This article explores advanced techniques to optimize the RAG workflow and address challenges in naive RAG systems. It introduces the concept of small-to-big retrieval and explains two primary techniques: smaller child chunks referring to bigger parent chunks and sentence window retrieval. The article also provides code examples using LlamaIndex and discusses future blog posts on advanced RAG techniques.

6m read timeFrom towardsdatascience.com
Post cover image
Table of contents
Advanced RAG 01: Small-to-Big RetrievalBasic RAG ReviewAdvanced Method 1: Smaller Child Chunks Referring to Bigger Parent ChunksAdvanced Method 2: Sentence Window RetrievalConclusionReferences:

Sort: