Spaces:
Sleeping
Sleeping
Daniel Sellmeier
Verbesserte Antwortformatierung und Parsing-Kompatibilität für exakte Antwortabgleiche
0f8361a
| import os | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| # --- New Imports --- | |
| import datetime | |
| import pytz | |
| import yaml | |
| import secrets | |
| import string | |
| import re # Import re for visit_webpage | |
| from smolagents import CodeAgent, DuckDuckGoSearchTool, OpenAIServerModel, load_tool, tool | |
| from tools.final_answer import FinalAnswerTool | |
| from smolagents.utils import truncate_content | |
| import dotenv | |
| dotenv.load_dotenv() | |
| OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") | |
| # (Keep Constants as is) | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| # --- Tool Definitions --- | |
| # Tool: search (using DuckDuckGoSearchTool) | |
| def search(query:str) -> str: | |
| """Perform a web query with the specified search string. | |
| Args: | |
| query: The search string to pass to the search engine. | |
| """ | |
| # Note: DuckDuckGoSearchTool itself handles the import check now. | |
| search_tool_instance = DuckDuckGoSearchTool() | |
| return search_tool_instance(query) | |
| # Tool: get_current_time_in_timezone | |
| def get_current_time_in_timezone(timezone: str) -> str: | |
| """A tool that fetches the current local time in a specified timezone. | |
| Args: | |
| timezone: A string representing a valid timezone (e.g., 'America/New_York'). | |
| """ | |
| try: | |
| # Create timezone object | |
| tz = pytz.timezone(timezone) | |
| # Get current time in that timezone | |
| local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S") | |
| return f"The current local time in {timezone} is: {local_time}" | |
| except Exception as e: | |
| return f"Error fetching time for timezone '{timezone}': {str(e)}" | |
| # Tool: get_open_meteo_weather | |
| def get_open_meteo_weather(city: str) -> str: | |
| """ | |
| Fetches the current weather for a given city using Open-Meteo's APIs. | |
| Args: | |
| city: The name of the city (e.g., "Berlin", "New York"). | |
| Returns: | |
| A string summarizing the current weather conditions, or an error message. | |
| """ | |
| try: | |
| # First, use the geocoding API to convert the city name to coordinates. | |
| geo_url = f"https://geocoding-api.open-meteo.com/v1/search?name={city}" | |
| geo_response = requests.get(geo_url) | |
| geo_response.raise_for_status() | |
| geo_data = geo_response.json() | |
| results = geo_data.get("results") | |
| if not results: | |
| return f"No coordinates found for city: {city}" | |
| # Use the first matching result. | |
| first_result = results[0] | |
| latitude = first_result.get("latitude") | |
| longitude = first_result.get("longitude") | |
| resolved_name = first_result.get("name", city) | |
| # Now, query the Open-Meteo weather API with the obtained coordinates. | |
| weather_url = ( | |
| f"https://api.open-meteo.com/v1/forecast" | |
| f"?latitude={latitude}&longitude={longitude}¤t_weather=true" | |
| ) | |
| weather_response = requests.get(weather_url) | |
| weather_response.raise_for_status() | |
| weather_data = weather_response.json() | |
| current = weather_data.get("current_weather") | |
| if not current: | |
| return "Current weather data not available." | |
| temperature = current.get("temperature") | |
| windspeed = current.get("windspeed") | |
| winddirection = current.get("winddirection") | |
| weathercode = current.get("weathercode") | |
| weather_time = current.get("time") | |
| return ( | |
| f"In {resolved_name} at {weather_time}, the temperature is {temperature}°C, " | |
| f"wind speed is {windspeed} km/h, wind direction is {winddirection}°, " | |
| f"weather code: {weathercode}." | |
| ) | |
| except Exception as e: | |
| return f"Error fetching weather data: {str(e)}" | |
| # Tool: get_random_joke | |
| def get_random_joke() -> str: | |
| """ | |
| Fetches a random joke from the Official Joke API. | |
| Returns: | |
| A string containing the joke's setup and punchline, or an error message. | |
| """ | |
| try: | |
| # The API endpoint for a random joke: | |
| url = "https://official-joke-api.appspot.com/random_joke" | |
| response = requests.get(url) | |
| response.raise_for_status() | |
| joke_data = response.json() | |
| setup = joke_data.get("setup") | |
| punchline = joke_data.get("punchline") | |
| if not setup or not punchline: | |
| return "Couldn't find a complete joke." | |
| return f"{setup} - {punchline}" | |
| except Exception as e: | |
| return f"Error fetching joke: {str(e)}" | |
| # Tool: generate_password | |
| def generate_password(length: int = 16, use_punctuation: bool = True) -> str: | |
| """ | |
| Generates a secure random password with at least 16 characters. | |
| Args: | |
| length: The desired length of the password (must be at least 16; default is 16). | |
| use_punctuation: Whether to include punctuation symbols in the password (default is True). | |
| Returns: | |
| A randomly generated password as a string. | |
| Raises: | |
| ValueError: If the requested length is less than 16. | |
| """ | |
| if length < 16: | |
| # Instead of raising an error, return a message for Gradio | |
| return "Error: Password length must be at least 16 characters" | |
| # Build the alphabet from which to choose characters. | |
| alphabet = string.ascii_letters + string.digits | |
| if use_punctuation: | |
| alphabet += string.punctuation | |
| # Generate a secure random password using secrets.choice. | |
| password = ''.join(secrets.choice(alphabet) for _ in range(length)) | |
