GregorBiswanger/SemanticChunker.NET
Embedding-driven, context-aware text chunking for Semantic Kernel and RAG workflows in .NET
Implements four statistical breakpoint strategies (Percentile, StandardDeviation, InterQuartile, Gradient) to split documents based on embedding similarity distances, with configurable context buffers and optional exact chunk-count targeting. Integrates seamlessly with Microsoft.Extensions.AI and Semantic Kernel, supporting any embedding provider while maintaining multilingual sentence splitting via ICU4N and automatic token-limit safety margins without external dependencies.
Stars
33
Forks
7
Language
C#
License
Apache-2.0
Category
Last pushed
Feb 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/GregorBiswanger/SemanticChunker.NET"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.