Infrastructure build to support third-party app integrations

backend/services/embedding.service.ts

@@ -0,0 +1,45 @@
+import { VoyageAIClient } from "voyageai";
+import { pipeline } from "node:stream/promises";
+import { Readable } from "node:stream";
+import { batch } from "../lib/streams.js";
+import type { EmbeddingMap } from "../types/domain.js";
+
+const client = new VoyageAIClient({
+    apiKey: process.env.VOYAGEAI_API_KEY,
+});
+
+const EMBED_BATCH_SIZE = 128;
+
+type EmbeddableNote = { id: string; text: string };
+
+/**
+ * @returns noteId to embedding vector
+ */
+export const embedNotes = async (notes: EmbeddableNote[]): Promise<EmbeddingMap> => {
+    const embeddingMap: EmbeddingMap = new Map();
+
+    if (!notes || notes.length === 0) {
+        return embeddingMap;
+    }
+
+    await pipeline(
+        Readable.from(notes, { objectMode: true }),
+        batch<EmbeddableNote>(EMBED_BATCH_SIZE),
+        async (batches: AsyncIterable<EmbeddableNote[]>) => {
+            for await (const chunk of batches) {
+                const response = await client.embed({
+                    input: chunk.map((n) => n.text),
+                    model: "voyage-3.5",
+                });
+
+                response.data?.forEach((item, i) => {
+                    if (item.embedding) {
+                        embeddingMap.set(chunk[i].id, item.embedding);
+                    }
+                });
+            }
+        }
+    );
+
+    return embeddingMap;
+};