diff --git a/doc/source/analytics/explainers.md b/doc/source/analytics/explainers.md index 5b8b087df0..99dc2a731a 100644 --- a/doc/source/analytics/explainers.md +++ b/doc/source/analytics/explainers.md @@ -45,7 +45,7 @@ For an e2e example, please check AnchorTabular notebook [here](../examples/iris_ ## Explain API -**Note**: Seldon is phasing out support for the Seldon and TensorFlow protocols, transitioning to the industry-standard Open Inference Protocol (OIP). We encourage customers to migrate to OIP, which facilitates seamless integration across various model serving runtimes, supports the development of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience. +**Note**: Seldon is no longer maintaining the Seldon and TensorFlow protocols. Instead, Seldon is adopting the industry-standard Open Inference Protocol (OIP). We strongly encourage customers to use the OIP, which offers seamless integration across diverse model serving runtimes, supports the creation of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience. For the Seldon Protocol an endpoint path will be exposed for: @@ -89,9 +89,9 @@ The explain method is also supported for tensorflow and Open Inference protocols | Protocol | URI | | ------ | ----- | +| v2 | `http:////v2/models//infer` | | seldon | `http:////api/v1.0/explain` | | tensorflow | `http:////v1/models/:explain` | -| v2 | `http:////v2/models//infer` | Note: for `tensorflow` protocol we support similar non-standard extension as for the [prediction API](../graph/protocols.md#rest-and-grpc-tensorflow-protocol), `http:////v1/models/:explain`. diff --git a/doc/source/graph/protocols.md b/doc/source/graph/protocols.md index 64d26cd439..0c334f2375 100644 --- a/doc/source/graph/protocols.md +++ b/doc/source/graph/protocols.md @@ -1,48 +1,19 @@ # Protocols -**Note**: Seldon is phasing out support for the Seldon and TensorFlow protocols, transitioning to the industry-standard Open Inference Protocol (OIP). We encourage customers to migrate to OIP, which facilitates seamless integration across various model serving runtimes, supports the development of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience.. +**Note**: Seldon is no longer maintaining the Seldon and TensorFlow protocols. Instead, Seldon is adopting the industry-standard Open Inference Protocol (OIP). We strongly encourage customers to use the OIP, which offers seamless integration across diverse model serving runtimes, supports the creation of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience. Tensorflow protocol is only available in version >=1.1. Seldon Core supports the following data planes: - * [REST and gRPC Seldon protocol](#rest-and-grpc-seldon-protocol) - * [REST and gRPC Tensorflow Serving Protocol](#rest-and-grpc-tensorflow-protocol) - * [REST and gRPC Open Inference Protocol](#v2-protocol) + * REST and gRPC Open Inference Protocol + * REST and gRPC Seldon protocol + * REST and gRPC Tensorflow Serving Protocol -## REST and gRPC Seldon Protocol - * [REST Seldon Protocol](../reference/apis/index.html) - -Seldon is the default protocol for SeldonDeployment resources. You can specify the gRPC protocol by setting `transport: grpc` in your SeldonDeployment resource or ensuring all components in the graph have endpoint.tranport set ot grpc. - -See [example notebook](../examples/protocol_examples.html). - -## REST and gRPC Tensorflow Protocol - - * [REST Tensorflow Protocol definition](https://github.com/tensorflow/serving/blob/master/tensorflow_serving/g3doc/api_rest.md). - * [gRPC Tensorflow Protocol definition](https://github.com/tensorflow/serving/blob/master/tensorflow_serving/apis/prediction_service.proto). - -Activate this protocol by speicfying `protocol: tensorflow` and `transport: rest` or `transport: grpc` in your Seldon Deployment. See [example notebook](../examples/protocol_examples.html). - -For Seldon graphs the protocol will work as expected for single model graphs for Tensorflow Serving servers running as the single model in the graph. For more complex graphs you can chain models: - - * Sending the response from the first as a request to the second. This will be done automatically when you defined a chain of models as a Seldon graph. It is up to the user to ensure the response of each changed model can be fed a request to the next in the chain. - * Only Predict calls can be handled in multiple model chaining. +{% tabs %} - -General considerations: - - * Seldon components marked as MODELS, INPUT_TRANSFORMER and OUTPUT_TRANSFORMERS will allow a PredictionService Predict method to be called. - * GetModelStatus for any model in the graph is available. - * GetModelMetadata for any model in the graph is available. - * Combining and Routing with the Tensorflow protocol is not presently supported. - * `status` and `metadata` calls can be asked for any model in the graph - * a non-standard Seldon extension is available to call predict on the graph as a whole: `/v1/models/:predict`. - * The name of the model in the `graph` section of the SeldonDeployment spec must match the name of the model loaded onto the Tensorflow Server. - - -## Open Inference Protocol (or V2 protocol) +{% tab title="REST and gRPC Open Inference Protocol" %} Seldon has collaborated with the [NVIDIA Triton Server Project](https://github.com/triton-inference-server/server) and the [KServe @@ -89,3 +60,38 @@ In particular, | [MLFLOW_SERVER](../servers/mlflow.md) | ✅ | [Seldon MLServer](https://github.com/seldonio/mlserver) | You can try out the `v2` in [this example notebook](../examples/protocol_examples.html). + {% endtab %} + +{% tab title="REST and gRPC Seldon Protocol" %} +* [REST Seldon Protocol](../reference/apis/index.html) + +Seldon is the default protocol for SeldonDeployment resources. You can specify the gRPC protocol by setting `transport: grpc` in your SeldonDeployment resource or ensuring all components in the graph have endpoint.tranport set ot grpc. + +See [example notebook](../examples/protocol_examples.html). +{% endtab %} + +{% tab title="REST and gRPC Tensorflow Protocol" %} + * [REST Tensorflow Protocol definition](https://github.com/tensorflow/serving/blob/master/tensorflow_serving/g3doc/api_rest.md). + * [gRPC Tensorflow Protocol definition](https://github.com/tensorflow/serving/blob/master/tensorflow_serving/apis/prediction_service.proto). + +Activate this protocol by speicfying `protocol: tensorflow` and `transport: rest` or `transport: grpc` in your Seldon Deployment. See [example notebook](../examples/protocol_examples.html). + +For Seldon graphs the protocol will work as expected for single model graphs for Tensorflow Serving servers running as the single model in the graph. For more complex graphs you can chain models: + + * Sending the response from the first as a request to the second. This will be done automatically when you defined a chain of models as a Seldon graph. It is up to the user to ensure the response of each changed model can be fed a request to the next in the chain. + * Only Predict calls can be handled in multiple model chaining. + + +General considerations: + + * Seldon components marked as MODELS, INPUT_TRANSFORMER and OUTPUT_TRANSFORMERS will allow a PredictionService Predict method to be called. + * GetModelStatus for any model in the graph is available. + * GetModelMetadata for any model in the graph is available. + * Combining and Routing with the Tensorflow protocol is not presently supported. + * `status` and `metadata` calls can be asked for any model in the graph + * a non-standard Seldon extension is available to call predict on the graph as a whole: `/v1/models/:predict`. + * The name of the model in the `graph` section of the SeldonDeployment spec must match the name of the model loaded onto the Tensorflow Server. {% endtab %} + +{% endtabs %} + + diff --git a/doc/source/production/optimization.md b/doc/source/production/optimization.md index 3fb3469a3a..962efa311e 100644 --- a/doc/source/production/optimization.md +++ b/doc/source/production/optimization.md @@ -9,7 +9,7 @@ Using the Seldon python wrapper there are various optimization areas one needs t ### Seldon Protocol Payload Types with REST and gRPC -**Note**: Seldon is phasing out support for the Seldon and TensorFlow protocols, transitioning to the industry-standard Open Inference Protocol (OIP). We encourage customers to migrate to OIP, which facilitates seamless integration across various model serving runtimes, supports the development of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience. +**Note**: Seldon is no longer maintaining the Seldon and TensorFlow protocols. Instead, Seldon is adopting the industry-standard Open Inference Protocol (OIP). We strongly encourage customers to use the OIP, which offers seamless integration across diverse model serving runtimes, supports the creation of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience. Depending on whether you want to use REST or gRPC and want to send tensor data the format of the request will have a deserialization/serialization cost in the python wrapper. This is investigated in a [python serialization notebook](../examples/python_serialization.html). diff --git a/doc/source/reference/upgrading.md b/doc/source/reference/upgrading.md index e6f92c89df..578cdd8760 100644 --- a/doc/source/reference/upgrading.md +++ b/doc/source/reference/upgrading.md @@ -93,7 +93,7 @@ Only the v1 versions of the CRD will be supported moving forward. The v1beta1 ve ### Model Health Checks -**Note**: Seldon is phasing out support for the Seldon and TensorFlow protocols, transitioning to the industry-standard Open Inference Protocol (OIP). We encourage customers to migrate to OIP, which facilitates seamless integration across various model serving runtimes, supports the development of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience. +**Note**: Seldon is no longer maintaining the Seldon and TensorFlow protocols. Instead, Seldon is adopting the industry-standard Open Inference Protocol (OIP). We strongly encourage customers to use the OIP, which offers seamless integration across diverse model serving runtimes, supports the creation of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience. We have updated the health checks