fix: update torchserve readme links (kubeflow#2394)

* fix: update readme doc Signed-off-by: Jagadeesh J <jagadeeshj@ideas2it.com> * Update torchserve transformer doc Signed-off-by: Jagadeesh J <jagadeeshj@ideas2it.com> * fix: website url Signed-off-by: Jagadeesh J <jagadeeshj@ideas2it.com> Signed-off-by: Jagadeesh J <jagadeeshj@ideas2it.com> Co-authored-by: Dan Sun <dsun20@bloomberg.net>
magdalenakuhn17 · Aug 25, 2022 · 94b1fab · 94b1fab
1 parent ba77c30
commit 94b1fab
Show file tree

Hide file tree

Showing 16 changed files with 17 additions and 17 deletions.
diff --git a/docs/samples/logger/basic/README.md b/docs/samples/logger/basic/README.md
@@ -46,7 +46,7 @@ Let's apply this YAML:
 kubectl create -f sklearn-logging.yaml
 ```
 
-We can now send a request to the sklearn model. Check the README [here](https://kserve.github.io/website/get_started/first_isvc/#3-determine-the-ingress-ip-and-ports)
+We can now send a request to the sklearn model. Check the README [here](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports)
 to learn how to determine the INGRESS_HOST and INGRESS_PORT used in curling the InferenceService.
 
 ```

diff --git a/docs/samples/logger/knative-eventing/README.md b/docs/samples/logger/knative-eventing/README.md
@@ -102,7 +102,7 @@ Let's apply this YAML:
 kubectl create -f sklearn-logging.yaml
 ```
 
-We can now send a request to the sklearn model. Check the README [here](https://kserve.github.io/website/get_started/first_isvc/#3-determine-the-ingress-ip-and-ports)
+We can now send a request to the sklearn model. Check the README [here](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports)
 to learn how to determine the INGRESS_HOST and INGRESS_PORT used in curling the InferenceService.
 
 ```

diff --git a/docs/samples/v1beta1/custom/prebuilt-image/README.md b/docs/samples/v1beta1/custom/prebuilt-image/README.md
@@ -20,7 +20,7 @@ inferenceservice.serving.kserve.io/custom-prebuilt-image
 ```
 
 ## Run a prediction
-The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/get_started/first_isvc/#3-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 This example uses the [codait/max-object-detector](https://github.com/IBM/MAX-Object-Detector) image. The Max Object Detector api server expects a POST request to the `/model/predict` endpoint that includes an `image` multipart/form-data and an optional `threshold` query string.
 

diff --git a/docs/samples/v1beta1/custom/torchserve/README.md b/docs/samples/v1beta1/custom/torchserve/README.md
@@ -35,7 +35,7 @@ $inferenceservice.serving.kubeflow.org/torchserve-custom created
 
 ## Run a prediction
 
-The first step is to [determine the ingress IP and ports](../../../../../README.md#determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 Download input image:
 

diff --git a/docs/samples/v1beta1/custom/torchserve/bert-sample/hugging-face-bert-sample.md b/docs/samples/v1beta1/custom/torchserve/bert-sample/hugging-face-bert-sample.md
@@ -95,7 +95,7 @@ $inferenceservice.serving.kubeflow.org/torchserve-bert created
 
 ## Run a prediction
 
-The first step is to [determine the ingress IP and ports](../../../../../../README.md#determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 ```bash
 MODEL_NAME=torchserve-bert

diff --git a/docs/samples/v1beta1/custom/torchserve/docs/autoscaling.md b/docs/samples/v1beta1/custom/torchserve/docs/autoscaling.md
@@ -35,7 +35,7 @@ $inferenceservice.serving.kserve.io/torchserve-custom created
 
 ## Run a prediction
 
-The first step is to [determine the ingress IP and ports](../../../../../../README.md#determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 ### Steps
 

diff --git a/docs/samples/v1beta1/custom/torchserve/docs/canary.md b/docs/samples/v1beta1/custom/torchserve/docs/canary.md
@@ -53,7 +53,7 @@ $inferenceservice.serving.kserve.io/torchserve-custom created
 
 ## Run a prediction
 
-The first step is to [determine the ingress IP and ports](../../../../../../README.md#determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 ```bash
 MODEL_NAME=torchserve-custom

diff --git a/docs/samples/v1beta1/custom/torchserve/docs/metrics.md b/docs/samples/v1beta1/custom/torchserve/docs/metrics.md
@@ -100,7 +100,7 @@ $inferenceservice.serving.kserve.io/torchserve-custom created
 
 ## Run a prediction
 
-The first step is to [determine the ingress IP and ports](../../../../../../README.md#determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 ## Inference
 

diff --git a/docs/samples/v1beta1/onnx/README.md b/docs/samples/v1beta1/onnx/README.md
@@ -18,7 +18,7 @@ $ inferenceservice.serving.kserve.io/style-sample configured
 ## Run a sample inference
 
 1. Setup env vars
-The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/get_started/first_isvc/#3-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 ```
 export MODEL_NAME=style-sample

diff --git a/docs/samples/v1beta1/sklearn/v1/README.md b/docs/samples/v1beta1/sklearn/v1/README.md
@@ -53,7 +53,7 @@ Expected Output
 $ inferenceservice.serving.kserve.io/sklearn-iris created
 ```
 ## Run a prediction
-The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/get_started/first_isvc/#3-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 ```
 MODEL_NAME=sklearn-iris

