Add rerank module: bi-encoder retrieval plus an ONNX Runtime cross-encoder reranker behind a Spring AI DocumentPostProcessor; hit@k and MRR by pool size and question kind, latency by candidates, batch size, threads and int8, and five reproduced traps. Local MiniLM models, no database or API key.

Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01Cfo2K4u4rF18QsPXPFnytf
2026-10-24 18:00:05 +00:00
parent 2ccf1d8d19
commit a429aa40f6
34 changed files with 1617 additions and 0 deletions
@@ -0,0 +1,65 @@
+<?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>rerank</artifactId>
+  <version>1.0.0</version>
+  <name>rerank</name>
+  <description>Cross-encoder reranking for RAG in Java: a bi-encoder retrieves 50 candidates, an ONNX Runtime cross-encoder rescores them, a Spring AI DocumentPostProcessor keeps the top 5. Quality and latency measured on 60 labelled queries.</description>
+
+  <properties>
+    <java.version>25</java.version>
+    <spring-ai.version>2.0.2</spring-ai.version>
+    <!-- Latest releases on Maven Central on 2026-10-24. -->
+    <onnxruntime.version>1.31.0</onnxruntime.version>
+    <djl.version>0.39.0</djl.version>
+  </properties>
+
+  <dependencyManagement>
+    <dependencies>
+      <dependency>
+        <groupId>org.springframework.ai</groupId>
+        <artifactId>spring-ai-bom</artifactId>
+        <version>${spring-ai.version}</version>
+        <type>pom</type>
+        <scope>import</scope>
+      </dependency>
+    </dependencies>
+  </dependencyManagement>
+
+  <dependencies>
+    <!-- DocumentPostProcessor, DocumentRetriever, Query and RetrievalAugmentationAdvisor. -->
+    <dependency><groupId>org.springframework.ai</groupId><artifactId>spring-ai-rag</artifactId></dependency>
+    <!-- Deliberately NOT spring-ai-transformers: its TransformersEmbeddingModel needs a DJL engine that downloads a PyTorch native library at first use. ONNX Runtime and the DJL tokenizers are enough for both stages. -->
+    <dependency><groupId>com.microsoft.onnxruntime</groupId><artifactId>onnxruntime</artifactId><version>${onnxruntime.version}</version></dependency>
+    <dependency><groupId>ai.djl</groupId><artifactId>api</artifactId><version>${djl.version}</version></dependency>
+    <dependency><groupId>ai.djl.huggingface</groupId><artifactId>tokenizers</artifactId><version>${djl.version}</version></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>