Chunking strategies that survive production
Structural, recursive, and semantic splitting compared — plus the sizes to start from and the five ways chunking quietly caps your retrieval quality.
Intermediate8 min
#rag
#retrieval
#pipeline
Grounding a model in your own data: the pipeline, the failure modes, and the frameworks.
17 articles
Structural, recursive, and semantic splitting compared — plus the sizes to start from and the five ways chunking quietly caps your retrieval quality.
Prepending model-generated context to each chunk before embedding, and the measured drop in failed retrievals it produced.
Pinecone walks through fixed, recursive, and document-aware splitting with concrete size and overlap recommendations.
LangChain's concept doc on the splitter family — what each one optimises for and when to reach for it.
Listed inStoring in a Vector DBRAGon
Index layout, namespaces, and re-indexing without downtime.
Listed inLlamaIndexRAGon
Ingestion and indexing primitives built specifically for RAG.
Listed inRAG Use CasesRAGon
Support, internal search, and docs Q&A — the shapes where RAG genuinely wins.
Listed inRAG with Dynamic FiltersRAGon
Narrowing the search space per user with metadata filters and tenancy rules.
Listed inRetrieval ProcessRAGon
Query rewriting, hybrid search, reranking, and how many chunks to actually pass.
Listed inEmbedding DocumentsRAGon
Turning chunks into vectors, with metadata that survives to query time.
Listed inRAG vs Fine-tuningRAGon
Knowledge that changes vs behaviour that doesn't — picking the right tool.
Listed inWhat is RAG?RAGon
Retrieval-augmented generation: fetch relevant context, then answer from it.
Listed inGenerationRAGon
Composing retrieved context into a prompt that forces grounded answers.