Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Milvus配置 #97

Open
yubo200526 opened this issue Nov 25, 2024 · 3 comments
Open

Milvus配置 #97

yubo200526 opened this issue Nov 25, 2024 · 3 comments

Comments

@yubo200526
Copy link

请问下使用video_understanding模块必须配置Milvus的docker嘛

@panregedit
Copy link
Collaborator

哈喽,用Docker部署Milvus服务并不是必须的。新版的Milvus支持了轻量版的Milvus Lite,通过在本地存储一个.db文件实现向量存储的搜索功能。OmAgent默认支持使用Milvus Lite,你不需要部署或者配置Milvus服务。
不过如果你需要更好的性能,还是推荐部署Docker版本。

@yubo200526
Copy link
Author

因为我在使用Milvus服务时,配置STORAGE_NAME为‘default’,貌似该collection的dim默认为512,即使我配置DIM为3072,仍然会报错<MilvusException: (code=2000, message=vector dimension mismatch, expected vector size(byte) 512, actual 12288.: segcore error)>;因此我想要配置STORAGE_NAME为其他字段时发现连接MilvusClient比较卡顿,好像不太支持其他函数例如get方法,会得到报错 <MilvusException: (code=100, message=Can not find test's schema: collection not found)>,请您帮我解答一下这个困惑,我该如何正确配置STORAGE_NAME和DIM?

@panregedit
Copy link
Collaborator

MilvusLTM 包含一个 dim 属性,通过设置这个属性可以设置存储的向量维度。当你compile container之后会得到一个container.yaml配置文件,你可以在配置文件中找到MilvusLTM以及dim属性,修改这个属性值,并使用container.from_config重新加载,就可以成功修改dim配置。LTM相关的例子可以参考 examples/step4_outfit_with_ltm 示例,以及 docs/examples/outfit_with_ltm.md 文档。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants