Swap the embedder for e5-small #16

Closed
claude wants to merge 4 commits from overnight/embedder-e5 into overnight/router-refusal

4 Commits

Author SHA1 Message Date
kami 34521c30b8 Merge branch 'worktree-agent-ad5da57e47b822152' into overnight-jul31 2026-07-31 11:39:35 +04:00
kami 1d48755d12 Record the recall numbers after the embedder swap
recall@1 60% to 72%, answered 48% to 72%, latency 3x better. But false
recall went 1/5 to 5/5: e5 packs every score into a narrow high band, so
the 0.55 gate now admits everything. Left the gate alone as instructed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 11:38:18 +04:00
kami f6d5a2a7a4 Swap the embedder to multilingual-e5-small (Vikunja #371, #372)
The old model was a symmetric paraphrase model, so it scored "do these
look alike" instead of "does this note answer this question". Also fixes
the file mismatch: the Makefile, the deploy config and both evals now all
name the same quantized file, and the quantized one is what gets measured.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 11:38:18 +04:00
kami 751c2a705f Embed a question and a stored note differently (Vikunja #371)
Note recall is asymmetric: a short question goes in, a longer note comes
out. Adds EmbedQuery/EmbedPassage helpers and the e5 prefixes, and points
the note/fact write path at the passage side and the query path at the
query side. Reviewers: the three call sites in voice.go.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 11:38:07 +04:00