Learn AI / Learning Paths /From embeddings to RAG
From embeddings to RAG
Why searching by meaning works, and how it turns a confident guess into a cited answer.
Vector and vector space
A vector is an ordered list of numbers, and a vector space is a set of same-length vectors that is closed under addition and scaling.
Embedding
A list of numbers that places a token or other item in a mathematical space so a model can compare patterns, relationships and context.
Semantic similarity
A measure of how close two pieces of text are in meaning, even if they use different words.
Semantic search
A search method that finds material by similar meaning, not just shared words, and returns the most relevant passages for review or further AI use.
Vector database
A specialised system stores numerical meaning-representations of content and quickly finds the closest matches to a query by semantic similarity.
Chunking
Chunking splits source material into smaller pieces so search and retrieval can find and return the most relevant passage, rather than an entire document or a random fragment.
Retrieval
Retrieval returns passages that a search method ranks as relevant, so a person or later model step can use source material.
Retrieval-augmented generation
A method that first finds relevant source passages and then asks a language model to answer using that material.
Grounding
Grounding ties an AI answer to specific retrieved source passages so the reply is based on provided material rather than only on the model's general patterns.
Citation (in AI answers)
A citation in an AI answer points you to a source passage or document intended to support a specific claim.