Update to Zilliz

{
  "description": "Use when the user wants to import bulk data into a Milvus collection via Zilliz Cloud import jobs, or manage import stages (pre-uploaded file holders that import jobs reference).",
  "included_files": [],
  "name": "import",
  "skill_md_contents": "---\nname: import\ndescription: Use when the user wants to import bulk data into a Milvus collection via Zilliz Cloud import jobs, or manage import stages (pre-uploaded file holders that import jobs reference).\n---\n\n## Prerequisites\n\n1. CLI installed and logged in (see setup skill).\n2. Target collection must exist on the target cluster.\n\n## Commands Reference\n\n### Import Jobs\n\n#### Start an Import Job\n\n```bash\nzilliz import start --collection <target-collection-name>\n# Optional:\n#   --cluster-id <target-cluster-id>\n#   --project-id <project-id>\n#   --region-id <region-id>\n# Or use raw JSON: --body '{\"files\": [[\"s3://bucket/path/data.parquet\"]]}'\n```\n\n#### List Imports\n\n```bash\nzilliz import list\n# Optional:\n#   --cluster-id <cluster-id>\n#   --project-id <project-id>\n#   --region-id <region-id>\n#   --database <database-name>\n```\n\n#### Check Import Status\n\n```bash\nzilliz import status --job-id <import-job-id>\n# Optional:\n#   --cluster-id <cluster-id>\n#   --project-id <project-id>\n#   --region-id <region-id>\n```\n\n### Import Stages\n\n#### List Stages\n\n```bash\nzilliz stage list\n# Optional: --project-id <filter-by-project-id>\n# Pagination: --page-size <n> --page <n>\n# Fetch all pages: --all\n```\n\n#### Create a Stage\n\n```bash\nzilliz stage create \\\n  --project-id <owning-project-id> \\\n  --region-id <cloud-region> \\\n  --stage-name <stage-name>\n```\n\n#### Delete a Stage\n\n```bash\nzilliz stage delete --stage-name <stage-name>\n```\n\n#### Apply\n\n```bash\nzilliz stage apply --stage-name <stage-name>\n# Optional:\n#   --project-id <project-id>\n#   --region-id <region-id>\n#   --cluster-id <target-cluster-id>\n#   --path <stage-subpath>\n```\n\n## Integration Setup\n\nImport requires a cloud storage integration to access data files. The `integration-id` is configured in the Zilliz Cloud console under **Project Settings > Integrations**. Ensure the integration has read access to the source bucket and path.\n\nSupported file formats: Parquet, JSON, CSV.\n\n## Stages vs. Direct Integrations\n\nA **stage** is a named, project-scoped handle to a pre-uploaded set of files in\nmanaged cloud storage. Import jobs reference either:\n\n- a customer-owned bucket via an integration (the original flow above), or\n- a stage (`zilliz stage create --project-id <id> --region-id <region> --stage-name <name>`), which is preferable when the user wants Zilliz Cloud to host the staging bucket.\n\n`stage apply` updates an existing stage in place; `stage delete` removes it\n(confirm with the user first -- pending import jobs referencing the stage\nwill fail).\n\n## Import Targets\n\n`import start`, `import list`, and `import status` accept either:\n\n- `--cluster-id <id>` (legacy form, still supported), or\n- `--project-id <id>` together with `--region-id <region>` (the server then\n  resolves the target instance from the project + region pair).\n\nYou must supply exactly one of those two grouping forms -- the CLI rejects\nan import command that provides neither, or that provides `--project-id`\nwithout `--region-id`.\n\n## Guidance\n\n- Import jobs run asynchronously. After starting a job, use `import status` to track progress.\n- The data files must be accessible from Zilliz Cloud (either via a configured integration or via a stage).\n- The collection schema must match the data file structure.\n- When importing into a Vector Lake / on-demand-cluster setup, prefer the `--project-id` + `--region-id` form -- on-demand clusters do not have a stable single cluster ID to point at.\n"
}