How Oracle VecDB Works

Understand how to use the Oracle VecDB Python SDK to store, index and search vector data.

Overview

Oracle VecDB is designed for vector-native use cases such as semantic search, retrieval augmented generation (RAG), knowledge assistants, and agent memory.

• About Oracle AI Database: Understand the Oracle VecDB architecture and client access paths.
• Workflows: Oracle VecDB supports integrated embedding and bring-your-own vectors.
• Models: Oracle VecDB supports integrated embedding and reranking with in-database ONNX models to simplify pipelines and reduce external dependencies.
• Vector Table: A vector table stores the records you want to search. Oracle VecDB supports integrated embedding vector tables and bring-your-own-vector tables.
• Indexes: Indexes accelerate similarity search over high-dimensional vectors. Depending on the configuration, indexing can be managed automatically or manually, for example around bulk loads.
• Record: 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.