Category:

RAG (Retrieval-Augmented Generation)

Category:

Retrieval & RAG

Definition

LLM enhanced with external retrieved knowledge for accuracy and grounding.

Explanation

RAG retrieves relevant context from a vector DB or search engine and injects it into the LLM’s context window to improve factuality and reduce hallucinations.

Technical Architecture

Query → Embedding → Vector Search → Rerank → LLM → Grounded Answer

Core Component

Embeddings, Vector DB, Retriever, Reranker

Use Cases

Enterprise knowledge assistants, documentation QA, semantic search

Pitfalls

Poor chunking, irrelevant retrievals, slow search layers

LLM Keywords

Retrieval Augmented Generation, RAG Architecture

Related Concepts

Related Frameworks

• Chunking
• Embeddings
• Vector DB
• Hybrid Retrieval

• RAG pipeline architecture

Back to Glossary Index