Chonky：神经网络语义分块工具

Chonky 是一个 Python 库，使用经过微调的 Transformer 模型将文本智能地分割成有意义的语义块。该库可用于 RAG 系统。

pip install chonky

from chonky import ParagraphSplitter

# on the first run it will download the transformer model
splitter = ParagraphSplitter(device="cpu")

# Or you can select the model
# splitter = ParagraphSplitter(
#  model_id="mirth/chonky_modernbert_base_1",
#  device="cpu"
# )

text = (
    "Before college the two main things I worked on, outside of school, were writing and programming. "
    "I didn't write essays. I wrote what beginning writers were supposed to write then, and probably still are: short stories. "
    "My stories were awful. They had hardly any plot, just characters with strong feelings, which I imagined made them deep. "
    "The first programs I tried writing were on the IBM 1401 that our school district used for what was then called 'data processing.' "
    "This was in 9th grade, so I was 13 or 14. The school district's 1401 happened to be in the basement of our junior high school, "
    "and my friend Rich Draves and I got permission to use it. It was like a mini Bond villain's lair down there, with all these alien-looking machines — "
    "CPU, disk drives, printer, card reader — sitting up on a raised floor under bright fluorescent lights."
)

for chunk in splitter(text):
  print(chunk)
  print("--")

Before college the two main things I worked on, outside of school, were writing and programming. I didn't write essays. I wrote what beginning writers were supposed to write then, and probably still are: short stories. My stories were awful. They had hardly any plot, just characters with strong feelings, which I imagined made them deep.
--
The first programs I tried writing were on the IBM 1401 that our school district used for what was then called "data processing." This was in 9th grade, so I was 13 or 14. The school district's 1401 happened to be in the basement of our junior high school, and my friend Rich Draves and I got permission to use it.
--
 It was like a mini Bond villain's lair down there, with all these alien-looking machines — CPU, disk drives, printer, card reader — sitting up on a raised floor under bright fluorescent lights.
--

使用模式如下：删除所有标记标签以生成纯文本，然后将该文本提供给分割器。为此有一个辅助类 MarkupRemover（它会自动检测内容格式）：

from chonky.markup_remover import MarkupRemover
from chonky import ParagraphSplitter

remover = MarkupRemover()
splitter = ParagraphSplitter()

text = remover("# Header 1 ...")
splitter(text)

支持的格式：markdown、xml、html。

以下值是基于令牌的 F1 分数，计算于每个数据集的前 100 万个令牌（出于性能原因）。

各种英文数据集：

SaT 模型中的 do_ps 片段是 do_paragraph_segmentation 标志。

Project Gutenberg 验证：