This image illustrates a typical Oracle AI Vector Search workflow containing the following five main parts:

1. Generating vector embeddings from your unstructured data.
2. Storing the resulting vector embeddings and associated unstructured data with your business data in Oracle Database.
3. Creating vector indexes on your vector embeddings.
4. Using Oracle AI Vector Search native SQL operations to combine similarity with relational searches to retrieve relevant data.
5. Generating a prompt and sending it to an LLM for a complete RAG inference.