Vector Database
A vector database is a database purpose-built for storing embeddings and searching them by similarity rather than exact match — given a query vector, it returns the stored vectors closest to it in meaning. This is what makes semantic search and RAG retrieval fast at scale, where comparing a query against millions of vectors one by one would be too slow.
Where This Term Is Used
Related Terms
Token
A token is the basic unit of text an LLM processes — roughly ¾ of a word for common English, though punctuation, numbers, and rare or technical words can each become their own token. Every API request is priced and limited by token count, not word or character count.
Context Window
The context window is the maximum number of tokens a model can process in a single request — the system prompt, conversation history, retrieved documents, the current message, and the model's own output all draw from this same shared budget. Content beyond the limit is truncated or the request is rejected.
System Prompt
A system prompt is a set of instructions sent with every request that defines how a model should behave — its role, tone, constraints, and output format — separate from the user's actual message. It counts against the same token budget as everything else in the request, so a longer system prompt leaves less room for conversation and output.