Indeks ScaNN menggunakan pengindeksan berbasis kuantisasi pohon. Dalam teknik Kuantisasi pohon, indeks mempelajari pohon penelusuran bersama dengan fungsi kuantisasi (atau hashing). Saat Anda menjalankan kueri, pohon penelusuran digunakan untuk memangkas ruang penelusuran, sedangkan kuantisasi digunakan untuk mengompresi ukuran indeks. Pemangkasan ini mempercepat pemberian skor kesamaan (yaitu, jarak) antara vektor kueri dan vektor database.
Untuk mencapai rasio kueri per detik (QPS) yang tinggi dan perolehan yang tinggi dengan kueri nearest neighbor, Anda harus mempartisi hierarki indeks ScaNN dengan cara yang paling sesuai untuk data dan kueri Anda.
Karakteristik umum model sematan berdimensi tinggi generasi saat ini adalah model tersebut masih dapat mempertahankan sebagian besar informasi pada dimensi yang jauh lebih rendah, misalnya 90% informasi dapat dipertahankan hanya dengan 20% dimensi sematan. Untuk membantu mempercepat set data tersebut, AlloyDB ScaNN akan otomatis melakukan reduksi dimensi menggunakan Analisis Komponen Utama (lihat scann.enable_pca below) pada vektor yang diindeks, yang selanjutnya mengurangi penggunaan CPU & memori untuk penelusuran vektor. Karena reduksi dimensi masih menyebabkan sedikit kehilangan recall dalam indeks, ScaNN AlloyDB mengompensasinya melalui langkah peringkat awal dengan sejumlah besar kandidat vektor yang di-PCA dari indeks, lalu memeringkat ulang kandidat tersebut berdasarkan vektor asli (lihat scann.pre_reordering_num_neighbors).
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Sulit dipahami","hardToUnderstand","thumb-down"],["Informasi atau kode contoh salah","incorrectInformationOrSampleCode","thumb-down"],["Informasi/contoh yang saya butuhkan tidak ada","missingTheInformationSamplesINeed","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-09-03 UTC."],[[["\u003cp\u003eScaNN index employs tree-quantization to accelerate vector similarity scoring by pruning the search space and compressing index size.\u003c/p\u003e\n"],["\u003cp\u003ePartitioning the ScaNN index tree appropriately is essential for achieving high query-per-second rates and recall in nearest-neighbor queries.\u003c/p\u003e\n"],["\u003cp\u003eAlloyDB ScaNN automatically reduces the dimensions of indexed vectors using Principal Component Analysis (PCA) to decrease CPU and memory usage.\u003c/p\u003e\n"],["\u003cp\u003eTo offset any recall loss from dimension reduction, AlloyDB ScaNN performs an initial ranking of a larger number of PCA'ed candidates and then re-ranks them using the original vectors.\u003c/p\u003e\n"]]],[],null,["Select a documentation version: 16.3.0keyboard_arrow_down\n\n- [Current (16.8.0)](/alloydb/omni/current/docs/ai/scann-vector-query-perf-overview)\n- [16.8.0](/alloydb/omni/16.8.0/docs/ai/scann-vector-query-perf-overview)\n- [16.3.0](/alloydb/omni/16.3.0/docs/ai/scann-vector-query-perf-overview)\n- [15.12.0](/alloydb/omni/15.12.0/docs/ai/scann-vector-query-perf-overview)\n- [15.7.1](/alloydb/omni/15.7.1/docs/ai/scann-vector-query-perf-overview)\n- [15.7.0](/alloydb/omni/15.7.0/docs/ai/scann-vector-query-perf-overview)\n\n\u003cbr /\u003e\n\nThis page provides a conceptual overview of improving vector query performance using AlloyDB AI's Scalable Nearest Neighbor (ScaNN) index. For more information, see [Create indexes and query vectors](/alloydb/omni/16.3.0/docs/ai/store-index-query-vectors?resource=scann).\n\n\u003cbr /\u003e\n\nThe ScaNN index uses tree-quantization-based indexing, in which indexes learn\na search tree together with a quantization (or hashing) function. When you run\na query, the search tree is used to prune the\nsearch space, while quantization is used to compress the index size. This pruning\nspeeds up the scoring of the similarity---in other words, the distance---between\nthe query vector and the database vectors.\n\nTo achieve both a high query-per-second rate (QPS)\nand a high recall with your nearest-neighbor queries, you must partition\nthe tree of your ScaNN index in a way that is most appropriate to your data\nand your queries.\n\nHigh-dimensional embedding models can retain much of the information at much\nlower dimensionality. For example, you can retain 90% of the information with\nonly 20% of the embedding's dimensions. To help speed up such datasets,\nthe AlloyDB AI ScaNN index automatically performs dimension reduction\nusing [Principal Component Analysis](https://en.wikipedia.org/wiki/Principal_component_analysis)\n(PCA) on the indexed vectors, which further reduces CPU and memory usage for\nthe vector search. For more information, see\n[`scann.enable_pca`](/alloydb/omni/16.3.0/docs/reference/scann-index-reference).\n\nBecause dimension reduction causes minor recall loss in the index, the\nAlloyDB AI ScaNN index compensates for recall loss\nby first performing a ranking\nstep with a larger number of PCAed vector candidates from the index. Then,\nScaNN re-ranks the PCAed vector candidates by the original vectors.\nFor more information, see [`scann.pre_reordering_num_neighbors`](/alloydb/omni/16.3.0/docs/reference/scann-index-reference).\n\nWhat's next\n\n- Learn [best practices for tuning ScaNN indexes](/alloydb/omni/16.3.0/docs/ai/best-practices-tuning-scann).\n- [Get started with vector embeddings using AlloyDB AI](https://codelabs.developers.google.com/alloydb-ai-embedding#0).\n- Learn more about the [AlloyDB AI ScaNN index](https://cloud.google.com/blog/products/databases/understanding-the-scann-index-in-alloydb?e=48754805)."]]
