Pipelines models
Pipelines has a model registry that manages configured instances of models. Any Pipelines functions that use models, such as embedding and retrieving, must reference a created model.
- How to create models in Pipelines.
- Discover the primitives that can be used to interact with models.
- See the supported models that come with Pipelines.
- Using models with OpenAI API-compatible services and Nvidia NIM with Pipelines.
Next Steps
Once you are familiar with models, you can learn how to use those models with retrievers.
Using models
How to create and use models in AI Accelerator Pipelines.
Primitives
The model primitives available in EDB Postgres AI - AI Accelerator Pipelines.
Supported models
Supported models in EDB Postgres AI - AI Accelerator Pipelines.
Using models with...
How to use OpenAI-compatible and Nvidia NIM models with AI Accelerator Pipelines.
- On this page
- Next Steps
Could this page be better? Report a problem or suggest an addition!