Spaces:
Sleeping
Sleeping
| from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool | |
| from bs4 import BeautifulSoup | |
| from sklearn.feature_extraction.text import TfidfVectorizer | |
| from sklearn.metrics.pairwise import cosine_similarity | |
| import datetime | |
| import requests | |
| import pytz | |
| import yaml | |
| from tools.final_answer import FinalAnswerTool | |
| from Gradio_UI import GradioUI | |
| def categorize_content(text, categories): | |
| """Categorizes text using NLP and TF-IDF similarity.""" | |
| vectorizer = TfidfVectorizer() | |
| category_texts = list(categories.values()) | |
| category_names = list(categories.keys()) | |
| tfidf_matrix = vectorizer.fit_transform([text] + category_texts) | |
| similarities = cosine_similarity(tfidf_matrix[0:1], tfidf_matrix[1:]).flatten() | |
| return category_names[similarities.argmax()] if similarities.any() else "Uncategorized" | |
| def scrape_webpage(url:str, categories:dict = None)-> str: #it's import to specify the return type | |
| #Keep this format for the description / args / args description but feel free to modify the tool | |
| """A tool that scrapes a webpage and categorizes the content using NLP. | |
| Args: | |
| url: the first argument | |
| categories: A dictionary with category names as keys and example text as values. | |
| """ | |
| try: | |
| response = requests.get(url, timeout=10) | |
| response.raise_for_status() | |
| soup = BeautifulSoup(response.text, "html.parser") | |
| text_content = ' '.join(soup.stripped_strings) | |
| if categories: | |
| category = categorize_content(text_content, categories) | |
| return f"The following text content {text_content} was scaped from {url} and categorized as: {category}" | |
| else: | |
| return "The following text content was scaped: %s" % text_content | |
| except requests.RequestException as e: | |
| return f"Error fetching webpage: {str(e)}" | |
| 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)}" | |
| final_answer = FinalAnswerTool() | |
| model = HfApiModel( | |
| max_tokens=2096, | |
| temperature=0.5, | |
| model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded | |
| custom_role_conversions=None, | |
| ) | |
| # Import tool from Hub | |
| image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True) | |
| with open("prompts.yaml", 'r') as stream: | |
| prompt_templates = yaml.safe_load(stream) | |
| agent = CodeAgent( | |
| model=model, | |
| tools=[final_answer, scrape_webpage], ## add your tools here (don't remove final answer) | |
| max_steps=6, | |
| verbosity_level=1, | |
| grammar=None, | |
| planning_interval=None, | |
| name=None, | |
| description=None, | |
| prompt_templates=prompt_templates | |
| ) | |
| GradioUI(agent).launch() |