Package sk.iway.iwcm.rag.indexing

package sk.iway.iwcm.rag.indexing
  • Class
    Description
    ContentExtractor<T>
    Interface for extracting plain text from an entity for embedding.
    DocDetailsContentExtractor
    Content extractor for DocDetails entities.
    MarkdownChunker
    Splits Markdown at block boundaries, preserving fitting structures and their heading context.
    MarkdownContentExtractor
    Prepares Markdown for chunking while preserving document structure and code examples.
    SlidingWindowChunker
    Splits text into bounded, overlapping chunks, preferring sentence or paragraph boundaries.
    SlidingWindowChunker.Chunk
    Stores a passage and its start offset in the normalized, trimmed source text.