Merge branch 'rh-rad-ai-roadshow:main' into main

Author: glroland

content/modules/ROOT/pages/index.adoc

@@ -12,11 +12,11 @@ Although we use the insurance industry in this workshop the principles are widel
 
 Throughout this workshop, you as a developer will be interfacing with a variety of LLMs deployed on *Red Hat OpenShift AI* and designed for different use cases. Some of these have been fine-tuned with Parasol's private corporate data to demonstrate how organizations like Parasol can achieve business value with AI without giving away their secrets. The models you will use:
 
-* https://huggingface.co/instructlab/merlinite-7b-lab[Merlinite 7B^] - This model is derived from a https://huggingface.co/mistralai[Mistral model^], and trained with the https://arxiv.org/abs/2403.01081[LAB methodology^] and a https://github.com/instructlab/taxonomy[community taxonomy] of data. It has not been tuned with Parasol-specific data.
+* https://huggingface.co/ibm-granite/granite-3.0-8b-instruct[IBM Granite-3.0-8B-Instruct^] - This model is developed using a diverse set of techniques with a structured chat format, including supervised finetuning, model alignment using reinforcement learning, and model merging. It has not been tuned with Parasol-specific data.
 
-* **parasol-chat** - This model is derived from the https://huggingface.co/instructlab/granite-7b-lab[InstructLab's Granite model^] and has been fine-tuned using the https://github.com/instructlab/community[InstructLAB project] with a https://github.com/rh-rad-ai-roadshow/parasol-taxonomy[Parasol-specific dataset^]. The name _chat_ implies that this is primarily useful for conversations, and can respond with knowledge of Parasol's private data.
+* **parasol-chat** - This model is derived from the https://huggingface.co/ibm-granite/granite-3.0-8b-instruct[IBM Granite-3.0-8B-Instruct^] and has been fine-tuned using the https://github.com/instructlab/community[InstructLAB project] with a https://github.com/rh-rad-ai-roadshow/parasol-taxonomy[Parasol-specific dataset^]. The name _chat_ implies that this is primarily useful for conversations, and can respond with knowledge of Parasol's private data.
 
-* **parasol-instruct** - This model is derived from https://huggingface.co/ibm-granite/granite-7b-instruct[IBM Granite Instruct], and also fine-tuned as above with Parasol-specific data. The name _instruct_ implies that this is primarily good at following instructions to complete a task. This is useful when you want the model to follow explicit instructions, such as "Respond only with JSON with the following schema: {...}".
+* **parasol-instruct** - This model is derived from https://huggingface.co/ibm-granite/granite-3.0-8b-instruct[IBM Granite-3.0-8B-Instruct^], and also fine-tuned as above with Parasol-specific data. The name _instruct_ implies that this is primarily good at following instructions to complete a task. This is useful when you want the model to follow explicit instructions, such as "Respond only with JSON with the following schema: {...}".
 
 * **parasol-tools** - This model is based on the https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct[Meta Llama Instruct^] model(s) and has specifically been trained to use agents (also called tools) to complete tasks that you as a developer instruct give it. This is used for "Agentic" applications that provide agents that can do specific tasks like send an email, calculate math problems, and more.
 

content/modules/ROOT/pages/module-discovery.adoc

@@ -274,31 +274,31 @@ Select the file `marty-mcfly-auto.pdf`, and click `Open`.
 
 image::discovery/text-summarization-open-claim.png[Podman AI Lab Text Summarization Open Claim]
 
-[NOTE]
-====
-If you see the following error message, the latest receipe has not been pulled to the RHEL virtual machine yet.
+// [NOTE]
+// ====
+// If you see the following error message, the latest receipe has not been pulled to the RHEL virtual machine yet.
 
-image::discovery/summerizer-error.png[Summerizer Error]
+// image::discovery/summerizer-error.png[Summerizer Error]
 
-You can fix this by pulling the lastest recipe from GitHub. 
+// You can fix this by pulling the lastest recipe from GitHub. 
 
-Open a new terminal (_Activities > Show Applications > Terminal_) and run the following command:
+// Open a new terminal (_Activities > Show Applications > Terminal_) and run the following command:
 
-[.console-input]
-[source,shell,subs="+attributes,macros+"]
-----
-cd /home/instruct/.local/share/containers/podman-desktop/extensions-storage/redhat.ai-lab/summarizer/recipes/natural_language_processing/summarizer
-git pull origin main
-----
+// [.console-input]
+// [source,shell,subs="+attributes,macros+"]
+// ----
+// cd /home/instruct/.local/share/containers/podman-desktop/extensions-storage/redhat.ai-lab/summarizer/recipes/natural_language_processing/summarizer
+// git pull origin main
+// ----
 
-Restart the recipe to re-build the container with the updated code.
+// Restart the recipe to re-build the container with the updated code.
 
-image::discovery/text-summarization-restart.png[Podman AI Lab Text Summarization Application Restart]
+// image::discovery/text-summarization-restart.png[Podman AI Lab Text Summarization Application Restart]
 
-Since the source code has changed, you may be notified from Podman AI Lab that the hash has changed. This is expected behavior, and you can select *Continue* to proceed building the application container image with the updated code.
+// Since the source code has changed, you may be notified from Podman AI Lab that the hash has changed. This is expected behavior, and you can select *Continue* to proceed building the application container image with the updated code.
 
