utils/text_processing.py

from __future__ import annotations

def chunk_text(text: str, chunk_size: int = 3000) -> list[str]:
    """
    Simple utility to chunk text into manageable pieces if needed
    for long transcripts.
    """
    words = text.split()
    chunks = []
    for i in range(0, len(words), chunk_size):
        chunks.append(" ".join(words[i:i+chunk_size]))
    return chunks