Getting Started
BaseLanguageDetector
BaseLanguageDetector.detect()
BaseTextChunker
BaseTextChunker.chunk()
Chunk
Chunk.content
Chunk.overlap
Chunk.size
Chunk.text
Chunk.text_parts
Chunks
Chunks.get_all_text()
Chunks.get_all_text_parts()
FastTextLanguageDetector
FastTextLanguageDetector.detect()
FixedSizeTextChunker
FixedSizeTextChunker.split_text()
LangdetectLanguageDetector
LangdetectLanguageDetector.detect()
Overlap
RecursiveTextChunker
RecursiveTextChunker.split_text()
TextPart
TextPart.size
TextPart.text
BaseSizeEstimator
CharSizeEstimator
OpenAISizeEstimator
WordSizeEstimator
BaseOverlapTextChunker
BaseTextSplitter
ColonTextSplitter
CommaTextSplitter
FullStopTextSplitter
NewlineTextSplitter
SemicolonTextSplitter
SeparatorTextSplitter
WordTextSplitter
MissingDependencyError
format_instructions()
import_dependencies()
Text Chunkers
Text Splitters
Language Detection
Size Estimators
Classes
BaseTextSplitter()
Base class for splitter strategies that divide text into smaller pieces.
Bases: ABC
ABC
Template method for splitting text. Validates the input and delegates the actual splitting logic to the subclass.
text (str) – The text to be split.
A list of text text parts.
list[str]