import
Use when the user wants to import bulk data into a Milvus collection via Zilliz Cloud import jobs, from object storage or from files uploaded to a volume.
Install
With your agent
Install OMGSkills skill "zilliztech/zilliz-plugin:plugins/zilliz/skills/import" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/zilliztech/zilliz-plugin /tmp/zilliz-plugin && ln -s /tmp/zilliz-plugin/plugins/zilliz/skills/import ~/.claude/skills/importFrom README
Prerequisites CLI installed and logged in (see skill). Target collection must exist on the target cluster. Commands Reference Start an Import Job List Imports Check Import Status Import Sources import start reads its source from --body. There are two kinds of source: A managed volume (preferred when the files are local). Upload them with zilliz volume upload (see the volume skill), then reference the volume and the file paths inside it: Object storage URLs the user already has, with access keys when the bucket is not public: Each inner list in dataPaths / objectUrls is one file group. Supported file formats: Parquet, JSON, CSV. --body also accepts dbName and partitionName. Import stages (zilliz stage ...) are deprecated in favor of volumes. The commands still work for existing stages, but do not suggest them for new imports.
More from this repo
acl
Used when the user wants to manage Zilliz Cloud access control -- custom org or project roles and their policies,...
ask-zilliz
Zilliz Cloud onboarding and usage assistant.
backup
Used when the user wants to create, list, describe, delete, export, or restore backups, or manage backup policies on...