edits

Author: KarlErickson

learn-pr/azure/build-enterprise-ai-agents-with-java-spring/2-pgvector-azure-postgresql-setup.yml

@@ -3,7 +3,7 @@ uid: learn.azure.build-enterprise-ai-agents-with-java-spring.2-pgvector-azure-po
 title: Set up the pgvector extension in Azure PostgreSQL for use with Spring AI
 metadata:
   title: Set Up the pgvector Extension in Azure PostgreSQL for Use with Spring AI
-  description: Learn how to use the pgvector extension in Azure PostgreSQL and apply the Vector Search Similarity abstraction in Spring AI.
+  description: Learn how to use the pgvector extension in Azure PostgreSQL and apply the vector similarity search abstraction in Spring AI.
   ms.date: 03/12/2024
   author: KarlErickson
   ms.author: karler

learn-pr/azure/build-enterprise-ai-agents-with-java-spring/3-exercise-pgvector-azure-postgresql-setup.yml

@@ -3,7 +3,7 @@ uid: learn.azure.build-enterprise-ai-agents-with-java-spring.3-exercise-pgvector
 title: Exercise - Set up the pgvector extension in Azure PostgresQL for use with Spring AI
 metadata:
   title: Exercise - Set Up the pgvector Extension in Azure PostgreSQL for Use with Spring AI
-  description: Set up the pgvector extension in Azure PostgreSQL to apply the Vector Search Similarity abstraction in Spring AI.
+  description: Set up the pgvector extension in Azure PostgreSQL to apply the vector similarity search abstraction in Spring AI.
   ms.date: 03/12/2024
   author: KarlErickson
   ms.author: karler

learn-pr/azure/build-enterprise-ai-agents-with-java-spring/5-exercise-spring-ai-development.yml

@@ -3,7 +3,7 @@ uid: learn.azure.build-enterprise-ai-agents-with-java-spring.5-exercise-spring-a
 title: Exercise - Develop a RAG application with Spring AI and Azure OpenAI
 metadata:
   title: Exercise - Develop a RAG Application with Spring AI and Azure OpenAI
-  description: Learn how to develop a Spring AI application integrated with Azure OpenAI for retrieval augmented generation (RAG) and implement an Evaluator Optimizer Agent to iteratively refine AI-generated content.
+  description: Learn how to develop a Spring AI application integrated with Azure OpenAI for retrieval augmented generation (RAG) and implement an Evaluator-Optimizer agent to iteratively refine AI-generated content.
   ms.date: 03/12/2024
   author: KarlErickson
   ms.author: karler

learn-pr/azure/build-enterprise-ai-agents-with-java-spring/6-agent-ai-development.yml

@@ -1,9 +1,9 @@
 ### YamlMime:ModuleUnit
 uid: learn.azure.build-enterprise-ai-agents-with-java-spring.6-agent-ai-development
-title: Implement the Evaluator Optimizer Agent pattern using Spring AI
+title: Implement the Evaluator-Optimizer agent pattern using Spring AI
 metadata:
-  title: Implement the Evaluator Optimizer Agent Pattern Using Spring AI
-  description: Learn how to implement the Evaluator Optimizer Agent pattern using Spring AI.
+  title: Implement the Evaluator-Optimizer agent Pattern Using Spring AI
+  description: Learn how to implement the Evaluator-Optimizer agent pattern using Spring AI.
   ms.date: 03/12/2024
   author: KarlErickson
   ms.author: karler

learn-pr/azure/build-enterprise-ai-agents-with-java-spring/7-exercise-agent-ai-development.yml

@@ -1,9 +1,9 @@
 ### YamlMime:ModuleUnit
 uid: learn.azure.build-enterprise-ai-agents-with-java-spring.7-exercise-agent-ai-development
-title: Exercise - Implement the Evaluator Optimizer Agent pattern using Spring AI
+title: Exercise - Implement the Evaluator-Optimizer agent pattern using Spring AI
 metadata:
-  title: Exercise - Implement the Evaluator Optimizer Agent pattern using Spring AI
-  description: Learn how to implement the Evaluator Optimizer Agent pattern using Spring AI.
+  title: Exercise - Implement the Evaluator-Optimizer agent pattern using Spring AI
+  description: Learn how to implement the Evaluator-Optimizer agent pattern using Spring AI.
   ms.date: 03/12/2024
   author: KarlErickson
   ms.author: karler

learn-pr/azure/build-enterprise-ai-agents-with-java-spring/includes/1-introduction.md

@@ -21,7 +21,7 @@ A RAG application typically has the following capabilities:
 
 ## Agents and workflows
 
-Spring AI also empowers you to build dynamic AI agents and orchestrated workflows. While various patterns exist - like chain, parallelization and routing - this module focuses exclusively on the *Evaluator-Optimizer* workflow.
+Spring AI also empowers you to build dynamic AI agents and orchestrated workflows. Although various patterns exist - like chain, parallelization and routing - this module focuses exclusively on the *Evaluator-Optimizer* workflow.
 
