SeldonIO · ukclivecox · May 31, 2019 · May 14, 2019 · May 18, 2019 · May 25, 2019
diff --git a/doc/source/examples/istio_examples.nblink b/doc/source/examples/istio_examples.nblink
@@ -0,0 +1,3 @@
+{
+  "path": "../../../notebooks/istio_example.ipynb"
+}
diff --git a/doc/source/examples/notebooks.rst b/doc/source/examples/notebooks.rst
@@ -17,6 +17,7 @@ Notebooks
    Go Model <go_example>
    H2O Java MoJo <h2o_mojo>
    Istio Canary <istio_canary>
+   Istio Examples <istio_examples>   
    Jaeger Tracing <tmpl_model_tracing>
    Keras MNIST <keras_mnist>
    Kubeflow Seldon E2E Pipeline <kubeflow_seldon_e2e_pipeline>

diff --git a/doc/source/index.rst b/doc/source/index.rst
@@ -54,12 +54,19 @@ Seldon Core is an open source platform for deploying machine learning models on
    Annotation-based Configuration <graph/annotations.md>
    Private Docker Registry <graph/private_registries.md>
 
+.. toctree::
+   :maxdepth: 1
+   :caption: Ingress
+
+   Ambassador Ingress <ingress/ambassador.md>
+   Istio Ingress <ingress/istio.md>
+   Seldon OAuth Gateway <ingress/seldon.md>
+
 .. toctree::
    :maxdepth: 1
    :caption: Deployment Options
 
    Helm Charts <graph/helm_charts.md>	     
-   Ambassador Deployment <graph/ambassador.md>	     
    Grafana Analytics <analytics/analytics.md>
    Autoscaling <graph/autoscaling.md>   
 

diff --git a/doc/source/graph/ambassador.md → doc/source/ingress/ambassador.md b/doc/source/graph/ambassador.md → doc/source/ingress/ambassador.md
diff --git a/doc/source/ingress/istio.md b/doc/source/ingress/istio.md
@@ -0,0 +1,51 @@
+# Istio
+
+Seldon core can be used in conjuction with [istio](https://istio.io/). Istio provides an [ingress gateway](https://istio.io/docs/tasks/traffic-management/ingress/) which Seldon Core can automatically wire up new deployments to. The steps to using istio are described below.
+
+## Install Seldon Core Operator
+
+Ensure when you install the seldon-core operator via Helm that you enabled istio. For example:
+
+```bash 
+helm install seldon-core-operator --name seldon-core --set istio.enabled=true --repo https://storage.googleapis.com/seldon-charts --set usage_metrics.enabled=true
+```
+
+You need an istio gateway installed. By default we assume one called seldon-gateway. For example you can create this with the following yaml:
+
+```
+apiVersion: networking.istio.io/v1alpha3
+kind: Gateway
+metadata:
+  name: seldon-gateway
+spec:
+  selector:
+    istio: ingressgateway # use istio default controller
+  servers:
+  - port:
+      number: 80
+      name: http
+      protocol: HTTP
+    hosts:
+    - "*"
+```
+
+If you have your own gateway you will use then you can provide the name when installing the seldon operator. For example if your gateway is called `mygateway` you can install the operator with:
+
+```bash 
+helm install seldon-core-operator --name seldon-core --set istio.enabled=true --set istio.gateway=mygateway --repo https://storage.googleapis.com/seldon-charts --set usage_metrics.enabled=true
+```
+
+You can also provide the gateway on a per Seldon Deployment resource basis by providing it with the annotation `seldon.io/istio-gateway`.
+
+## Traffic Routing
+
+Istio has the capability for fine grained traffic routing to your deployments. This allows:
+
+ * canary updates
+ * green-blue deployments
+ * A/B testing
+
+An example showing canary updates can be found [here](../exmaples/istio_canary.html)
+
+
+
diff --git a/doc/source/ingress/seldon.md b/doc/source/ingress/seldon.md
@@ -0,0 +1,53 @@
+# Seldon OAuth Gateway
+
+Seldon provides an example OAuth gateway you can use. We recommend however that you utilize for production gateway solutions such as Ambassador or istio.
+
+## Install Seldon OAuth Gateway
+
+You can install the Seldon OAuth gateway using Helm:
+
+```bash
+helm install helm-charts/seldon-core-oauth-gateway --name seldon-gateway --repo https://storage.googleapis.com/seldon-charts
+```
+
+## Provide OAuth Credentials
+
+Provide OAuth credentials for your deployments when creating them. You should add `oauth_key` and `oauth_secret` values to your resource. For example:
+
+```
+apiVersion: machinelearning.seldon.io/v1alpha2
+kind: SeldonDeployment
+metadata:
+  labels:
+    app: seldon
+  name: seldon-model
+spec:
+  name: test-deployment
+  oauth_key: oauth-key
+  oauth_secret: oauth-secret
+  predictors:
+  - componentSpecs:
+    - spec:
+        containers:
+        - image: seldonio/mock_classifier:1.0
+          imagePullPolicy: IfNotPresent
+          name: classifier
+          resources:
+            requests:
+              memory: 1Mi
+        terminationGracePeriodSeconds: 1
+    graph:
+      children: []
+      endpoint:
+        type: REST
+      name: classifier
+      type: MODEL
+    labels:
+      version: v1
+    name: example
+    replicas: 1
+```
+
+## Serve Requests
+
+To serve requests from your running deployment via the gateway follow the instructions [here](../workflow/serving.html#api-oauth-gateway)
diff --git a/doc/source/python/python_module.md b/doc/source/python/python_module.md
@@ -37,7 +37,7 @@ The python package contains a module that provides a reference python client for
     * Send data as tensor, TFTensor or ndarray
  * External API
     * Make REST or gRPC calls
-    * Call the API via Ambassador or Seldon's OAUTH API gateway.
+    * Call the API via Ambassador, Istio or Seldon's OAUTH API gateway.
     * Test `predict` or `feedback` endpoints
     * Provide a numpy array, binary data or string data as payload or get random data generated as payload for given shape
     * Send data as tensor, TFTensor or ndarray
@@ -46,7 +46,7 @@ Basic usage of the client is to create a `SeldonClient` object first. For exampl
 
 ```python
 from seldon_core.seldon_client import SeldonClient
-sc = SeldonClient(deployment_name="mymodel",namespace="seldon", ambassador_endpoint="localhost:8003")
+sc = SeldonClient(deployment_name="mymodel",namespace="seldon", gateway_endpoint="localhost:8003")
 ```
 
