transceiver-db/packages/api/src/routes/search.ts

/**
 * Semantic search API routes (Qdrant vector search)
 *
 * GET /api/search?q=<query>&collection=<col>&limit=<n>
 * GET /api/search/products?q=<query>&form_factor=&speed_gbps=&fiber_type=
 * GET /api/search/documents?q=<query>&doc_type=&vendor=
 * GET /api/search/news?q=<query>&source=
 */
import { Router, Request, Response } from "express";
import { semanticSearch, getCollectionInfo, CollectionName } from "../embeddings/client";

export const searchRouter = Router();

const VALID_COLLECTIONS: CollectionName[] = [
  "product_embeddings",
  "datasheet_chunks",
  "faq_embeddings",
  "manual_chunks",
  "troubleshooting_embeddings",
  "news_embeddings",
];

const q = (p: string, req: Request): string | undefined =>
  req.query[p] ? String(req.query[p]) : undefined;

// GET /api/search — Generic semantic search across any collection
searchRouter.get("/", async (req: Request, res: Response) => {
  const query = q("q", req);
  const collection = (q("collection", req) || "product_embeddings") as CollectionName;
  const limit = parseInt(q("limit", req) || "10");

  if (!query) {
    res.status(400).json({ success: false, error: "Missing 'q' parameter" });
    return;
  }

  if (!VALID_COLLECTIONS.includes(collection)) {
    res.status(400).json({
      success: false,
      error: `Invalid collection. Valid: ${VALID_COLLECTIONS.join(", ")}`,
    });
    return;
  }

  try {
    const results = await semanticSearch(collection, query, limit);
    res.json({
      success: true,
      query,
      collection,
      results: results.map((r) => ({
        id: r.id,
        score: Math.round(r.score * 1000) / 1000,
        ...r.payload,
      })),
      count: results.length,
    });
  } catch (err) {
    res.status(503).json({
      success: false,
      error: "Vector search unavailable",
      detail: (err as Error).message,
    });
  }
});

// GET /api/search/products — Product-specific semantic search with filters
searchRouter.get("/products", async (req: Request, res: Response) => {
  const query = q("q", req);
  const limit = parseInt(q("limit", req) || "10");
  const formFactor = q("form_factor", req);
  const speedGbps = q("speed_gbps", req);
  const fiberType = q("fiber_type", req);
  const wdmType = q("wdm_type", req);

  if (!query) {
    res.status(400).json({ success: false, error: "Missing 'q' parameter" });
    return;
  }

  // Build Qdrant payload filter
  const mustConditions: Array<Record<string, unknown>> = [];
  if (formFactor) {
    mustConditions.push({ key: "form_factor", match: { value: formFactor.toUpperCase() } });
  }
  if (speedGbps) {
    mustConditions.push({ key: "speed_gbps", match: { value: parseFloat(speedGbps) } });
  }
  if (fiberType) {
    mustConditions.push({ key: "fiber_type", match: { value: fiberType.toUpperCase() } });
  }
  if (wdmType) {
    mustConditions.push({ key: "wdm_type", match: { value: wdmType.toUpperCase() } });
  }

  const filter = mustConditions.length > 0 ? { must: mustConditions } : undefined;

  try {
    const results = await semanticSearch("product_embeddings", query, limit, filter);
    res.json({
      success: true,
      query,
      filters: { formFactor, speedGbps, fiberType, wdmType },
      results: results.map((r) => ({
        id: r.id,
        score: Math.round(r.score * 1000) / 1000,
        slug: r.payload.slug,
        standard_name: r.payload.standard_name,
        form_factor: r.payload.form_factor,
        speed: r.payload.speed,
        reach: r.payload.reach_label,
        fiber_type: r.payload.fiber_type,
        connector: r.payload.connector,
        category: r.payload.category,
        vendor: r.payload.vendor,
      })),
      count: results.length,
    });
  } catch (err) {
    res.status(503).json({
      success: false,
      error: "Vector search unavailable",
      detail: (err as Error).message,
    });
  }
});

