- A technique that grants generative artificial intelligence models information retrieval capabilities. RAG modifies interactions with a large language model (LLM) so that the model responds to user queries with reference to a specified set of documents, using this information to augment information drawn from its own vast, static training data. This allows LLMs to use domain-specific or updated information. ← Wikipedia
This term is sponsored by: your name/company?
- Previous term: Retained mode
- Next term: Revalidation
- Random term: VPS (webglossary.info/random 🎲)