 This pattern iteratively refines outputs through a generator-evaluator loop, ensuring high-quality and adaptive AI responses.
 

learn-pr/azure/build-enterprise-ai-agents-with-java-spring/includes/10-summary.md

@@ -9,7 +9,7 @@ Congratulations! You completed this comprehensive module on building AI-powered
 
 - AI agents:
   - Agent AI design patterns.
-  - The Evaluator-Optimizer Agent pattern.
+  - The Evaluator-Optimizer agent pattern.
 
 - Azure integration:
   - OpenAI service configuration.

learn-pr/azure/build-enterprise-ai-agents-with-java-spring/includes/2-pgvector-azure-postgresql-setup.md

@@ -1,6 +1,6 @@
-## What is Vector Search Similarity?
+## What is vector similarity search?
 
-Vector Search Similarity is a technique used to find similar items in a dataset by comparing their vector representations. Vector similarity is commonly calculated using distance metrics, such as Euclidean distance or `cosine` similarity. In the context of AI and machine learning, vector representations or embeddings are numerical representations of data points, such as words, images, or user queries. These vectors capture the semantic meaning of the data points, enabling efficient similarity searches.
+Vector similarity search is a technique used to find similar items in a dataset by comparing their vector representations. Vector similarity is commonly calculated using distance metrics, such as Euclidean distance or `cosine` similarity. In the context of AI and machine learning, vector representations or embeddings are numerical representations of data points, such as words, images, or user queries. These vectors capture the semantic meaning of the data points, enabling efficient similarity searches.
 
 For example, in a question-answering system, user queries can be converted into vector embeddings. These embeddings can then be compared to a database of precomputed embeddings of previous prompts and answers to find the most similar ones. This process is known as vector similarity search.
 
@@ -48,6 +48,6 @@ On startup, Spring Boot installs the required extensions and creates the require
 
 ## Unit summary
 
-Vector Search Similarity and the `pgvector` extension provide powerful capabilities for building AI-powered applications that require semantic search functionality. By using these tools in Azure PostgreSQL, you can efficiently store, index, and query vector embeddings, enabling advanced search and retrieval features in your applications.
+Vector similarity search and the `pgvector` extension provide powerful capabilities for building AI-powered applications that require semantic search functionality. By using these tools in Azure PostgreSQL, you can efficiently store, index, and query vector embeddings, enabling advanced search and retrieval features in your applications.
 
 In the next unit, you perform the steps to create and configure a PostgreSQL database, enable the `pgvector` extension, and create required tables for use with Spring AI.

learn-pr/azure/build-enterprise-ai-agents-with-java-spring/includes/4-spring-ai-development.md

@@ -1,4 +1,4 @@
-In this unit, you learn how to implement retrieval-augmented generation (RAG) in a Spring Boot application using vector search similarity provided by the `pgvector` extension in a PostgreSQL database. We introduce relevant RAG concepts such as embeddings, embedding models, and vector stores. By the end of this unit, you should understand how to apply these tools to enhance your applications with advanced search and retrieval capabilities.
+In this unit, you learn how to implement retrieval-augmented generation (RAG) in a Spring Boot application using vector similarity search provided by the `pgvector` extension in a PostgreSQL database. We introduce relevant RAG concepts such as embeddings, embedding models, and vector stores. By the end of this unit, you should understand how to apply these tools to enhance your applications with advanced search and retrieval capabilities.
 
 ## What are embeddings?
 

learn-pr/azure/build-enterprise-ai-agents-with-java-spring/includes/5-exercise-spring-ai-development.md

@@ -28,7 +28,7 @@ For your application, you first need to deploy one chat model - `gpt-4o` - and o
 
 ### Create an Azure OpenAI account
 
-Use the following command to create the Azure OpenAI account:
+Use the following command to create an Azure OpenAI account:
 
 ```azurecli
 az cognitiveservices account create \
@@ -93,45 +93,38 @@ curl https://start.spring.io/starter.zip \
 
 The generated Spring Boot starter project includes the following configurations and dependencies:
 
-- Spring Boot Version: 3.4.3
-- Java Version: 17
+- Spring Boot version: 3.4.3
+- Java version: 17
 - Dependencies:
   - `web`: adds support for building web applications, including RESTful services using Spring Model View Controller (MVC).
   - `jdbc`: provides Java Database Connectivity (JDBC) support for database access.
   - `azure-support`: adds support for integrating with Azure services.
   - `spring-ai-azure-openai`: adds support for integrating with Azure OpenAI services.
   - `spring-ai-vectordb-pgvector`: adds support for using `pgvector`, a PostgreSQL extension for vector embeddings.
 
-Unzip the downloaded file using the command:
+Use the following commands to unzip the downloaded file and navigate to the created directory:
 
 ```bash
 unzip -u spring-ai-app.zip -d spring-ai-app
-```
-
-Switch directory to this path:
-
-```bash
 cd spring-ai-app
 ```
 
-You need to change the **pom.xml** file to include a dependency for passwordless authentication for PostgreSQL.
-
-Open the **pom.xml** file, locate the `<dependencies>` section and add the following dependency:
+Next, you need to change the **pom.xml** file to include a dependency for passwordless authentication for PostgreSQL. Open the **pom.xml** file, locate the `<dependencies>` section, and then add the following dependency:
 
