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
This commit is contained in:
kami
2026-07-31 11:38:18 +04:00
parent 751c2a705f
commit f6d5a2a7a4
6 changed files with 48 additions and 19 deletions
+27 -5
View File
@@ -117,18 +117,40 @@ type cachingEmbedder struct {
seen map[string][]float32
}
var _ router.AsymmetricEmbedder = (*cachingEmbedder)(nil)
func (c *cachingEmbedder) Dim() int { return c.inner.Dim() }
func (c *cachingEmbedder) Close() error { return nil } // the caller owns inner
func (c *cachingEmbedder) Embed(ctx context.Context, text string) ([]float32, error) {
if v, ok := c.seen[text]; ok {
return c.cached(ctx, "embed:"+text, func() ([]float32, error) {
return c.inner.Embed(ctx, text)
})
}
// The two sides of an asymmetric embedder give different vectors for the same
// string, so the cache key has to say which side asked.
func (c *cachingEmbedder) EmbedQuery(ctx context.Context, text string) ([]float32, error) {
return c.cached(ctx, "query:"+text, func() ([]float32, error) {
return router.EmbedQuery(ctx, c.inner, text)
})
}
func (c *cachingEmbedder) EmbedPassage(ctx context.Context, text string) ([]float32, error) {
return c.cached(ctx, "passage:"+text, func() ([]float32, error) {
return router.EmbedPassage(ctx, c.inner, text)
})
}
func (c *cachingEmbedder) cached(_ context.Context, key string, embed func() ([]float32, error)) ([]float32, error) {
if v, ok := c.seen[key]; ok {
return v, nil
}
v, err := c.inner.Embed(ctx, text)
v, err := embed()
if err != nil {
return nil, err
}
c.seen[text] = v
c.seen[key] = v
return v, nil
}
@@ -305,7 +327,7 @@ func scoreCase(ctx context.Context, emb router.Embedder, newStore NewStore, minS
all := append(append([]StoredNote(nil), c.Notes...), filler...)
for _, n := range all {
vec, err := emb.Embed(ctx, n.Text)
vec, err := router.EmbedPassage(ctx, emb, n.Text)
if err != nil {
return Outcome{}, fmt.Errorf("%s: embed note %s: %w", c.ID, n.ID, err)
}
@@ -317,7 +339,7 @@ func scoreCase(ctx context.Context, emb router.Embedder, newStore NewStore, minS
o := Outcome{Case: c}
start := time.Now()
qvec, err := emb.Embed(ctx, c.Query)
qvec, err := router.EmbedQuery(ctx, emb, c.Query)
if err != nil {
o.Latency = time.Since(start)
o.Err = err
@@ -246,8 +246,8 @@ func TestONNXRecall(t *testing.T) {
if lib == "" {
t.Skip("MAVEN_ONNX_LIB unset — see AGENTS.md § Embedder model for intent routing")
}
model := filepath.Join("../../..", "models/embedder/model.onnx")
tok := filepath.Join("../../..", "models/embedder/tokenizer.json")
model := filepath.Join("../../..", "models/embedder/multilingual-e5-small/model_quantized.onnx")
tok := filepath.Join("../../..", "models/embedder/multilingual-e5-small/tokenizer.json")
for _, p := range []string{lib, model, tok} {
if _, err := os.Stat(p); err != nil {
t.Skipf("missing %s: %v", p, err)