What Chunking means in practice
Chunking is the most under-appreciated lever in RAG quality. Fixed-size chunking (the LangChain default of 1000 chars + 200 overlap) is fine for tutorials and terrible for production: it breaks sentences mid-thought, drops the semantic boundaries that make retrieval work, and ignores document structure. Better strategies: semantic chunking that splits on sentence boundaries and merges short ones; section-aware chunking for structured documents with explicit headings; parent-document retrieval that retrieves small chunks but expands the context the LLM sees to the surrounding paragraph or section. Match the chunker to the document type — one chunking strategy across a heterogeneous corpus reliably under-performs a small number of type-specific strategies.
Related terms
Retrieval-Augmented Generation (RAG) →
A pattern where, instead of relying solely on the LLM's training, the system retrieves relevant documents from a knowledge base and includes them in the prompt as context.
Embedding →
A dense numeric vector representation of a piece of text (or image, or audio) such that semantically similar inputs produce vectors close in the embedding space.
More in this category
All 62 terms, in plain language
Sovereign AI, RAG, agentic AI, IDP, MLOps and the regulations that shape enterprise AI.