| return password | |
| # Tool: VisitWebpageTool | |
| def visit_webpage(url: str) -> str: | |
| """Visits a webpage at the given url and reads its content as a markdown string. | |
| Use this to browse webpages. | |
| Args: | |
| url: The url of the webpage to visit. | |
| """ | |
| try: | |
| # Send a GET request to the URL with a 20-second timeout | |
| response = requests.get(url, timeout=20) | |
| response.raise_for_status() # Raise an exception for bad status codes | |
| # Convert the HTML content to Markdown | |
| # Ensure markdownify is imported | |
| from markdownify import markdownify | |
| markdown_content = markdownify(response.text).strip() | |
| # Remove multiple line breaks | |
| markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content) | |
| # Truncate content (ensure truncate_content is imported from smolagents.utils) | |
| return truncate_content(markdown_content, 10000) | |
| except requests.exceptions.Timeout: | |
| return "The request timed out. Please try again later or check the URL." | |
| except requests.exceptions.RequestException as e: | |
| return f"Error fetching the webpage: {str(e)}" | |
| except Exception as e: | |
| return f"An unexpected error occurred: {str(e)}" | |
| # --- User's Agent Definition --- | |
| class MyCodeAgent: | |
| def __init__(self): | |
| print("Initializing MyCodeAgent...") | |
| try: | |
| # Load prompts | |
| with open("prompts.yaml", 'r') as stream: | |
| self.prompt_templates = yaml.safe_load(stream) | |
| print("Prompts loaded successfully.") | |
| # Initialize OpenAI Model | |
| openai_api_key = os.getenv("OPENAI_API_KEY") | |
| if not openai_api_key: | |
| # Raise an error if the key is missing, as the app cannot function without it. | |
| # Provide a clear message for the user. | |
| raise ValueError("Environment variable OPENAI_API_KEY is not set. Please set it to your OpenAI API key.") | |
| self.model = OpenAIServerModel( | |
| model_id="gpt-4.1", # Or use "gpt-4o" or another compatible model | |
| api_base="https://api.openai.com/v1", # Default OpenAI API base | |
| api_key=openai_api_key, | |
| ) | |
| print(f"OpenAIServerModel initialized with model_id='{self.model.model_id}'.") | |
| # Load tools | |
| self.final_answer_tool = FinalAnswerTool() | |
| # Assuming 'agents-course/text-to-image' needs trust_remote_code | |
| self.image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True) | |
| print("Tools loaded.") | |
| # Initialize CodeAgent | |
| self.agent = CodeAgent( | |
| model=self.model, | |
| tools=[self.final_answer_tool, get_current_time_in_timezone, self.image_generation_tool, search, get_open_meteo_weather, get_random_joke, generate_password, visit_webpage], | |
| max_steps=15, # As per user's code | |
| verbosity_level=1, # As per user's code | |
| grammar=None, | |
| planning_interval=None, | |
| name=None, | |
| description=None, | |
| prompt_templates=self.prompt_templates, | |
| additional_authorized_imports=['pandas', 'numpy', 'openpyxl', 'xlrd'] | |
| ) | |
| print("CodeAgent initialized.") | |
| print("MyCodeAgent initialized successfully.") | |
| except Exception as e: | |
| print(f"Error during MyCodeAgent initialization: {e}") | |
| # Raise the exception to prevent the app from potentially running in a broken state | |
| raise | |
| def __call__(self, question: str) -> str: | |
| print(f"MyCodeAgent received question (first 50 chars): {question[:50]}...") | |
| try: | |
| response = self.agent(question) | |
| # Ensure the response is a string for submission | |
| if not isinstance(response, str): | |
| print(f"Warning: Agent returned non-string type ({type(response)}). Converting to string.") | |
| response = str(response) | |
| # Verarbeite die Antwort, um nur die kurze Version zu extrahieren | |
| if "### 1. Task outcome (short version):" in response: | |
| short_answer_start = response.find("### 1. Task outcome (short version):") + len("### 1. Task outcome (short version):") | |
| # Suche nach dem Ende der kurzen Antwort (dem Beginn des nächsten Abschnitts) | |
| next_section = response.find("### 2.", short_answer_start) | |
| if next_section != -1: | |
| short_answer = response[short_answer_start:next_section].strip() | |
| else: | |
| short_answer = response[short_answer_start:].strip() | |
| # Bereinige die Antwort von unnötigen Formatierungen | |
| short_answer = short_answer.strip() | |
| print(f"Extrahierte kurze Antwort: {short_answer}") | |
| # Verwende die vollständige Antwort nur für Debugging-Zwecke | |
| print(f"Vollständige Antwort für Debugging: {response[:100]}...") | |
| return short_answer | |
| print(f"MyCodeAgent returning answer (first 100 chars): {response[:100]}...") | |
| return response | |
| except Exception as e: | |
| print(f"Error during MyCodeAgent execution: {e}") | |
| # Return an error message instead of crashing the Gradio app | |
| return f"AGENT_EXECUTION_ERROR: {e}" | |
| def run_and_submit_all( profile: gr.OAuthProfile | None): | |
| """ | |
| Fetches all questions, runs the MyCodeAgent 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 | |
| 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 = MyCodeAgent() | |
| 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 | |
| # 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(question_text) | |
| 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}"}) | |
| 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 | |
| # --- 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 MyCodeAgent Evaluation...") | |
| demo.launch(debug=True, share=False) |