storage utilisation is substantial. store both inverted indexes and dense embeddings creates significant overhead. with 1k dimension vectors, an average like 20 page doc with 30-100 chunks will be 120-400kb. HNSW tops…
> open source project further and beat the Jev-ers That is a seriously good idea. I tested Jev against local models. Confirmed that local architecture outperforms the closed cloud one marginally. Limits mostly come from…
storage utilisation is substantial. store both inverted indexes and dense embeddings creates significant overhead. with 1k dimension vectors, an average like 20 page doc with 30-100 chunks will be 120-400kb. HNSW tops…
> open source project further and beat the Jev-ers That is a seriously good idea. I tested Jev against local models. Confirmed that local architecture outperforms the closed cloud one marginally. Limits mostly come from…