Added an example for the jvector embedding store

jvector-example/pom.xml

@@ -0,0 +1,29 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+
+    <groupId>dev.langchain4j</groupId>
+    <artifactId>jvector-example</artifactId>
+    <version>1.9.0-beta16-SNAPSHOT</version>
+
+    <properties>
+        <maven.compiler.source>17</maven.compiler.source>
+        <maven.compiler.target>17</maven.compiler.target>
+        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+    </properties>
+
+    <dependencies>
+        <dependency>
+            <groupId>dev.langchain4j</groupId>
+            <artifactId>langchain4j-community-jvector</artifactId>
+            <version>${project.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>dev.langchain4j</groupId>
+            <artifactId>langchain4j-embeddings-all-minilm-l6-v2-q</artifactId>
+            <version>1.8.0-beta15</version>
+        </dependency>
+    </dependencies>
+</project>

jvector-example/src/main/java/JVectorEmbeddingStoreExample.java

@@ -0,0 +1,162 @@
+import dev.langchain4j.community.store.embedding.jvector.JVectorEmbeddingStore;
+import dev.langchain4j.data.embedding.Embedding;
+import dev.langchain4j.data.segment.TextSegment;
+import dev.langchain4j.model.embedding.EmbeddingModel;
+import dev.langchain4j.model.embedding.onnx.allminilml6v2q.AllMiniLmL6V2QuantizedEmbeddingModel;
+import dev.langchain4j.store.embedding.EmbeddingMatch;
+import dev.langchain4j.store.embedding.EmbeddingSearchRequest;
+import dev.langchain4j.store.embedding.EmbeddingSearchResult;
+import dev.langchain4j.store.embedding.EmbeddingStore;
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Random;
+
+public class JVectorEmbeddingStoreExample {
+
+    private final static String TEST_DOCUMENT = "test-document.txt";
+    public static final String TMP_JVECTOR_EMBEDDING_STORE = "/tmp/jvector-embedding-store";
+
+    public static void main(String[] args) {
+
+        File tempPath = new File(TMP_JVECTOR_EMBEDDING_STORE);
+        try {
+            // Create the default embedding model
+            EmbeddingModel embeddingModel = new AllMiniLmL6V2QuantizedEmbeddingModel();
+
+            // Read all lines from the text file once
+            if (JVectorEmbeddingStoreExample.class.getClassLoader().getResource(TEST_DOCUMENT) == null) {
+                throw new RuntimeException("Test document not found: " + TEST_DOCUMENT);
+            }
+            List<String> lines = readLinesFromResource(TEST_DOCUMENT);
+            System.out.println("Read " + lines.size() + " lines from " + TEST_DOCUMENT);
+            System.out.println();
+
+            if (!tempPath.exists()) {
+                boolean created = tempPath.mkdirs();
+                if (!created) {
+                    throw new RuntimeException("Failed to create temporary directory: " + TMP_JVECTOR_EMBEDDING_STORE);
+                }
+            }
+            File indexPath = new File(tempPath, "example-index");
+
+            // First store: JVector with maxDegree 16
+            EmbeddingStore<TextSegment> jvectorStore1 = JVectorEmbeddingStore.builder()
+                    .dimension(384)
+                    .maxDegree(16)
+                    .build();
+
+            runWithStore(jvectorStore1, embeddingModel, lines, "JVectorStore(maxDegree=16)");
+
+            // Second store: JVector with a different configuration (maxDegree 8)
+            EmbeddingStore<TextSegment> jvectorStore2 = JVectorEmbeddingStore.builder()
+                    .dimension(384)
+                    .maxDegree(8)
+                    .persistencePath(indexPath.getAbsolutePath())
+                    .build();
+
+            runWithStore(jvectorStore2, embeddingModel, lines, "JVectorStore(maxDegree=8)");
+        } catch (Exception e) {
+            System.err.println("Failed to run the example due to: " + e.getMessage());
+        } finally {
+            // Clean up the temporary index directory
+            if (tempPath.exists() && tempPath.isDirectory()) {
+                final File[] files = tempPath.listFiles();
+                if (files != null) {
+                    for (File file : files) {
+                        if (!file.delete()) {
+                            System.err.println("Failed to delete file: " + file.getAbsolutePath());
+                        }
+                    }
+                }
+            }
+        }
+    }
+
+    /**
+     * Runs the common workflow against the provided embedding store.
+     */
+    private static void runWithStore(EmbeddingStore<TextSegment> embeddingStore,
+                                     EmbeddingModel embeddingModel,
+                                     List<String> lines,
+                                     String storeName) {
+
+        long startTime = System.currentTimeMillis();
+        System.out.println("=== Running with store: " + storeName + " ===");
+        System.out.println("Adding embeddings to the store...");
+        int added = 0;
+        for (String line : lines) {
+            if (!line.trim().isEmpty()) {
+                TextSegment segment = TextSegment.from(line);
+                Embedding embedding = embeddingModel.embed(segment).content();
+                embeddingStore.add(embedding, segment);
+                added++;
+            }
+        }
+        System.out.println("Successfully added " + added + " embeddings to the store");
+        System.out.println();
+
+        // Query the store with random lines from the file
+        Random random = new Random();
+        int numberOfQueries = 5;
+
+        System.out.println("Querying the embedding store with " + numberOfQueries + " random lines:");
+        System.out.println("=========================================");
+
+        for (int i = 0; i < numberOfQueries; i++) {
+            String randomLine = lines.get(random.nextInt(lines.size()));
+            System.out.println("\nQuery " + (i + 1) + ": " + randomLine);
+
+            Embedding queryEmbedding = embeddingModel.embed(randomLine).content();
+
+            EmbeddingSearchRequest searchRequest = EmbeddingSearchRequest.builder()
+                    .queryEmbedding(queryEmbedding)
+                    .maxResults(3)
+                    .build();
+
+            EmbeddingSearchResult<TextSegment> result = embeddingStore.search(searchRequest);
+            List<EmbeddingMatch<TextSegment>> matches = result.matches();
+
+            System.out.println("Top 3 matches:");
+            for (int j = 0; j < matches.size(); j++) {
+                EmbeddingMatch<TextSegment> match = matches.get(j);
+                System.out.printf("  %d. Score: %.4f - %s%n",
+                        j + 1,
+                        match.score(),
+                        match.embedded().text());
+            }
+        }
+
+        long endTime = System.currentTimeMillis();
+        System.out.printf("=== Finished running with store: %s in %d msec. ===%n",
+                storeName, (endTime - startTime));
+        System.out.println();
+    }
+
+    /**
+     * Read all lines from a resource file
+     */
+    private static List<String> readLinesFromResource(String resourceName) {
+        List<String> lines = new ArrayList<>();
+        try (InputStream inputStream = JVectorEmbeddingStoreExample.class
+                .getClassLoader()
+                .getResourceAsStream(resourceName)) {
+            if (inputStream == null) {
+                throw new RuntimeException("Resource not found: " + resourceName);
+            }
+            try (BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream))) {
+                String line;
+                while ((line = reader.readLine()) != null) {
+                    lines.add(line);
+                }
+            }
+        } catch (Exception e) {
+            throw new RuntimeException("Failed to read resource file: " + resourceName, e);
+        }
+        return lines;
+    }
+}

