Configuring a RAG Agent

A Retrieval-Augmented Generation (RAG) Agent uses a vector database and a large language model (LLM) to query and enrich your real-time event data.

When you create or edit a RAG Agent, you must supply the appropriate connection details for the LLM you want to use and the vector database you want to query. For details about how to configure the parameters for your Agent type, see the sections linked below:

• Amazon Bedrock with Qdrant (Beta)

• OpenAI-Compatible with Qdrant (Beta)

To configure your event broker service, see Configuring Your Event Broker Service.