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("--")

from chonky.markup_remover import MarkupRemover
from chonky import ParagraphSplitter

remover = MarkupRemover()
splitter = ParagraphSplitter()

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