Add local AI and Qdrant vector backends

scripts/database/sqlite-repair-fts.sh

@@ -20,7 +20,17 @@ fi
 DB_DIR="$(dirname "$DB_PATH")"
 DB_NAME="$(basename "$DB_PATH")"
 ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
-VEC_EXTENSION_PATH="${SQLITE_VEC_EXTENSION_PATH:-$ROOT_DIR/vendor/sqlite-extensions/vec0.dylib}"
+case "$(uname -s)" in
+  Darwin*) VEC_EXT="dylib" ;;
+  MINGW*|MSYS*|CYGWIN*) VEC_EXT="dll" ;;
+  *) VEC_EXT="so" ;;
+esac
+VEC_EXTENSION_PATH="${SQLITE_VEC_EXTENSION_PATH:-$ROOT_DIR/vendor/sqlite-extensions/vec0.$VEC_EXT}"
+EMBEDDING_DIMENSIONS="${EMBEDDING_DIMENSIONS:-1536}"
+if ! [[ "$EMBEDDING_DIMENSIONS" =~ ^[0-9]+$ ]] || [ "$EMBEDDING_DIMENSIONS" -le 0 ]; then
+  echo "Invalid EMBEDDING_DIMENSIONS: $EMBEDDING_DIMENSIONS" >&2
+  exit 1
+fi
 TS=$(date +"%Y%m%d_%H%M%S")
 RAW_BACKUP_DIR="$DB_DIR/working/fts_repair_${TS}"
 REBUILT_DB="$DB_DIR/${DB_NAME}.rebuilt.${TS}"
@@ -36,12 +46,12 @@ if [ -f "$VEC_EXTENSION_PATH" ]; then
     VEC_SQL_BODY="
 CREATE VIRTUAL TABLE vec_nodes USING vec0(
   node_id INTEGER PRIMARY KEY,
-  embedding FLOAT[1536]
+  embedding FLOAT[$EMBEDDING_DIMENSIONS]
 );
 
 CREATE VIRTUAL TABLE vec_chunks USING vec0(
   chunk_id INTEGER PRIMARY KEY,
-  embedding FLOAT[1536]
+  embedding FLOAT[$EMBEDDING_DIMENSIONS]
 );
 "
 

scripts/dev/bootstrap-local.mjs

@@ -554,17 +554,21 @@ function ensureCoreSchema(db) {
 function tryInitVectorTables(db, dbPath) {
   const extension = process.platform === 'darwin' ? 'dylib' : process.platform === 'win32' ? 'dll' : 'so';
   const extensionPath = process.env.SQLITE_VEC_EXTENSION_PATH || path.join(repoDir, 'vendor', 'sqlite-extensions', `vec0.${extension}`);
+  const dimensions = Number(process.env.EMBEDDING_DIMENSIONS || '1536');
+  if (!Number.isInteger(dimensions) || dimensions <= 0) {
+    throw new Error(`Invalid EMBEDDING_DIMENSIONS="${process.env.EMBEDDING_DIMENSIONS}"`);
+  }
 
   try {
     db.loadExtension(extensionPath);
     db.exec(`
       CREATE VIRTUAL TABLE IF NOT EXISTS vec_nodes USING vec0(
         node_id INTEGER PRIMARY KEY,
-        embedding FLOAT[1536]
+        embedding FLOAT[${dimensions}]
       );
       CREATE VIRTUAL TABLE IF NOT EXISTS vec_chunks USING vec0(
         chunk_id INTEGER PRIMARY KEY,
-        embedding FLOAT[1536]
+        embedding FLOAT[${dimensions}]
       );
     `);
     log(`Initialized sqlite-vec tables using ${extensionPath}`);

scripts/doctor-local-ai.ts

@@ -0,0 +1,38 @@
+import { createEmbeddingProvider } from '@/services/embedding/provider';
+import { createUtilityLlmProvider } from '@/services/llm/provider';
+import { getSQLiteClient } from '@/services/database/sqlite-client';
+import { getVectorBackend } from '@/services/vectorBackend/factory';
+
+async function main() {
+  const sqlite = getSQLiteClient();
+  const utility = createUtilityLlmProvider();
+  const embedding = createEmbeddingProvider();
+  const vectorBackend = await getVectorBackend();
+
+  const [utilityHealth, embeddingHealth, vectorHealth] = await Promise.all([
+    utility.healthCheck(),
+    embedding.healthCheck(),
+    vectorBackend.healthCheck(),
+  ]);
+  const profileStatus = sqlite.getEmbeddingProfileStatus();
+
+  console.log(JSON.stringify({
+    ok: utilityHealth.ok && embeddingHealth.ok && vectorHealth.ok && !profileStatus.rebuild_required,
+    utility_llm: utilityHealth,
+    embedding_provider: embeddingHealth,
+    vector_backend: vectorHealth,
+    embedding_profile: profileStatus,
+    next_action: profileStatus.rebuild_required
+      ? 'Run npm run rebuild:embeddings after confirming your embedding provider/model/dimensions.'
+      : 'Local AI/vector configuration is ready.',
+  }, null, 2));
+
+  if (!utilityHealth.ok || !embeddingHealth.ok || !vectorHealth.ok || profileStatus.rebuild_required) {
+    process.exitCode = 1;
+  }
+}
+
+main().catch((error) => {
+  console.error(error);
+  process.exit(1);
+});

