feat(mcpedia): Phase 2 — semantic + hybrid search, tRPC/Hono API

- @mcpedia/embeddings: OpenRouter provider (9router /v1, encoding_format float),
  chunkText + embedChunks; EMBED_DIM=2048
- document_chunks table (real[] embedding) — pgvector NOT available on shared
  imrnes Postgres, so cosine is computed in-app (KB-scale fine); pgvector deferred
- indexer: chunk + embed + upsert per document
- @mcpedia/search: semanticSearch (cosine) + hybridSearch (FTS+cosine RRF)
- apps/api: Hono + tRPC v11 (6 procedures), serve on :4020
- MCP: semantic_search + hybrid_search tools (6 total)
- web: keyword/hybrid toggle; .env.example + README + PHASES updated
This commit is contained in:
asepharyana
2026-08-19 19:00:29 +07:00
parent ec3a2867d4
commit 9397303f01
32 changed files with 1120 additions and 42 deletions
+36 -5
View File
@@ -1,18 +1,45 @@
import Link from "next/link";
import { keywordSearch } from "@mcpedia/core";
import { keywordSearch, hybridSearch } from "@mcpedia/core";
type Mode = "keyword" | "hybrid";
export default async function SearchPage({
searchParams,
}: {
searchParams: Promise<{ q?: string }>;
searchParams: Promise<{ q?: string; mode?: string }>;
}) {
const { q } = await searchParams;
const { q, mode } = await searchParams;
const query = q?.trim() ?? "";
const hits = query ? await keywordSearch(query, 30) : [];
const activeMode: Mode = mode === "hybrid" ? "hybrid" : "keyword";
const hits = query
? activeMode === "hybrid"
? await hybridSearch(query, 30)
: await keywordSearch(query, 30)
: [];
const toggle = (m: Mode) => `/search?q=${encodeURIComponent(query)}&mode=${m}`;
return (
<div className="space-y-4">
<h1 className="text-2xl font-semibold tracking-tight">Search</h1>
<div className="flex items-center justify-between">
<h1 className="text-2xl font-semibold tracking-tight">Search</h1>
<div className="flex rounded overflow-hidden border border-zinc-300 dark:border-zinc-700 text-sm">
<Link
href={toggle("keyword")}
className={`px-3 py-1.5 ${activeMode === "keyword" ? "bg-zinc-900 text-white dark:bg-zinc-100 dark:text-zinc-900" : "hover:bg-zinc-100 dark:hover:bg-zinc-800"}`}
>
Keyword
</Link>
<Link
href={toggle("hybrid")}
className={`px-3 py-1.5 ${activeMode === "hybrid" ? "bg-zinc-900 text-white dark:bg-zinc-100 dark:text-zinc-900" : "hover:bg-zinc-100 dark:hover:bg-zinc-800"}`}
>
Hybrid
</Link>
</div>
</div>
<form method="get" className="flex gap-2">
<input
name="q"
@@ -20,6 +47,7 @@ export default async function SearchPage({
placeholder="e.g. websocket contract typescript"
className="flex-1 rounded border border-zinc-300 dark:border-zinc-700 bg-white dark:bg-zinc-900 px-3 py-2 text-sm"
/>
<input type="hidden" name="mode" value={activeMode} />
<button
type="submit"
className="rounded bg-zinc-900 text-white dark:bg-zinc-100 dark:text-zinc-900 px-4 py-2 text-sm font-medium"
@@ -44,6 +72,9 @@ export default async function SearchPage({
>
{h.doc.title}
</Link>
{/* Snippet comes from Postgres ts_headline (keyword mode) or our own
chunk content (hybrid mode) — both trusted, first-party data, not
user input. The only markup is <mark> from ts_headline. */}
<p
className="text-sm text-zinc-600 dark:text-zinc-400 mt-1"
dangerouslySetInnerHTML={{ __html: h.snippet }}