Standardize Q&A in Sample Applications folder pt 2 (open-edge-platform#2090)

jbuksinski-intel · wiwaszko-intel · web-flow · commit baa7f9eb7bd9 · 2026-04-08T08:49:27.000+02:00
Co-authored-by: Wiktor Iwaszko &lt;wiktorx.iwaszko@intel.com&gt;
diff --git a/microservices/document-ingestion/pgvector/docs/user-guide/how-to-customize.md b/microservices/document-ingestion/pgvector/docs/user-guide/how-to-customize.md
@@ -84,4 +84,4 @@ source ./run.sh --build dataprep my-registry/my-dataprep:v1.0
 ## Common Customizations
 
 Customization options are currently provided in the context of the sample application. Refer
-to [Chat Q&A sample application](https://docs.openedgeplatform.intel.com/dev/edge-ai-libraries/chat-question-and-answer/index.html) for details like Helm and customization options.
+to the [Chat Q&A sample application](https://docs.openedgeplatform.intel.com/dev/edge-ai-libraries/chat-question-and-answer/index.html) for details like Helm and customization options.
diff --git a/sample-applications/chat-question-and-answer-core/docs/user-guide/benchmarks.md b/sample-applications/chat-question-and-answer-core/docs/user-guide/benchmarks.md
@@ -1,6 +1,6 @@
 # Benchmarks
 
-This document provides reference benchmark results for the Chat Question & Answer (Chat Q&A) Sample Application. The benchmark numbers published here are indicative of the performance to be expected on given test environment.
+This document provides reference benchmark results for the Chat Question & Answer (Chat Q&A) sample application. The benchmark numbers published here are indicative of the performance to be expected on given test environment.
 
 ## Test Environment
 
diff --git a/sample-applications/chat-question-and-answer-core/docs/user-guide/deploy-with-helm.md b/sample-applications/chat-question-and-answer-core/docs/user-guide/deploy-with-helm.md
@@ -1,6 +1,6 @@
 # How to deploy with Helm
 
-This guide provides step-by-step instructions for deploying the Chat Question-and-Answer Core Sample Application using Helm.
+This guide provides step-by-step instructions for deploying the Chat Question & Answer (Chat Q&A) Core Sample Application using Helm.
 
 ## Prerequisites
 
diff --git a/sample-applications/chat-question-and-answer-core/docs/user-guide/get-started.md b/sample-applications/chat-question-and-answer-core/docs/user-guide/get-started.md
@@ -1,6 +1,6 @@
 # Get Started
 
-The Chat Question & Answer (Chat Q&A) Sample Application is a Retrieval Augmented Generation (RAG) pipeline designed to be used in a single user non concurrent deployment primarily targeting  Intel® Core&trade; deployments.  The application is intended to help developers create personal intelligent chatbots that can answer questions based on their private data. This guide will help you set up, run, and modify the Chat Q&A Sample Application on Intel Edge AI systems.
+The Chat Question & Answer (Chat Q&A) sample application is a Retrieval Augmented Generation (RAG) pipeline designed to be used in a single user non concurrent deployment primarily targeting  Intel® Core&trade; deployments.  The application is intended to help developers create personal intelligent chatbots that can answer questions based on their private data. This guide will help you set up, run, and modify the Chat Q&A sample application on Intel Edge AI systems.
 
 By following this guide, you will learn how to:
 
diff --git a/sample-applications/chat-question-and-answer-core/docs/user-guide/index.md b/sample-applications/chat-question-and-answer-core/docs/user-guide/index.md
@@ -11,7 +11,7 @@
 </div>
 hide_directive-->
 
-Chat Question & Answer (Chat Q&A) Sample Application is a foundational Retrieval Augmented Generation (RAG) pipeline,
+The Chat Question & Answer (Chat Q&A) sample application is a foundational Retrieval Augmented Generation (RAG) pipeline,
 enabling users to ask questions and receive answers including on their own private data
 corpus. The sample application demonstrates how to build RAG pipelines.
 Compared to the
diff --git a/sample-applications/chat-question-and-answer-core/docs/user-guide/release-notes.md b/sample-applications/chat-question-and-answer-core/docs/user-guide/release-notes.md
@@ -40,7 +40,7 @@
 **Version**: 1.2.1 \
 **Release Date**: WW27 2025
 
