text-splitters[minor], langchain[minor], community[patch], templates, docs: langchain-text-splitters 0.0.1 (#18346)

This commit is contained in:
Bagatur
2024-02-29 18:33:21 -08:00
committed by GitHub
parent 7891934173
commit 5efb5c099f
226 changed files with 6626 additions and 1980 deletions

View File

@@ -0,0 +1,71 @@
"""**Text Splitters** are classes for splitting text.
**Class hierarchy:**
.. code-block::
BaseDocumentTransformer --> TextSplitter --> <name>TextSplitter # Example: CharacterTextSplitter
RecursiveCharacterTextSplitter --> <name>TextSplitter
Note: **MarkdownHeaderTextSplitter** and **HTMLHeaderTextSplitter do not derive from TextSplitter.
**Main helpers:**
.. code-block::
Document, Tokenizer, Language, LineType, HeaderType
""" # noqa: E501
from langchain_text_splitters.base import (
Language,
TextSplitter,
Tokenizer,
TokenTextSplitter,
split_text_on_tokens,
)
from langchain_text_splitters.character import (
CharacterTextSplitter,
RecursiveCharacterTextSplitter,
)
from langchain_text_splitters.html import ElementType, HTMLHeaderTextSplitter
from langchain_text_splitters.json import RecursiveJsonSplitter
from langchain_text_splitters.konlpy import KonlpyTextSplitter
from langchain_text_splitters.latex import LatexTextSplitter
from langchain_text_splitters.markdown import (
HeaderType,
LineType,
MarkdownHeaderTextSplitter,
MarkdownTextSplitter,
)
from langchain_text_splitters.nltk import NLTKTextSplitter
from langchain_text_splitters.python import PythonCodeTextSplitter
from langchain_text_splitters.sentence_transformers import (
SentenceTransformersTokenTextSplitter,
)
from langchain_text_splitters.spacy import SpacyTextSplitter
__all__ = [
"TokenTextSplitter",
"TextSplitter",
"Tokenizer",
"Language",
"RecursiveCharacterTextSplitter",
"RecursiveJsonSplitter",
"LatexTextSplitter",
"PythonCodeTextSplitter",
"KonlpyTextSplitter",
"SpacyTextSplitter",
"NLTKTextSplitter",
"split_text_on_tokens",
"SentenceTransformersTokenTextSplitter",
"ElementType",
"HeaderType",
"LineType",
"HTMLHeaderTextSplitter",
"MarkdownHeaderTextSplitter",
"MarkdownTextSplitter",
"CharacterTextSplitter",
]