ToCode: post #6037 — TG.ME

def embed_texts(texts: list[str]) -> list[list[float]]:
    """Embed a batch of texts, returning one 768-dim vector per text."""
    embeddings = get_model().encode(texts, show_progress_bar=True)
    return [vec.tolist() for vec in embeddings]

def build_chunks(
    verses: list[tuple[str, int, int, str]],
    chunk_size: int,
    overlap: int,
) -> list[dict]:
    """Group verses per (book, chapter) and split into overlapping windows."""
    if chunk_size <= overlap:
        raise ValueError(f"CHUNK_SIZE ({chunk_size}) must be greater than OVERLAP ({overlap})")
    step = chunk_size - overlap

    # Preserve file order while grouping by (book, chapter).
    chapters: dict[tuple[str, int], list[tuple[int, str]]] = {}
    order: list[tuple[str, int]] = []
    for book, chapter, verse, text in verses:
        key = (book, chapter)