Record which embedder wrote the stored vectors and warn on a swap (#378)
The embedder moved from paraphrase-multilingual-MiniLM-L12-v2 to multilingual-e5-small. Both are 384-dimensional, so nothing in the code noticed: cosine between an old stored vector and a new query vector is noise, and recall degrades silently. So the DB now records the embedder that wrote its vectors. One value for the whole DB (migration #11, a small `meta` key/value table) rather than a column on every vector row: the backfill re-embeds every note and fact in one pass, so a per-row marker would hold the same string in every row and cost a column on two tables for nothing. The identity comes from the embedder itself via a new optional ID() method ("multilingual-e5-small@384", model file name plus dimension), so pointing the config at another model changes the string without anyone editing a constant. mavend logs a loud WARNING at startup naming both the stored and the configured embedder when they differ. Detection only — recall behaviour is unchanged. TODO(#378) in store.CheckEmbedder marks where the backfill will hook in. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
This commit is contained in:
@@ -0,0 +1,65 @@
|
||||
package store
|
||||
|
||||
import (
|
||||
"context"
|
||||
"database/sql"
|
||||
"errors"
|
||||
"fmt"
|
||||
)
|
||||
|
||||
// metaKeyEmbedderID names the embedder that wrote the stored vectors.
|
||||
//
|
||||
// Why one value for the whole DB and not a column on every vector row: the
|
||||
// vectors are only ever rewritten all at once (one backfill re-embeds every
|
||||
// note and fact together), so a per-row marker would hold the same string in
|
||||
// every row and cost a column on two tables for nothing.
|
||||
const metaKeyEmbedderID = "embedder_id"
|
||||
|
||||
// Meta reads a single value from the meta table. Missing key ⇒ empty string.
|
||||
func (s *Store) Meta(ctx context.Context, key string) (string, error) {
|
||||
var v string
|
||||
err := s.db.QueryRowContext(ctx, `SELECT value FROM meta WHERE key = ?`, key).Scan(&v)
|
||||
if errors.Is(err, sql.ErrNoRows) {
|
||||
return "", nil
|
||||
}
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("read meta %s: %w", key, err)
|
||||
}
|
||||
return v, nil
|
||||
}
|
||||
|
||||
// SetMeta writes (or overwrites) a single meta value.
|
||||
func (s *Store) SetMeta(ctx context.Context, key, value string) error {
|
||||
_, err := s.db.ExecContext(ctx,
|
||||
`INSERT INTO meta (key, value) VALUES (?,?)
|
||||
ON CONFLICT(key) DO UPDATE SET value = excluded.value`, key, value)
|
||||
if err != nil {
|
||||
return fmt.Errorf("write meta %s: %w", key, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// CheckEmbedder compares the embedder now configured against the one that
|
||||
// wrote the stored vectors.
|
||||
//
|
||||
// A DB that has never recorded one is claimed for the current embedder: either
|
||||
// it is fresh (nothing stored yet, nothing to fix) or it predates this marker.
|
||||
// Returns the stored id and whether it differs from the current one.
|
||||
//
|
||||
// Vectors from two different models live in different spaces, so cosine
|
||||
// between them is noise rather than a low score — and both of our models are
|
||||
// 384-dimensional, so nothing else catches it.
|
||||
//
|
||||
// TODO(#378): on a mismatch, run the one-shot backfill here — re-embed every
|
||||
// stored note and fact text with the current embedder (EmbedPassage side),
|
||||
// write the vectors back, then SetMeta the current id.
|
||||
func (s *Store) CheckEmbedder(ctx context.Context, currentID string) (stored string, mismatch bool, err error) {
|
||||
stored, err = s.Meta(ctx, metaKeyEmbedderID)
|
||||
if err != nil {
|
||||
return "", false, err
|
||||
}
|
||||
if stored == "" {
|
||||
return currentID, false, s.SetMeta(ctx, metaKeyEmbedderID, currentID)
|
||||
}
|
||||
return stored, stored != currentID, nil
|
||||
}
|
||||
@@ -0,0 +1,67 @@
|
||||
package store
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// A fresh DB has no marker yet, so the current embedder is recorded and
|
||||
// nothing is flagged.
|
||||
func TestCheckEmbedderFreshDBRecords(t *testing.T) {
|
||||
s := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
|
||||
stored, mismatch, err := s.CheckEmbedder(ctx, "multilingual-e5-small@384")
|
||||
if err != nil {
|
||||
t.Fatalf("CheckEmbedder: %v", err)
|
||||
}
|
||||
if mismatch {
|
||||
t.Fatal("fresh DB reported a mismatch")
|
||||
}
|
||||
if stored != "multilingual-e5-small@384" {
|
||||
t.Fatalf("stored = %q", stored)
|
||||
}
|
||||
got, err := s.Meta(ctx, metaKeyEmbedderID)
|
||||
if err != nil {
|
||||
t.Fatalf("Meta: %v", err)
|
||||
}
|
||||
if got != "multilingual-e5-small@384" {
|
||||
t.Fatalf("marker not persisted, got %q", got)
|
||||
}
|
||||
}
|
||||
|
||||
// Both models are 384-dim, so this is the only thing that catches the swap.
|
||||
func TestCheckEmbedderDifferentModelMismatch(t *testing.T) {
|
||||
s := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
|
||||
if err := s.SetMeta(ctx, metaKeyEmbedderID, "paraphrase-multilingual-MiniLM-L12-v2@384"); err != nil {
|
||||
t.Fatalf("SetMeta: %v", err)
|
||||
}
|
||||
stored, mismatch, err := s.CheckEmbedder(ctx, "multilingual-e5-small@384")
|
||||
if err != nil {
|
||||
t.Fatalf("CheckEmbedder: %v", err)
|
||||
}
|
||||
if !mismatch {
|
||||
t.Fatal("different embedder not detected")
|
||||
}
|
||||
if stored != "paraphrase-multilingual-MiniLM-L12-v2@384" {
|
||||
t.Fatalf("stored = %q", stored)
|
||||
}
|
||||
}
|
||||
|
||||
// The same embedder must never raise a false alarm, including on re-check.
|
||||
func TestCheckEmbedderSameModelNoAlarm(t *testing.T) {
|
||||
s := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
|
||||
for i := 0; i < 2; i++ {
|
||||
_, mismatch, err := s.CheckEmbedder(ctx, "multilingual-e5-small@384")
|
||||
if err != nil {
|
||||
t.Fatalf("CheckEmbedder: %v", err)
|
||||
}
|
||||
if mismatch {
|
||||
t.Fatalf("false alarm on pass %d", i)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -83,6 +83,11 @@ ALTER TABLE reminders ADD COLUMN next_fire_ts INTEGER;`, // #2
|
||||
expires_ts INTEGER NOT NULL
|
||||
);
|
||||
CREATE INDEX IF NOT EXISTS idx_dialogue_sessions_expires ON dialogue_sessions (expires_ts);`, // #10 — the follow-up session survives a restart (Vikunja #363); small, TTL-pruned table, not a history log
|
||||
|
||||
`CREATE TABLE IF NOT EXISTS meta (
|
||||
key TEXT PRIMARY KEY,
|
||||
value TEXT NOT NULL
|
||||
);`, // #11 — small key/value table for facts about the DB itself; first key is embedder_id (Vikunja #378)
|
||||
}
|
||||
|
||||
// migrate applies every migration with a number greater than the DB's current
|
||||
|
||||
Reference in New Issue
Block a user