fix: review findings - auth scope, consistency, env vars

- Java: Fix TOKEN_RESOURCE from cosmos.azure.com to ossrdbms-aad.database.windows.net
- TypeScript IVF: Remove inconsistent returnStoredSource field
- .NET .env.example: Fix vector field name to contentVector, remove unused AZURE_TENANT_ID
- Java .env.example: Remove unused AZURE_MANAGED_IDENTITY_PRINCIPAL_ID
- Python .env.example: Fix API version to 2023-05-15 for consistency

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: diberry

ai/select-algorithm-dotnet/.env.example

@@ -0,0 +1,19 @@
+# Azure OpenAI Embedding Settings
+AZURE_OPENAI_EMBEDDING_MODEL=text-embedding-3-small
+AZURE_OPENAI_EMBEDDING_API_VERSION=2023-05-15
+AZURE_OPENAI_EMBEDDING_ENDPOINT=https://<RESOURCE-NAME>.openai.azure.com
+
+# Data File Paths and Vector Configuration
+DATA_FILE_WITH_VECTORS=../../data/Hotels_Vector.json
+EMBEDDED_FIELD=contentVector
+EMBEDDING_DIMENSIONS=1536
+LOAD_SIZE_BATCH=100
+
+# MongoDB/DocumentDB Connection Settings
+MONGO_CLUSTER_NAME=<CLUSTER-NAME>
+
+# Algorithm Selection
+# ALGORITHM: all | diskann | hnsw | ivf
+ALGORITHM=all
+# SIMILARITY: all | COS | L2 | IP
+SIMILARITY=COS

ai/select-algorithm-java/.env.example

@@ -0,0 +1,26 @@
+# Azure DocumentDB cluster name (find in Azure Portal > DocumentDB > Overview)
+MONGO_CLUSTER_NAME=your-cluster-name
+
+# Azure OpenAI embedding endpoint(find in Azure Portal > Azure OpenAI > Keys and Endpoint)
+AZURE_OPENAI_EMBEDDING_ENDPOINT=https://your-resource.openai.azure.com
+
+# Azure OpenAI embedding model deployment name
+AZURE_OPENAI_EMBEDDING_MODEL=text-embedding-3-small
+
+# Path to pre-computed vectors JSON file
+DATA_FILE_WITH_VECTORS=../data/Hotels_Vector.json
+
+# Database name (default: Hotels)
+AZURE_DOCUMENTDB_DATABASENAME=Hotels
+
+# Field name containing embeddings in the data file
+EMBEDDED_FIELD=contentVector
+
+# Embedding dimensions (default: 1536)
+EMBEDDING_DIMENSIONS=1536
+
+# Algorithm to test: all, diskann, hnsw, ivf (default: all)
+ALGORITHM=all
+
+# Similarity to test: COS, L2, IP (default: COS)
+SIMILARITY=COS

ai/select-algorithm-java/src/main/java/com/azure/documentdb/selectalgorithm/Utils.java

@@ -52,7 +52,7 @@ public static MongoClient getMongoClient() {
         MongoCredential mongoCredential = MongoCredential.createOidcCredential(null)
                 .withMechanism(MongoCredential.MONGODB_OIDC_MECHANISM)
                 .withMechanismProperty("ENVIRONMENT", "azure")
-                .withMechanismProperty("TOKEN_RESOURCE", "https://cosmos.azure.com");
+                .withMechanismProperty("TOKEN_RESOURCE", "https://ossrdbms-aad.database.windows.net");
 
         MongoClientSettings settings = MongoClientSettings.builder()
                 .applyConnectionString(new ConnectionString(connectionUri))

ai/select-algorithm-python/.env.example

@@ -0,0 +1,29 @@
+# Azure DocumentDB cluster name (find in Azure Portal > DocumentDB > Overview)
+MONGO_CLUSTER_NAME=your-cluster-name
+
+# Azure OpenAI embedding endpoint (find in Azure Portal > Azure OpenAI > Keys and Endpoint)
+AZURE_OPENAI_EMBEDDING_ENDPOINT=https://your-resource.openai.azure.com
+
+# Azure OpenAI embedding model deployment name
+AZURE_OPENAI_EMBEDDING_MODEL=text-embedding-3-small
+
+# Azure OpenAI API version (see: https://learn.microsoft.com/azure/ai-services/openai/api-version-deprecation)
+AZURE_OPENAI_EMBEDDING_API_VERSION=2023-05-15
+
+# Database name (default: Hotels)
+AZURE_DOCUMENTDB_DATABASENAME=Hotels
+
+# Path to pre-computed vectors JSON file (default: ../data/Hotels_Vector.json)
+DATA_FILE_WITH_VECTORS=../data/Hotels_Vector.json
+
+# Field name containing embeddings in the data file
+EMBEDDED_FIELD=contentVector
+
+# Embedding dimensions (default: 1536)
+EMBEDDING_DIMENSIONS=1536
+
+# Algorithm to test: all, diskann, hnsw, ivf (default: all)
+ALGORITHM=all
+
+# Similarity to test: COS, L2, IP (default: COS)
+SIMILARITY=COS

ai/select-algorithm-typescript/src/ivf.ts

@@ -69,8 +69,7 @@ async function main() {
                         vector: createEmbeddedForQueryResponse.data[0].embedding,
                         path: config.embeddedField,
                         k: 5
-                    },
-                    returnStoredSource: true
+                    }
                 }
             },
             {