scripts/rebuild-embeddings.ts

@@ -0,0 +1,71 @@
+import { getSQLiteClient } from '@/services/database/sqlite-client';
+import { NodeEmbedder } from '@/services/typescript/embed-nodes';
+import { UniversalEmbedder } from '@/services/typescript/embed-universal';
+
+async function maybeRecreateQdrantCollections() {
+  if (process.env.VECTOR_BACKEND !== 'qdrant' || process.env.QDRANT_RECREATE_COLLECTIONS !== 'true') {
+    return;
+  }
+
+  const baseUrl = (process.env.QDRANT_URL || 'http://localhost:6333').replace(/\/+$/, '');
+  const headers = process.env.QDRANT_API_KEY ? { 'api-key': process.env.QDRANT_API_KEY } : undefined;
+  const collections = [
+    process.env.QDRANT_CHUNKS_COLLECTION || 'rah_chunks',
+    process.env.QDRANT_NODES_COLLECTION || 'rah_nodes',
+  ];
+
+  for (const collection of collections) {
+    const response = await fetch(`${baseUrl}/collections/${encodeURIComponent(collection)}`, {
+      method: 'DELETE',
+      headers,
+    });
+    if (!response.ok && response.status !== 404) {
+      const detail = await response.text().catch(() => response.statusText);
+      throw new Error(`Failed to delete Qdrant collection ${collection}: ${detail}`);
+    }
+    console.log(`[rebuild-embeddings] Recreated Qdrant collection on next upsert: ${collection}`);
+  }
+}
+
+async function main() {
+  const sqlite = getSQLiteClient();
+  await maybeRecreateQdrantCollections();
+  const nodeRows = sqlite.query<{ id: number; source?: string | null }>(`
+    SELECT id, source
+    FROM nodes
+    ORDER BY id
+  `).rows;
+
+  console.log(`[rebuild-embeddings] Rebuilding node embeddings for ${nodeRows.length} nodes`);
+  const nodeEmbedder = new NodeEmbedder();
+  try {
+    await nodeEmbedder.embedNodes({ forceReEmbed: true, verbose: true });
+  } finally {
+    nodeEmbedder.close();
+  }
+
+  const sourceRows = nodeRows.filter((node) => typeof node.source === 'string' && node.source.trim().length > 0);
+  console.log(`[rebuild-embeddings] Rebuilding chunk embeddings for ${sourceRows.length} nodes with source text`);
+
+  const chunkEmbedder = new UniversalEmbedder();
+  try {
+    let processed = 0;
+    for (const node of sourceRows) {
+      await chunkEmbedder.processNode({ nodeId: node.id, verbose: false });
+      processed += 1;
+      if (processed % 10 === 0 || processed === sourceRows.length) {
+        console.log(`[rebuild-embeddings] Chunked ${processed}/${sourceRows.length}`);
+      }
+    }
+  } finally {
+    chunkEmbedder.close();
+  }
+
+  sqlite.markEmbeddingProfileCurrent();
+  console.log('[rebuild-embeddings] Active embedding/vector profile recorded.');
+}
+
+main().catch((error) => {
+  console.error(error);
+  process.exit(1);
+});

scripts/tmp-init-vec.js

@@ -8,13 +8,18 @@ if (!dbPath) {
 }
 
 const db = new Database(dbPath);
-const vecPath = path.join(process.cwd(), 'vendor', 'sqlite-extensions', 'vec0.dylib');
+const ext = process.platform === 'darwin' ? 'dylib' : process.platform === 'win32' ? 'dll' : 'so';
+const vecPath = process.env.SQLITE_VEC_EXTENSION_PATH || path.join(process.cwd(), 'vendor', 'sqlite-extensions', `vec0.${ext}`);
+const dimensions = Number(process.env.EMBEDDING_DIMENSIONS || '1536');
+if (!Number.isInteger(dimensions) || dimensions <= 0) {
+  throw new Error(`Invalid EMBEDDING_DIMENSIONS="${process.env.EMBEDDING_DIMENSIONS}"`);
+}
 
 db.loadExtension(vecPath);
 db.exec(`
-  CREATE VIRTUAL TABLE IF NOT EXISTS vec_nodes USING vec0(node_id INTEGER PRIMARY KEY, embedding FLOAT[1536]);
-  CREATE VIRTUAL TABLE IF NOT EXISTS vec_chunks USING vec0(chunk_id INTEGER PRIMARY KEY, embedding FLOAT[1536]);
+  CREATE VIRTUAL TABLE IF NOT EXISTS vec_nodes USING vec0(node_id INTEGER PRIMARY KEY, embedding FLOAT[${dimensions}]);
+  CREATE VIRTUAL TABLE IF NOT EXISTS vec_chunks USING vec0(chunk_id INTEGER PRIMARY KEY, embedding FLOAT[${dimensions}]);
 `);
 
 console.log('✓ vec tables ensured');
-db.close();
+db.close();