From 461699806417ac68197f10a7b9a2a4e62948b99c Mon Sep 17 00:00:00 2001
From: ImBenji <benjamin.watt@imbenji.net>
Date: Sat, 18 Apr 2026 17:19:55 +0100
Subject: [PATCH] migrate article embeddings to support multi-model
 architecture and enhance data integrity

---
 src/db.js            | 45 ++++++++++++++++++++++++++++++++++++--------
 src/embeddings.js    | 34 +++++++++++++++++++++++----------
 src/routes/status.js |  8 ++++++--
 3 files changed, 67 insertions(+), 20 deletions(-)

diff --git a/src/db.js b/src/db.js
index 7dc0706..c70ead0 100644
--- a/src/db.js
+++ b/src/db.js
@@ -134,17 +134,46 @@ db.exec(`
 {
   const existing = db.prepare(`SELECT sql FROM sqlite_master WHERE type = 'table' AND name = 'article_embeddings'`).get();
   const currentDim = existing && existing.sql && existing.sql.match(/FLOAT\[(\d+)\]/);
+  const needsMigration = existing && (!currentDim || parseInt(currentDim[1], 10) !== 8192);
+
+  if (needsMigration) {
+    // save everything in vec0 to the store before dropping it, keyed by whatever model is in meta
+    try {
+      const BATCH = 500;
+      let offset = 0;
+
+      const fetchBatch = db.prepare(`
+        SELECT e.article_id, m.model, e.embedding
+        FROM article_embeddings e
+        JOIN article_embedding_meta m ON m.article_id = e.article_id
+        LIMIT ? OFFSET ?
+      `);
+
+      const insert = db.prepare(`
+        INSERT OR IGNORE INTO article_embedding_store (article_id, model, embedding)
+        VALUES (?, ?, ?)
+      `);
+
+      const insertMany = db.transaction((rows) => {
+        for (const row of rows) insert.run(row.article_id, row.model, row.embedding);
+      });
+
+      while (true) {
+        const rows = fetchBatch.all(BATCH, offset);
+        if (rows.length === 0) break;
+        insertMany(rows);
+        offset += rows.length;
+        if (rows.length < BATCH) break;
+      }
+    } catch (err) {
+      console.error('failed to rescue embeddings from vec0 before migration:', err);
+    }
 
-  if (!existing) {
-    db.exec(`
-      CREATE VIRTUAL TABLE article_embeddings USING vec0(
-        article_id INTEGER PRIMARY KEY,
-        embedding FLOAT[8192]
-      );
-    `);
-  } else if (!currentDim || parseInt(currentDim[1], 10) !== 8192) {
     db.exec(`DROP TABLE article_embeddings`);
     db.exec(`DELETE FROM article_embedding_meta`);
+  }
+
+  if (!existing || needsMigration) {
     db.exec(`
       CREATE VIRTUAL TABLE article_embeddings USING vec0(
         article_id INTEGER PRIMARY KEY,
diff --git a/src/embeddings.js b/src/embeddings.js
index 0914f96..40e57c9 100644
--- a/src/embeddings.js
+++ b/src/embeddings.js
@@ -85,22 +85,27 @@ const upsertQueryEmbedding = db.prepare(`
     created_at = datetime('now')
 `);
 
-// backfill store from any embeddings that predate multi-model support
+// backfill store from vec0 for any embeddings that predate multi-model support.
+// only runs when store is completely empty, so we never stamp the wrong model on existing data.
 try {
-  db.prepare(`
-    INSERT OR IGNORE INTO article_embedding_store (article_id, model, embedding)
-    SELECT e.article_id, ?, e.embedding FROM article_embeddings e
-  `).run(EMBEDDING_MODEL);
+  const storeEmpty = !db.prepare(`SELECT 1 FROM article_embedding_store LIMIT 1`).get();
 
-  db.prepare(`
-    INSERT OR IGNORE INTO article_embedding_meta (article_id, model)
-    SELECT article_id, ? FROM article_embedding_store WHERE model = ?
-  `).run(EMBEDDING_MODEL, EMBEDDING_MODEL);
+  if (storeEmpty) {
+    // use model from meta if available, fall back to config model
+    const metaRow = db.prepare(`SELECT model FROM article_embedding_meta LIMIT 1`).get();
+    const legacyModel = (metaRow && metaRow.model) || EMBEDDING_MODEL;
+
+    db.prepare(`
+      INSERT OR IGNORE INTO article_embedding_store (article_id, model, embedding)
+      SELECT e.article_id, ?, e.embedding FROM article_embeddings e
+    `).run(legacyModel);
+  }
 } catch (err) {
   console.error('embedding store backfill failed:', err);
 }
 
-// if the config model changed, rebuild the vec0 search index from store
+// if the config model changed, rebuild the vec0 search index from store.
+// only proceeds if the store actually has embeddings for the new model.
 function rebuildVec0IfModelChanged() {
   const stale = db.prepare(`
     SELECT 1 FROM article_embedding_meta WHERE model != ? LIMIT 1
@@ -108,6 +113,15 @@ function rebuildVec0IfModelChanged() {
 
   if (!stale) return;
 
+  const storeCount = db.prepare(`
+    SELECT COUNT(*) AS n FROM article_embedding_store WHERE model = ?
+  `).get(EMBEDDING_MODEL);
+
+  if (!storeCount || storeCount.n === 0) {
+    console.log(`embedding model changed to ${EMBEDDING_MODEL} but store has no embeddings for it yet — skipping index rebuild`);
+    return;
+  }
+
   console.log(`embedding model changed to ${EMBEDDING_MODEL}, rebuilding search index...`);
 
   db.exec('BEGIN');
diff --git a/src/routes/status.js b/src/routes/status.js
index dce57b5..36ac822 100644
--- a/src/routes/status.js
+++ b/src/routes/status.js
@@ -29,8 +29,11 @@ async function statusRoutes(fastify) {
     );
 
     const embeddingModelRows = db.prepare(`
-      SELECT model, COUNT(*) AS article_count
-      FROM article_embedding_store
+      SELECT
+        model,
+        COUNT(*) AS article_count,
+        (SELECT LENGTH(embedding) FROM article_embedding_store s2 WHERE s2.model = s.model LIMIT 1) AS sample_bytes
+      FROM article_embedding_store s
       GROUP BY model
       ORDER BY article_count DESC
     `).all();
@@ -45,6 +48,7 @@ async function statusRoutes(fastify) {
       embeddingModels: embeddingModelRows.map((row) => ({
         model: row.model,
         articles: row.article_count,
+        dimensions: row.sample_bytes ? row.sample_bytes / 4 : null,
       })),
     };
   });