Technique
Cache-augmented generation (CAG)
Loading a fixed knowledge set into the model's context and cache instead of retrieving per question.
What should you learn before CAG?
- ChunkingSplitting documents into passages sized for embedding and retrieval.
- EmbeddingsLists of numbers that place similar meanings close together, used for search and clustering.
- Large language models (LLMs)Transformer models trained on large amounts of text to predict the next token.
- Tokens and tokenizationSplitting text into the units a language model reads and is billed by.
- TransformersThe attention-based neural network architecture behind modern language models.
- Prompt engineeringWriting instructions and examples that get reliable output from a model.
- Vector search and retrievalFinding the stored embeddings closest to a query, usually with an approximate index.
- Context engineeringChoosing what goes into a model's context window and in what order.
- Retrieval-augmented generation (RAG)Fetching relevant passages from your documents and giving them to the model with the question.