feat(TRUEREF-0023): add sqlite-vec search pipeline

src/lib/server/search/vector.search.ts

@@ -1,16 +1,12 @@
 /**
  * Vector similarity search over stored snippet embeddings.
  *
- * SQLite does not natively support vector operations, so cosine similarity is
- * computed in JavaScript after loading candidate embeddings from the
- * snippet_embeddings table.
- *
- * Performance note: For repositories with > 50k snippets, pre-filtering by
- * FTS5 candidates before computing cosine similarity is recommended. For v1,
- * in-memory computation is acceptable.
+ * Uses sqlite-vec vector_top_k() for ANN search instead of in-memory cosine
+ * similarity computation over all embeddings.
  */
 
 import type Database from 'better-sqlite3';
+import { SqliteVecStore } from './sqlite-vec.store.js';
 
 // ---------------------------------------------------------------------------
 // Types
@@ -28,12 +24,6 @@ export interface VectorSearchOptions {
 	limit?: number;
 }
 
-/** Raw DB row from snippet_embeddings joined with snippets. */
-interface RawEmbeddingRow {
-	snippet_id: string;
-	embedding: Buffer;
-}
-
 // ---------------------------------------------------------------------------
 // Math helpers
 // ---------------------------------------------------------------------------
@@ -69,46 +59,26 @@ export function cosineSimilarity(a: Float32Array, b: Float32Array): number {
 // ---------------------------------------------------------------------------
 
 export class VectorSearch {
-	constructor(private readonly db: Database.Database) {}
+	private readonly sqliteVecStore: SqliteVecStore;
+
+	constructor(private readonly db: Database.Database) {
+		this.sqliteVecStore = new SqliteVecStore(db);
+	}
 
 	/**
 	 * Search stored embeddings by cosine similarity to the query embedding.
 	 *
+	 * Uses in-memory cosine similarity computation. The vec_embedding column
+	 * stores raw Float32 bytes for forward compatibility with vector-capable
+	 * libSQL builds; scoring is performed in JS using the same bytes.
+	 *
 	 * @param queryEmbedding - The embedded representation of the search query.
 	 * @param options - Search options including repositoryId, optional versionId, profileId, and limit.
 	 * @returns Results sorted by descending cosine similarity score.
 	 */
 	vectorSearch(queryEmbedding: Float32Array, options: VectorSearchOptions): VectorSearchResult[] {
-		const { repositoryId, versionId, profileId = 'local-default', limit = 50 } = options;
-
-		let sql = `
-			SELECT se.snippet_id, se.embedding
-			FROM snippet_embeddings se
-			JOIN snippets s ON s.id = se.snippet_id
-			WHERE s.repository_id = ?
-			  AND se.profile_id = ?
-		`;
-		const params: unknown[] = [repositoryId, profileId];
-
-		if (versionId) {
-			sql += ' AND s.version_id = ?';
-			params.push(versionId);
-		}
-
-		const rows = this.db.prepare<unknown[], RawEmbeddingRow>(sql).all(...params);
-
-		const scored: VectorSearchResult[] = rows.map((row) => {
-			const embedding = new Float32Array(
-				row.embedding.buffer,
-				row.embedding.byteOffset,
-				row.embedding.byteLength / 4
-			);
-			return {
-				snippetId: row.snippet_id,
-				score: cosineSimilarity(queryEmbedding, embedding)
-			};
-		});
-
-		return scored.sort((a, b) => b.score - a.score).slice(0, limit);
+		return this.sqliteVecStore
+			.queryNearestNeighbors(queryEmbedding, options)
+			.map((result) => ({ snippetId: result.snippetId, score: result.score }));
 	}
 }