RAG System Architecture | Vellum

LLM applications often require specific context from a Vector DB which is added into the prompt. Forget signing up for multiple systems and being stuck on various micro decisions, with Vellum you can prototype a RAG system in minutes.

Implementation Steps

Create a Document Index and upload your documents

Follow this article for tips: Uploading Documents)

Add a Search Node in your Workflow

Place this anywhere and connect it to the “entrypoint”

Add a Prompt Node

The prompt node should take the results of your Search Node as an input variable

Link to a Final Output or other downstream node

For example, if the Prompt Node result is a certain value branch execution based on a Conditional Node)

Set up input variables and hit Run!

Retrieval Augmented Generation (RAG) system