Oracle AI Vector Search Workflow

A typical Oracle AI Vector Search workflow follows the included primary steps.

This is illustrated in the following diagram:

Figure 2-2 Oracle AI Vector Search Use Case Flowchart

Description of "Figure 2-2 Oracle AI Vector Search Use Case Flowchart"

To understand the diagram, consider this high level workflow description. Vector embeddings are generated by passing unstructured data through an embedding model. Vector embeddings can then be stored alongside business data in relational tables and vector indexes can optionally be created. Once you have the vector representations of your unstructured data stored in your database table(s), a sample of unstructured data can be passed through the embedding model to create a query vector. With the query vector, you can perform similarity searches against the vectors that are already stored in the database, in combination with relational queries if desired. To form a complete Retrieval Augmented Generation (RAG) pipeline, it is also possible to make a call to a generative Large Language Model (LLM) as part of the query step.

Primary workflow steps:

1. Generate Vector Embeddings from Your Unstructured Data

   You can perform this step either outside or within Oracle Database. For more information, see Generate Vector Embeddings.

2. Store Vector Embeddings, Unstructured Data, and Relational Business Data in Oracle Database

   You store the resulting vector embeddings and associated unstructured data with your relational business data in Oracle Database. For more information, see Store Vector Embeddings.

3. Create Vector Indexes

   You may want to create vector indexes on your vector embeddings. This is beneficial for running similarity searches over huge vector spaces. For more information, see Create Vector Indexes.

4. Query Data with Similarity Searches

   You can then use Oracle AI Vector Search native SQL operations to combine similarity with relational searches to retrieve relevant data. For more information, see Query Data with Similarity Searches.

5. Generate a Prompt and Send it to an LLM for a Full RAG Inference

   You can use the similarity search results to generate a prompt and send it to your generative LLM of choice for a complete RAG pipeline. For more information, see Work with Retrieval Augmented Generation.