嘉兴优化网站公司百度推广外包

 ​检查中文分词配置​

Milvus 2.5+ 支持原生中文全文检索，但需显式配置中文分词器：

创建集合时指定分词器类型为 chinese

python

schema.add_field(field_name="text", datatype=DataType.VARCHAR, max_length=65535, enable_analyzer=True, analyzer_params={"type": "chinese"}  # 关键配置[7,6](@ref)
)

Java

        CreateCollectionReq.CollectionSchema schema = CreateCollectionReq.CollectionSchema.builder().build();        Map<String, Object> analyzerParams = new HashMap<>();analyzerParams.put("type", "chinese");schema.addField(AddFieldReq.builder().fieldName("text").dataType(DataType.VarChar).maxLength(65535).enableAnalyzer(true).analyzerParams(analyzerParams).build());