-image::discovery/text-summarization-hash-change.png[Podman AI Lab Text Summarization Hash Change]
-====
+// image::discovery/text-summarization-hash-change.png[Podman AI Lab Text Summarization Hash Change]
+// ====
 
 ==== Review the summarization that is generated from the claim
 
@@ -380,8 +380,6 @@ image::discovery/text-summarization-app-refine.png[Podman AI Lab Text Summarizat
 
 By updating the template with these specific requirements, you can tailor the summarization output to provide more detailed and relevant information for insurance claims processing at Parasol Insurance.
 
-==== Save your changes
-
 ==== Switch back to Podman Desktop and to the running `Summarizer` recipe
 
 ==== Restart the recipe to re-build the container with the updated code

content/modules/ROOT/pages/module-ilab.adoc

@@ -112,7 +112,7 @@ sh parasol-insurance/scripts/run-parasol-app.sh
 This script will perform the following actions:
 
 * Build the Quarkus (_parasol-insurnce_) application
-* Run the Quarkus application locally in the REHL VM
+* Run the Quarkus application locally in the RHEL VM
 
 It will take a few minutes to complete.
 
@@ -273,7 +273,7 @@ image::ilab/ilab-taxonomy-qna.png[New folder]
 Enter the filename `qna.yaml` to create the file. Then, copy in the following content into the file (using the special copy/paste procedure as before):
 
 [.console-input]
-[source,yaml,subs="+attributes,macros+"]
+[source,yaml]
 ----
 include::https://raw.githubusercontent.com/rh-rad-ai-roadshow/parasol-taxonomy/refs/heads/main/knowledge/economy/finance/insurance/parasol/qna.yaml[]
 
@@ -517,4 +517,4 @@ This exercise showed how organizations can leverage fine tuning with InstructLab
 * You gained hands-on experience in *training and serving* a customized AI model
 * You understand the *benefits and limitations* of fine-tuning compared to other AI customization methods
 
-These skills and tools will be invaluable as you continue to develop AI-enabled applications at Parasol Insurance, allowing you to quickly iterate on ideas and integrate powerful AI capabilities into your workflow.
+These skills and tools will be invaluable as you continue to develop AI-enabled applications at Parasol Insurance, allowing you to quickly iterate on ideas and integrate powerful AI capabilities into your workflow.

content/modules/ROOT/pages/module-model-testing.adoc

@@ -160,9 +160,9 @@ Let's change the model our tests are performed against to an untrained model (*m
 {
     "jest": {
         "nodeEnv": {
-            "PARASOL_MODEL_URL": "http://merlinite-7b-lab-predictor.aiworkshop.svc.cluster.local:8080/v1/chat/completions",
+            "PARASOL_MODEL_URL": "http://granite-30-8b-instruct-predictor.aiworkshop.svc.cluster.local:8080/v1/chat/completions",
             "EMBEDDING_MODEL_URL": "http://parasol-embedding-predictor.aiworkshop.svc.cluster.local:8080/v1",
-            "PARASOL_MODEL_NAME": "merlinite-7b-lab"
+            "PARASOL_MODEL_NAME": "granite-30-8b-instruct"
         },
         "rootPath": "prompt-testing"
     }

content/modules/ROOT/pages/module-private-docs.adoc

@@ -365,7 +365,6 @@ Open `src/main/resources/application.properties` and overwrite these lines:
 
 [source,properties]
 ----
-quarkus.langchain4j.openai.parasol-chat.chat-model.stop=DONE,done,stop,STOP
 quarkus.langchain4j.openai.parasol-chat.chat-model.model-name=parasol-chat
 quarkus.langchain4j.openai.parasol-chat.base-url=http://parasol-chat-predictor.aiworkshop.svc.cluster.local:8080/v1
 ----
@@ -375,7 +374,6 @@ with:
 [.console-input]
 [source,properties,subs="+attributes,macros+"]
 ----
-# quarkus.langchain4j.openai.parasol-chat.chat-model.stop=DONE,done,stop,STOP
 quarkus.langchain4j.openai.parasol-chat.chat-model.model-name=llama3.1
 quarkus.langchain4j.openai.parasol-chat.base-url=http://parasol-tools.aiworkshop.svc.cluster.local/v1
 ----

content/modules/ROOT/pages/module-prompt.adoc

@@ -680,7 +680,7 @@ public record EmailResponse(String subject, String message, String address) { }
 
 image::prompt/new-field-added-to-email-response.png[Add "address" field to EmailResponse Record]
 
-Now let's revisit the https://parasol-app-{user}-dev-parasol-app-{user}-dev.{openshift_cluster_ingress_domain}[web form^] and test out the new AI-generated attribute:
+Now let's revisit the https://{user}-parasol-insurance-parasol-webui.{openshift_cluster_ingress_domain}[web form^] and test out the new AI-generated attribute:
 
 - Reload the Email generate page. It take 10 - 20 seconds to recompile and apply the new prompt in the Quarkus dev mode.
 - Copy and paste the new claim #1 example from the prior section into the form.