Embeddings
also: embedding space · embeddingVectors that place text in a high-dimensional space so that similar meaning lands close together. Ours have 1,024 dimensions.
Reference ↗Twelve modules we wrote by hand instead of installing a framework: rank fusion in 84 lines, a tool-call salvager in 197. What each replaced, and when a library is still the right call.
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.
12 MB of vectors, a 39 GB index, zero dead rows. A nightly sync updated every row whether or not anything had changed, and a vector index never gives back space from updates. Ten million no-op writes, found by one ratio.
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.
We clustered 1,046 knowledge-graph entities and found nothing, at every k, with two methods. Two clean hypotheses for why were falsified. The structure was there all along, in a different representation.
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.
Retrieved by its own wording, a behavioural rule came back 1 time in 5. Stored as the situations it should fire in, 10 of 10. And where the trick stops working.
The first A/B that actually queried both sides. The document store returns a filename. The organic memory returns the sentence that answers. Plus the bug that held 38% of every answer hostage.
Crystal RAG, The Wisdomkeeper and SEO Brain: what each does, what it runs on, and why all three keep your data on your machine or your own server.
One day of mistakes, read back. Every one came from reasoning like an intelligence. Every correct step came from reading what was there and following the gradient.