This version is still in development and is not considered stable yet. For the latest snapshot version, please use Spring AI 1.0.0-SNAPSHOT!spring-doc.cn
It is recommended that the Qdrant collection is created in advance with the appropriate dimensions and configurations. If the collection is not created, the QdrantVectorStore will attempt to create one using the Cosine similarity and the dimension of the configured EmbeddingModel.
this is a breaking change! In earlier versions of Spring AI, this schema initialization happened by default.
Refer to the Dependency Management section to add the Spring AI BOM to your build file. Refer to the Repositories section to add Milestone and/or Snapshot Repositories to your build file.
Check the list of configuration parameters to learn about the default values and configuration options.
Property Description Default value

spring.ai.vectorstore.qdrant.hostspring-doc.cn

The host of the Qdrant server.spring-doc.cn

localhostspring-doc.cn

spring.ai.vectorstore.qdrant.portspring-doc.cn

The gRPC port of the Qdrant server.spring-doc.cn

6334spring-doc.cn

spring.ai.vectorstore.qdrant.api-keyspring-doc.cn

The API key to use for authentication with the Qdrant server.spring-doc.cn

-spring-doc.cn

spring.ai.vectorstore.qdrant.collection-namespring-doc.cn

The name of the collection to use in Qdrant.spring-doc.cn

-spring-doc.cn

spring.ai.vectorstore.qdrant.use-tlsspring-doc.cn

Whether to use TLS(HTTPS).spring-doc.cn

falsespring-doc.cn

spring.ai.vectorstore.qdrant.initialize-schemaspring-doc.cn

Whether to initialize the backend schema or notspring-doc.cn

falsespring-doc.cn
These filter expressions are converted into the equivalent Qdrant filters.