Learn AI
Build your understanding from AI fundamentals to production AI systems.
Prefer a guided sequence? Explore Learning PathsRAG
Learn how applications connect language models to external knowledge.
8 conceptsRAG
Retrieval-Augmented Generation retrieves relevant external information and provides it to a language model as context before generating a response.
Intermediate · 5 minChunking
Chunking splits documents into smaller pieces so they can be embedded and retrieved effectively.
Intermediate · 4 minRetrieval
Retrieval is the step of finding the most relevant pieces of content for a given query before generation.
Intermediate · 4 minQuery Transformation
Query transformation rewrites or expands a user's query before retrieval to improve the chances of finding relevant results.
Advanced · 4 minReranking
Reranking reorders an initial set of retrieved results using a more precise model to surface the most relevant ones first.
Advanced · 4 minMetadata
Metadata is structured information attached to a chunk, such as source or date, used to filter or organize retrieval results.
Intermediate · 3 minHybrid Search
Hybrid search combines vector similarity with traditional keyword search to improve retrieval quality.
Intermediate · 4 minRAG Evaluation
RAG evaluation measures retrieval quality and answer accuracy to check whether a RAG system is actually helpful.
Advanced · 5 min