Merge pull request #72 from jamesfalkner/rh1finalfixes

minor fixes

Author: danieloh30

content/modules/ROOT/assets/images/private-docs/chat-response-hlcn.png

@@ -67,7 +67,7 @@ Run the following command in the VS Code terminal to start Quarkus Dev Mode.
 ./mvnw clean quarkus:dev
 ----
 
-The output should look similar to the following.
+The output should look similar to the following (wait for the ASCII art!):
 
 [.console-output]
 [source,bash]

content/modules/ROOT/assets/images/private-docs/chat-response-rag.png

@@ -62,7 +62,7 @@ There are a three things to take note of in this JSON file.
 
 == The initial set of tests
 
-We have included an initial set of tests which should pass when run against the *Parasol Chat* model.  
+We have included an initial set of tests which should pass when run against the *Parasol Chat* model.
 
 For each of these tests we're provided an expected response, so for example, when we ask the question: *"In one sentence, who founded Parasol Insurance?"* we should get a response similar to: *"Parasol Insurance was founded in 1936 by James Falkner and James Labocki."*
 
@@ -107,7 +107,7 @@ The output should be similar to the following.
 [.console-output]
 [source,bash]
 ----
-npm WARN skipping integrity check for git dependency ssh://[email protected]/kenlimmj/rouge.git 
+npm WARN skipping integrity check for git dependency ssh://[email protected]/kenlimmj/rouge.git
 npm WARN deprecated [email protected]: Glob versions prior to v9 are no longer supported
 npm WARN deprecated [email protected]: This module is not supported, and leaks memory. Do not use it. Check out lru-cache if you want a good and tested way to coalesce async requests by a key value, which is much more comprehensive and powerful.
 
@@ -142,7 +142,7 @@ When the test run is complete you should see.
 
 image::model-testing/run-complete.png[run complete, 800]
 
-Both of the tests should have passed successfully.  
+Both of the tests should have passed successfully.
 
 == Failing the tests
 
@@ -152,7 +152,7 @@ As we discussed above, one of our tests is testing responses to the question: *"
 
 To answer this question our model has been trained with knowledge about the history of Parasol Insurance.
 
-Let's change the model our tests are performed against to an untrained model (*merlinite-7b-lab*).  To do this, open the `.vscode/settings.json` file to `replace` the contents with:
+Let's change the model our tests are performed against to an untrained model (*granite-30-8b-instruct*).  To do this, open the `.vscode/settings.json` file to `replace` the contents with:
 
 [.console-input]
 [source,json,subs="+attributes,macros+"]
@@ -169,7 +169,7 @@ Let's change the model our tests are performed against to an untrained model (*m
 }
 ----
 
-Go back to the `Testing` panel. Then, click on the `Run Tests` to run the tests again.  
+Go back to the `Testing` panel. Then, click on the `Run Tests` to run the tests again.
 
 image::model-testing/run-tests.png[run tests]
 

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

@@ -149,7 +149,11 @@ You should notice that the chatbot can answer these questions based on the claim
 
 image::private-docs/chat-policies-unknown.png[Chatbot questions about policies]
 
-The answer you will get back might be different from the one in the screenshot above, but you'll likely observe that the chatbot struggles with this question, as it doesn't have access to Parasol's specific policies, *in particular the 6 month policy term limit*. It might even respond with an incorrect decision! If only there was a way to automatically retrieve this information and provide it to the chatbot.
+The answer you will get back might be different from the one in the screenshot above, but you'll likely observe that the chatbot struggles with this question, as it doesn't have access to Parasol's specific policies, *in particular the 6 month policy term limit*. It might even respond with an incorrect decision, but sound very authoritative when doing so:
+
+image::private-docs/chat-response-hlcn.png[Chatbot halluncination]
+
+If only there was a way to automatically retrieve this information and provide it to the chatbot so that answers were more accurate!
 
 == Embedding Documents with RAG
 
@@ -314,7 +318,7 @@ import io.quarkiverse.langchain4j.ToolBox;
 ----
 ====
 
-By doing this we have now registered the `NotificationService` file as class that contains one or more `@Tool` annotated methods. These methods become available to the LLM to be called.
+By doing this we have now registered the `NotificationService` file as a class that contains one or more `@Tool` annotated methods. These methods become available to the LLM to be called.
 
 === Convert chat from streaming to synchronous
 

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

@@ -569,8 +569,8 @@ their inquiry and lets them know we are concerned about their health and safety.
 Email addresses are MUST be provided and are ALWAYS one of the 4 addresses
 provided in this system prompt..
 
-Emails informing Parasol Insurance of a new accident or discuss filing a new 
-claim are always classified as NEW CLAIMS and forwarded to [email protected]. 
+Emails informing Parasol Insurance of a new accident or discuss filing a new
+claim are always classified as NEW CLAIMS and forwarded to [email protected].
 
 Emails that are asking for a status update, voicing concerns about taking too
 long to process, or providing additional details about an accident that were
@@ -605,14 +605,14 @@ You MUST ALWAYS respond only with JSON in one of the following ways:
 Here is an example response for a new claim:
 
 Message: "I ran a stop light yesterday and hit another vehicle.  Regards, John Doe"
-{ "address": "[email protected]", "subject": "Customer At-Fault in Multi-Vehicle Collision", 
+{ "address": "[email protected]", "subject": "Customer At-Fault in Multi-Vehicle Collision",
  "message": "Dear John,
- 
+
 We hope you and the other party are ok!  Thank you for promptly informing us of the accident.
- 
+
 I understand that you potentially were at fault in a collision with another vehicle as a result of running a stop light.
 
-I'm forwarding your note to a team that can assist you with your claim.  
+I'm forwarding your note to a team that can assist you with your claim.
 Please be prepared with any associated police reports and photographs.  We look forward to supporting
 you through this process.
 
@@ -638,7 +638,7 @@ Now, you'll notice that this does not look drastically different from before the
 
 Open the `src/main/webui/src/app/components/EmailGenerate/EmailGenerate.tsx` typescript file for the Generate Email view.
 
-At the top of the source file there is a data structured called EmailResponse.  Add `address` of type `string` to the end of the list.
+At the top of the source file there is a data structure called `ResponseData`.  Add `address` of type `string` to the end of the list.
 
 [.console-input]
 [source,javascript,subs="attributes"]
@@ -651,7 +651,7 @@ image::prompt/email-generate-view-data-structure.png[Add "address" to EmailRespo
 Add the following html to the `email-response` div block:
 
 [.console-input]
-[source,javascript,subs="+attributes,macros+"]
+[source,html,subs="+attributes,macros+"]
 ----
             <div id="email-response-address" style={{ fontWeight: 'bold', fontFamily: 'Arial' }}>
               To: {response.address}