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
this is a breaking change! In earlier versions of Spring AI, this schema initialization happened by default.

You can replace Azure Open AI implementation with any valid OpenAI implementation that supports the Embeddings interface. For example, you could use Spring AI’s Open AI or TransformersEmbedding implementations for embeddings instead of the Azure implementation.spring-doc.cn
Refer to the Dependency Management section to add the Spring AI BOM to your build file.
Property Default value

spring.ai.vectorstore.azure.urlspring-doc.cn

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

spring.ai.vectorstore.azure.initialze-schemaspring-doc.cn

falsespring-doc.cn

spring.ai.vectorstore.azure.index-namespring-doc.cn

spring_ai_azure_vector_storespring-doc.cn

spring.ai.vectorstore.azure.default-top-kspring-doc.cn

4spring-doc.cn

spring.ai.vectorstore.azure.default-similarity-thresholdspring-doc.cn

0.0spring-doc.cn

spring.ai.vectorstore.azure.embedding-propertyspring-doc.cn

embeddingspring-doc.cn

spring.ai.vectorstore.azure.index-namespring-doc.cn

spring-ai-document-indexspring-doc.cn

You must list explicitly all metadata field names and types for any metadata key used in the filter expression. The list above registers filterable metadata fields: country of type TEXT, year of type INT64, and active of type BOOLEAN.spring-doc.cn

If the filterable metadata fields are expanded with new entries, you have to (re)upload/update the documents with this metadata.spring-doc.cn