A friend said they expand SPLADE terms into an OpenSearch BM25 text field and it works. We tested it — 0.36 NDCG@10, worse than plain BM25. Here is why, and how to mostly fix it.
- Published on
All Posts
- Inference-free SPLADE nearly matches full SPLADE quality at 13× lower query latency, no GPU needed at query time. Benchmarked against full SPLADE and BM25 on Qdrant and pyserini.
- Published on
- Vector databases compress text payloads with generic codecs like LZ4, but not with token-aware schemes. BPE tokenization + static entropy coding gives you ~3x lossless compression — 2× better than gzip — using infrastructure already in every ML stack.
- Published on
- Search is everywhere and is one of the hardest problems in CS. Here's why I'm obsessed with it.
- Published on
- Reflections on a year of growth, travel, and pursuing mastery
- Published on