Re:Production RAG: what I learned from processing 5M+ documents
by deepsquirrelnet on Monday October 20, 2025 @02:11PM
(#45647160)
> For the searches we use hybrid dense + sparse bm25, since dense doesn't work well for technical words.
One thing I’m always curious about is if you could simplify this and get good/better results using SPLADE. The v3 models look really good and seem to provide a good balance of semantic and lexical retrieval.
One thing I’m always curious about is if you could simplify this and get good/better results using SPLADE. The v3 models look really good and seem to provide a good balance of semantic and lexical retrieval.