Spaces:
Running
Running
| """ | |
| NOTE: | |
| - If USE_RATE_LIMITER env variable is True, the agent will use a rate limiter to avoid hitting API limits. | |
| """ | |
| import os | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| from agent import build_agent | |
| from langchain_core.messages import HumanMessage | |
| from langfuse.langchain import CallbackHandler | |
| langfuse_handler = CallbackHandler() | |
| # (Keep Constants as is) | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| questions_url = f"{DEFAULT_API_URL}/questions" | |
| submit_url = f"{DEFAULT_API_URL}/submit" | |
| files_url = f"{DEFAULT_API_URL}/files/" # Needs task_id | |
| # --- Basic Agent Definition --- | |
| class SuperAgent: | |
| def __init__(self): | |
| print("SuperAgent initialized.") | |
| self.agent = build_agent(provider="google") # Change to "hf" for HuggingFace | |
| self.recursion_limit = os.getenv("RECURSION_LIMIT", "25") | |
| def __call__(self, data: dict) -> str: | |
| """ | |
| Args: | |
| data (str): A string containing the question to be answered. | |
| Schema: { | |
| task_id: str, | |
| question: str, | |
| file_name: str, | |
| } | |
| """ | |
| # Quick validation of input data (TODO: Use pydantic for schema) | |
| required_keys = ["question", "task_id", "file_name"] | |
| if not all(k in data for k in required_keys): | |
| raise ValueError("Input data must contain 'question', 'task_id', and 'file_name'.") | |
| task_id, question, file_name = data["task_id"], data["question"], data["file_name"] | |
| print(f"Agent received question (first 50 chars): {question[:50]}...") | |
| # Build HumanMessage | |
| content = [ | |
| {"type": "text", "text": question} | |
| ] | |
| if file_name != "": | |
| file_url = f"{files_url}{task_id}" | |
| if file_name.endswith((".png", ".jpg", ".jpeg")): | |
| content.append({"type": "image_url", "image_url": {"url": file_url}}) | |
| elif file_name.endswith((".py")): | |
| # For code files, we can just send the text content | |
| try: | |
| response = requests.get(file_url, timeout=15) | |
| response.raise_for_status() | |
| code_content = response.text | |
| content.append({"type": "text", "text": code_content}) | |
| except Exception as e: | |
| print(f"Error fetching code file: {e}") | |
| elif file_name.endswith((".xlsx", ".xls")): | |
| content.append({"type": "text", "text": "Excel file url: " + file_url}) | |
| elif file_name.endswith((".mp3", ".wav")): | |
| content.append({"type": "text", "text": "Audio file url: " + file_url}) | |
| else: | |
| raise ValueError(f"Unsupported file type for file: {file_name}") | |
| human_msg = HumanMessage(content=content) | |
| try: | |
| answer = self.agent.invoke( | |
| {"messages": [human_msg]}, | |
| config={"callbacks": [langfuse_handler], "recursion_limit": self.recursion_limit} | |
| ) | |
| # for message in answer["messages"]: | |
| # message.pretty_print() | |
| # Result already printed inside assistant() node | |
| except Exception as e: | |
| print(f"Error: {e}") | |
| return answer["messages"][-1].content | |
| def run_and_submit_all( profile: gr.OAuthProfile | None): | |
| """ | |
| Fetches all questions, runs the SuperAgent 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 | |
| # 1. Instantiate Agent ( modify this part to create your agent) | |
| try: | |
| agent = SuperAgent() | |
| 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: | |
| print(f"Error decoding JSON response from questions endpoint: {e}") | |
| print(f"Response text: {response.text[:500]}") | |
| 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 | |
| # Read excluded task IDs from file | |
| excluded_tasks = set() | |
| with open("excluded_tasks.txt", "r") as f: | |
| for line in f: | |
| task_id = line.strip() | |
| if task_id: | |
| excluded_tasks.add(task_id) | |
| # 3. Run your Agent | |
| results_log = [] | |
| answers_payload = [] | |
| print(f"Running agent on {len(questions_data)} questions...") | |
| for idx, item in enumerate(questions_data): | |
| task_id = item.get("task_id") | |
| question_text = item.get("question") | |
| print(f"[{idx+1}/{len(questions_data)}]", end=" ") | |
| if not task_id or question_text is None: | |
| print(f"Skipping item with missing task_id or question: {item}") | |
| continue | |
| # Skip excluded tasks | |
| if task_id in excluded_tasks: | |
| print(f"Skipping excluded task: {task_id}") | |
| 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}) | |
| # Print the answer for debugging | |
| # print the timestamp | |
| print(f"Task ID: {task_id}, Submitted Answer: {submitted_answer[:50]}") | |
| 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}"}) | |
| 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 | |
| # Read the app description from markdown file | |
| with open("description.md", "r", encoding="utf-8") as f: | |
| description_md = f.read() | |
| # --- Build Gradio Interface using Blocks --- | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# Super Agent Evaluation Runner") | |
| gr.Markdown(description_md) | |
| 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=True) |