Bug description

When I configure the databaseName and collectionName in the spring-ai-milvus-store-spring-boot-starter, I encounter an error when calling vectorStore.add(splitDocuments). The error message is:

can't find collection[database=default][collection=vector_store]

Upon investigation, I found that the configuration parameters are correctly read, but it seems that at some point, the values are being overwritten and set back to the default values.

Image

Environment

springboot 3.4.2 
jdk 17
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>

        <dependency>
            <groupId>com.alibaba.cloud.ai</groupId>
            <artifactId>spring-ai-alibaba-starter</artifactId>
            <version>1.0.0-M5.1</version>
        </dependency>

        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-tika-document-reader</artifactId>
            <version>1.0.0-M5</version>
        </dependency>

        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-milvus-store-spring-boot-starter</artifactId>
            <version>1.0.0-M5</version>
        </dependency>

Steps to reproduce

package com.njy.ai.embedding.controller;

import org.springframework.ai.document.Document;
import org.springframework.ai.reader.tika.TikaDocumentReader;
import org.springframework.ai.transformer.splitter.TokenTextSplitter;
import org.springframework.ai.vectorstore.milvus.MilvusVectorStore;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RestController;

import java.util.List;

@RestController
public class DocumentEmbeddingController {
    @Autowired
    private MilvusVectorStore vectorStore;

    @GetMapping("/insertDocuments")
    public void insertDocuments() {
        TikaDocumentReader tikaDocumentReader = new TikaDocumentReader("app.md");
        List<Document> documents = tikaDocumentReader.get();
        List<Document> splitDocuments = new TokenTextSplitter().apply(documents);
        vectorStore.add(splitDocuments);
    }

}

Expected behavior Correct use of configuration files

Minimal Complete Reproducible example example