tools/extract_dates/tool.py

import re
from typing import List

from smolagents import tool


@tool
def extract_dates(text: str) -> List[str]:
    """
    Extract dates from text content.

    Args:
        text: Text content to extract dates from

    Returns:
        List of date strings found in the text
    """
    # Simple regex patterns for date extraction
    # These patterns can be expanded for better coverage
    date_patterns = [
        r"\d{1,2}/\d{1,2}/\d{2,4}",  # MM/DD/YYYY or DD/MM/YYYY
        r"\d{1,2}-\d{1,2}-\d{2,4}",  # MM-DD-YYYY or DD-MM-YYYY
        r"\b(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)[a-z]* \d{1,2},? \d{4}\b",  # Month DD, YYYY
        r"\b\d{1,2} (?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)[a-z]* \d{4}\b",  # DD Month YYYY
    ]

    results = []
    for pattern in date_patterns:
        matches = re.findall(pattern, text, re.IGNORECASE)
        results.extend(matches)

    return results