Class CharacterTextSplitter
Splits documents into chunks based on character count with configurable overlap.
public class CharacterTextSplitter : ITextSplitter
- Inheritance
-
CharacterTextSplitter
- Implements
- Inherited Members
Constructors
CharacterTextSplitter()
public CharacterTextSplitter()
CharacterTextSplitter(int, int, string?)
public CharacterTextSplitter(int chunkSize, int chunkOverlap = 200, string? separator = "\n\n")
Parameters
Properties
ChunkOverlap
Number of overlapping characters between consecutive chunks.
public int ChunkOverlap { get; set; }
Property Value
ChunkSize
Maximum number of characters per chunk.
public int ChunkSize { get; set; }
Property Value
Separator
Separator string to attempt to split on (e.g., "\n\n", "\n", " "). If null, splits at exact character boundaries.
public string? Separator { get; set; }
Property Value
Methods
Split(RagDocument)
Splits a document into chunks. Implementations may split by character count, token count, sentence boundary, etc.
public IReadOnlyList<RagChunk> Split(RagDocument document)
Parameters
documentRagDocumentThe document to split.
Returns
- IReadOnlyList<RagChunk>
An ordered list of chunks.