AI engineering glossary · RAG vector search
What is knowledge base?
Knowledge base: The collection of documents or records a RAG system searches, such as manuals, wiki pages, tickets or database rows. It is usually cleaned, split into chunks, embedded and indexed ahead of time so lookups are fast at question time.
Knowledge base: an example
A telecom's knowledge base holds 12,000 support articles in English and Hindi, re-indexed every night.
Related terms
More RAG vector search terms
- Knowledge graph
- Late interaction
- Layout-aware parsing
- Learned sparse retrieval
- LLM-as-judge
- Locality-sensitive hashing
- M parameter
- Maximal marginal relevance
Where you learn it
Knowledge base is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.