Redis

spring:
  data:
    redis:
      url: <redis instance url>
  ai:
    vectorstore:
      redis:
        initialize-schema: true
        index-name: custom-index
        prefix: custom-prefix

spring.data.redis.host=localhost
spring.data.redis.port=6379
spring.data.redis.username=default
spring.data.redis.password=

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-starter-vector-store-redis-semantic-cache</artifactId>
</dependency>

dependencies {
    implementation 'org.springframework.ai:spring-ai-starter-vector-store-redis-semantic-cache'
}

spring:
  ai:
    vectorstore:
      redis:
        semantic-cache:
          enabled: true
          host: localhost
          port: 6379
          similarity-threshold: 0.85
          index-name: my-app-cache
          prefix: "my-app:semantic-cache:"

@Autowired
private SemanticCache semanticCache;

@Autowired
private ChatModel chatModel;

public void example() {
    // Create the cache advisor
    SemanticCacheAdvisor cacheAdvisor = SemanticCacheAdvisor.builder()
        .cache(semanticCache)
        .build();

    // First query - calls the LLM and caches the response
    ChatResponse response1 = ChatClient.builder(chatModel)
        .build()
        .prompt("What is the capital of France?")
        .advisors(cacheAdvisor)
        .call()
        .chatResponse();

    // Similar query - returns cached response (no LLM call)
    ChatResponse response2 = ChatClient.builder(chatModel)
        .build()
        .prompt("Tell me the capital city of France")
        .advisors(cacheAdvisor)
        .call()
        .chatResponse();

    // response1 and response2 contain the same cached answer
}

@Autowired
private SemanticCache semanticCache;

// Store a response with a query
semanticCache.set("What is the capital of France?", chatResponse);

// Store with TTL (time-to-live) for automatic expiration
semanticCache.set("What's the weather today?", weatherResponse, Duration.ofHours(1));

// Retrieve a semantically similar response
Optional<ChatResponse> cached = semanticCache.get("Tell me France's capital");

if (cached.isPresent()) {
    // Use the cached response
    String answer = cached.get().getResult().getOutput().getText();
}

// Clear all cached entries
semanticCache.clear();

@Configuration
public class SemanticCacheConfig {

    @Bean
    public JedisPooled jedisPooled() {
        return new JedisPooled("localhost", 6379);
    }

    @Bean
    public SemanticCache semanticCache(JedisPooled jedisPooled, EmbeddingModel embeddingModel) {
        return DefaultSemanticCache.builder()
            .jedisClient(jedisPooled)
            .embeddingModel(embeddingModel)
            .distanceThreshold(0.3)           // Lower = stricter matching
            .indexName("my-semantic-cache")
            .prefix("cache:")
            .build();
    }

    @Bean
    public SemanticCacheAdvisor semanticCacheAdvisor(SemanticCache cache) {
        return SemanticCacheAdvisor.builder()
            .cache(cache)
            .build();
    }
}

// Create isolated caches for different users or contexts
SemanticCache user1Cache = DefaultSemanticCache.builder()
    .jedisClient(jedisPooled)
    .embeddingModel(embeddingModel)
    .indexName("user-1-cache")
    .build();

SemanticCache user2Cache = DefaultSemanticCache.builder()
    .jedisClient(jedisPooled)
    .embeddingModel(embeddingModel)
    .indexName("user-2-cache")
    .build();

// Each user gets their own isolated cache space
SemanticCacheAdvisor user1Advisor = SemanticCacheAdvisor.builder()
    .cache(user1Cache)
    .build();

SemanticCacheAdvisor cacheAdvisor = SemanticCacheAdvisor.builder()
    .cache(semanticCache)
    .build();

// Query with technical support persona
ChatResponse technicalResponse = ChatClient.builder(chatModel)
    .build()
    .prompt()
    .system("You are a technical support specialist. Provide detailed technical answers.")
    .user("How do I reset my password?")
    .advisors(cacheAdvisor)
    .call()
    .chatResponse();

// Same query with customer service persona - cache MISS (different context)
ChatResponse serviceResponse = ChatClient.builder(chatModel)
    .build()
    .prompt()
    .system("You are a friendly customer service agent. Keep responses brief and helpful.")
    .user("How do I reset my password?")
    .advisors(cacheAdvisor)
    .call()
    .chatResponse();

// Same query with technical support persona again - cache HIT
ChatResponse technicalAgain = ChatClient.builder(chatModel)
    .build()
    .prompt()
    .system("You are a technical support specialist. Provide detailed technical answers.")
    .user("How do I reset my password?")
    .advisors(cacheAdvisor)
    .call()
    .chatResponse();
// Returns the cached technical response

// Store with explicit context hash
String contextHash = "technical-support-context";
semanticCache.set("How do I reset my password?", response, contextHash);

// Retrieve with context filtering
Optional<ChatResponse> cached = semanticCache.get("How do I reset my password?", contextHash);

// Different context hash returns empty (no match)
Optional<ChatResponse> otherContext = semanticCache.get("How do I reset my password?", "billing-context");

// Strict matching - only very similar queries hit the cache
SemanticCache strictCache = DefaultSemanticCache.builder()
    .jedisClient(jedisPooled)
    .embeddingModel(embeddingModel)
    .distanceThreshold(0.2)  // Strict (distance-based, lower = stricter)
    .build();

// Lenient matching - broader semantic similarity accepted
SemanticCache lenientCache = DefaultSemanticCache.builder()
    .jedisClient(jedisPooled)
    .embeddingModel(embeddingModel)
    .distanceThreshold(0.5)  // Lenient
    .build();

// Cache weather data for 1 hour
semanticCache.set("What's the weather in New York?", weatherResponse, Duration.ofHours(1));

// Cache general knowledge indefinitely (no TTL)
semanticCache.set("What is photosynthesis?", scienceResponse);

// Redis automatically removes expired entries