RHIDP-12721: CQA 2.1 compliance for integrate_interacting-with-developer-lightspeed-for-rhdh (#1943)

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

Author: themr0c

build/scripts/cqa-10-titles-are-brief-complete-and-descriptive.sh

@@ -460,7 +460,7 @@ if [ "$EXPECTED_FORM" = "imperative" ]; then
     if [[ ! "$FIRST_WORD_CHECK" =~ ^\{.*\}$ ]]; then
         FIRST_LOWER=$(echo "$FIRST_WORD_CHECK" | tr '[:upper:]' '[:lower:]')
         # Known valid imperative verbs (from gerund_to_imperative + common doc verbs)
-        KNOWN_IMPERATIVES=" run set get put cut stop drop map plan scan ship shop skip snap spin split step strip swap tap trim wrap begin configure create enable disable manage upgrade update remove delete edit resolve authorize validate customize integrate migrate generate define override retrieve prepare scale secure authenticate automate bootstrap restore replace browse close compose describe ensure use include invoke provide produce reduce release require subscribe change locate navigate operate isolate install deploy build add test monitor check import export connect disconnect adjust restart start register unregister assign review access fetch search find provision encrypt mount unmount attach detach extend limit inspect trigger troubleshoot understand publish select track transform view verify modify specify apply send download design delegate determine "
+        KNOWN_IMPERATIVES=" run set get put cut stop drop map plan scan ship shop skip snap spin split step strip swap tap trim wrap begin configure create enable disable manage upgrade update remove delete edit resolve authorize validate customize integrate migrate generate define override retrieve prepare scale secure authenticate automate bootstrap restore replace browse close compose describe ensure use include invoke provide produce reduce release require subscribe change locate navigate operate isolate install deploy build add test monitor check import export connect disconnect adjust restart start register unregister assign review access fetch search find provision encrypt mount unmount attach detach extend limit inspect trigger troubleshoot understand publish select track transform view verify modify specify apply send download design delegate determine gather interact "
         if ! echo "$KNOWN_IMPERATIVES" | grep -q " ${FIRST_LOWER} "; then
             echo "  ⚠ Title starts with '${FIRST_WORD_CHECK}' which is not a recognized imperative verb (possible truncation?)"
             WILL_CHANGE=true

modules/shared/con-about-bring-your-own-model.adoc

@@ -4,7 +4,7 @@
 = About Bring Your Own Model
 
 [role="_abstract"]
-{ls-short} does not provide its own inference services, but uses a _Bring Your Own Model_ approach. This means that you can configure the {lcs-name} to talk to the inference server or service of your choice. This also means that you are responsible for ensuring that the configured service meets your particular company policies and legal requirements, including any applicable terms with the third-party model provider.
+{ls-short} uses a _Bring Your Own Model_ approach, letting you connect {lcs-name} to any OpenAI API-compatible inference service.
 //Add the cross reference to "Bring your own model"
 The only technical requirements for inference services are:
 

modules/shared/con-about-data-use.adoc

@@ -4,6 +4,6 @@
 = About data use
 
 [role="_abstract"]
-{ls-short} is a virtual assistant you interact with using natural language. Using the {ls-short} interface, you send chat messages that {ls-short} transforms and sends to the large language model (LLM) provider you have configured for your environment. These messages could potentially contain information provided by your users about themselves, your cluster, cluster resources, or other aspects of your business or working environment.
+{ls-short} sends your chat messages to the large language model (LLM) provider configured for your environment. These messages could potentially contain information about your users, cluster, or business environment.
 
 {ls-short} has limited capabilities to filter or redact the information you provide to the LLM. Do not enter information into {ls-short} that you do not want to send to the LLM provider. To remind end users not to share private or confidential information, {ls-short} begins each new chat with an 'Important' message asking them not to “include personal or sensitive information” in their chat messages.

modules/shared/con-about-feedback-collection.adoc

@@ -4,4 +4,4 @@
 = About feedback collection
 
 [role="_abstract"]
-{ls-short} collects feedback from users who engage with the feedback feature in the virtual assistant interface. If a user submits feedback, the feedback score (thumbs up or down), text feedback (if entered), the user query, and the LLM provider response are stored locally in the file system of the Pod. {company-name} does not have access to the collected feedback data.
+{ls-short} stores user feedback submissions, including scores and text, locally in the Pod file system. {company-name} does not have access to the collected feedback data.

