openshift · mburke5678 · Aug 28, 2024 · Aug 16, 2024
diff --git a/_attributes/common-attributes.adoc b/_attributes/common-attributes.adoc
@@ -29,10 +29,10 @@
 :ols-release: Developer Preview
 //LLM
 :openai: OpenAI
-:azure-openai: Azure OpenAI
-:watsonx: WatsonX
+:azure-openai: Microsoft Azure OpenAI
+:watsonx: IBM WatsonX
 //Microsoft
-:azure-full: Microsoft Azure
+:azure-official: Microsoft Azure
 //service mesh v3
 :SMProductName: Red Hat OpenShift Service Mesh
 :SMProductShortName: Service Mesh

diff --git a/about/ols-about-openshift-lightspeed.adoc b/about/ols-about-openshift-lightspeed.adoc
@@ -6,12 +6,13 @@ include::_attributes/common-attributes.adoc[]
 
 toc::[]
 
-The following topics provide an overview of {ols-full} and discuss functional requirements.
+The following topics provide an overview of {ols-official} and discuss functional requirements.
 
 include::modules/ols-openshift-lightspeed-overview.adoc[leveloffset=+1]
 include::modules/ols-openshift-requirements.adoc[leveloffset=+1]
 include::modules/ols-large-language-model-requirements.adoc[leveloffset=+1]
-include::modules/ols-about-openshift-ai-vllm.adoc[leveloffset=+2]
+//Xavier wanted to remove vLLM until further testing is performed.
+//include::modules/ols-about-openshift-ai-vllm.adoc[leveloffset=+2]
 include::modules/ols-about-openai.adoc[leveloffset=+2]
 include::modules/ols-about-azure-openai.adoc[leveloffset=+2]
 include::modules/ols-about-watsonx.adoc[leveloffset=+2]

diff --git a/modules/ols-about-azure-openai.adoc b/modules/ols-about-azure-openai.adoc
@@ -5,6 +5,4 @@
 [id="ols-about-azure-openai_{context}"]
 = About Azure OpenAI 
 
-To use {azure-openai} with {ols-full}, you must have access to {azure-openai}. If you have already applied for and received access to {azure-openai}, you can ignore the rest of the information in this topic.
-
-{azure-openai} access currently requires an approval process initiated from within the {azure-full} portal. It can take several days for Microsoft to approve your access. When your access to {azure-openai} is approved, make sure you know which Azure subscription your {azure-openai} access is associated with.
+To use {azure-official} with {ols-full}, you must have access to {azure-openai}.
diff --git a/modules/ols-creating-lightspeed-custom-resource-file-using-cli.adoc b/modules/ols-creating-lightspeed-custom-resource-file-using-cli.adoc
@@ -9,9 +9,7 @@ The Custom Resource (CR) file contains information that the Operator uses to dep
 
 .Prerequisites
 
-* You are logged in to the {ocp-product-title} web console as a user with the `cluster-admin` role. Alternatively, you are logged in to a user account that has permission to create a cluster-scoped custom resource file.
-
-* You have access to the {ocp-short-name} CLI (oc).
+* You have access to the {ocp-short-name} CLI (oc) and are logged in as a user with the `cluster-admin` role. Alternatively, you are logged in to a user account that has permission to create a cluster-scoped custom resource file.
 
 * You have installed the {ols-long} Operator.
 
