Gunakan ekstensi vector, versi 0.5.0.google-1 atau yang lebih baru, yang mencakup fungsi dan operator pgvector, untuk menyimpan sematan yang dihasilkan sebagai nilai vector. Ini adalah versi pgvector yang telah diperluas oleh Google dengan pengoptimalan khusus untuk AlloyDB.
CREATEEXTENSIONIFNOTEXISTSvector;
Menyimpan embedding yang dibuat
Pastikan Anda telah membuat tabel di database AlloyDB.
Untuk menyimpan embedding vektor, lakukan hal berikut:
Buat kolom vector[] di tabel Anda untuk menyimpan embedding:
Misalnya, jika Anda menggunakan salah satu model berbahasa Inggris textembedding-gecko—misalnya, textembedding-gecko@003 dengan Vertex AI, tentukan 768.
Salin vektor ke kolom vektor. Contoh berikut mengasumsikan bahwa sematan Anda tersedia dalam file CSV:
[[["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 2025-09-04 UTC."],[[["\u003cp\u003eAlloyDB can be used as a vector database by utilizing the \u003ccode\u003evector\u003c/code\u003e extension, which includes \u003ccode\u003epgvector\u003c/code\u003e functions and operators to store embeddings as vector values.\u003c/p\u003e\n"],["\u003cp\u003eTo use this feature, ensure you install the \u003ccode\u003evector\u003c/code\u003e extension, version \u003ccode\u003e0.5.0.google-1\u003c/code\u003e or later, optimized for AlloyDB, by running \u003ccode\u003eCREATE EXTENSION IF NOT EXISTS vector;\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eYou can store embeddings in an existing AlloyDB table by adding a \u003ccode\u003evector[]\u003c/code\u003e column, specifying the number of dimensions supported by the model being used, and copying the vectors into this column from a CSV file or using \u003ccode\u003eAlloyDBVectorStore\u003c/code\u003e for LangChain integration.\u003c/p\u003e\n"],["\u003cp\u003eAfter storing vector data, consider creating indexes using the \u003ccode\u003evector\u003c/code\u003e or \u003ccode\u003ealloydb_scann\u003c/code\u003e extension for enhanced query performance.\u003c/p\u003e\n"],["\u003cp\u003eThe AlloyDB ScaNN index is currently in preview and subject to Pre-GA Offerings Terms, with features available "as is" and having potentially limited support.\u003c/p\u003e\n"]]],[],null,["# Store vector embeddings\n\nSelect a documentation version: 15.5.5keyboard_arrow_down\n\n- [15.5.5](/alloydb/omni/15.5.5/docs/store-embeddings)\n\n\u003cbr /\u003e\n\nThis page shows you how to use AlloyDB as a vector database with the `vector` extension that includes `pgvector` functions and operators. These functions and operators let you store embeddings as vector values.\n\n\u003cbr /\u003e\n\nRequired database extension\n---------------------------\n\nUse the `vector` extension, version `0.5.0.google-1` or later, which includes\n`pgvector` functions and operators, to store generated embeddings as `vector` values. This\nis a version of `pgvector` that Google has extended with optimizations specific\nto AlloyDB. \n\n CREATE EXTENSION IF NOT EXISTS vector;\n\nStore generated embeddings\n--------------------------\n\nEnsure that you have already created a table in your AlloyDB database.\n| **Note:** If your application uses the LangChain framework and your dataset has `O(100k)` embeddings, we recommend that you use the `AlloyDBVectorStore` vector class included in the AlloyDB LangChain library to store your embeddings. For more information, see [Build LLM-powered applications using\n| LangChain](/alloydb/docs/ai/langchain#vector_store_procedure_guide).\n\nTo store vector embeddings, do the following:\n\n1. Create a `vector[]` column in your table to store your embeddings:\n\n ALTER TABLE \u003cvar translate=\"no\"\u003e\u003cspan class=\"devsite-syntax-k\"\u003eTABLE\u003c/span\u003e\u003c/var\u003e ADD COLUMN \u003cvar translate=\"no\"\u003e\u003cspan class=\"devsite-syntax-n\"\u003eEMBEDDING_COLUMN\u003c/span\u003e\u003c/var\u003e vector(\u003cvar translate=\"no\"\u003e\u003cspan class=\"devsite-syntax-n\"\u003eDIMENSIONS\u003c/span\u003e\u003c/var\u003e);\n\n Replace the following:\n - \u003cvar translate=\"no\"\u003eTABLE\u003c/var\u003e: the table name\n\n - \u003cvar translate=\"no\"\u003eEMBEDDING_COLUMN\u003c/var\u003e: the name of the new embedding column\n\n - \u003cvar translate=\"no\"\u003eDIMENSIONS\u003c/var\u003e: the number of dimensions that the model\n supports.\n\n For example, if you are using one of the `textembedding-gecko`English models---for example, `textembedding-gecko@003` with Vertex AI, specify `768`.\n2. Copy the vectors to the vector column. The following example assumes your embeddings are available in a `CSV` file:\n\n COPY \u003cvar translate=\"no\"\u003e\u003cspan class=\"devsite-syntax-k\"\u003eTABLE\u003c/span\u003e\u003c/var\u003e (\u003cvar translate=\"no\"\u003e\u003cspan class=\"devsite-syntax-n\"\u003eEMBEDDING_COLUMN\u003c/span\u003e\u003c/var\u003e) FROM '\u003cvar translate=\"no\"\u003e\u003cspan class=\"devsite-syntax-n\"\u003ePATH_TO_VECTOR_CSV\u003c/span\u003e\u003c/var\u003e (FORMAT CSV);\n\n Replace the following:\n - \u003cvar translate=\"no\"\u003ePATH_TO_VECTOR_CSV\u003c/var\u003e: the full path of where you have stored your `CSV` file.\n\n|\n| **Preview\n| --- AlloyDB ScaNN index**\n|\n|\n| This feature is subject to the \"Pre-GA Offerings Terms\" in the General Service Terms section\n| of the [Service Specific Terms](/terms/service-terms#1).\n|\n| Pre-GA features are available \"as is\" and might have limited support.\n|\n| For more information, see the\n| [launch stage descriptions](/products#product-launch-stages).\n\nAfter you store the embeddings, you can use the `vector` extension or the `alloydb_scann`\nextension to create indexes for faster query performance.\n\nWhat's next\n-----------\n\n- [Create indexes and query vectors](/alloydb/omni/15.5.5/docs/store-index-query-vectors)\n- [An example embedding workflow](/alloydb/omni/15.5.5/docs/example-embeddings)"]]
