RAG (Retrieval Augmented Generation)

What is RAG?

Retrieval Augmented Generation (RAG) is an AI framework that combines the strengths of large language models (LLMs) with external knowledge sources. By retrieving relevant documents or data from a knowledge base and incorporating them into the generation process, RAG enables more accurate, up-to-date, and context-aware responses. This approach is especially useful for scenarios where the model needs to reference specific, dynamic, or proprietary information beyond its training data.

General

• Document Grounding
• Vector RAG vs Graph RAG

Vector Database

• Vector-based RAG (1/2) Embedding
• Vector-based RAG (2/2) Query Pipeline

Knowledge Graph

• Graph-based RAG (1/2) KG Creation
• Graph-based RAG (2/2) KG Query Pipeline