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
+2 -2
View File
@@ -185,8 +185,8 @@ func TestONNXBaseline(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)