Tool

bge-m3

Multilingual embedding model from BAAI producing 1024-dimensional vectors. Embeds every collection in the hive.

Reference ↗
Related
6 articles
02 · MEMORY ARCHITECTUREA corpus that looks indexed

Every counter said 1,047 memories were indexed. 653 of them were their opening 4,000 characters. 72% of the text never reached the vector store.

1 Nov 2026
01 · RETRIEVAL THAT WORKSMultilingual on paper: Slovak questions fail 2.75× more often

Our embedder and both rerankers we tested are sold as multilingual. Measured with paired Slovak and English queries, Slovak failed 55% of the time against 20%, and a cross-encoder gave three different documents the identical score.

1 Nov 2026
01 · RETRIEVAL THAT WORKSWhy your retrieval scores cannot be averaged

Our unified search compared three different quantities in one column. The exact answer ranked below a weaker one, purely because of scale. What we measured, and what we changed.

1 Nov 2026 · ▶ 19 min audio
03 · FAILURE MODESThe backup that was never incremental

For five months the backup script's header promised hard links and only changed bytes. Every file in every snapshot had a link count of 1: 24 full copies, 756 GB. One path argument was relative to the wrong directory.

1 Nov 2026
02 · MEMORY ARCHITECTURE44,196 chunks behind a tool nobody routed to

Our unified search tool says 'prefer this over individual tools'. Our entire research corpus was not one of its layers. On six topics that live only there, the direct search won 6 of 6. And 75% of our memory had never been retrieved even once.

1 Nov 2026
01 · RETRIEVAL THAT WORKSWhen the biology buried the exact name

Ask our memory for a record by its own name: 93% rank-1 on plain semantic search, 43% after the biological rescore. Why a smarter score lost the easiest query, and the fix we chose.

1 Nov 2026

Glossary →