1. Oracle AI Vector Search User's Guide
  2. Work with LLM-Powered APIs and Retrieval Augmentation Generation
  3. Use Retrieval Augmented Generation to Complement LLMs

Use Retrieval Augmented Generation to Complement LLMs

RAG lets you mitigate the inaccuracies and hallucinations faced when using LLMs. Oracle AI Vector Search enables RAG within Oracle Database using the DBMS_VECTOR_CHAIN PL/SQL package or through popular frameworks (such as LangChain).

  • About Retrieval Augmented Generation
    Oracle AI Vector Search supports Enterprise Retrieval Augmented Generation (RAG) to enable sophisticated queries that can combine vectors with relational data, graph data, spatial data, and JSON collections.
  • SQL RAG Example
    This scenario allows you to run a similarity search for specific documentation content based on a user query. Once documentation chunks are retrieved, they are concatenated and a prompt is generated to ask an LLM to answer the user question using retrieved chunks.

Parent topic: Work with LLM-Powered APIs and Retrieval Augmentation Generation