Technology

Technology

Retrieval-Augmented Generation (RAG) with LLMs

RAG is an AI technology pattern that employs large language models (LLMs) to retrieve facts from a specific knowledge base.

Used in the following Interventions

Integrate a Large Language Model (LLM) AI with a Knowledge Graph

Connect a Large Language Model AI service with a knowledge graph so that the information source is scoped and accurate. This provides a reliable information repository for using the LLM in a specific business area.

Other technologies used

Machine Learning (ML)

Large Language Model (LLM) AI

Knowledge Graphs

Deploy a RAG LLM stack with a Knowledge Graph

Use a Knowledge Graph as the source for information retrieval to provide the LLM with correct, scoped, and contextual information.

Other technologies used

Machine Learning (ML)

Artificial Intelligence (AI)

Large Language Model (LLM) AI

FAQs

What's involved in Retrieval-Augmented Generation (RAG)?

RAG is a technology pattern that employs large language model (LLM) AI to retrieve facts from a specific knowledge base.

What is the benefit of the Retrieval-Augmented Generation (RAG) pattern?

The benefit of the RAG pattern is that it scopes the information available to the LLM to increase relevance and accuracy, and to reduce irrelevant or hallucinated outputs.

This approach has been used to scope the knowledge used for LLMs to answer questions and perform tasks, and to thereby ground them in relevant, accurate information. This reduces the scope for irrelevant or hallucinated outputs.

Exploring new RAG stack approaches with LLMs and Knowledge Graphs

The team at Data Language has been looking into the RAG stack approach in R&D, and also in collaboration with customers.