revisions after peer review

Author: jeremyary

content/patterns/amd-rag-chat-qna/_index.adoc

@@ -30,11 +30,12 @@ include::modules/comm-attributes.adoc[]
 
 Background::
 This Validated Pattern implements an enterprise-ready question-and-answer chatbot utilizing retrieval-augmented generation (RAG) & capability reasoning via large language model (LLM). The application is based on the publicly-available
-https://github.com/opea-project/GenAIExamples/tree/main/ChatQnA[OPEA Chat QnA] example application created by the https://opea.dev/[Open Platform for Enterprise AI (OPEA)] community. OPEA defines itself as "a framework that enables the
-creation and evaluation of open, multi-provider, robust, and composable generative AI (GenAI) solutions. It harnesses the best innovations across the ecosystem while keeping enterprise-level needs front and center. It simplifies the
+https://github.com/opea-project/GenAIExamples/tree/main/ChatQnA[OPEA Chat QnA] example application created by the https://opea.dev/[Open Platform for Enterprise AI (OPEA)] community.
++
+OPEA provides a framework that enables the creation and evaluation of open, multi-provider, robust, and composable generative AI (GenAI) solutions. It harnesses the best innovations across the ecosystem while keeping enterprise-level needs front and center. It simplifies the
 implementation of enterprise-grade composite GenAI solutions, starting with a focus on Retrieval Augmented Generative AI (RAG). The platform is designed to facilitate efficient integration of secure,
-performant, and cost-effective GenAI workflows into business systems and manage its deployments, leading to quicker GenAI adoption and business value."
-
+performant, and cost-effective GenAI workflows into business systems and manage its deployments, leading to quicker GenAI adoption and business value.
++
 This pattern aims to leverage the strengths of OPEA's framework in combination with other OpenShift-centric toolings in order to deploy a modern, LLM-backed reasoning application stack capable of leveraging https://www.amd.com/en/products/accelerators/instinct.html[AMD's Instinct]
 hardware acceleration in an enterprise-ready & distributed manner. The pattern utilizes https://www.redhat.com/en/technologies/cloud-computing/openshift/gitops[Red Hat OpenShift GitOps] to bring a continuous delivery approach to the application's development & usage based on declarative
 Git-driven workflows, backed by a centralized, single-source-of-truth git repository.
@@ -56,7 +57,7 @@ Components::
 * AI/ML Services
 ** Text Embeddings Inference (TEI)
 ** Document Retriever
-** Reranking Service
+** Retriever Service
 ** LLM-TGI (Text Generation Inference) from OPEA
 ** vLLM accelerated by AMD Instinct GPUs
 ** Redis Vector Database
@@ -73,12 +74,12 @@ Components::
 {empty} +
 
 .Overview of the solution
-image::/images/amd-rag-chat-qna/amd-rag-chat-qna-overview.png[alt=OPEA Chat QnA accelerated with AMD Instinct Validated Pattern architecture,65%,65%]
+image::/images/qna-chat-amd/amd-rag-chat-qna-overview.png[alt=OPEA Chat QnA accelerated with AMD Instinct Validated Pattern architecture,65%,65%]
 
 {empty} +
 
 .Overview of application flow
-image::/images/amd-rag-chat-qna/amd-rag-chat-qna-flow.png[OPEA Chat QnA accelerated with AMD Instinct application flow]
+image::/images/qna-chat-amd/amd-rag-chat-qna-flow.png[OPEA Chat QnA accelerated with AMD Instinct application flow]
 
 {empty} +
 

content/patterns/amd-rag-chat-qna/amd-rag-chat-qna-getting-started.adoc

@@ -87,7 +87,7 @@ To upload the model that is needed for this article, you need to create a workbe
 ** Container size: `Medium`
 ** Accelerator: `AMD`
 ** Cluster storage: Make sure the storage is at least 50GB
-** Connection: Click on Attach existing connections button and attach the connection named model-store created in the previous step (Figure 4). This will pass on the connection values to the workbench when it is started, which will be used to upload the model.
+** Connection: Click on Attach existing connections button and attach the connection named model-store created in the previous step. This will pass on the connection values to the workbench when it is started, which will be used to upload the model.
 * Create the workbench by clicking on the `Create workbench` button. This workbench will be started and will move to `Running` status soon.
 +
 image::/images/qna-chat-amd/rhoai-create-workbench.png[Red Hat OpenShift AI - Create Workbench - Attach existing connections]
@@ -101,12 +101,13 @@ Open Workbench::
 Open workbench named `chatqna` by following these steps:
 * Once `chatqna` workbench is in `Running` status, open the workbench by clicking on its name, in `Workbenches` tab
 * The workbench will open up in a new tab
-** When the workbench is opened for the first time, you will be shown an _Authorize Access page_*
+** When the workbench is opened for the first time, you will be shown an _Authorize Access page_
 ** Click `Allow selected permissions` button in this page
 
 Clone Code Repository:: [[clone_pattern_code]]
 
 Now that the workbench is created and running, follow these steps to setup the project:
+
 * In the open workbench, click on the `Terminal` icon in the `Launcher` tab.
 * Clone the following repository in the Terminal by running the following command:
 
@@ -174,7 +175,7 @@ Once all the prerequisites are met, install the ChatQnA application
 +
 * Configure secrets for Hugging Face and inference endpoint
 +
-    cp values-secret.yaml.template `~/values-secret-qna-chat-amd.yaml`
+    cp values-secret.yaml.template ~/values-secret-qna-chat-amd.yaml
 +
 * Modify the `value` field in `~/values-secret-qna-chat-amd.yaml` file
 +
@@ -183,13 +184,13 @@ Once all the prerequisites are met, install the ChatQnA application
     - name: huggingface
       fields:
       - name: token
-      value: null  <- CHANGE THIS TO YOUR HUGGING_FACE TOKEN
-      vaultPolicy: validatePatternDefaultPolicy
+        value: null  <- CHANGE THIS TO YOUR HUGGING_FACE TOKEN
+        vaultPolicy: validatePatternDefaultPolicy
 
     - name: rhoai_model
       fields:
       - name: inference_endpoint
-      value: null  <- CHANGE THIS TO YOUR MODEL'S INFERENCE ENDPOINT
+        value: null  <- CHANGE THIS TO YOUR MODEL'S INFERENCE ENDPOINT
 ----
 +
 * Deploy the application
@@ -243,6 +244,7 @@ Query ChatQnA without RAG::
 +
 Since we have not yet provided any external knowledge base regarding the above query to the application, it does not the correct answer to this query and returns a generic response:
 +
+
 image::/images/qna-chat-amd/chatqna-ui-no-rag.png[ChatQnA UI - response without RAG,40%,40%]
 
 Query ChatQnA with RAG - add external knowledge base::