sift/docs at f6644c92783e4b9303e7b84cb60ad379d5834cce - sift

kyle/sift

Files

T

kyleandornith-1.5-35b-a3b f6644c9278 digest: cache chunk embeddings; long documents answer from BM25 while embedding in the background

Cached chunk embeddings change what a long document answers with: BM25 first,
embedding uncached chunks (or the whole document) in the background so the next
question on the same doc scores hybrid. selectText now returns its mode and the
number of chunks that had a vector at answer-build time; the digest cache stores
only hybrid answers, never a provisional bm25 one. The background worker batches
through a Dixie gate and WaitBackground polls for true idle.

Co-Authored-By: ornith-1.5-35b-a3b <ornith-1.5-35b-a3b@llama.cpp.invalid>

2026-09-26 18:44:28 -07:00

plans

P5b given test: the embedding-cache test used a 12-page document (4.6k tokens), under SmallDoc, so the rules make it "whole", not "hybrid"; use 30 pages (11.7k tokens, 10 chunks) and assert the precondition

2026-09-26 17:57:14 -07:00

implementer-log.md

digest: cache chunk embeddings; long documents answer from BM25 while embedding in the background

2026-09-26 18:44:28 -07:00

P1.md

docs: P1.1 dynamic self-IP deny (DDNS/trace discovery, keep previous, atomic swap)

2026-09-22 22:06:20 -07:00

P2.7.md

p2.7: prometheus /metrics