RAG (Retrieval-Augmented Generation)
Look up relevant documents first, then ask the model to answer using them.
Read definition →Embeddings
Numerical representations of text so a computer can measure meaning by distance.
Read definition →Embedding Model
A model whose only job is to turn text into vectors for semantic search.
Read definition →Vector Database
A database optimized for storing embeddings and finding the nearest matches fast.
Read definition →Reranker
A second-pass model that re-orders retrieval results by true relevance.
Read definition →Context Window
How much text (in tokens) you can feed the model in one request.
Read definition →Tokens
The chunks of text models count and bill by — usually 3-4 characters each.
Read definition →Chunking
Splitting documents into smaller pieces before embedding and indexing them.
Read definition →Hybrid Search
Combining vector (semantic) search with keyword (BM25) search for better retrieval.
Read definition →Semantic Search
Finding documents by meaning, not just matching keywords.
Read definition →Knowledge Base
A curated store of documents, FAQs, or structured data an AI can retrieve from.
Read definition →Document Parsing
Extracting clean, structured text from PDFs, Word files, HTML, and other formats.
Read definition →Metadata Filtering
Narrowing retrieval to specific document subsets using attributes like date, department, or type.
Read definition →AI Search (Retrieval + Generation)
A search experience that returns generated answers grounded in retrieved sources, not just a list of links.
Read definition →