Add nonblocking/asyn I/O operations

backend/services/embedding.service.js

@@ -1,25 +1,42 @@
 import { VoyageAIClient } from "voyageai";
+import { pipeline } from "node:stream/promises";
+import { Readable } from "node:stream";
+import { batch } from "../lib/streams.js";
 
 const client = new VoyageAIClient({
   apiKey: process.env.VOYAGEAI_API_KEY,
 });
 
+// Well under Voyage's per-request input and token ceilings.
+const EMBED_BATCH_SIZE = 128;
+
 /**
  * @param {Array<{id: string, text: string}>} notes
  * @returns {Promise<Map<string, number[]>>} noteId → embedding vector
  */
 export const embedNotes = async (notes) => {
-  const texts = notes.map((n) => n.text);
-
-  const response = await client.embed({
-    input: texts,
-    model: "voyage-3",
-  });
-
   const embeddingMap = new Map();
-  response.data.forEach((item, i) => {
-    embeddingMap.set(notes[i].id, item.embedding);
-  });
+
+  if (!notes || notes.length === 0) {
+    return embeddingMap;
+  }
+
+  await pipeline(
+    Readable.from(notes, { objectMode: true }),
+    batch(EMBED_BATCH_SIZE),
+    async (batches) => {
+      for await (const chunk of batches) {
+        const response = await client.embed({
+          input: chunk.map((n) => n.text),
+          model: "voyage-3",
+        });
+
+        response.data.forEach((item, i) => {
+          embeddingMap.set(chunk[i].id, item.embedding);
+        });
+      }
+    }
+  );
 
   return embeddingMap;
 };