Retrieval-Augmented Generation
Noun · AI & Machine Learning
Definitions
An architecture that improves LLM outputs by first retrieving relevant documents from an external knowledge base, then including them in the prompt as context. Combines the generative ability of LLMs with up-to-date, domain-specific information. Reduces hallucination and enables citing sources. The vector database + LLM pattern.
In plain English: Having an AI search for relevant information first, then use that information to give a more accurate answer.
Example: "Our customer support bot uses RAG — it searches the knowledge base for relevant articles and includes them in the prompt for accurate answers."
Related Terms
- mixture of agents
- system prompt
- Context Window
- Temperature
- Guardrails
- Vector Database
- Attention
- Prompt Injection
- Multimodal AI
- AI Agent
- Adapter Layer
- Approximate Nearest Neighbor
- Beam Search
- Differential Transformer
- Dual Encoder
- Function Calling
- Gemma
- GPT Architecture
- Graph Transformer
- Hypernetwork
- Large Multimodal Model
- Learning to Rank
- Gating Network