Fast search index for SPLADE sparse retrieval models implemented in Python using Numpy and Numba

python lib for sparse parameter server using rocksdb, written in c++

A hybrid vector search using a mixture of sparse and dense vectors using Qdrant.

A modular and open-source RAG-ready Embedding API supporting dense and sparse. Easily configurable via config.yaml — no code changes required.

A simple hybrid search Flask application that integrates traditional full-text (lexical/BM25) search with semantic (neural sparse embeddings) search. It also provides autocomplete functionality for an improved search experience.