Skip to content

RAG Pipeline - Indexing

RAG (Retrieval-Augmented Generation) expands the knowledge of large language models (LLMs) from their initial training data to external datasets you provide.

You provide the data. RAGs give your users immediate access to accurate, real-time, and relevant answers. So when one of your employees or customers asks your LLM a question, they get answers trained on your secure business data.

The pipeline is built around two steps:

  1. Indexing. Getting your data, preparing it for the Large Langugage Model (LLM), and storing it.
  2. Retrieval and generation. That's where the user interacts and your model generates the response.