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
This commit is contained in:
kami
2026-07-31 11:38:07 +04:00
parent 8a174c1c70
commit 751c2a705f
4 changed files with 119 additions and 4 deletions
+57
View File
@@ -37,3 +37,60 @@ func TestHashEmbedderCyrillic(t *testing.T) {
t.Fatalf("cosine(shared)=%.3f not > cosine(disjoint)=%.3f", cosine(a, b), cosine(a, c))
}
}
// recordingEmbedder — an asymmetric embedder that only remembers which side
// was asked for. Enough to pin the dispatch; real vectors need the model.
type recordingEmbedder struct{ calls []string }
func (r *recordingEmbedder) Dim() int { return 2 }
func (r *recordingEmbedder) Close() error { return nil }
func (r *recordingEmbedder) Embed(_ context.Context, _ string) ([]float32, error) {
r.calls = append(r.calls, "embed")
return []float32{1, 0}, nil
}
func (r *recordingEmbedder) EmbedQuery(_ context.Context, _ string) ([]float32, error) {
r.calls = append(r.calls, "query")
return []float32{1, 0}, nil
}
func (r *recordingEmbedder) EmbedPassage(_ context.Context, _ string) ([]float32, error) {
r.calls = append(r.calls, "passage")
return []float32{0, 1}, nil
}
// TestEmbedQueryAndPassageSplit — a question and a stored note must not take
// the same path. If both ended up on the same call the asymmetric model buys
// nothing, which is the whole reason for the swap.
func TestEmbedQueryAndPassageSplit(t *testing.T) {
rec := &recordingEmbedder{}
if _, err := EmbedQuery(context.Background(), rec, "где логи?"); err != nil {
t.Fatalf("EmbedQuery: %v", err)
}
if _, err := EmbedPassage(context.Background(), rec, "логи в /var/log"); err != nil {
t.Fatalf("EmbedPassage: %v", err)
}
if len(rec.calls) != 2 || rec.calls[0] != "query" || rec.calls[1] != "passage" {
t.Errorf("calls %v, want [query passage]", rec.calls)
}
}
// TestEmbedFallsBackToPlainEmbed — HashEmbedder has no sides, so both helpers
// must still work and give the same vector.
func TestEmbedFallsBackToPlainEmbed(t *testing.T) {
h := NewHashEmbedder(64)
q, err := EmbedQuery(context.Background(), h, "text")
if err != nil {
t.Fatalf("EmbedQuery: %v", err)
}
p, err := EmbedPassage(context.Background(), h, "text")
if err != nil {
t.Fatalf("EmbedPassage: %v", err)
}
for i := range q {
if q[i] != p[i] {
t.Fatalf("hash embedder gave two different vectors for the same text")
}
}
}