RAG
Quick Definition
Enhancing LLMs by retrieving relevant external knowledge
Full Definition
Retrieval-Augmented Generation enhancing LLM responses by retrieving relevant external knowledge.
Examples
enterprise search, knowledge chatbots, document QA
Related Terms
vector-database
semantic-search
More Large Language Models Terms
Structured Output
Generating LLM responses in predefined machine-readable formats
Inference LLM
Using a trained LLM to generate outputs from inputs
QLoRA
Combining 4-bit quantization with LoRA for efficiency
Grounded Generation
Generating outputs faithful to provided source documents
Mistral
Efficient open-source LLMs with strong performance
Scaling Laws
Relationships between model size, data, compute, and performance