[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-08-19。"],[],[],null,["# About vector search\n\nMemorystore for Valkey supports storing and querying vector data. This page provides\ninformation about vector search on Memorystore for Valkey.\n| **Important:** To use vector search, your instance must be created after the feature launch date of September 13, 2024. If your instance was created prior to this date, you will need to [create](/memorystore/docs/valkey/create-instances) a new instance to use this feature.\n\nVector search on Memorystore for Valkey is compatible with the open-source LLM\nframework [LangChain](https://python.langchain.com/docs/get_started/introduction).\nUsing vector search with LangChain lets you build solutions for the following\nuse cases:\n\n- Retrieval Augmented Generation (RAG)\n- LLM cache\n- Recommendation engine\n- Semantic search\n- Image similarity search\n\nThe advantage of using Memorystore to store your Gen AI data, as opposed\nto other Google Cloud databases is Memorystore's speed. Vector\nsearch on Memorystore for Valkey leverages multi-threaded queries, resulting in\nhigh query throughput (QPS) at low latency.\n\nMemorystore also provides two distinct search approaches to help you find the right balance between speed and accuracy. The HNSW (Hierarchical Navigable Small World) option delivers fast, approximate results - ideal for large datasets where a close match is sufficient. If you require absolute precision, the 'FLAT' approach produces exact answers, though it may take slightly longer to process.\n\nIf you want to optimize your application for the fastest vector data read and write\nspeeds, Memorystore for Valkey is likely the best option for you."]]