• embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
• reranking — A second pass that re-scores retrieved candidates by reading each one against the query, fixing the ordering that fast vector search got approximately right.
• inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.

Teams bound by EU data-residency rules can run Voyage embedding and reranking through Atlas without inference leaving the region, removing a common blocker for retrieval systems built in Europe.

• postVoyage's rerankers start taking instructions at query time
• postWhy code retrieval benchmarks mislead, and how to rebuild them
• postWhen embedding a chunk should include the whole document
• postLong context windows do not fix LLM reranking

• postVoyage 4 shares one embedding space across large, lite and nanoVoyage AI by MongoDB
• postVoyage embedding models deploy inside your own AWS VPCVoyage AI by MongoDB
• postVoyage 4 puts every model size in one embedding spaceVoyage AI by MongoDB

Checking sign-in…

Loading comments…