Group: GitHub Slaouiss
Sort by:Popular

The pipeline and the domain model, plus the two extension contracts (ChunkingModel and DocumentExtractor). Depends on no extraction technology and no model provider.
Last Release on Sep 17, 2026

2.Semantic Chunker

io.github.slaouiss » semantic-chunker Apache

A focused Java library for turning documents into high-quality semantic chunks using a language model. This is the multi-module aggregator and the parent that owns every shared version and build configuration.
Last Release on Sep 17, 2026
A ChunkingModel adapter that lets a language model be supplied by way of Spring AI. Depends on the core; the core does not depend on it.
Last Release on Sep 17, 2026

4.Semantic Chunker Tika

io.github.slaouiss » semantic-chunker-tika Apache

A DocumentExtractor that turns documents into the normalized representation using Apache Tika. Depends on the core; the core does not depend on it.
Last Release on Sep 17, 2026
A DocumentExtractor that turns documents into the normalized representation using the Unstructured partition API. Depends on the core; the core does not depend on it.
Last Release on Sep 17, 2026
Composable hybrid DocumentRetriever for Spring AI — combine dense and sparse retrievers with Reciprocal Rank Fusion.
Last Release on Jul 14, 2026
Framework-agnostic core: HybridDocumentRetriever, RRFDocumentJoiner, DocumentIdentityStrategy.
Last Release on Jul 14, 2026