Sha256: ea4cb9673426e08c0acc438b35d2ffb7d547bb117ff697cca334962f4370d731
Contents?: true
Size: 453 Bytes
Versions: 6
Compression:
Stored size: 453 Bytes
Contents
require_relative './text_splitter' module Baran class CharacterTextSplitter < TextSplitter attr_accessor :separator def initialize(chunk_size: 1024, chunk_overlap: 64, separator: nil) super(chunk_size: chunk_size, chunk_overlap: chunk_overlap) @separator = separator || "\n\n" end def splitted(text) splits = separator.empty? ? text.chars : text.split(separator) merged(splits, @separator) end end end
Version data entries
6 entries across 6 versions & 1 rubygems