first commit

server/services/embeddingService.js

@@ -0,0 +1,55 @@
+const logger = require('../utils/logger');
+
+let pipeline;
+try {
+  // Lazy import to avoid startup cost when unused
+  ({ pipeline } = require('@xenova/transformers'));
+} catch (e) {
+  logger.warn('Embedding pipeline not available. Did you install @xenova/transformers?');
+}
+
+class EmbeddingService {
+  constructor() {
+    this.initialized = false;
+    this.extractor = null;
+    this.modelName = process.env.EMBEDDING_MODEL || 'Xenova/all-MiniLM-L6-v2';
+  }
+
+  async initIfNeeded() {
+    if (this.initialized) return;
+    if (!pipeline) {
+      throw new Error('Transformers pipeline not available');
+    }
+    this.extractor = await pipeline('feature-extraction', this.modelName);
+    this.initialized = true;
+    logger.info(`Embedding model loaded: ${this.modelName}`);
+  }
+
+  async embedText(text) {
+    if (!text || !text.trim()) return [];
+    await this.initIfNeeded();
+    const output = await this.extractor(text, { pooling: 'mean', normalize: true });
+    // output is a Tensor; convert to plain JS array
+    // Depending on version, .data or .tolist()
+    const vector = Array.isArray(output) ? output : (output?.data ? Array.from(output.data) : output.tolist());
+    return vector;
+  }
+
+  cosineSimilarity(a, b) {
+    if (!a || !b || a.length !== b.length || a.length === 0) return 0;
+    let dot = 0;
+    let normA = 0;
+    let normB = 0;
+    for (let i = 0; i < a.length; i++) {
+      const va = a[i] || 0;
+      const vb = b[i] || 0;
+      dot += va * vb;
+      normA += va * va;
+      normB += vb * vb;
+    }
+    const denom = Math.sqrt(normA) * Math.sqrt(normB);
+    return denom ? dot / denom : 0;
+  }
+}
+
+module.exports = new EmbeddingService();