update sk sdk to 1.0.2 and azure openai sdk to 1.0.0.0-beta-8

Author: dantelmomsft

README.md

@@ -43,7 +43,7 @@ What this demo application does:
 ![Chat screen](docs/chatscreen.png)
 
 
-## Solution Architecture and deployment options
+## Solution architecture and deployment options
 
 ![Microservice RAG Architecture](docs/aks/aks-hla.png)
 
@@ -53,7 +53,7 @@ This sample supports different architectural styles. It can be deployed as stand
 - For **Azure Container Apps** deployment, see [here](docs/aca/README-ACA.md).
 - For **Azure Kubernetes Service** deployment, see [here](docs/aks/README-AKS.md).
 
-## RAG Implementation Options
+## RAG implementation options
 This repo is focused to showcase different options to implement **"chat with your private documents"** scenario using RAG patterns with Java, Azure OpenAI and Semantic Kernel.
 Below you can find the list of available implementations.
 
@@ -67,7 +67,7 @@ Below you can find the list of available implementations.
 | Chat                 | [JavaSemanticKernelChainsApproach](https://github.com/Azure-Samples/azure-search-openai-demo-java/blob/main/app/backend/src/main/java/com/microsoft/openai/samples/rag/chat/approaches/semantickernel/JavaSemanticKernelChainsChatApproach.java)         | Use Java Semantic Kernel framework with semantic and native functions chaining. It uses an imperative style for AI orchestration through semantic kernel functions chaining. [InformationFinder.SearchFromConversation](https://github.com/Azure-Samples/azure-search-openai-demo-java/blob/main/app/backend/src/main/java/com/microsoft/openai/samples/rag/retrieval/semantickernel/CognitiveSearchPlugin.java) native function and [RAG.AnswerConversation](https://github.com/Azure-Samples/azure-search-openai-demo-java/blob/main/app/backend/src/main/resources/semantickernel/Plugins/RAG/AnswerConversation/config.json) semantic function are called sequentially. Several search retrieval options are available: Text, Vector, Hybrid.                                                                                                | :x:                                                                                            | :white_check_mark:    |
 
 
-## Production Deployment on Azure Application Landing Zones
+## Production deployment on Azure Application Landing Zones
 
 This sample is designed to get you started quickly and let you experiment with Java intelligent Apps RAG architectures on Azure. For production deployment, you can use the [Azure Application Landing Zones (LZA)](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/scenarios/app-platform/ready) to deploy the solution maintaining best practices for security, monitoring, networking and operational excellence.
 

app/backend/pom.xml

@@ -18,7 +18,7 @@
 
 		<spring-cloud-azure.version>4.9.0</spring-cloud-azure.version>
 		<azure-search.version>11.6.0-beta.8</azure-search.version>
-		<semantic-kernel.version>1.0.1</semantic-kernel.version>
+		<semantic-kernel.version>1.0.2</semantic-kernel.version>
 		<mockito-inline.version>4.5.1</mockito-inline.version>
 		<maven.compiler-plugin.version>3.11.0</maven.compiler-plugin.version>
 

app/backend/src/main/java/com/microsoft/openai/samples/rag/retrieval/CognitiveSearchRetriever.java

@@ -65,9 +65,7 @@ public List<ContentSource> retrieveFromQuestion(String question, RAGOptions ragO
 
             Embeddings response = openAIProxy.getEmbeddings(List.of(question));
             var questionVector =
-                    response.getData().get(0).getEmbedding().stream()
-                            .map(Double::floatValue)
-                            .toList();
+                    response.getData().get(0).getEmbedding();
             if (ragOptions.getRetrievalMode() == RetrievalMode.vectors) {
                 setSearchOptionsForVector(ragOptions, questionVector, searchOptions);
             } else {

app/frontend/.env.dev

@@ -1 +1 @@
-VITE_BACKEND_URI=http://127.0.0.1:8081/api
+VITE_BACKEND_URI=http://localhost:8081/api

app/frontend/.env.local

@@ -1 +1 @@
-VITE_BACKEND_URI=http://127.0.0.1:8081/api
+VITE_BACKEND_URI=http://localhost:8081/api

app/indexer/core/src/main/java/com/microsoft/openai/samples/indexer/embeddings/AbstractTextEmbeddingsService.java

@@ -44,9 +44,9 @@ public AbstractTextEmbeddingsService(String openAiDeploymentName, boolean verbos
     protected abstract OpenAIAsyncClient createClient();
 
 
-    public List<List<Double>> createEmbeddingBatch(List<String> texts) {
+    public List<List<Float>> createEmbeddingBatch(List<String> texts) {
         List<EmbeddingBatch> batches = splitTextIntoBatches(texts);
-        List<List<Double>> embeddings = new ArrayList<>();
+        List<List<Float>> embeddings = new ArrayList<>();
         OpenAIAsyncClient client = createClient();
         for (int batchIndex =0; batchIndex < batches.size(); batchIndex++) {
                     EmbeddingBatch batch = batches.get(batchIndex);

app/indexer/core/src/main/java/com/microsoft/openai/samples/indexer/embeddings/TextEmbeddingsService.java

@@ -4,5 +4,5 @@
 
 public interface TextEmbeddingsService {
 
-    public List<List<Double>> createEmbeddingBatch(List<String> texts);
+    public List<List<Float>> createEmbeddingBatch(List<String> texts);
 }

app/indexer/core/src/main/java/com/microsoft/openai/samples/indexer/index/SearchIndexManager.java

@@ -154,7 +154,7 @@ public void updateContent(List<Section> sections) {
 
 
             //Create embeddings for sections. 
-            List<List<Double>> embeddings = embeddingsService.createEmbeddingBatch(textsToEmbed);
+            List<List<Float>> embeddings = embeddingsService.createEmbeddingBatch(textsToEmbed);
 
             //Embeddings are assigned back to section using index in batch. Using Array List assure ordering is preserved.
             for (int i = 0; i < documents.size(); i++) {

app/indexer/pom.xml

@@ -13,7 +13,7 @@
         <maven.compiler.source>17</maven.compiler.source>
         <maven.compiler.target>17</maven.compiler.target>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
-        <azure-openai.version>1.0.0-beta.6</azure-openai.version>
+        <azure-openai.version>1.0.0-beta.8</azure-openai.version>
         <azure-document-intelligence.version>4.1.4</azure-document-intelligence.version>
         <itextpdf.version>5.5.13.3</itextpdf.version>
         <apache.common.text>1.11.0</apache.common.text>