diff --git a/docs/samples/v1beta1/torchserve/autoscaling/README.md b/docs/samples/v1beta1/torchserve/autoscaling/README.md
@@ -2,7 +2,7 @@
 KServe supports the implementation of Knative Pod Autoscaler (KPA) and Kubernetes’ Horizontal Pod Autoscaler (HPA).
 The features and limitations of each of these Autoscalers are listed below.
 
-IMPORTANT: If you want to use Kubernetes Horizontal Pod Autoscaler (HPA), you must install [HPA extension](https://knative.dev/docs/install/any-kubernetes-cluster/#optional-serving-extensions)
+IMPORTANT: If you want to use Kubernetes Horizontal Pod Autoscaler (HPA), you must install [HPA extension](https://knative.dev/docs/install/yaml-install/serving/install-serving-with-yaml/#install-optional-serving-extensions)
  after you install Knative Serving.
 
 Knative Pod Autoscaler (KPA)
@@ -66,7 +66,7 @@ $inferenceservice.serving.kserve.io/torchserve created
 
 ## Run inference with concurrent requests
 
-The first step is to [determine the ingress IP and ports](../../../../../README.md#determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 Install hey load generator 
 ```bash

diff --git a/docs/samples/v1beta1/torchserve/canary/README.md b/docs/samples/v1beta1/torchserve/canary/README.md
@@ -58,7 +58,7 @@ torchserve-predictor-default-kxp96   torchserve-predictor-default   torchserve-p
 
 ## Run a prediction
 
-The first step is to [determine the ingress IP and ports](../../../../../README.md#determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 ```bash
 MODEL_NAME=mnist

diff --git a/docs/samples/v1beta1/torchserve/metrics/README.md b/docs/samples/v1beta1/torchserve/metrics/README.md
@@ -57,7 +57,7 @@ $inferenceservice.serving.kserve.io/torch-metrics created
 
 ## Run a prediction
 
-The first step is to [determine the ingress IP and ports](../../../../../README.md#determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 ## Inference
 

diff --git a/docs/samples/v1beta1/torchserve/v1/README.md b/docs/samples/v1beta1/torchserve/v1/README.md
@@ -30,7 +30,7 @@ Expected Output
 $inferenceservice.serving.kserve.io/torchserve created
 ```
 
-The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/get_started/first_isvc/#3-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 ```bash
 MODEL_NAME=mnist

diff --git a/docs/samples/v1beta1/torchserve/v2/README.md b/docs/samples/v1beta1/torchserve/v2/README.md
@@ -29,7 +29,7 @@ $inferenceservice.serving.kserve.io/torchserve-mnist-v2 created
 
 ## Inference with V2 REST Protocol
 
-The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/get_started/first_isvc/#3-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 ```bash
 MODEL_NAME=mnist

diff --git a/docs/samples/v1beta1/transformer/torchserve_image_transformer/README.md b/docs/samples/v1beta1/transformer/torchserve_image_transformer/README.md
@@ -108,7 +108,7 @@ inferenceservice.serving.kserve.io/torchserve-transformer created
 
 ## Run a prediction
 
-The first step is to [determine the ingress IP and ports](../../../../../README.md#determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
+The first step is to [determine the ingress IP and ports](https://kserve.github.io/website/master/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) and set `INGRESS_HOST` and `INGRESS_PORT`
 
 ```bash
 SERVICE_NAME=torchserve-transformer