done by Seldon for the model nodes in your inference graph. If `executor.fullHealthChecks` is set to true then: * For Seldon protocol each node will be probed with `/api/v1.0/health/status`. diff --git a/examples/models/lightgbm_custom_server/iris.ipynb b/examples/models/lightgbm_custom_server/iris.ipynb index 3d81540ca8..d0db169fc5 100644 --- a/examples/models/lightgbm_custom_server/iris.ipynb +++ b/examples/models/lightgbm_custom_server/iris.ipynb @@ -7,7 +7,7 @@ "source": [ "# Custom LightGBM Prepackaged Model Server\n", "\n", - "**Note**: Seldon is phasing out support for the Seldon and TensorFlow protocols, transitioning to the industry-standard Open Inference Protocol (OIP). We encourage customers to migrate to OIP, which facilitates seamless integration across various model serving runtimes, supports the development of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience.\n", + "**Note**: Seldon is no longer maintaining the Seldon and TensorFlow protocols. Instead, Seldon is adopting the industry-standard Open Inference Protocol (OIP). We strongly encourage customers to use the OIP, which offers seamless integration across diverse model serving runtimes, supports the creation of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience.\n", "\n", "\n", "In this notebook we create a new custom LIGHTGBM_SERVER prepackaged server with two versions:\n", diff --git a/notebooks/backwards_compatability.ipynb b/notebooks/backwards_compatability.ipynb index da6f884cad..ea6e94596b 100644 --- a/notebooks/backwards_compatability.ipynb +++ b/notebooks/backwards_compatability.ipynb @@ -13,7 +13,7 @@ " * grpcurl\n", " * pygmentize\n", "\n", - "**Note**: Seldon is phasing out support for the Seldon and TensorFlow protocols, transitioning to the industry-standard Open Inference Protocol (OIP). We encourage customers to migrate to OIP, which facilitates seamless integration across various model serving runtimes, supports the development of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience. \n", + "**Note**: Seldon is no longer maintaining the Seldon and TensorFlow protocols. Instead, Seldon is adopting the industry-standard Open Inference Protocol (OIP). We strongly encourage customers to use the OIP, which offers seamless integration across diverse model serving runtimes, supports the creation of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience.\n", "\n", "## Setup Seldon Core\n", "\n", diff --git a/notebooks/protocol_examples.ipynb b/notebooks/protocol_examples.ipynb index b08ce036b0..cb5b41b438 100644 --- a/notebooks/protocol_examples.ipynb +++ b/notebooks/protocol_examples.ipynb @@ -15,11 +15,10 @@ " \n", "## Examples\n", "\n", - "**Note**: Seldon is phasing out support for the Seldon and TensorFlow protocols, transitioning to the industry-standard Open Inference Protocol (OIP). We encourage customers to migrate to OIP, which facilitates seamless integration across various model serving runtimes, supports the development of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience.\n", - "\n", + "**Note**: Seldon is no longer maintaining the Seldon and TensorFlow protocols. Instead, Seldon is adopting the industry-standard Open Inference Protocol (OIP). We strongly encourage customers to use the OIP, which offers seamless integration across diverse model serving runtimes, supports the creation of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience.\n", + " * [Open Inference Protocol or V2 Protocol](#V2-Protocol-Model)\n", " * [Seldon Protocol](#Seldon-Protocol-Model)\n", " * [Tensorflow Protocol](#Tensorflow-Protocol-Model)\n", - " * [V2 Protocol](#V2-Protocol-Model)\n", " \n", "\n", "## Setup Seldon Core\n", diff --git a/notebooks/server_examples.ipynb b/notebooks/server_examples.ipynb index c27b62f702..3ce53573a9 100644 --- a/notebooks/server_examples.ipynb +++ b/notebooks/server_examples.ipynb @@ -65,13 +65,13 @@ "source": [ "## Serve SKLearn Iris Model\n", "\n", - "**Note**: Seldon is phasing out support for the Seldon and TensorFlow protocols, transitioning to the industry-standard Open Inference Protocol (OIP). We encourage customers to migrate to OIP, which facilitates seamless integration across various model serving runtimes, supports the development of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience.\n", + "**Note**: Seldon is no longer maintaining the Seldon and TensorFlow protocols. Instead, Seldon is adopting the industry-standard Open Inference Protocol (OIP). We strongly encourage customers to use the OIP, which offers seamless integration across diverse model serving runtimes, supports the creation of versatile client and benchmarking tools, and ensures a high-performance, consistent, and unified inference experience.\n", "\n", "In order to deploy SKLearn artifacts, we can leverage the [pre-packaged SKLearn inference server](https://docs.seldon.io/projects/seldon-core/en/latest/servers/sklearn.html).\n", "The exposed API can follow either:\n", + "- Open Inference Protocol or V2 Protocol.\n", + "- Seldon protocol. \n", "\n", - "- The default Seldon protocol. \n", - "- The V2 protocol.\n", "\n" ] },