Class SlidingWindowChunker

java.lang.Object
sk.iway.iwcm.rag.indexing.SlidingWindowChunker

@Component public class SlidingWindowChunker extends Object
Splits text into overlapping chunks using a sliding window approach. This ensures context is preserved at chunk boundaries for better embedding quality.
  • Constructor Details

    • SlidingWindowChunker

      public SlidingWindowChunker()
  • Method Details

    • chunk

      public List<String> chunk(String text)
      Split text into overlapping chunks.
      Parameters:
      text - the full text to split
      Returns:
      list of text chunks
    • chunk

      public List<String> chunk(String text, int chunkSize, int overlap)
      Split text into overlapping chunks with specified parameters. Chunk ends prefer paragraph, line, sentence, and whitespace boundaries before falling back to a hard character split.
      Parameters:
      text - the full text to split
      chunkSize - maximum number of characters per chunk
      overlap - number of characters to overlap between consecutive chunks
      Returns:
      list of text chunks