[[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["難以理解","hardToUnderstand","thumb-down"],["資訊或程式碼範例有誤","incorrectInformationOrSampleCode","thumb-down"],["缺少我需要的資訊/範例","missingTheInformationSamplesINeed","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["上次更新時間:2025-08-27 (世界標準時間)。"],[],[],null,["# Vector database choices in Vertex AI RAG Engine\n\n| The [VPC-SC security controls](/vertex-ai/generative-ai/docs/security-controls) and\n| CMEK are supported by Vertex AI RAG Engine. Data residency and AXT security controls aren't\n| supported.\n\nThis page introduces the vector databases supported on Vertex AI RAG Engine.\nYou can also see how to connect a vector database (vector store) to your RAG\ncorpus.\n\nVector databases play a crucial role in enabling retrieval for RAG applications.\nVector databases offer a specialized way to store and query vector embeddings,\nwhich are mathematical representations of text or other data that capture\nsemantic meaning and relationships. Vector embeddings allow RAG systems to\nquickly and accurately find the most relevant information within a vast\nknowledge base, even when dealing with complex or nuanced queries. When combined\nwith an embedding model, vector databases can help overcome the limitations of\nLLMs, and provide more accurate, relevant, and comprehensive responses.\n\nSupported vector databases\n--------------------------\n\nWhen creating a RAG corpus, Vertex AI RAG Engine offers the\nenterprise-ready `RagManagedDb` as the default vector database, which requires\nno additional provisioning or managing.\n`RagManagedDb` offers both KNN and ANN search options and\nallows switching to a basic tier for some quick prototyping and experimentation.\nTo learn more about choosing a retrieval strategy on `RagManagedDb` or for\nupdating the tier, see [Use `RagManagedDb` with\nRAG](/vertex-ai/generative-ai/docs/rag-engine/use-ragmanageddb-with-rag). For\nVertex AI RAG Engine to automatically create and manage the\nvector database for you, see [Create a RAG\ncorpus](/vertex-ai/generative-ai/docs/model-reference/rag-api#create-a-rag-corpus-params-api).\n\nIn addition to the default `RagManagedDb`, Vertex AI RAG Engine\nlets you provision and use your vector database within your RAG corpus. In this\ncase, you are responsible for the lifecycle and scalability of your vector\ndatabase.\n\nCompare vector database options\n-------------------------------\n\nThis table lists your choices of vector databases that are supported within\nVertex AI RAG Engine and provides links to pages that explain how\nto use the vector databases within your RAG corpus. \n\nWhat's next\n-----------\n\n- To create a RAG corpus, see [Create a RAG corpus\n example](/vertex-ai/generative-ai/docs/model-reference/rag-api#create-a-rag-corpus-example-api).\n- To list all of the RAG corpora, see [List RAG corpora\n example](/vertex-ai/generative-ai/docs/model-reference/rag-api#list-rag-corpora-example-api)."]]