Spring-ai PgVector column cannot have more than 2000 dimensions for index

Bug description yml config :

      spring:
        datasource:
          url: jdbc:postgresql://localhost:5432/postgres
          username: pgvector
          password: pgvector
          driver-class-name: org.postgresql.Driver
        ai:
          ollama:
            base-url: http://localhost:11434
            embedding:
              options:
                model: gemma:2b
          vectorstore:
            pgvector:
              index-type: HNSW 
              distance-type: cosine_distance 
              dimensions: 2048

when start application, Failed to load ApplicationContext

Caused by: org.springframework.beans.factory.BeanCreationException: Error creating bean with name 'vectorStore' defined in class path resource [org/springframework/ai/autoconfigure/vectorstore/pgvector/PgVectorStoreAutoConfiguration.class]: StatementCallback; uncategorized SQLException for SQL [CREATE INDEX IF NOT EXISTS spring_ai_vector_index ON public.vector_store USING HNSW (embedding vector_cosine_ops) ]; SQL state [XX000]; error code [0]; ERROR: column cannot have more than 2000 dimensions for hnsw index at org.springframework.beans.factory.support.AbstractAutowireCapableBeanFactory.initializeBean(AbstractAutowireCapableBeanFactory.java:1786) at org.springframework.beans.factory.support.AbstractAutowireCapableBeanFactory.doCreateBean(AbstractAutowireCapableBeanFactory.java:600) at org.springframework.beans.factory.support.AbstractAutowireCapableBeanFactory.createBean(AbstractAutowireCapableBeanFactory.java:522) at org.springframework.beans.factory.support.AbstractBeanFactory.lambda$doGetBean$0(AbstractBeanFactory.java:326) at org.springframework.beans.factory.support.DefaultSingletonBeanRegistry.getSingleton(DefaultSingletonBeanRegistry.java:234) at org.springframework.beans.factory.support.AbstractBeanFactory.doGetBean(AbstractBeanFactory.java:324) at org.springframework.beans.factory.support.AbstractBeanFactory.getBean(AbstractBeanFactory.java:200) at org.springframework.beans.factory.support.DefaultListableBeanFactory.preInstantiateSingletons(DefaultListableBeanFactory.java:975) at org.springframework.context.support.AbstractApplicationContext.finishBeanFactoryInitialization(AbstractApplicationContext.java:962) at org.springframework.context.support.AbstractApplicationContext.refresh(AbstractApplicationContext.java:624) at org.springframework.boot.SpringApplication.refresh(SpringApplication.java:754) at org.springframework.boot.SpringApplication.refreshContext(SpringApplication.java:456) at org.springframework.boot.SpringApplication.run(SpringApplication.java:334) at org.springframework.boot.test.context.SpringBootContextLoader.lambda$loadContext$3(SpringBootContextLoader.java:137) at org.springframework.util.function.ThrowingSupplier.get(ThrowingSupplier.java:58) at org.springframework.util.function.ThrowingSupplier.get(ThrowingSupplier.java:46) at org.springframework.boot.SpringApplication.withHook(SpringApplication.java:1454) at org.springframework.boot.test.context.SpringBootContextLoader$ContextLoaderHook.run(SpringBootContextLoader.java:553) at org.springframework.boot.test.context.SpringBootContextLoader.loadContext(SpringBootContextLoader.java:137) at org.springframework.boot.test.context.SpringBootContextLoader.loadContext(SpringBootContextLoader.java:108) at org.springframework.test.context.cache.DefaultCacheAwareContextLoaderDelegate.loadContextInternal(DefaultCacheAwareContextLoaderDelegate.java:225) at org.springframework.test.context.cache.DefaultCacheAwareContextLoaderDelegate.loadContext(DefaultCacheAwareContextLoaderDelegate.java:152) ... 17 more

Environment Spring boot version: Spring AI version: 1.0.0-SNAPSHOT Java version JDK17 Vector Store : PgVector

when spring.ai.vectorstore.pgvector.index-type =HNSW and spring.ai.vectorstore.pgvector.dimensions > 2000 it will error. Spring-ai PgVector column cannot have more than 2000 dimensions for index

Comment From: ThomasVitale

That is the expected behavior because PGvector doesn't support higher dimensions than 2000 when the HNSW indexing strategy is used. There is an ongoing discussion in the PGvector project to raise the limit to at least 4096: https://github.com/pgvector/pgvector/issues/461.

This limitation is mentioned in the Spring AI documentation: https://docs.spring.io/spring-ai/reference/api/vectordbs/pgvector.html#_prerequisites.

Comment From: Fj-ivy

Thank you！