Recommended stack
What are you building? Semantic search
One technology per slot, with the reason it is suggested and what to use instead.
Embedding
conceptDense numeric vector representing the meaning of a piece of text.
Why editorial
Everything else in semantic search depends on the quality of the embedding: a weak one makes good ranking impossible.
Vector database
databaseOpen-source vector database with hybrid keyword and vector search built in.
Alternatives
Base model
modelEncoder-only Transformer pre-trained with masked language modelling.
Alternatives
Reranking
techniqueSecond-stage ordering of retrieved candidates by a more accurate scoring model.
Why derived from the graph
Retrieve-then-rerank is the standard shape of a semantic search pipeline.