Ravi Sir's Cards › Generative AI
Why do we chunk documents, and what chunk size do you use?
Interview Q&A card: Why do we chunk documents, and what chunk size do you use? Chunking means splitting long documents into small pieces before indexing. Small pieces match questions more precisely and fit in the context window (how much text the model can read at once).
Read card text
What this card says
Interview Q&A card: Why do we chunk documents, and what chunk size do you use? Chunking means splitting long documents into small pieces before indexing. Small pieces match questions more precisely and fit in the context window (how much text the model can read at once).
Learn this in the lesson: RAG on AWS: Bedrock Knowledge Bases with S3 (Step by Step)