From 2b8d608c0eb5acc738f5bb15aea6603585d0f74c Mon Sep 17 00:00:00 2001
From: Rui Vieira <ruidevieira@googlemail.com>
Date: Tue, 25 Jun 2024 16:31:20 +0100
Subject: [PATCH] Change prediction to inference

---
 .../pages/saliency-explanations-on-odh.adoc   | 20 +++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/docs/modules/ROOT/pages/saliency-explanations-on-odh.adoc b/docs/modules/ROOT/pages/saliency-explanations-on-odh.adoc
index bf6a976..baa06d9 100644
--- a/docs/modules/ROOT/pages/saliency-explanations-on-odh.adoc
+++ b/docs/modules/ROOT/pages/saliency-explanations-on-odh.adoc
@@ -1,6 +1,6 @@
 = Saliency explanations on ODH
 
-This tutorial will walk you through setting up and using TrustyAI to provide saliency explanations for model predictions within a OpenShift environment using OpenDataHub. We will deploy a model, configure the environment, and demonstrate how to obtain predictions and their explanations.
+This tutorial will walk you through setting up and using TrustyAI to provide saliency explanations for model inferences within a OpenShift environment using OpenDataHub. We will deploy a model, configure the environment, and demonstrate how to obtain inferences and their explanations.
 
 [NOTE]
 ====
@@ -107,12 +107,12 @@ export TOKEN=$(oc whoami -t)
 
 == Requesting Explanations
 
-=== Issue a Prediction
+=== Request an inference
 
-In order to obtain an explanation, we first need to make a prediction.
-The explanation request will be based on this prediction ID.
+In order to obtain an explanation, we first need to make an inference.
+The explanation request will be based on this inference ID.
 
-Start by sending an inference request to the model to get a prediction. Replace `${TOKEN}` with your actual authorization token.
+Start by sending an inference request to the model to get an inference. Replace `${TOKEN}` with your actual authorization token.
 
 [source,shell]
 ----
@@ -142,10 +142,10 @@ The response will be similar to
 ]
 ```
 
-Extract the latest prediction ID for use in obtaining an explanation.
+Extract the latest inference ID for use in obtaining an explanation.
 
 ```shell
-export PREDICTION_ID=$(curl -skv -H "Authorization: Bearer ${TOKEN}" \
+export INFERENCE_ID=$(curl -skv -H "Authorization: Bearer ${TOKEN}" \
   https://${TRUSTYAI_ROUTE}/info/inference/ids/explainer-test?type=organic | jq -r '.[-1].id')
 ```
 
@@ -153,14 +153,14 @@ export PREDICTION_ID=$(curl -skv -H "Authorization: Bearer ${TOKEN}" \
 
 We will use LIME as our explainer for this tutorial. More information on LIME can be found xref:local-explainers.adoc#LIME[here].
 
-Request a LIME explanation for the selected prediction ID.
+Request a LIME explanation for the selected inference ID.
 
 [source,shell]
 ----
 curl -sk -X POST -H "Authorization: Bearer ${TOKEN}" \
     -H "Content-Type: application/json" \
     -d "{
-    \"predictionId\": \"$PREDICTION_ID\",
+    \"predictionId\": \"$INFERENCE_ID\",
     \"modelConfig\": {
         \"target\": \"modelmesh-serving.${NAMESPACE}.svc.cluster.local:8033\",
         \"name\": \"explainer-test\",
@@ -173,7 +173,7 @@ curl -sk -X POST -H "Authorization: Bearer ${TOKEN}" \
 
 === Results
 
-The output will show the saliency scores and confidence for each input feature used in the prediction.
+The output will show the saliency scores and confidence for each input feature used in the inference.
 
 [source,json]
 ----