// GET /api/search/documents — Search datasheets and manuals
searchRouter.get("/documents", async (req: Request, res: Response) => {
  const query = q("q", req);
  const limit = parseInt(q("limit", req) || "10");
  const docType = q("doc_type", req);
  const vendor = q("vendor", req);
  const collection = (q("collection", req) || "datasheet_chunks") as CollectionName;

  if (!query) {
    res.status(400).json({ success: false, error: "Missing 'q' parameter" });
    return;
  }

  if (!["datasheet_chunks", "manual_chunks"].includes(collection)) {
    res.status(400).json({
      success: false,
      error: "collection must be 'datasheet_chunks' or 'manual_chunks'",
    });
    return;
  }

  const mustConditions: Array<Record<string, unknown>> = [];
  if (docType) {
    mustConditions.push({ key: "document_type", match: { value: docType.toLowerCase() } });
  }
  if (vendor) {
    mustConditions.push({ key: "vendor", match: { value: vendor } });
  }

  const filter = mustConditions.length > 0 ? { must: mustConditions } : undefined;

  try {
    const results = await semanticSearch(collection, query, limit, filter);

    // Group by document for cleaner output
    const byDocument = new Map<string, { title: string; vendor: string; source_url: string; chunks: Array<{ score: number; heading: string; text: string; chunk_index: number }> }>();

    for (const r of results) {
      const docId = String(r.payload.document_id || r.id);
      if (!byDocument.has(docId)) {
        byDocument.set(docId, {
          title: String(r.payload.title || ""),
          vendor: String(r.payload.vendor || ""),
          source_url: String(r.payload.source_url || ""),
          chunks: [],
        });
      }
      byDocument.get(docId)!.chunks.push({
        score: Math.round(r.score * 1000) / 1000,
        heading: String(r.payload.section_heading || ""),
        text: String(r.payload.text || "").slice(0, 500),
        chunk_index: Number(r.payload.chunk_index || 0),
      });
    }

    res.json({
      success: true,
      query,
      collection,
      filters: { docType, vendor },
      documents: Array.from(byDocument.values()),
      totalChunks: results.length,
    });
  } catch (err) {
    res.status(503).json({
      success: false,
      error: "Vector search unavailable",
      detail: (err as Error).message,
    });
  }
});

// GET /api/search/news — Search news articles
searchRouter.get("/news", async (req: Request, res: Response) => {
  const query = q("q", req);
  const limit = parseInt(q("limit", req) || "10");
  const source = q("source", req);

  if (!query) {
    res.status(400).json({ success: false, error: "Missing 'q' parameter" });
    return;
  }

  const mustConditions: Array<Record<string, unknown>> = [];
  if (source) {
    mustConditions.push({ key: "source", match: { value: source } });
  }

  const filter = mustConditions.length > 0 ? { must: mustConditions } : undefined;

  try {
    const results = await semanticSearch("news_embeddings", query, limit, filter);
    res.json({
      success: true,
      query,
      filters: { source },
      results: results.map((r) => ({
        id: r.id,
        score: Math.round(r.score * 1000) / 1000,
        title: r.payload.title,
        url: r.payload.url,
        source: r.payload.source,
        summary: r.payload.summary,
        published_at: r.payload.published_at,
      })),
      count: results.length,
    });
  } catch (err) {
    res.status(503).json({
      success: false,
      error: "Vector search unavailable",
      detail: (err as Error).message,
    });
  }
});

// GET /api/search/stats — Collection statistics
searchRouter.get("/stats", async (_req: Request, res: Response) => {
  try {
    const stats = await Promise.all(
      VALID_COLLECTIONS.map(async (col) => {
        try {
          const info = await getCollectionInfo(col);
          return { collection: col, ...info };
        } catch {
          return { collection: col, pointsCount: 0, vectorsCount: 0, error: "unavailable" };
        }
      })
    );

    res.json({ success: true, collections: stats });
  } catch (err) {
    res.status(503).json({
      success: false,
      error: "Qdrant unavailable",
      detail: (err as Error).message,
    });
  }
});