Add semantic-cache module: CallAdvisor over a Redis Stack vector index with a real in-process embedding model; threshold sweep (hit rate against wrong answers), 600-request replay with an illustrative cost model, tenant filter, expiry, look-alike and embedding-model-change traps; optional real local model

Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01G8ikz8xdWuTP5yun8DZ1hk
2026-10-11 09:46:19 +00:00
parent cdee85d3f4
commit d51ef56468
24 changed files with 1383 additions and 0 deletions
@@ -0,0 +1,76 @@
+<?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>4.1.1</version>
+    <relativePath/>
+  </parent>
+
+  <groupId>com.ankurm</groupId>
+  <artifactId>semantic-cache</artifactId>
+  <version>1.0.0</version>
+  <name>semantic-cache</name>
+  <description>A semantic cache for LLM calls on Spring AI 2.0: a CallAdvisor over Redis vector search, a real local embedding model, threshold tuning and hit rate measured.</description>
+
+  <properties>
+    <java.version>25</java.version>
+    <spring-ai.version>2.0.1</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>
+    <dependency>
+      <groupId>org.springframework.ai</groupId>
+      <artifactId>spring-ai-client-chat</artifactId>
+    </dependency>
+    <!-- The store module, not the starter: the store is built by hand so the index settings are visible. -->
+    <dependency>
+      <groupId>org.springframework.ai</groupId>
+      <artifactId>spring-ai-redis-store</artifactId>
+    </dependency>
+    <!-- all-MiniLM-L6-v2 run in-process through ONNX Runtime and DJL. -->
+    <dependency>
+      <groupId>org.springframework.ai</groupId>
+      <artifactId>spring-ai-transformers</artifactId>
+    </dependency>
+    <!-- Only the optional real-model test uses this; it is skipped when no Ollama is listening. -->
+    <dependency>
+      <groupId>org.springframework.ai</groupId>
+      <artifactId>spring-ai-ollama</artifactId>
+      <scope>test</scope>
+    </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 -Xmx2g</argLine>
+        </configuration>
+      </plugin>
+    </plugins>
+  </build>
+</project>