Skip to content

Latest commit

 

History

History
23 lines (13 loc) · 871 Bytes

README.md

File metadata and controls

23 lines (13 loc) · 871 Bytes

Advanced RAG

What is RAG?

Retrieval augmented generation (RAG) is a natural language processing (NLP) technique that employes the capabilities of retrieval and generative based AI models.

What is Naive RAG?

Naive RAG often refers to splitting documents into chunks, embedding them, and retrieving chunks based on semantic similarity search to a user question.

It's simple, but of poor overall performance.

That's why we need Advanced RAG.

In this tutorials (Advanced RAG), we will learn the techniques and best practices in RAG application development, that can improve the quality of the RAG.

It's crucial to the success of a RAG application.

Episodes

  1. RAG on Semi-structured data
  2. Multi-Modal RAG
  3. Multi-Document RAG with LlamaIndex