Varagity

retrieval, with context.

A self-hosted RAG system that turns a document collection into grounded, cited answers. Hybrid retrieval, local GPUs, and a clear view into how each answer was built.

Varagity combines semantic and keyword search, contextualizes document chunks, and can rerank results before generating a response. The interface exposes the retrieval evidence alongside each answer.

• Hybrid semantic and BM25 retrieval
• Source citations and per-chunk evidence
• Local GPU inference and pipeline observability