jvector-example/src/main/resources/test-document.txt

@@ -0,0 +1,40 @@
+The Earth completes one revolution around the Sun in approximately 365.25 days.
+Each year the Earth makes a full orbit around the Sun, taking about 365.25 days.
+Machine learning is a field of AI that builds models to learn patterns from data.
+ML focuses on creating algorithms that learn from examples and improve over time.
+The Pacific Ocean covers more area than any other ocean and is also the deepest.
+The Pacific is the biggest and deepest ocean on the planet, containing the deepest trenches.
+Photosynthesis enables plants to convert light energy into chemical energy and oxygen.
+Plants use photosynthesis to transform sunlight into glucose and release oxygen.
+The Great Wall of China stretches thousands of kilometers and is a famous historic structure.
+China's Great Wall is a renowned fortified structure built over centuries across the landscape.
+Python is a versatile high-level language commonly used for data analysis and scripting.
+Python's simplicity and libraries make it a preferred language for data science tasks.
+Mount Everest stands at about 8,848 meters and is the highest peak on Earth.
+At roughly 8,848 meters above sea level, Mount Everest is the planet's tallest mountain.
+Shakespeare authored plays such as Hamlet and many other notable works.
+William Shakespeare wrote famous plays including Hamlet, Othello, and Macbeth.
+DNA stores the genetic code that guides the growth and functioning of living organisms.
+The sequence of nucleotides in DNA encodes the hereditary information for organisms.
+The Eiffel Tower in Paris was finished in 1889 and measures around 330 meters tall.
+Completed in 1889, the Eiffel Tower rises to approximately 330 meters above Paris.
+Artificial neural networks are inspired by the structure and function of biological neurons.
+Neural network models imitate networks of neurons to process information and learn.
+The Amazon rainforest is estimated to produce about twenty percent of the world's oxygen.
+About one-fifth of global oxygen production is attributed to the vast Amazon rainforest.
+Albert Einstein introduced the theory of relativity in the early twentieth century.
+Einstein developed both special and general relativity during the early 1900s.
+James Naismith invented the game of basketball in 1891 while in Massachusetts.
+Basketball was created by James Naismith in 1891 at a Massachusetts training school.
+The adult human brain contains on the order of 86 billion neurons forming complex networks.
+Researchers estimate the human brain has roughly 86 billion nerve cells.
+Coffee ranks among the most widely consumed beverages worldwide each day.
+Globally, coffee is one of the leading beverages consumed by millions daily.
+The speed of light in a vacuum is approximately 299,792 kilometers per second.
+In vacuum, light travels at about 299,792 km/s, a fundamental physical constant.
+Ancient Egyptians constructed pyramids to serve as monumental tombs for their pharaohs.
+The pyramids were built by the ancient Egyptians as burial complexes for their rulers.
+Quantum computing harnesses quantum phenomena like superposition to perform computation.
+Quantum computers use entanglement and superposition to tackle certain computational problems.
+The Mona Lisa was painted by Leonardo da Vinci during the sixteenth century.
+Leonardo da Vinci created the Mona Lisa in the 1500s, one of the most famous paintings.

pom.xml

@@ -54,6 +54,7 @@
         <module>payara-micro-example</module>
         <module>gpullama3.java-example</module>
         <module>watsonx-ai-examples</module>
+        <module>jvector-example</module>
     </modules>
 
 </project>