/alibabacloud-milvus-manage

name: alibabacloud-milvus-manage
description: >
  Alibaba Cloud Milvus full-stack Skill for two planes: control-plane instance management via aliyun CLI,
  and data-plane Milvus operations via pymilvus. Use when users want to create, inspect, scale, configure,
  network-enable, or whitelist Alibaba Cloud Milvus instances; or connect to Milvus and perform
  collection management, vector insert/search, hybrid search, full-text search, index management,
  partition/database management, or RBAC with Python.
license: MIT AND Apache-2.0
compatibility: >
  Control-plane requires Alibaba Cloud CLI (`aliyun` >= 3.3.3) with valid credentials; every aliyun CLI call must include
  `--user-agent AlibabaCloud-Agent-Skills/alibabacloud-milvus-manage`, and Milvus calls must use `--force`.
  Data-plane requires Python 3.8+ and `pymilvus`. Works on macOS and Linux.
metadata:
  domain: vector-database
  owner: milvus-team
  data-plane-author: jinchen
allowed-tools: Bash Read Write

Alibaba Cloud Milvus Full-Stack Skill

Prerequisites

**[MUST] CLI User-Agent** — Every `aliyun` CLI command invocation must include: `--user-agent AlibabaCloud-Agent-Skills/alibabacloud-milvus-manage`

**[MUST] PyMilvus User-Agent** — Every `pymilvus` SDK connection must include: `grpc_options={"grpc.primary_user_agent": "AlibabaCloud-Agent-Skills/alibabacloud-milvus-manage"}`

Alibaba Cloud CLI version must be `>= 3.3.3`.

Handle two distinct planes:

• **Control-plane**: manage Alibaba Cloud managed Milvus instances with `aliyun` CLI.
• **Data-plane**: operate Milvus with `pymilvus` Python code.

Treat `SKILL.md` as the router. Load `references/*.md` for detailed commands, parameters, and examples.

Scope

Use this skill for:

• Alibaba Cloud managed Milvus instance lifecycle: create, inspect, scale, rename, configure, network, whitelist.
• Milvus Python SDK workflows with `pymilvus`: connect, collections, vectors, search, indexes, partitions, databases, RBAC.
• Retrieval use cases built on Milvus: semantic search, hybrid search, full-text search, RAG patterns.

Do not use this skill for:

• self-hosted Milvus deployment on Docker, Helm, Kubernetes, or Milvus Operator,
• Milvus Java / Go / Node SDKs,
• other Alibaba Cloud products such as ECS, RDS, OSS, EMR, Kafka, StarRocks,
• other vector databases such as Zilliz Cloud, Pinecone, Qdrant, or Weaviate.

Route The Request

Control-plane

Route here when the user asks about:

• creating, scaling, renaming, or inspecting a Milvus instance,
• connection address, component spec, configuration, public network, whitelist,
• VPC/VSwitch prerequisites for Alibaba Cloud Milvus,
• Milvus REST-style CLI APIs, creation parameters, or control-plane troubleshooting.

Read:

• first-time flow: [references/getting-started.md](references/getting-started.md)
• create / list / detail / scale / release: [references/instance-lifecycle.md](references/instance-lifecycle.md)
• config / network / inspection / troubleshooting: [references/operations.md](references/operations.md)
• creation field meanings and templates: [references/create-params.md](references/create-params.md)
• raw API field reference: [references/api-reference.md](references/api-reference.md)
• RAM permissions: [references/ram-policies.md](references/ram-policies.md)

Data-plane

Route here when the user asks about:

• connecting to Milvus with Python,
• creating collections or schemas,
• inserting, upserting, querying, deleting, or searching vectors,
• hybrid search, BM25 full-text search, iterators, indexes,
• partitions, databases, users, roles, or privileges,
• Milvus-based RAG or semantic retrieval patterns.

Read:

• collection schema and lifecycle: [references/collection.md](references/collection.md)
• vector CRUD, search, hybrid search, full-text search: [references/vector.md](references/vector.md)
• index types and metrics: [references/index.md](references/index.md)
• partitions: [references/partition.md](references/partition.md)
• databases: [references/database.md](references/database.md)
• RBAC: [references/user-role.md](references/user-role.md)
• common solution patterns: [references/patterns.md](references/patterns.md)

Shared Guardrails

• Decide the plane first. Do not mix control-plane instance operations with data-plane SDK code.
• Confirm destructive actions before execution.
• Validate untrusted user input before passing it into shell commands or code.
• Prefer loading a targeted reference doc instead of keeping large inline examples in this file.

Control-Plane Rules

Required Environment

• Reuse the configured `aliyun` profile. Verify credentials are configured before API calls.
• Every `aliyun` CLI invocation must include the required User-Agent flag:

aliyun ... --user-agent AlibabaCloud-Agent-Skills/alibabacloud-milvus-manage

• Milvus OpenAPI calls through `aliyun` must include `--force`.

Preconditions

Before create or major modify operations:

1. Confirm `RegionId` with the user. 2. Verify VPC and VSwitch resources in that region. 3. For create, record `ZoneId`, `VpcId`, and `VSwitchId`. 4. If the request is ambiguous, ask whether the user wants dev/test standalone or production HA cluster.

Baseline decision rule:

• `standalone_pro` is the default for dev/test.
• HA cluster is for production.
• In HA mode, `streaming`, `data`, `mix_coordinator`, and `query` must use at least 4 CU; `proxy` must use at least 2 CU.

Detailed templates and field definitions live in [references/instance-lifecycle.md](references/instance-lifecycle.md) and [references/create-params.md](references/create-params.md).

CLI Calling Modes

Use the API's expected parameter mode. Do not improvise.

# get / delete: business params in URL query
aliyun milvus get "/path?RegionId=<region>&instanceId=<id>" --RegionId <region> --force --user-agent AlibabaCloud-Agent-Skills/alibabacloud-milvus-manage

# post / put with request body: business params in --body JSON
aliyun milvu