Christian Kadner
Christian Kadner
**Description:** Implement the new "[Generic Protocol for Kubeflow Pipeline Template Registry](https://github.com/kubeflow/pipelines/issues/7382)" API in MLX. > At high level, the protocol will define the generic APIs between KFP SDK client and...
Should the MLX UI allow to enter a description for assets to be registered? Currently only a name is required to be entered. Without a description the asset card on...
There are currently 2 documents that contain UI developer content: * [dashboard/origin-mlx/README.md](https://github.com/machine-learning-exchange/mlx/blob/main/dashboard/origin-mlx/README.md) * [https://github.com/machine-learning-exchange/mlx/blob/main/dashboard/origin-mlx/developer-guide.md](https://github.com/machine-learning-exchange/mlx/blob/main/dashboard/origin-mlx/developer-guide.md) The `README.md` should focus on how to use the MLX API with increasing levels of complexity:...
**Outstanding work items before cutting the `v0.2.0` release:** MLX `v0.2.0` is intended to be a stable release for Kubeflow 1.5 before introducing new "breaking" changes (asset versioning, component registry, KFP...
**Current State:** We currently depend on the `elyra-server` package with the `ExecuteFileOp` to run notebooks in a Kubeflow Pipeline. While that works fairly well and provides much flexibility, there are...
Currently we use `tensorflow/tensorflow:latest` or (`tensorflow/tensorflow:2.7.0` and `tensorflow/tensorflow:2.3.0`) to run our notebooks inside a Kubeflow Pipeline. However, that image is very large and laden with many dependencies, many of which...
MLX currently supports self contained notebooks. MLX should allow users to upload a set of files along with the notebook metadata YAML like what Elyra is using for notebook definition:...
This is the UI related work for the `filter_categories` #167 - [ ] Add the `filter_categories` item values (not keys) to the featured asset cards - [ ] Include `filter_categories`...
We use the asset IDs for direct access links to our assets. But pipeline IDs are generated by KFP (outside our control). So the URLs for the same pipeline on...
### ModelMesh Integration: - [x] API #242 - [x] Deployment Manifests - [ ] UI