# Overview # Key Considerations ## Approaches for Chunking in RAG #flashcard ### Character Splitting <!--ID: 1751507777246--> ### Recursive Character Text Splitting ### Document Specific Splitting HTML, Markdown, JSON, Python, JS, etc... ### Semantic Chunking Chunk based on semantics, rather than chunk sizes or document structure. ### Proposition Chunking [The Propositions Method: Enhancing Information Retrieval for AI Systems](https://diamantai.substack.com/p/the-propositions-method-enhancing?r=336pe4&utm_campaign=post&utm_medium=web&triedRedirect=true) ### Agentic Chunking ### Late Chunking [Chunk Better With Chonkie: How Late Chunking Improves Text Segmentation \| by Michael Ryaboy \| Towards AI](https://pub.towardsai.net/easy-late-chunking-with-chonkie-7f05e5916997) # Pros # Cons # Use Cases # Products - [GitHub - chonkie-ai/chonkie: 🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library](https://github.com/chonkie-ai/chonkie) # References - [RetrievalTutorials/tutorials/LevelsOfTextSplitting/5\_Levels\_Of\_Text\_Splitting.ipynb at main · FullStackRetrieval-com/RetrievalTutorials · GitHub](https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb)