OpenSearch:Panduan Cepat untuk Edisi Serbaguna

Langkah 1: Konfigurasi informasi dasar tabel

1. Pada halaman detail instans, klik Table Management di panel kiri.

2. Klik Add Table.

3. Pada langkah Basic Table Information wizard Create, konfigurasikan parameter berikut, lalu klik Next.

Langkah 2: Tambahkan sumber data

Pada langkah Data Synchronization, tambahkan sumber data. OpenSearch mendukung sumber data MaxCompute, API, dan OSS.

Contoh berikut menggunakan MaxCompute + API sebagai Sumber Data Penuh:

1. Konfigurasikan parameter Project, AccessKey, AccessKey Secret, Table, dan Partition Key.

2. Atur Automatic Reindexing menjadi Yes atau No.

3. Klik Check. Jika pemeriksaan berhasil, klik Next.

Untuk instruksi penyiapan lengkap berdasarkan jenis sumber data:

• MaxCompute: Buat tabel untuk sumber data MaxCompute

• API: Buat tabel untuk sumber data API

• OSS: Buat tabel untuk sumber data OSS

Langkah 3: Konfigurasi bidang

OpenSearch secara otomatis menyediakan bidang preset berdasarkan Scenario Template yang Anda pilih dan mengimpor semua bidang dari sumber data Anda.

Pada langkah Field Configuration, konfigurasikan minimal dua bidang wajib: bidang kunci primer dan bidang vektor.

Persyaratan bidang:

• Bidang kunci primer: Atur Type ke INT atau STRING dan pilih opsi pada kolom Primary Key.

• Bidang vektor: Atur Type ke FLOAT dan centang kotak pada kolom Vector Field. Bidang vektor secara default merupakan bidang multi-nilai, dengan nilai dipisahkan oleh delimiter HA3 (^], dikodekan sebagai \x1D dalam format UTF). Delimiter kustom didukung.

• Bidang kategori (opsional): Tambahkan bidang kategori di antara bidang kunci primer dan bidang vektor untuk membangun indeks vektor yang terorganisir berdasarkan kategori.

Saat mengonfigurasi indeks vektor, tentukan bidang dalam urutan berikut: bidang kunci primer → bidang namespace (opsional) → bidang vektor.

Jenis bidang namespace dibatasi oleh versi mesin. Untuk versi mesin vector_service_1.0.2 atau lebih awal, bidang namespace tidak boleh bertipe STRING. Untuk versi yang lebih baru, tidak ada batasan tipe.

Langkah 4: Konfigurasi skema indeks

OpenSearch secara otomatis membuat indeks untuk bidang kunci primer dan bidang vektor, menggunakan nama bidang sebagai nama indeks.

Pada langkah Index Schema, konfigurasikan indeks vektor:

• Parameter Fields Contained hanya mendukung tiga bidang tetap dan tidak dapat diperluas.

• Konfigurasikan advanced configurations untuk indeks vektor secara terpisah. Untuk detail selengkapnya, lihat Konfigurasi umum indeks vektor.

• Jika tidak ada persyaratan khusus, klik Next untuk melanjutkan dengan konfigurasi default otomatis.

Langkah 5: Konfirmasi pembuatan

Pada langkah Confirm, tinjau konfigurasi Anda dan klik Confirm.

Langkah 6: Verifikasi progres di riwayat perubahan

Di panel kiri, klik Change History. Pada tab Data Source Changes, Anda dapat melacak semua mesin keadaan hingga (finite-state machines/FSM) yang terkait dengan pembuatan tabel, pembuatan indeks, dan pengindeksan ulang data penuh.

Saat semua FSM mencapai status selesai, mesin pencari siap dan Anda dapat menjalankan pengujian kueri.

Langkah 7: Jalankan pengujian kueri

Untuk menguji instans Anda, kirim kueri vektor. Di lingkungan produksi, vektor biasanya dihasilkan oleh model penyematan dari input teks atau gambar. Contoh berikut menggunakan vektor float berdimensi 128 yang telah dihitung sebelumnya.

Gunakan kueri contoh berikut:

{
  "vector": [0.0019676427,0.005902928,0.021644069,0.21644068,0.12199384,0.043288138,0.007870571,0.0,0.08460863,0.041320495,0.043288138,0.035417568,0.011805856,0.055093993,0.12592913,0.017708784,0.021644069,0.0019676427,0.0,0.0,0.0019676427,0.078705706,0.1987319,0.041320495,0.039352853,0.0039352854,0.007870571,0.0039352854,0.0039352854,0.017708784,0.035417568,0.06886749,0.0019676427,0.0019676427,0.013773498,0.049191065,0.2125054,0.22824654,0.123961486,0.0039352854,0.0,0.0,0.021644069,0.14560555,0.078705706,0.1987319,0.22824654,0.005902928,0.064932205,0.0019676427,0.0019676427,0.021644069,0.027546996,0.035417568,0.22824654,0.22824654,0.1337997,0.023611711,0.009838213,0.007870571,0.0039352854,0.0039352854,0.017708784,0.20069954,0.033449925,0.005902928,0.019676426,0.035417568,0.015741142,0.029514639,0.13183205,0.123961486,0.029514639,0.0,0.027546996,0.22824654,0.15741141,0.0,0.0039352854,0.043288138,0.18889369,0.072802775,0.055093993,0.17315255,0.08460863,0.0019676427,0.007870571,0.035417568,0.22824654,0.10034977,0.009838213,0.021644069,0.062964566,0.027546996,0.015741142,0.04525578,0.086576276,0.033449925,0.023611711,0.017708784,0.0,0.0,0.03738521,0.072802775,0.16724962,0.035417568,0.031482283,0.20463483,0.043288138,0.011805856,0.0039352854,0.051158708,0.023611711,0.11412327,0.13183205,0.16134669,0.049191065,0.023611711,0.0039352854,0.0039352854,0.049191065,0.035417568,0.015741142,0.0039352854,0.03738521,0.08264099,0.094446845,0.021644069],
  "topK": 10,
  "includeVector": true
}

Untuk informasi lebih lanjut tentang sintaks kueri, lihat bagian Referensi sintaks kueri di bawah.