You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
使用milvus作为向量库,新建知识图谱或者向量类型的知识库时,上传第一个文件后,进行文件同步时报错DataNotMatchException: (code=1, message=The data doesn't match with schema fields, expect 4 list, got 20); 目前测试的情况是只有第一个文件的第一次同步会报错。
Search before asking
Operating system information
Linux
Python version information
DB-GPT version
main
Related scenes
Installation Information
Installation From Source
Docker Installation
Docker Compose Installation
Cluster Installation
AutoDL Image
Other
Device information
GPU
GPU Count:1
gpu memory:24G
Models information
LLM_MODEL: qwen2.5-7b-instruct
EMBEDDING_MODEL:m3e-base
What happened
使用milvus作为向量库,新建知识图谱或者向量类型的知识库时,上传第一个文件后,进行文件同步时报错DataNotMatchException: (code=1, message=The data doesn't match with schema fields, expect 4 list, got 20);
目前测试的情况是只有第一个文件的第一次同步会报错。
What you expected to happen
只有新建的知识库在上传第一个文件进行同步时才会提示以上错误,初步定位到文件milvus_store的init_schema_and_load方法中,成员变量self.fields的字段长度应该是4,但是以上报错是因为它的长度变为20,其实是4个字段重复出现了5次,导致总共是20次,看起来像是线程不安全导致的问题
How to reproduce
1.构建一个知识图谱/向量类型的知识库;
2.上传一个文件;
3.选择上传的文件,点击"同步"
Additional context
No response
Are you willing to submit PR?
The text was updated successfully, but these errors were encountered: