What is RAG vs Fine-Tune?
The build-versus-train choice for domain knowledge: retrieval grounds answers in fresh documents without retraining, while fine-tuning bakes in stable style and vocabulary. Most builders need retrieval first, training rarely.
Related terms
Chunking
Splitting content into retrievable passages for embeddings and RAG. Clear headings, one idea per section, and definitions up front make chunks that rank and quote cleanly.
Retrieval-Augmented Generation (RAG)
A pattern where a model retrieves relevant documents first, then grounds its answer in them. Most AI search answers are RAG systems, which is why retrievable, chunkable pages get cited.
Vector Embedding
A numeric representation of text meaning used to match queries to passages by semantic similarity rather than exact keywords. Embeddings power chunk retrieval in AI search.
Grounding
Tying a model’s answer to retrieved sources instead of pure parametric memory. Grounded answers cite pages, which turns citation readiness into visible referral and brand presence.
Temperature
Sampling randomness for generation: low values make output focused and repeatable, high values make it varied and surprising. BYOB chat configs default near 0.5 while tool calls use 0.3 for steadier structured actions.
Thinking Budget
The token allowance reserved for internal model reasoning before answering. Larger budgets suit hard multi-step problems; BYOB prices thinking tokens separately so runaway reasoning shows up in metering.