 ```xml
-    <dependency>
-      <groupId>com.azure.spring</groupId>
-      <artifactId>spring-cloud-azure-starter-jdbc-postgresql</artifactId>
-    </dependency>
+<dependency>
+  <groupId>com.azure.spring</groupId>
+  <artifactId>spring-cloud-azure-starter-jdbc-postgresql</artifactId>
+</dependency>
 ```
 
-You can compile the application skipping tests using this command:
+Then, use the following command to compile the application, skipping tests:
 
 ```bash
 mvn clean package -DskipTests
 ```
 
-Expect to see a successful build output:
+The output should include a success message similar to the following example:
 
 ```output
 [INFO] ------------------------------------------------------------------------
@@ -144,7 +137,7 @@ Expect to see a successful build output:
 
 ### Project structure
 
-From the **spring-ai-app** directory, run the following commands to create new directories for new source files to be added:
+From the **spring-ai-app** directory, use the following commands to create new directories for new source files to be added:
 
 ```bash
 mkdir -p src/main/java/com/example/springaiapp/controller
@@ -210,9 +203,9 @@ az postgres flexible-server show \
     --output tsv
 ```
 
-#### Review the application.properties file
+#### Update the application.properties file
 
-Locate and open the **application.properties** file in the **src/main/resources** directory. There are three properties that are initialized using values from the following environment variables: `AZURE_OPENAI_API_KEY`, `AZURE_OPENAI_ENDPOINT`, and `PGHOST`:
+Locate and open the **application.properties** file in the **src/main/resources** directory. There are three properties that are initialized using values from the following environment variables: `AZURE_OPENAI_API_KEY`, `AZURE_OPENAI_ENDPOINT`, and `PGHOST`. Replace the file's content with the following content:
 
 ```properties
 spring.application.name=spring-ai-app
@@ -232,7 +225,7 @@ spring.ai.vectorstore.pgvector.schema-name=postgres
 
 #### Create the service
 
-Within the **service** directory, create a new file named **RagService.java** with the following content:
+Within the **service** directory, create a new file named **RagService.java** and add the following code:
 
 ```java
 package com.example.springaiapp.service;
@@ -298,7 +291,7 @@ This code implements RAG by generating an answer to a given query, augmenting th
 
 #### Create the RAG controller
 
-Next, you need to expose a REST endpoint for your RAG application. Create a new file named **RagController.java** within the **controller** directory:
+Next, you need to expose a REST endpoint for your RAG application. Create a new file named **RagController.java** within the **controller** directory, and then add the following code:
 
 ```java
 package com.example.springaiapp.controller;
@@ -323,7 +316,7 @@ public class RagController {
 
 #### Test the RAG application
 
-With these changes in place, test the implementation by using the following command:
+With these changes in place, use the following command to compile and run the code:
 
 ```bash
 mvn spring-boot:run
@@ -332,7 +325,8 @@ mvn spring-boot:run
 Test the new REST endpoint either from a browser or by using the following command:
 
 ```bash
-curl -G "http://localhost:8080/api/rag" --data-urlencode "query=What is pgvector?"
+curl -G "http://localhost:8080/api/rag" \
+    --data-urlencode "query=What is pgvector?"
 ```
 
 You should see a valid response similar to the following example:
@@ -345,14 +339,15 @@ and querying of vector embeddings within a PostgreSQL database.
 Next, try the following command:
 
 ```bash
-curl -G "http://localhost:8080/api/rag" --data-urlencode "query=How does QuestionAnswerAdvisor work in Spring AI?"
+curl -G "http://localhost:8080/api/rag" \
+    --data-urlencode "query=How does QuestionAnswerAdvisor work in Spring AI?"
 ```
 
-While the answer might appear valid, it might include phrasing that indicates it's a reasoned guess.
+Although the answer might appear valid, it might include phrasing that indicates it's a reasoned guess.
 
 #### Test the application with extra knowledge
 
-Next, provide extra knowledge by adding the following documents to the vector store. Create a new file named **DocumentService.java** within the **service** directory, and then add the following contents:
+Next, provide extra knowledge by adding documents to the vector store. Create a new file named **DocumentService.java** within the **service** directory, and then add the following code:
 
 ```java
 package com.example.springaiapp.service;
@@ -410,7 +405,7 @@ public class DocumentService {
 }
 ```
 
-Test these changes by using the following commands:
+To test these changes, use the following command to compile and run the code:
 
 ```bash
 mvn spring-boot:run
@@ -419,7 +414,8 @@ mvn spring-boot:run
 Then, ask a question by using the following command:
 
 ```bash
-curl -G "http://localhost:8080/api/rag" --data-urlencode "query=How does QuestionAnswerAdvisor work in Spring AI?"
+curl -G "http://localhost:8080/api/rag" \
+    --data-urlencode "query=How does QuestionAnswerAdvisor work in Spring AI?"
 ```
 
 You should now see an answer that clearly explains the role of `QuestionAnswerAdvisor` within Spring AI.