mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
c28efb878c
- **Description:** the layout of html pages can be variant based on the bootstrap framework or the styles of the pages. So we need to have a splitter to transform the html tags to a proper layout and then split the html content based on the provided list of tags to determine its html sections. We are using BS4 library along with xslt structure to split the html content using an section aware approach. - **Dependencies:** No new dependencies - **Twitter handle:** @m_setayesh Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Bagatur <baskaryan@gmail.com>
77 lines
2.0 KiB
Python
77 lines
2.0 KiB
Python
"""**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,
|
|
HTMLSectionSplitter,
|
|
)
|
|
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",
|
|
"HTMLSectionSplitter",
|
|
"MarkdownHeaderTextSplitter",
|
|
"MarkdownTextSplitter",
|
|
"CharacterTextSplitter",
|
|
]
|