Vector database choices in RAG Engine

This page introduces you to your choices of a supported vector database on RAG Engine. You can also see how to connect a vector database (vector store) to your RAG corpus.

A common problem with LLMs is that they don't understand private knowledge, that is, your organization's data. With RAG Engine, you can enrich the LLM context with additional private information, because the model can reduce hallucination and answer questions more accurately.

Vector databases play a crucial role in enabling retrieval for RAG applications. Vector databases offer a specialized way to store and query vector embeddings, which are mathematical representations of text or other data that capture semantic meaning and relationships. Vector embeddings allow RAG systems to quickly and accurately find the most relevant information within a vast knowledge base, even when dealing with complex or nuanced queries. When combined with an embedding model, vector databases can help overcome the limitations of LLMs, and provide more accurate, relevant, and comprehensive responses.

Supported vector databases

When creating a RAG corpus, RAG Engine offers RagManagedDb as the default choice of a vector database, which requires no additional provisioning or managing. If you would prefer for RAG Engine to automatically create and manage the vector database for you, then see Create a RAG corpus.

In addition to the default RagManagedDb, RAG Engine lets you provision and bring your vector database for use within your RAG corpus. In this case, you are responsible for the lifecycle and scalability of your vector database.

This table lists your choices of vector databases that are supported within RAG Engine and links to pages that explain how to use them within your RAG corpus.

What's next

• To learn more about choosing embedding models, see Use embedding models with RAG Engine.
• To learn more about RAG Engine, see Overview of RAG Engine.