Understand your catalogue
Bring your own embeddings
Connect embeddings from TwelveLabs, OpenAI or your own internal models without rebuilding the recommendation layer.
What it does
The mechanism
- 01
Embeddings you already produce can be attached to items and used for retrieval and ranking straight away, alongside or instead of ours.
- 02
Changing provider is a configuration change rather than a migration: the ranking layer, the rules and the API you integrated against all stay where they are.
What it gets you
Three things you can point at
01
Provider-agnostic
TwelveLabs, OpenAI, an open-weights model you host, or a representation your own team trained - all attach the same way.
02
Mix representations
Different parts of a catalogue can carry different embeddings where that is genuinely the right answer.
03
No lock-in at the vector layer
Nothing about the integration assumes a particular embedding model, so replacing one does not cost you the rest of the system.