"Running agent on {len(questions_data)} questions...") | |
| list(executor.map(_process_question, questions_data)) | |
| results_log = list(results.queue) | |
| answers_payload = list(answers.queue) | |
| 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 | |
| def run_in_space(): | |
| # --- 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]) | |
| # 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) | |
| def run_locally(): | |
| print("Running locally...") | |
| # questions = get_questions(1) | |
| # if not questions: | |
| # print("No questions available to run.") | |
| # return | |
| questions = [ | |
| # { | |
| # "task_id": "8e867cd7-cff9-4e6c-867a-ff5ddc2550be", | |
| # "question": "How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia.", | |
| # "file_name": "", | |
| # }, | |
| # { | |
| # "task_id": "cf106601-ab4f-4af9-b045-5295fe67b37d", | |
| # "question": "What country had the least number of athletes at the 1928 Summer Olympics? If there's a tie for a number of athletes, return the first in alphabetical order. Give the IOC country code as your answer.", | |
| # "file_name": "", | |
| # }, | |
| # { | |
| # "task_id": "9d191bce-651d-4746-be2d-7ef8ecadb9c2", | |
| # "question": "Examine the video at https://www.youtube.com/watch?v=1htKBjuUWec.\n\nWhat does Teal'c say in response to the question \"Isn't that hot?\"", | |
| # "file_name": "", | |
| # }, | |
| # { | |
| # "task_id": "2d83110e-a098-4ebb-9987-066c06fa42d0", | |
| # "question": '.rewsna eht sa "tfel" drow eht fo etisoppo eht etirw ,ecnetnes siht dnatsrednu uoy fI', | |
| # "file_name": "", | |
| # }, | |
| # { | |
| # "task_id": "7bd855d8-463d-4ed5-93ca-5fe35145f733", | |
| # "question": "The attached Excel file contains the sales of menu items for a local fast-food chain. What were the total sales that the chain made from food (not including drinks)? Express your answer in USD with two decimal places.", | |
| # "file_name": "7bd855d8-463d-4ed5-93ca-5fe35145f733.xlsx", | |
| # }, | |
| # { | |
| # "task_id": "f918266a-b3e0-4914-865d-4faa564f1aef", | |
| # "question": "What is the final numeric output from the attached Python code?", | |
| # "file_name": "f918266a-b3e0-4914-865d-4faa564f1aef.py", | |
| # }, | |
| # { | |
| # "task_id": "305ac316-eef6-4446-960a-92d80d542f82", | |
| # "question": "Who did the actor who played Ray in the Polish-language version of Everybody Loves Raymond play in Magda M.? Give only the first name.", | |
| # "file_name": "", | |
| # }, | |
| # { | |
| # "task_id": "6f37996b-2ac7-44b0-8e68-6d28256631b4", | |
| # "question": "Given this table defining * on the set S = {a, b, c, d, e}\n\n|*|a|b|c|d|e|\n|---|---|---|---|---|---|\n|a|a|b|c|b|d|\n|b|b|c|a|e|c|\n|c|c|a|b|b|a|\n|d|b|e|b|e|d|\n|e|d|b|a|d|c|\n\nprovide the subset of S involved in any possible counter-examples that prove * is not commutative. Provide your answer as a comma separated list of the elements in the set in alphabetical order.", | |
| # "file_name": "", | |
| # }, | |
| # { | |
| # "task_id": "3cef3a44-215e-4aed-8e3b-b1e3f08063b7", | |
| # "question": "I'm making a grocery list for my mom, but she's a professor of botany and she's a real stickler when it comes to categorizing things. I need to add different foods to different categories on the grocery list, but if I make a mistake, she won't buy anything inserted in the wrong category. Here's the list I have so far:\n\nmilk, eggs, flour, whole bean coffee, Oreos, sweet potatoes, fresh basil, plums, green beans, rice, corn, bell pepper, whole allspice, acorns, broccoli, celery, zucchini, lettuce, peanuts\n\nI need to make headings for the fruits and vegetables. Could you please create a list of just the vegetables from my list? If you could do that, then I can figure out how to categorize the rest of the list into the appropriate categories. But remember that my mom is a real stickler, so make sure that no botanical fruits end up on the vegetable list, or she won't get them when she's at the store. Please alphabetize the list of vegetables, and place each item in a comma separated list.", | |
| # "file_name": "", | |
| # }, | |
| { | |
| "task_id": "cca530fc-4052-43b2-b130-b30968d8aa44", | |
| "question": "Review the chess position provided in the image. It is black's turn. Provide the correct next move for black which guarantees a win. Please provide your response in algebraic notation.", | |
| "file_name": "cca530fc-4052-43b2-b130-b30968d8aa44.png", | |
| }, | |
| ] | |
| def _process_question(question: Question) -> Answer: | |
| try: | |
| print(f"Processing question: {question}") | |
| response = agent.invoke( | |
| {"question": question}, | |
| ) | |
| answer_text = ( | |
| response["messages"][-1].content | |
| if response | |
| and response.get("messages") | |
| and len(response["messages"]) > 0 | |
| else "No valid answer provided by the agent." | |
| ) | |
| except Exception as e: | |
| answer_text = f"AGENT ERROR: {e}" | |
| answer = Answer(task_id=question["task_id"], answer=answer_text) | |
| print(f"Answer: {answer['answer']}") | |
| return answer | |
| max_concurrency = int(os.getenv("MAX_CONCURRENCY", 1)) | |
| with ThreadPoolExecutor(max_workers=max_concurrency) as executor: | |
| answers = list(executor.map(_process_question, questions)) | |
| print(answers) | |
| if __name__ == "__main__": | |
| print("\n" + "-" * 30 + " App Starting " + "-" * 30) | |
| env = os.getenv("ENV", "local") | |
| print(f"Environment: {env}") | |
| if env == "space": | |
| print("Running in Hugging Face Space environment.") | |
| run_in_space() | |
| else: | |
| print("Running in local environment.") | |
| run_locally() | |