@@ -40,15 +38,14 @@ spec:
   ols:
     defaultModel: gpt-3.5-turbo
     defaultProvider: myOpenai
-    logLevel: DEBUG
 ----
 +
 [NOTE]
 ====
 For OpenShift AI vLLM use the same configuration as OpenAI but update the URL to point to your Virtual Large Language Model (vLLM) endpoint. If OpenShift Lightspeed operates in the same cluster as the vLLM model serving instance, you can point to the internal OpenShift service hostname instead of exposing vLLM with a route.
 ====
 +
-.Example Azure OpenAI custom resource file
+.Example {azure-openai} custom resource file
 +
 [source,yaml, subs="attributes,verbatim"]
 ----
@@ -61,19 +58,19 @@ spec:
     providers:
       - credentialsSecretRef:
           name: credentials
-        deploymentName: <USE THE NAME OF THE DEPLOYMENT YOU CREATED EARLIER>
+        deploymentName: <azure_ai_deployment_name>
         models:
           - name: gpt-35-turbo-16k
         name: myAzure
         type: azure_openai
-        url: <USE THE URL YOU RECORDED EARLIER>
+        url: <azure_ai_deployment_url>
   ols:
     defaultModel: gpt-35-turbo-16k
     defaultProvider: myAzure
     logLevel: DEBUG
 ----
 +
-.Example WatsonX custom resource file
+.Example {watsonx} custom resource file
 +
 [source,yaml, subs="attributes,verbatim"]
 ----
@@ -88,8 +85,8 @@ spec:
         type: watsonx
         credentialsSecretRef:
           name: credentials
-        url: <APPROPRIATE URL FROM REGIONAL URLS>
-        projectId: <your project ID>
+        url: <ibm_watsonx_deployment_name>
+        projectId: <ibm_watsonx_project_id>
         models:
           - name: ibm/granite-13b-chat-v2
   ols:

diff --git a/modules/ols-creating-lightspeed-custom-resource-file-using-web-console.adoc b/modules/ols-creating-lightspeed-custom-resource-file-using-web-console.adoc
@@ -11,8 +11,6 @@ The Custom Resource (CR) file contains information that the Operator uses to dep
 
 * You are logged in to the {ocp-product-title} web console as a user with the `cluster-admin` role. Alternatively, you are logged in to a user account that has permission to create a cluster-scoped custom resource file.
 
-* You have access to the {ocp-short-name} CLI (oc).
-
 * You have installed the {ols-long} Operator.
 
 .Procedure 
@@ -42,15 +40,9 @@ spec:
   ols:
     defaultModel: gpt-3.5-turbo
     defaultProvider: myOpenai
-    logLevel: DEBUG
 ----
 +
-[NOTE]
-====
-For OpenShift AI vLLM use the same configuration as OpenAI but update the URL to point to your Virtual Large Language Model (vLLM) endpoint. If OpenShift Lightspeed operates in the same cluster as the vLLM model serving instance, you can point to the internal OpenShift service hostname instead of exposing vLLM with a route.
-====
-+
-.Example Azure OpenAI custom resource file
+.Example {azure-openai} custom resource file
 +
 [source,yaml, subs="attributes,verbatim"]
 ----
@@ -63,19 +55,18 @@ spec:
     providers:
       - credentialsSecretRef:
           name: credentials
-        deploymentName: <USE THE NAME OF THE DEPLOYMENT YOU CREATED EARLIER>
+        deploymentName: <azure_ai_deployment_name>
         models:
           - name: gpt-35-turbo-16k
         name: myAzure
         type: azure_openai
-        url: <USE THE URL YOU RECORDED EARLIER>
+        url: <azure_ai_deployment_url>
   ols:
     defaultModel: gpt-35-turbo-16k
     defaultProvider: myAzure
-    logLevel: DEBUG
 ----
 +
-.Example WatsonX custom resource file
+.Example {watsonx} custom resource file
 +
 [source,yaml, subs="attributes,verbatim"]
 ----
@@ -90,14 +81,13 @@ spec:
         type: watsonx
         credentialsSecretRef:
           name: credentials
-        url: <APPROPRIATE URL FROM REGIONAL URLS>
-        projectId: <your project ID>
+        url: <ibm_watsonx_deployment_name>
+        projectId: <ibm_watsonx_project_id>
         models:
           - name: ibm/granite-13b-chat-v2
   ols:
     defaultModel: ibm/granite-13b-chat-v2
     defaultProvider: myWatsonx
-    logLevel: DEBUG
 ----
 
 . Click *Create*.
diff --git a/modules/ols-creating-the-credentials-secret-using-cli.adoc b/modules/ols-creating-the-credentials-secret-using-cli.adoc
@@ -5,21 +5,19 @@
 [id="ols-creating-the-credentials-secret-using-cli_{context}"]
 = Creating the credentials secret using the command line
 
-Create a file that is associated with the secret key used to access the API of your LLM provider.
+Create a file that is associated with the secret key used to access the API of your LLM provider. You can use API tokens to authenticate your LLM provider. Additionally, {azure-official} supports authentication using Entra ID.
 
