Add hybrid-search module: vector, tsvector and BM25 fused with Reciprocal Rank Fusion in Java and SQL over one PostgreSQL table; quality by query type, held-out k check, plans and latency at 50k rows

Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_0146opDKBYtADXvkc39zdiyw
2026-10-22 18:04:49 +00:00
parent d7e68a14af
commit 2ccf1d8d19
26 changed files with 1508 additions and 0 deletions
@@ -0,0 +1,64 @@
+<?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 https://maven.apache.org/xsd/maven-4.0.0.xsd">
+  <modelVersion>4.0.0</modelVersion>
+
+  <parent>
+    <groupId>org.springframework.boot</groupId>
+    <artifactId>spring-boot-starter-parent</artifactId>
+    <version>4.1.2</version>
+    <relativePath/>
+  </parent>
+
+  <groupId>com.ankurm</groupId>
+  <artifactId>hybrid-search</artifactId>
+  <version>1.0.0</version>
+  <name>hybrid-search</name>
+  <description>Hybrid search on one PostgreSQL: pgvector and tsvector queries fused with Reciprocal Rank Fusion in Java, a real BM25 for comparison, and a Spring AI DocumentRetriever, measured on a labelled set of 60 queries.</description>
+
+  <properties>
+    <java.version>25</java.version>
+    <spring-ai.version>2.0.2</spring-ai.version>
+  </properties>
+
+  <dependencyManagement>
+    <dependencies>
+      <dependency>
+        <groupId>org.springframework.ai</groupId>
+        <artifactId>spring-ai-bom</artifactId>
+        <version>${spring-ai.version}</version>
+        <type>pom</type>
+        <scope>import</scope>
+      </dependency>
+    </dependencies>
+  </dependencyManagement>
+
+  <dependencies>
+    <!-- Store module, not the starter: the table is created by the store and then extended by hand. -->
+    <dependency><groupId>org.springframework.ai</groupId><artifactId>spring-ai-pgvector-store</artifactId></dependency>
+    <!-- DocumentRetriever, Query and RetrievalAugmentationAdvisor. -->
+    <dependency><groupId>org.springframework.ai</groupId><artifactId>spring-ai-rag</artifactId></dependency>
+    <!-- all-MiniLM-L6-v2 in-process through ONNX Runtime: a real embedding model, no API key. -->
+    <dependency><groupId>org.springframework.ai</groupId><artifactId>spring-ai-transformers</artifactId></dependency>
+    <dependency><groupId>org.postgresql</groupId><artifactId>postgresql</artifactId></dependency>
+    <dependency><groupId>org.springframework.boot</groupId><artifactId>spring-boot-starter-jdbc</artifactId></dependency>
+    <dependency>
+      <groupId>org.springframework.boot</groupId>
+      <artifactId>spring-boot-starter-test</artifactId>
+      <scope>test</scope>
+    </dependency>
+  </dependencies>
+
+  <build>
+    <plugins>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-surefire-plugin</artifactId>
+        <configuration>
+          <argLine>-Duser.timezone=UTC -Dstdout.encoding=UTF-8 -Dfile.encoding=UTF-8 -Xmx3g</argLine>
+        </configuration>
+      </plugin>
+    </plugins>
+  </build>
+</project>