RAG combines a retrieval system with an LLM to answer questions using up-to-date or private knowledge.
| Term | Meaning |
|---|---|
| embedding | A vector representation of text capturing semantic meaning |
| vector database | Database optimized for similarity search on embeddings |
| chunking | Splitting documents into smaller pieces for embedding |
| semantic search | Finding documents by meaning, not just keyword match |
| grounding | Providing the LLM with factual context to reduce hallucinations |