AI向量搜索最佳实践[LRN2891].pdf

1、The following is intended to outline our general product direction.It is intended for information purposes only,and may not be incorporated into any contract.It is not a commitment to deliver any material,code,or functionality,and should not be relied upon in making purchasing decisions.The developm

2、ent,release,timing,and pricing of any features or functionality described for Oracles products may change and remains at the sole discretion of Oracle Corporation.Safe harbor statement1Copyright 2025,Oracle and/or its affiliatesSean StaceyProduct Manager Database AI EnginesOracle Database Andy Riven

3、esProduct Manager Database In-MemoryOracle Database AI Vector Search Best PracticesAI Database includes dozens of new AI capabilitiesCopyright 2025,Oracle and/or its affiliates3Agentic RAGIn-Database ONNX Vector CreationHNSW vector IndexesVector Support in JSON/OSONIVF Flat IndexesExadataAI Smart Sc

4、anHybrid Vector IndexesAI Vector SearchCustomDistance FunctionsExternal Table Support for VectorsChainableUtility Functions for VectorsIntegration with LangGraphAutomatic Accuracy CalibrationPrivate AIAI Developer RoleLlamaIndex SupportVector Search with LangChainOver 30 Machine Learning ModelsSpars

5、e,Dense,and Binary VectorsGoldenGate Distributed AILLM IntegrationMCP Server65K DimensionsAI Private Agent FactoryWhat are Vectors?Vector3342162150AI Vector Search works by representing the semantic content of a document,image,video,or even relational data as a sequence of numbers,called a vectorDev

6、elopers create a vector for an object by just passing the object to a built-in vectorization functionOracle Vector Database natively stores vectors and compares vectors to find objects with similar semantic content5Copyright 2025,Oracle and/or its affiliatesThe main operation on vectors is the Mathe