RAG (Retrieval-Augmented Generation)

Retrieve relevant info → Augment the prompt with it → Generate the answer. The key memory pattern.

Fetching relevant documents at question time and adding them to the prompt so the model answers from real text rather than memory.

Fetching relevant documents at question time and adding them to the prompt so the model answers from real text.

Retrieve relevant chunks, then have an LLM answer using them. The killer app; reduces hallucination, adds current/private knowledge with citations.

Giving a model relevant information at inference time by retrieving it from a knowledge source and inserting it into the prompt. The tool for knowledge, vs fine-tuning for behavior. (M02)

Searching your own documents for relevant text and pasting it into the prompt so the model can answer with private/current data. Like an open-book exam. (Mod 1)