I am trying to do something where I have 2 advisors, one is a typical RAG vector store for my QuestionAnswerAdvisor and one is using redis for an embedding based cache of questions. The original QuestionAnswerAdvisor works great but when I add the redis store I don’t see how to qualify the injected bean to make sure it is using redis instead of pinecone. I tried this

@Bean(name = "openAiBuildClient")
public ChatClient buildClient(
  @Qualifier("openAiChatClientBuilder") ChatClient.Builder openAiBuilder,
  MessageChatMemoryAdvisor messageChatMemoryAdvisor,
  RedisVectorStore redisVectorStore,
  PineconeVectorStore pineconeVectorStore
) {

spring:
  application:
    name: "my-spring-ai"
  ai:
    vectorstore:
      redis:
        index: spring-ai-example
        uri: redis://localhost:6379
      pinecone:
        apiKey: ${PINECONE_API_KEY}
        index-name: spring-ai-example

But it doesn’t work like that because the Bean is a VectorStore instead of the individual RedisVectorStore and PineconeVectorStore.

So is it possible to have multiple vector stores at the same time with an @Qualifier? If so how do I do it?