tools.py

import re
import requests
from markdownify import markdownify
from requests.exceptions import RequestException
from smolagents import tool
from huggingface_hub import InferenceClient


@tool
def visit_webpage(url: str) -> str:
    """Visits a webpage at the given URL and returns its content as a markdown string.

    Args:
        url: The URL of the webpage to visit.

    Returns:
        The content of the webpage converted to Markdown, or an error message if the request fails.
    """
    try:
        # Send a GET request to the URL
        response = requests.get(url)
        response.raise_for_status()  # Raise an exception for bad status codes

        # Convert the HTML content to Markdown
        markdown_content = markdownify(response.text).strip()

        # Remove multiple line breaks
        markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)

        return markdown_content

    except RequestException as e:
        return f"Error fetching the webpage: {str(e)}"
    except Exception as e:
        return f"An unexpected error occurred: {str(e)}"

@tool
def analyze_image(url: str, prompt: str) -> str:
    """Uses a vision model to identify features in an describe an image.

    Args:
        url: The URL of the image to analyze
        prompt: Specific questions or things you are looking for in the image. Can also specify how to format a response. The model will return a general description if this is blank.

    Retruns:
        Answers to your question(s) or else a textual description of the image
    """
    
    model_id = "Qwen/Qwen2.5-VL-32B-Instruct"
    client = InferenceClient()
    image_url = "https://agents-course-unit4-scoring.hf.space/files/cca530fc-4052-43b2-b130-b30968d8aa44"

    if prompt is None:
        prompt = "Describe the content of the image in detail."
        
    model_prompt = [
                {
                    "role": "user",
                    "content": [
                        {"type": "image_url", "image_url": {"url": image_url}},
                        {"type": "text", "text": prompt}
                    ]
                }
            ]
    
    response = client.chat_completion(
        model=model_id,
        messages=model_prompt,
        max_tokens=1000,
        temperature=0.7
    )
    description = response.choices[0].message.content