{"id":19434,"plugin_id":"plugins_6a992fa57b6481918dffd35d23f03408","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:15:34.558Z","digest":"78921960967acb1da0d03e5e716ff951f3021ce972e38ff61d25556c33913583","against":null,"payload":{"description":"Use when the user wants to create, list, describe, or drop indexes on Milvus collections.","included_files":[],"name":"index","skill_md_contents":"---\nname: index\ndescription: Use when the user wants to create, list, describe, or drop indexes on Milvus collections.\n---\n\n## Prerequisites\n\n1. CLI installed, a usable data-plane credential configured, and cluster context set (see setup skill).\n2. Target collection must exist (see collection skill).\n\n## Commands Reference\n\nAll index commands accept an optional `--database <db-name>` flag. If omitted, the database from the current context is used.\n\n### Create an Index\n\n```bash\nzilliz index create --collection <collection-name>\n# Optional: --database <database-name>\n# Or use raw JSON: --body '{\"indexParams\": [{\"fieldName\": \"vector\", \"indexType\": \"AUTOINDEX\", \"metricType\": \"COSINE\"}]}'\n```\n\n### List Indexes\n\n```bash\nzilliz index list --collection <collection-name>\n# Optional: --database <database-name>\n```\n\n### Describe an Index\n\n```bash\nzilliz index describe --collection <collection-name> --index-name <index-name>\n# Optional: --database <database-name>\n```\n\n### Drop an Index\n\n```bash\nzilliz index drop --collection <collection-name> --index-name <index-name-to-drop>\n# Optional: --database <database-name>\n```\n\nBefore dropping an index, describe the affected collection and index, then obtain explicit user confirmation.\n\n## Index Types\n\nCommon index types:\n- `AUTOINDEX` -- recommended, automatically selects the best index\n- `IVF_FLAT`, `IVF_SQ8`, `HNSW` -- manual selection for advanced users\n\nCommon metric types:\n- `COSINE` -- cosine similarity (default)\n- `L2` -- Euclidean distance\n- `IP` -- inner product\n\n## Guidance\n\n- On Zilliz Cloud, `AUTOINDEX` is recommended for most use cases.\n- An index is required before loading a collection for search.\n- Before creating an index, check the collection schema to identify vector fields.\n- After creating an index, remind the user to load the collection.\n- Before dropping an index, obtain explicit user confirmation because search availability may be affected.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}