KServe Python SDK¶
Python SDK for KServe controller plane client and data plane serving runtime API.
Installation¶
KServe Python SDK can be installed by pip or poetry.
pip install¶
pip install kserve
Poetry¶
Checkout KServe GitHub repository and Install via poetry.
cd kserve/python/kserve
peotry install
KServe Serving Runtime API¶
KServe's python serving runtime API implements the open inference protocol
using FastAPI, see Serving Runtime API docs for
more details.
KServe Client API¶
KServe's python client interacts with KServe control plane APIs for executing operations on a remote KServe cluster, such as creating, patching and deleting of a InferenceService instance.
Getting Started¶
Please see the Sample for Python SDK Client to get started.
KServe Client API Reference¶
| Class | Method | Description |
|---|---|---|
| KServeClient | set_credentials | Set Credentials |
| KServeClient | create | Create InferenceService |
| KServeClient | get | Get or watch the specified InferenceService or all InferenceServices in the namespace |
| KServeClient | patch | Patch the specified InferenceService |
| KServeClient | replace | Replace the specified InferenceService |
| KServeClient | delete | Delete the specified InferenceService |
| KServeClient | wait_isvc_ready | Wait for the InferenceService to be ready |
| KServeClient | is_isvc_ready | Check if the InferenceService is ready |
Reference for Generated Data Models¶
- KnativeAddressable
- KnativeCondition
- KnativeURL
- KnativeVolatileTime
- NetUrlUserinfo
- V1beta1AIXExplainerSpec
- V1beta1AlibiExplainerSpec
- V1beta1Batcher
- V1beta1ComponentExtensionSpec
- V1beta1ComponentStatusSpec
- V1beta1CustomExplainer
- V1beta1CustomPredictor
- V1beta1CustomTransformer
- V1beta1ExplainerSpec
- V1beta1InferenceService
- V1beta1InferenceServiceList
- V1beta1InferenceServiceSpec
- V1beta1InferenceServiceStatus
- V1alpha1InferenceGraph
- V1alpha1InferenceGraphList
- V1alpha1InferenceGraphSpec
- V1alpha1InferenceGraphStatus
- V1beta1LightGBMSpec
- V1beta1LoggerSpec
- V1beta1ModelSpec
- V1beta1ModelStatus
- V1beta1ONNXRuntimeSpec
- V1beta1PaddleServerSpec
- V1beta1PMMLSpec
- V1beta1PodSpec
- V1beta1PredictorExtensionSpec
- V1beta1PredictorSpec
- V1beta1SKLearnSpec
- V1beta1TFServingSpec
- V1beta1TorchServeSpec
- V1beta1TransformerSpec
- V1beta1TritonSpec
- V1beta1XGBoostSpec