 .Prerequisites
 
-* You are logged in to the {ocp-product-title} web console as a user with the `cluster-admin` role. Alternatively, you are logged in to a user account that has permission to create a secret to store the Provider tokens.
-
-* You have access to the {ocp-short-name} CLI (oc).
+* You have access to the {ocp-short-name} CLI (oc) as a user with the `cluster-admin` role. Alternatively, you are logged in to a user account that has permission to create a secret to store the Provider tokens.
 
 * You have installed the {ols-long} Operator.
 
-.Pocedure 
+.Procedure 
 
 . Create a file that contains the following YAML content:
 +
-.Example credential secret
+.Example credential secret for LLM provider
 +
 [source,yaml, subs="attributes,verbatim"]
 ----
@@ -34,10 +32,21 @@ stringData:
 ----
 <1> The `apitoken` is not `base64` encoded.
 +
-[NOTE]
-====
-The YAML element is always `apitoken` regardless of what the LLM provider calls the access details.
-====
+.Example credential secret for {azure-official} {openai}
++
+[source,yaml, subs="attributes,verbatim"]
+----
+apiVersion: v1
+data:
+  client_id: <base64_encoded_client_id>
+  client_secret: <base64_encoded_client_secret>
+  tenant_id: <base64_encoded_tenant_id>
+kind: Secret
+metadata:
+  name: azure-api-keys
+  namespace: openshift-lightspeed
+type: Opaque
+----
 
 . Run the following command to create the secret:
 +

diff --git a/modules/ols-creating-the-credentials-secret-using-web-console.adoc b/modules/ols-creating-the-credentials-secret-using-web-console.adoc
@@ -5,23 +5,21 @@
 [id="ols-creating-the-credentials-secret-using-web-console_{context}"]
 = Creating the credentials secret using the web console
 
-Create a file that is associated with the secret key used to access the API of your LLM provider.
+Create a file that is associated with the secret key used to access the API of your LLM provider. You can use API tokens to authenticate your LLM provider. Additionally, {azure-official} supports authentication using Entra ID.
 
 .Prerequisites
 
 * You are logged in to the {ocp-product-title} web console as a user with the `cluster-admin` role. Alternatively, you are logged in to a user account that has permission to create a secret to store the Provider tokens.
 
-* You have access to the {ocp-short-name} CLI (oc).
-
 * You have installed the {ols-long} Operator.
 
-.Pocedure 
+.Procedure 
 
 . Click the plus button in the upper-right corner of the {ocp-short-name} web console.
 
 . Paste the following YAML content into the text area:
 +
-.Example credential secret
+.Example credential secret for LLM provider
 +
 [source,yaml, subs="attributes,verbatim"]
 ----
@@ -39,4 +37,22 @@ stringData:
 [NOTE]
 ====
 The YAML element is always `apitoken` regardless of what the LLM provider calls the access details.
-====
+====
++
+.Example credential secret for {azure-openai}
++
+[source,yaml, subs="attributes,verbatim"]
+----
+apiVersion: v1
+data:
+  client_id: <base64_encoded_client_id>
+  client_secret: <base64_encoded_client_secret>
+  tenant_id: <base64_encoded_tenant_id>
+kind: Secret
+metadata:
+  name: azure-api-keys
+  namespace: openshift-lightspeed
+type: Opaque
+----
+
+. Click *Create*.
diff --git a/modules/ols-large-language-model-requirements.adoc b/modules/ols-large-language-model-requirements.adoc
@@ -1,6 +1,6 @@
 :_mod-docs-content-type: CONCEPT
 [id="ols-large-language-model-requirements"]
-= Large Language Model (LLM) Requirements 
+= Large Language Model (LLM) requirements 
 :context: ols-large-language-model-requirements
 
 As part of the {ols-release}  release, {ols-long} relies on Software as a Service (SaaS) LLM providers. You will need to have either a trial or paid subscription that allows for API access to completions and inferences with one of the following providers: