Books demo with vector similarity search

Author: psilberk

samples/semantickernel-learn-resources/src/main/java/com/microsoft/semantickernel/samples/documentationexamples/data/vectorstores/oracle/Book.java

@@ -4,12 +4,12 @@
 import com.microsoft.semantickernel.data.vectorstorage.annotations.VectorStoreRecordData;
 import com.microsoft.semantickernel.data.vectorstorage.annotations.VectorStoreRecordKey;
 import com.microsoft.semantickernel.data.vectorstorage.annotations.VectorStoreRecordVector;
-import com.microsoft.semantickernel.data.vectorstorage.definition.DistanceFunction;
-import com.microsoft.semantickernel.data.vectorstorage.definition.IndexKind;
 import java.util.List;
 
 public class Book {
 
+    public Book() {}
+
     public Book(String isbn, String title, String author, int pages,
         List<String> tags, String summary, List<Float> summaryEmbedding) {
         this.isbn = isbn;
@@ -21,27 +21,26 @@ public Book(String isbn, String title, String author, int pages,
         this.summaryEmbedding = summaryEmbedding;
     }
 
-
     @VectorStoreRecordKey
-    private final String isbn;
+    private String isbn;
 
     @VectorStoreRecordData(isFilterable = true)
-    private final String title;
+    private String title;
 
     @VectorStoreRecordData(isFilterable = true)
-    private final String author;
+    private String author;
 
     @VectorStoreRecordData
-    private final int pages;
+    private int pages;
 
     @VectorStoreRecordData(isFilterable = true)
-    private final List<String> tags;
+    private List<String> tags;
 
     @VectorStoreRecordData( isFilterable = true, isFullTextSearchable = true )
-    private final String summary;
+    private String summary;
 
-    @VectorStoreRecordVector(dimensions = 4, distanceFunction = DistanceFunction.COSINE_DISTANCE, indexKind = IndexKind.HNSW)
-    private final List<Float> summaryEmbedding;
+    @VectorStoreRecordVector(dimensions = 2)
+    private List<Float> summaryEmbedding;
 
     public String getIsbn() {
         return isbn;
@@ -70,4 +69,32 @@ public String getSummary() {
     public List<Float> getSummaryEmbedding() {
         return summaryEmbedding;
     }
+
+    public void setIsbn(String isbn) {
+        this.isbn = isbn;
+    }
+
+    public void setTitle(String title) {
+        this.title = title;
+    }
+
+    public void setAuthor(String author) {
+        this.author = author;
+    }
+
+    public void setPages(int pages) {
+        this.pages = pages;
+    }
+
+    public void setTags(List<String> tags) {
+        this.tags = tags;
+    }
+
+    public void setSummaryEmbedding(List<Float> summaryEmbedding) {
+        this.summaryEmbedding = summaryEmbedding;
+    }
+
+    public void setSummary(String summary) {
+        this.summary = summary;
+    }
 }

samples/semantickernel-learn-resources/src/main/java/com/microsoft/semantickernel/samples/documentationexamples/data/vectorstores/oracle/Main.java

@@ -5,11 +5,14 @@
 import com.microsoft.semantickernel.data.jdbc.JDBCVectorStoreOptions;
 import com.microsoft.semantickernel.data.jdbc.JDBCVectorStoreRecordCollectionOptions;
 import com.microsoft.semantickernel.data.jdbc.oracle.OracleVectorStoreQueryProvider;
+import com.microsoft.semantickernel.data.vectorsearch.VectorSearchResults;
 import com.microsoft.semantickernel.data.vectorstorage.VectorStoreRecordCollection;
 import java.sql.SQLException;
 import java.util.Arrays;
 import java.util.List;
+import com.microsoft.semantickernel.data.vectorstorage.options.VectorSearchOptions;
 import oracle.jdbc.datasource.impl.OracleDataSource;
+import reactor.core.publisher.Mono;
 
 public class Main {
     public static void main(String[] args) throws SQLException {
@@ -45,23 +48,30 @@ public static void main(String[] args) throws SQLException {
         collection.upsertBatchAsync(books, null).block();
 
         // Retrieve the upserted record.
-        //var retrievedBook = collection.getAsync("1", null).block();
+        Book retrievedBook = collection.getAsync("2", null).block();
+
+        System.out.println(retrievedBook.getAuthor());
 
         // Generate a vector for your search text, using your chosen embedding generation implementation.
         // Just showing a placeholder method here for brevity.
-        // var searchVector = generateEmbeddingsAsync(
-        // "I'm looking for a Book where customer happiness is the priority.").block();
+        List<Float> searchVector = generateEmbeddingsAsync(
+            "I'm looking for a horror book.").block();
 
         // Do the search.
-        // var searchResult = collection.searchAsync(searchVector, VectorSearchOptions.builder()
-        // .withTop(1).build()).block();
+        VectorSearchResults<Book> searchResult = collection.searchAsync(
+            searchVector, VectorSearchOptions.builder().withTop(1).build()).block();
 
-        // Book record = searchResult.getResults().get(0).getRecord();
-        // System.out.printf("Found Book description: %s\n", record.getDescription());
+        retrievedBook = searchResult.getResults().get(0).getRecord();
+        System.out.println("Found Book: " + retrievedBook.getIsbn());
 
     }
 
     static List<Book> books = Arrays.asList(
-        new Book("1", "one", "sking", 0, null, "sum", null));
+        new Book("1", "one", "sking", 0, null, "horror", List.of(1f, 1f)),
+        new Book("2", "two", "squeen", 0, null, "non-fiction", List.of(-11f, -11f)));
+
+    private static Mono<List<Float>> generateEmbeddingsAsync(String text) {
+        return Mono.just(List.of(-0.9f, -0.9f));
+    }
 
 }