Retrieval-Augmented Generation
Letting a model answer with knowledge it wasn't trained on. Embeddings, vector search, the chunking choices that decide whether the right passage shows up, and the pipelines that wire it all together.
Embeddings
Compressing meaning into vectors so similar things land near each other in space.
Vector Databases
Storing and searching billions of embeddings in milliseconds.
Chunking Strategies
Splitting documents so retrieval surfaces the right unit of meaning — not too narrow, not too wide.
Retrieval Methods
Dense, sparse, hybrid — when to reach for each, and what each can and can't find.
Reranking
A second pass that pays attention to the query itself, not just the retrieved set.
Hybrid Search
Combining lexical and semantic retrieval to cover what neither catches alone.
End-to-End RAG Pipelines
Stitching it all together — ingestion, retrieval, generation, evaluation — into a production system.