Overview
Oracle Autonomous AI Vector Database is a low-cost vector database designed for AI developers and data scientists. It provides a streamlined vector experience, with straightforward APIs and a web console, along with a clear path to enterprise scale and reliability as workloads grow.
The Autonomous AI Vector Database is designed for vector-native use cases such as semantic search, retrieval augmented generation (RAG), knowledge assistants, and agent memory.
-
About Autonomous AI Vector Database
Oracle Autonomous AI Vector Database provides a fully autonomous database that is optimized for vector workloads.
-
About the Autonomous AI Vector Database User
When you provision an Autonomous AI Vector Database, you are prompted to create an Autonomous AI Vector Database user, which you will use to interact with the Vector Database and connect to the Vector Database Console.
-
Oracle Autonomous AI Vector Database supports two different workflows: integrated embedding and bring-your-own vectors.
-
Oracle Autonomous AI Vector Database supports integrated embedding and reranking using in-database ONNX models to simplify pipelines and reduce external dependencies.
-
A vector table is where you store the records that you want to search. Autonomous AI Vector Database supports the creation of two types of vector tables; Integrated Embedding and Bring Your Own Vectors.
-
Indexes accelerate similarity search over high-dimensional vectors. Depending on the configuration, indexing can be managed automatically or controlled manually (for example, create and manage indexing around bulk loads).
-
A record is one row in a vector table. It represents one retrievable unit and consists of a record ID, a dense vector, and metadata.