modules/shared/con-about.adoc

@@ -50,7 +50,7 @@ Alternatively, if you prefer to test it locally first, you can try {ls-short} us
 ----
 ====
 
-image::shared/homepage-lightspeed-fab.png[]
+image::shared/homepage-lightspeed-fab.png["Lightspeed chatbot on the home page"]
 
 .Additional resources
 * https://github.com/redhat-developer/rhdh-local/blob/main/README.md[{product-local-very-short}]

modules/shared/con-large-language-model-llm-requirements.adoc

@@ -4,7 +4,7 @@
 = Large language model (LLM) requirements
 
 [role="_abstract"]
-{ls-short} follows a _Bring Your Own Model_ approach. This model means that to function, {ls-short} requires access to a large language model (LLM) which you must provide. An LLM is a type of generative AI that interprets natural language and generates human-like text or audio responses. When an LLM is used as a virtual assistant, the LLM can interpret questions and provide answers in a conversational manner.
+{ls-short} follows a _Bring Your Own Model_ approach, requiring you to provide access to a large language model (LLM). You must configure your preferred LLM provider during installation.
 
 LLMs are usually provided by a service or server. Because {ls-short} does not provide an LLM for you, you must configure your preferred LLM provider during installation. You can configure the underlying Llama Stack server to integrate with several LLM `providers` that offer compatibility with the OpenAI API including the following inference providers:
 

modules/shared/con-ollama.adoc

@@ -4,7 +4,7 @@
 = Ollama
 
 [role="_abstract"]
-Ollama is a powerful and easy-to-use open-source project that simplifies the process of running large language models (LLMs) locally on your computer. It provides a simple command-line interface for downloading, managing, and running a wide variety of open-source models, such as Llama 3, Mistral, and many others, all without requiring a dedicated server or cloud service. By abstracting away the complex setup and dependencies, Ollama makes it accessible for developers, researchers, and enthusiasts to experiment with, build on, and integrate state-of-the-art LLMs into their applications directly from their personal machines.
+Ollama is an open-source tool that simplifies running large language models (LLMs) locally. It provides a command-line interface for downloading, managing, and running open-source models such as Llama 3 and Mistral.
 
 The open source Ollama server in container form provides a convenient local testbed for LLM models that is very accessible and easily controlled.
 

modules/shared/con-supported-architecture-for.adoc

@@ -8,7 +8,7 @@
 
 The {lcs-short} container acts as the intermediary layer, which interfaces with and manages the Llama Stack service.
 
-image::integrate_interacting-with-developer-lightspeed-for-rhdh/developer-lightspeed-architecture-1-8-0.png[]
+image::integrate_interacting-with-developer-lightspeed-for-rhdh/developer-lightspeed-architecture-1-8-0.png["Lightspeed supported architecture diagram"]
 
 .Additional resources
 * link:https://access.redhat.com/support/policy/updates/developerhub[{product} Life Cycle and supported platforms]

modules/shared/con-vllm.adoc

@@ -4,7 +4,7 @@
 = vLLM
 
 [role="_abstract"]
-vLLM is an open-source, high-throughput serving engine for large language models (LLMs) that significantly improves upon traditional serving systems. It achieves this by introducing several key optimizations to reduce memory usage and eliminate redundant computations. vLLM prominently increases the number of concurrent requests an LLM can handle, making it a powerful tool for deploying and scaling LLM-based applications.
+vLLM is an open-source, high-throughput serving engine for large language models (LLMs). It optimizes memory usage and increases the number of concurrent requests an LLM can handle.
 
 .Additional resources
 * link:https://docs.vllm.ai/en/stable/[vLLM documentation]

modules/shared/proc-customize-the-chat-history-storage-in.adoc

@@ -4,7 +4,7 @@
 = Customize the chat history storage in {ls-short}
 
 [role="_abstract"]
-By default, the {ls-short} service stores chat history in a non-persistent local SQL database within the {lcs-short} container. This means that chat history is lost if you create and use a new {lcs-short} sidecar. You can manually configure {ls-short} to store the chat history persistently as a long-term backup with PostgreSQL by updating your {lcs-short} service configuration.
+By default, {ls-short} stores chat history in a non-persistent local database within the {lcs-short} container. You can configure {ls-short} to use PostgreSQL for persistent chat history storage.
 
 [WARNING]
 ====