-- Image Optimization for Chat Q&A Core Backend. Reducing image sizes, which will lead to faster processing times and reduced bandwidth usage.
+- Image Optimization for the Chat Q&A Core Backend. Reducing image sizes, which will lead to faster processing times and reduced bandwidth usage.
 - Security Vulnerabilities Fix for Dependency Packages.
 - Update in Setup Scripts for default model download path in the backend.
 - Bug fixes.
diff --git a/sample-applications/chat-question-and-answer/docs/user-guide/benchmarks.md b/sample-applications/chat-question-and-answer/docs/user-guide/benchmarks.md
@@ -1,6 +1,6 @@
 # Benchmarks
 
-This document provides reference benchmark results for the Chat Question & Answer (Chat Q&A) Sample Application. The benchmark numbers published here are indicative of the performance to be expected on given test environment.
+This document provides reference benchmark results for the Chat Question & Answer (Chat Q&A) sample application. The benchmark numbers published here are indicative of the performance to be expected on given test environment.
 
 ## Test Environment
 
diff --git a/sample-applications/chat-question-and-answer/docs/user-guide/get-started.md b/sample-applications/chat-question-and-answer/docs/user-guide/get-started.md
@@ -4,7 +4,7 @@
 **Sample Description**: Provide a brief overview of the application and its purpose.
 -->
 
-The Chat Question & Answer (Chat Q&A) Sample Application is a modular Retrieval Augmented Generation (RAG) pipeline designed to help developers create intelligent chatbots that can answer questions based on enterprise data. This guide will help you set up, run, and modify the Chat Q&A Sample Application on Intel Edge AI systems.
+The Chat Question & Answer (Chat Q&A) sample application is a modular Retrieval Augmented Generation (RAG) pipeline designed to help developers create intelligent chatbots that can answer questions based on enterprise data. This guide will help you set up, run, and modify the Chat Q&A sample application on Intel Edge AI systems.
 
 <!--
 **What You Can Do**: Highlight the developer workflows supported by the guide.
diff --git a/sample-applications/chat-question-and-answer/docs/user-guide/get-started/build-from-source.md b/sample-applications/chat-question-and-answer/docs/user-guide/get-started/build-from-source.md
@@ -1,6 +1,6 @@
 # Build from Source
 
-This guide provides step-by-step instructions for building the Chat Q&A Sample Application from source.
+This guide provides step-by-step instructions for building the Chat Q&A sample application from source.
 
 > **Note:**
 >
@@ -18,7 +18,7 @@ Before you begin, ensure that you have the following prerequisites:
 ## Steps to Build from Source
 
 1. **Clone the Repository**:
-    - Clone the Chat Q&A Sample Application repository:
+    - Clone the Chat Q&A sample application repository:
 
       ```bash
       # Clone the latest on mainline
@@ -89,7 +89,7 @@ Before you begin, ensure that you have the following prerequisites:
     ```
 
 5. **Build the Docker Image**:
-    - Build the Docker image for the Chat Q&A Sample Application:
+    - Build the Docker image for the Chat Q&A sample application:
 
       ```bash
       docker compose build
diff --git a/sample-applications/chat-question-and-answer/docs/user-guide/get-started/deploy-with-helm.md b/sample-applications/chat-question-and-answer/docs/user-guide/get-started/deploy-with-helm.md
@@ -1,6 +1,6 @@
 # Deploy with Helm
 
-This guide provides step-by-step instructions for deploying the Chat Question & Answer (Chat Q&A) Sample Application using Helm.
+This guide provides step-by-step instructions for deploying the Chat Question & Answer (Chat Q&A) sample application using Helm.
 
 ## Prerequisites
 
@@ -11,7 +11,7 @@ Before you begin, ensure that you have the following prerequisites:
 - Install `kubectl` on your system. Refer to [Installation Guide](https://kubernetes.io/docs/tasks/tools/install-kubectl/). Ensure access to the Kubernetes cluster.
 - Helm installed on your system: [Installation Guide](https://helm.sh/docs/intro/install/).
 - Model Download microservice is deployed using Helm and is up and running (required for OVMS). Refer to the [Deploy with Helm Chart Guide](https://docs.openedgeplatform.intel.com/dev/edge-ai-libraries/model-download/get-started/deploy-with-helm-chart.html) for deployment instructions.
-- Ensure the Model Download Helm chart is deployed and the `model-download` microservice is up and running before deploying Chat QnA. Refer to the [Model Download Get Started Guide](https://docs.openedgeplatform.intel.com/dev/edge-ai-libraries/model-download/get-started.html).
+- Ensure the Model Download Helm chart is deployed and the `model-download` microservice is up and running before deploying Chat Q&A. Refer to the [Model Download Get Started Guide](https://docs.openedgeplatform.intel.com/dev/edge-ai-libraries/model-download/get-started.html).
 
 ## Steps to deploy with Helm
 
@@ -213,9 +213,9 @@ helm uninstall <name> -n <your-namespace>
   ```
 
 **Note:**
-Chat QnA uses a shared PVC created and managed by the `model-download` microservice. Do not delete this PVC while either service is running, as it stores downloaded model data and is required by both.
+Chat Q&A uses a shared PVC created and managed by the `model-download` microservice. Do not delete this PVC while either service is running, as it stores downloaded model data and is required by both.
 
-Only delete the shared PVC when intentionally cleaning up model artifacts and after ensuring no workloads depend on it. Typically, uninstall Chat QnA first, then clean up `model-download` resources, and remove the PVC if needed.
+Only delete the shared PVC when intentionally cleaning up model artifacts and after ensuring no workloads depend on it. Typically, uninstall Chat Q&A first, then clean up `model-download` resources, and remove the PVC if needed.
 
 ## Related links
 
diff --git a/sample-applications/chat-question-and-answer/docs/user-guide/how-it-works.md b/sample-applications/chat-question-and-answer/docs/user-guide/how-it-works.md
@@ -1,10 +1,10 @@
 # How It Works
 
-The Chat Question & Answer (Chat Q&A) Sample Application is a RAG based chatbot pipeline that allows developers to customize and deploy the sample application in an on-prem environment and on their private documents without compromising on the accuracy of the responses. The application is built on a modular microservices approach using popular [LangChain framework](https://www.langchain.com/). This page provides a technical overview of the application’s architecture, components, and extensibility.
+The Chat Question & Answer (Chat Q&A) sample application is a RAG based chatbot pipeline that allows developers to customize and deploy the sample application in an on-prem environment and on their private documents without compromising on the accuracy of the responses. The application is built on a modular microservices approach using popular [LangChain framework](https://www.langchain.com/). This page provides a technical overview of the application’s architecture, components, and extensibility.
 
 ## Purpose
 
-The Chat Q&A Sample Application is designed to:
+The Chat Q&A sample application is designed to:
 
 - Demonstrate how Intel Edge AI catalog of inference microservices can be used to quickly build and deploy on Intel Edge AI systems portfolio.
 - Serve as a blueprint for building similar scalable and modular solutions that can be deployed on Intel Edge AI systems.
@@ -19,7 +19,7 @@ The Chat Q&A application is a combination of the core LangChain application logi
 ### Technical Architecture Diagram
 
 ![Technical Architecture Diagram](./_assets/TEAI_ChatQnA_Arch.png)
-**Figure 1**: Detailed Architecture of the Chat Q&A Sample Application
+**Figure 1**: Detailed Architecture of the Chat Q&A sample application
 
 ### Application Flow
 
@@ -68,7 +68,7 @@ The application flow is illustrated in the flow diagram below. The diagram shows
    - **Benefits**: The core part of the document ingestion microservice is the vector handling capability which is optimized for target deployment hardware. Selection of the vectorDB is based on performance considerations. Rest of the document ingestion microservice can be treated as sample reference implementation.
 
 3. **Chat Q&A backend microservice**:
-   - **What it is**: The Chat Q&A backend microservice is a LangChain based implementation of Chat Q&A RAG pipeline providing required handling of the user queries.
+   - **What it is**: The Chat Q&A backend microservice is a LangChain based implementation of the Chat Q&A RAG pipeline providing required handling of the user queries.
    - **How it’s used**: A `streamlog` REST API endpoint is provided which is used by the UI front end to send user queries and trigger the RAG pipeline.
    - **Benefits**: The microservice provides a reference of how LangChain framework is used to implement Chat Q&A using Intel Edge AI inference microservices.
 
@@ -79,7 +79,7 @@ The application flow is illustrated in the flow diagram below. The diagram shows
 
 ## Extensibility
 
-The Chat Q&A Sample Application is designed with modularity in mind, allowing developers to:
+The Chat Q&A sample application is designed with modularity in mind, allowing developers to:
 
 1. **Change inference microservices**:
    - The default option is OVMS for LLM and TEI for embeddings and reranker.
diff --git a/sample-applications/chat-question-and-answer/docs/user-guide/how-to-performance.md b/sample-applications/chat-question-and-answer/docs/user-guide/how-to-performance.md
@@ -1,11 +1,11 @@
 # How to Test Performance
 
-This guide provides step-by-step instructions for testing the performance of the Chat Q&A Sample Application.
+This guide provides step-by-step instructions for testing the performance of the Chat Q&A sample application.
 
 ## Prerequisites
 
 Before you begin, ensure that you have the following prerequisites:
-- The Chat Q&A Sample Application is set up and running. Refer to the [Get Started](./get-started.md) guide for setup instructions.
+- The Chat Q&A sample application is set up and running. Refer to the [Get Started](./get-started.md) guide for setup instructions.
 
 ## Steps to Test Performance
 
diff --git a/sample-applications/chat-question-and-answer/docs/user-guide/index.md b/sample-applications/chat-question-and-answer/docs/user-guide/index.md
@@ -11,7 +11,7 @@
 </div>
 hide_directive-->
 
-Chat Q&A sample application is a foundational Retrieval-Augmented Generation (RAG) pipeline
+The Chat Question & Answer (Chat Q&A) sample application is a foundational Retrieval-Augmented Generation (RAG) pipeline
 that allows users to ask questions and receive answers, including those based on their own
 private data corpus. The sample application demonstrates how to build a RAG pipeline using
 Intel's Edge AI microservices catalog and deploy it optimally on Intel's Edge AI systems.
diff --git a/sample-applications/chat-question-and-answer/docs/user-guide/release-notes.md b/sample-applications/chat-question-and-answer/docs/user-guide/release-notes.md
@@ -12,7 +12,7 @@
 
 - The upload button is temporarily disabled during chat response generation to prevent delays. File or link uploads trigger embedding generation, which runs on the same OVMS server as the LLM, potentially slowing response streaming if both run together.
 - Chat data is stored in localStorage for session continuity. After container restarts, old chats may reappear — clear your browser’s localStorage to start fresh.
-- Limited validation done on EMT-S due to EMT-S issues. It is not recommended to use Chat QnA modular on EMT-S until full validation is completed.
+- Limited validation done on EMT-S due to EMT-S issues. It is not recommended to use Chat Q&A modular on EMT-S until full validation is completed.
 - DeepSeek/Phi Models are observed, at times, to continue generating responses in an endless loop. Close the browser and restart in such cases.
 
 ## Previous Releases
diff --git a/sample-applications/chat-question-and-answer/docs/user-guide/release-notes/release-notes-2025.md b/sample-applications/chat-question-and-answer/docs/user-guide/release-notes/release-notes-2025.md
@@ -17,7 +17,7 @@
 
 - The upload button is temporarily disabled during chat response generation to prevent delays. File or link uploads trigger embedding generation, which runs on the same OVMS server as the LLM, potentially slowing response streaming if both run together.
 - Chat data is stored in localStorage for session continuity. After container restarts, old chats may reappear — clear your browser’s localStorage to start fresh.
-- Limited validation done on EMT-S due to EMT-S issues. It is not recommended to use Chat QnA modular on EMT-S until full validation is completed.
+- Limited validation done on EMT-S due to EMT-S issues. It is not recommended to use Chat Q&A modular on EMT-S until full validation is completed.
 - TGI on EMT 3.0 on Core&trade; configuration has a long startup time due to resource constraints. Alternative is to use TGI only on Xeon® based systems. (*Low priority as TGI and vLLM is deprecated effective 2025.2.0*)
 - DeepSeek/Phi Models are observed, at times, to continue generating response in an endless loop. Close the browser and restart in such cases.
 
@@ -48,7 +48,7 @@
 **Version**: 1.2.1 \
 **Release Date**: WW27 2025
 
-- Image Optimization for Chat QnA Backend and Document Ingestion Microservices. Reducing image sizes, which will lead to faster processing times and reduced bandwidth usage.
+- Image Optimization for the Chat Q&A Backend and Document Ingestion Microservices. Reducing image sizes, which will lead to faster processing times and reduced bandwidth usage.
 - Update to Run Chat Q&A UI and Nginx Container with Non-Root Access Privileges.
 - Security Vulnerabilities Fix for Dependency Packages.
 - Max Token Parameter Added to /stream_log API.
@@ -80,6 +80,6 @@
 **Version**: 1.0.0 \
 **Release Date**: WW11 2025
 
-- Initial release of the Chat Q&A Sample Application.
+- Initial release of the Chat Q&A sample application.
 - Added support for vLLM, TGI, and OVMS inference methods.
 - Improved user interface for better user experience.
