transceiver-db/packages/api/src/embeddings/seed-products.ts

/**
 * Seed product_embeddings collection in Qdrant from PostgreSQL transceivers.
 *
 * Creates a rich text representation of each transceiver, embeds it via
 * Ollama nomic-embed-text, and stores in Qdrant with payload filters.
 *
 * Run: npx tsx packages/api/src/embeddings/seed-products.ts
 */
import { pool } from "../db/client";
import { embed, upsertPoints } from "./client";

function transceiverToText(row: Record<string, unknown>): string {
  const parts = [
    row.standard_name && `${row.standard_name}`,
    row.form_factor && `Form factor: ${row.form_factor}`,
    row.speed && `Speed: ${row.speed}`,
    row.reach_label && `Reach: ${row.reach_label}`,
    row.fiber_type && `Fiber: ${row.fiber_type}`,
    row.connector && `Connector: ${row.connector}`,
    row.wavelengths && `Wavelengths: ${row.wavelengths}`,
    row.wdm_type && `WDM: ${row.wdm_type}`,
    row.category && `Category: ${row.category}`,
    row.coherent && `Coherent optics`,
    row.power_consumption_w && `Power: ${row.power_consumption_w}W`,
    row.temp_range && `Temperature: ${row.temp_range}`,
    row.vendor_name && `Vendor: ${row.vendor_name}`,
    row.description && `${row.description}`,
  ].filter(Boolean);

  return parts.join(". ");
}

async function main() {
  console.log("=== Seeding product_embeddings ===\n");

  const result = await pool.query(
    `SELECT t.id, t.slug, t.standard_name, t.form_factor, t.speed, t.speed_gbps,
            t.reach_label, t.reach_meters, t.fiber_type, t.connector,
            t.wavelengths, t.wdm_type, t.coherent, t.power_consumption_w,
            t.temp_range, t.category, t.notes as description,
            v.name as vendor_name
     FROM transceivers t
     LEFT JOIN vendors v ON v.id = t.vendor_id
     ORDER BY t.speed_gbps DESC`
  );

  console.log(`Found ${result.rows.length} transceivers to embed\n`);

  const BATCH_SIZE = 10;
  let total = 0;

  for (let i = 0; i < result.rows.length; i += BATCH_SIZE) {
    const batch = result.rows.slice(i, i + BATCH_SIZE);

    const points = await Promise.all(
      batch.map(async (row) => {
        const text = transceiverToText(row);
        const vector = await embed(text);

        return {
          id: row.id,
          vector,
          payload: {
            slug: row.slug,
            standard_name: row.standard_name || "",
            form_factor: row.form_factor || "",
            speed: row.speed || "",
            speed_gbps: parseFloat(row.speed_gbps) || 0,
            reach_label: row.reach_label || "",
            reach_meters: row.reach_meters || 0,
            fiber_type: row.fiber_type || "",
            connector: row.connector || "",
            wdm_type: row.wdm_type || "",
            category: row.category || "",
            coherent: row.coherent || false,
            vendor: row.vendor_name || "",
            text,
          },
        };
      })
    );

    await upsertPoints("product_embeddings", points);
    total += points.length;
    console.log(`  Embedded ${total}/${result.rows.length} transceivers`);
  }

  console.log(`\n=== Done: ${total} products embedded ===`);
  await pool.end();
}

main().catch((err) => {
  console.error("Fatal:", err);
  pool.end();
  process.exit(1);
});