Files
Chromy/chromy/chunking/service.py
T
mrosati fb62d1b539
build / build (push) Successful in 45s
pytest / pytest (push) Successful in 26s
refactor chunking and embedding into their own modules
2026-05-01 11:01:30 +02:00

20 lines
457 B
Python

from __future__ import annotations
from pathlib import Path
from typing import cast
from semchunk import semchunk
def chunk_text(text: str, chunk_size: int = 800) -> list[str]:
chunker = semchunk.chunkerify("gpt-4", chunk_size)
chunks = chunker(text)
return cast("list[str]", chunks)
def chunk_file(filename: str, chunk_size: int = 800) -> list[str]:
contents = Path(filename).read_text()
return chunk_text(contents, chunk_size)