# sparse

> Browse 3 items tagged with sparse.

## Items

- [Dense-Sparse Hybrid Embeddings](https://vectordb.ever.works/pl/items/dense-sparse-hybrid-embeddings) — Combining dense vector embeddings with sparse representations in a single unified model. Captures both semantic meaning (dense) and exact term matching (sparse) for superior retrieval performance.
- [BM42](https://vectordb.ever.works/pl/items/bm42) — Experimental sparse embedding approach combining exact keyword search with transformer intelligence, integrating sparse and dense vector searches for improved RAG results, developed by Qdrant.
- [SLIM (Sparsified Late Interaction Multi-Vector Retrieval)](https://vectordb.ever.works/pl/items/slim-sparsified-late-interaction-multi-vector-retrieval) — Efficient multi-vector retrieval system using sparsified late interaction with inverted indexes. Achieves 40% less storage and 83% lower latency than ColBERT-v2 while maintaining competitive accuracy.

---

_Canonical page: https://vectordb.ever.works/pl/tags/sparse_