 Then make calls of various types. For example, to make a random prediction  via the Ambassador gateway using REST:

diff --git a/doc/source/workflow/install.md b/doc/source/workflow/install.md
@@ -14,19 +14,26 @@ First [install Helm](https://docs.helm.sh). When helm is installed you can deplo
 
 ```bash 
 helm install seldon-core-operator --name seldon-core --repo https://storage.googleapis.com/seldon-charts --set usage_metrics.enabled=true
-
 ```
 
 Notes
 
  * You can use ```--namespace``` to install the seldon-core controller to a particular namespace
  * For full configuration options see [here](../reference/helm.md)
 
+For particular ingresses we support you can inform the controller it should activate processing for them.
+
+ * Ambassador
+   * add `--set ambassador.enabled=true` : The controller will add annotations to services it creates so Ambassador can pick them up and wire an endpoint for your deployments.
+ * Istio Gateway
+   * add `--set istio.enabled=true` : The controller will create virtual services and destination rules to wire up endpoints in your istio ingress gateway.
+
 ## Install an Ingress Gateway
 
 We presently support two API Ingress Gateways
 
  * [Ambassador](https://www.getambassador.io/)
+ * [Istio Ingress](https://istio.io/)
  * Seldon Core OAuth Gateway
 
 ### Install Ambassador
@@ -37,10 +44,15 @@ We suggest you install [the official helm chart](https://github.com/helm/charts/
 helm install stable/ambassador --name ambassador --set crds.keep=false
 ```
 
+### Install Istio Ingress Gateway
+
+If you are using istio then the controller will create virtual services for an istio gateway. By default it will assume the gateway `seldon-gateway` as the name of the gateway. To change the default gateway add `--set istio.gateway=XYZ` when installing the seldon-core-operator.
+
 ### Install Seldon OAuth Gateway
+
 This provides a basic OAuth Gateway.
 
-```
+```bash
 helm install seldon-core-oauth-gateway --name seldon-gateway --repo https://storage.googleapis.com/seldon-charts
 ```