Added Disco example [skip ci]

Author: ankane

README.md

@@ -41,6 +41,7 @@ Or check out some examples:
 - [Hybrid search](examples/hybrid/src/main/java/com/example/Example.java) with Deep Java Library (Reciprocal Rank Fusion)
 - [Sparse search](examples/sparse/src/main/java/com/example/Example.java) with Text Embeddings Inference
 - [Extended-connectivity fingerprints](examples/cdk/src/main/java/com/example/Example.java) with the Chemistry Development Kit
+- [Recommendations](examples/disco/src/main/java/com/example/Example.java) with Disco
 - [Horizontal scaling](examples/citus/src/main/java/com/example/Example.java) with Citus
 - [Bulk loading](examples/loading/src/main/java/com/example/Example.java) with `COPY`
 

examples/disco/pom.xml

@@ -0,0 +1,56 @@
+<?xml version='1.0' encoding='UTF-8'?>
+<project xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://maven.apache.org/POM/4.0.0">
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>com.example</groupId>
+    <artifactId>example</artifactId>
+    <version>1</version>
+    <properties>
+        <maven.compiler.release>11</maven.compiler.release>
+        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+    </properties>
+    <dependencies>
+        <dependency>
+            <groupId>org.postgresql</groupId>
+            <artifactId>postgresql</artifactId>
+            <version>42.7.3</version>
+        </dependency>
+        <dependency>
+            <groupId>com.pgvector</groupId>
+            <artifactId>pgvector</artifactId>
+            <version>0.1.6</version>
+        </dependency>
+        <dependency>
+            <groupId>org.ankane</groupId>
+            <artifactId>disco</artifactId>
+            <version>0.1.0</version>
+        </dependency>
+    </dependencies>
+    <build>
+        <plugins>
+            <plugin>
+                <artifactId>maven-assembly-plugin</artifactId>
+                <version>3.7.1</version>
+                <configuration>
+                    <descriptorRefs>
+                        <descriptorRef>jar-with-dependencies</descriptorRef>
+                    </descriptorRefs>
+                    <archive>
+                        <manifest>
+                            <mainClass>com.example.Example</mainClass>
+                        </manifest>
+                    </archive>
+                    <finalName>example</finalName>
+                </configuration>
+                <executions>
+                <execution>
+                    <id>make-assembly</id>
+                    <phase>package</phase>
+                        <goals>
+                            <goal>single</goal>
+                        </goals>
+                    </execution>
+                </executions>
+            </plugin>
+        </plugins>
+    </build>
+</project>

examples/disco/src/main/java/com/example/Example.java

@@ -0,0 +1,69 @@
+package com.example;
+
+import java.sql.Connection;
+import java.sql.DriverManager;
+import java.sql.PreparedStatement;
+import java.sql.ResultSet;
+import java.sql.SQLException;
+import java.sql.Statement;
+import java.util.ArrayList;
+import com.pgvector.PGvector;
+import org.ankane.disco.Data;
+import org.ankane.disco.Dataset;
+import org.ankane.disco.Recommender;
+
+public class Example {
+    public static void main(String[] args) throws Exception {
+        Connection conn = DriverManager.getConnection("jdbc:postgresql://localhost:5432/pgvector_example");
+        Statement setupStmt = conn.createStatement();
+        setupStmt.executeUpdate("CREATE EXTENSION IF NOT EXISTS vector");
+        PGvector.addVectorType(conn);
+
+        Statement createStmt = conn.createStatement();
+        createStmt.executeUpdate("DROP TABLE IF EXISTS users");
+        createStmt.executeUpdate("DROP TABLE IF EXISTS movies");
+        createStmt.executeUpdate("CREATE TABLE users (id integer PRIMARY KEY, factors vector(20))");
+        createStmt.executeUpdate("CREATE TABLE movies (name text PRIMARY KEY, factors vector(20))");
+
+        Dataset<Integer, String> data = Data.loadMovieLens();
+        Recommender<Integer, String> recommender = Recommender
+            .builder()
+            .factors(20)
+            .fitExplicit(data);
+
+        for (Integer userId : recommender.userIds()) {
+            PreparedStatement insertStmt = conn.prepareStatement("INSERT INTO users (id, factors) VALUES (?, ?)");
+            insertStmt.setInt(1, userId);
+            insertStmt.setObject(2, new PGvector(recommender.userFactors(userId).get()));
+            insertStmt.executeUpdate();
+        }
+
+        for (String itemId : recommender.itemIds()) {
+            PreparedStatement insertStmt = conn.prepareStatement("INSERT INTO movies (name, factors) VALUES (?, ?)");
+            insertStmt.setString(1, itemId);
+            insertStmt.setObject(2, new PGvector(recommender.itemFactors(itemId).get()));
+            insertStmt.executeUpdate();
+        }
+
+        String movie = "Star Wars (1977)";
+        System.out.printf("Item-based recommendations for %s\n", movie);
+        PreparedStatement neighborStmt = conn.prepareStatement("SELECT name FROM movies WHERE name != ? ORDER BY factors <=> (SELECT factors FROM movies WHERE name = ?) LIMIT 5");
+        neighborStmt.setString(1, movie);
+        neighborStmt.setString(2, movie);
+        ResultSet rs = neighborStmt.executeQuery();
+        while (rs.next()) {
+            System.out.println("- " + rs.getString("name"));
+        }
+
+        int userId = 123;
+        System.out.printf("\nUser-based recommendations for user %d\n", userId);
+        neighborStmt = conn.prepareStatement("SELECT name FROM movies ORDER BY factors <#> (SELECT factors FROM users WHERE id = ?) LIMIT 5");
+        neighborStmt.setInt(1, userId);
+        rs = neighborStmt.executeQuery();
+        while (rs.next()) {
+            System.out.println("- " + rs.getString("name"));
+        }
+
+        conn.close();
+    }
+}