Splitters
mash.ai.splitters · AI
Split text for AI processing
Methods
Section titled “Methods”character
Section titled “character”splitters.character(chunk_size?: int = 1000, chunk_overlap?: int = 200, separator?: string = "\n\n")
Create a character-based text splitter.
htmlHeaderTextSplitter
Section titled “htmlHeaderTextSplitter”splitters.htmlHeaderTextSplitter(headers_to_split_on: array, return_each_element?: bool = false)
Create an HTML header-based text splitter.
htmlSectionSplitter
Section titled “htmlSectionSplitter”splitters.htmlSectionSplitter(headers_to_split_on: array)
Create an HTML section splitter.
htmlSemanticPreservingSplitter
Section titled “htmlSemanticPreservingSplitter”splitters.htmlSemanticPreservingSplitter(headers_to_split_on: array, max_chunk_size: int, chunk_overlap: int)
Create an HTML semantic-preserving splitter.
markdownTextSplitter
Section titled “markdownTextSplitter”splitters.markdownTextSplitter(chunk_size?: int = 1000, chunk_overlap?: int = 200, separators?: array = ["\n\n","\n"," ",""])
Create a Markdown-aware text splitter.
recursiveCharacter
Section titled “recursiveCharacter”splitters.recursiveCharacter(chunk_size?: int = 1000, chunk_overlap?: int = 200, separators?: array = ["\n\n","\n"," ",""])
Create a recursive character text splitter.
recursiveJsonSplitter
Section titled “recursiveJsonSplitter”splitters.recursiveJsonSplitter(chunk_size?: int = 1000, chunk_overlap?: int = 200)
Create a recursive JSON splitter.