Aliyun Milvus Search

Name: Aliyun Milvus Search
Author: cinience

cinience/alicloud-skills

51 installs
396 repo stars
Updated July 18, 2026
cinience/alicloud-skills

Connect to AliCloud Milvus serverless with PyMilvus to create collections, insert vectors, and run filtered similarity search.

About

Uses standard PyMilvus APIs to connect to AliCloud Milvus serverless, create collections, insert vectors, and run filtered similarity search. A developer uses it for vector retrieval and RAG flows.

MILVUS_URI/MILVUS_TOKEN env-var connection
Create collection, insert, and filtered search quickstart

Aliyun Milvus Search by the numbers

51 all-time installs (skills.sh)
Ranked #413 of 911 Databases skills by installs in the Skillselion catalog
Data as of Aug 5, 2026 (Skillselion catalog sync)

npx skills add https://github.com/cinience/alicloud-skills --skill aliyun-milvus-search

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/cinience/alicloud-skills/aliyun-milvus-search.svg)](https://skillselion.com/skills/cinience/alicloud-skills/aliyun-milvus-search)

Installs	51
repo stars	★ 396
Last updated	July 18, 2026
Repository	cinience/alicloud-skills ↗

What it does

Connect to AliCloud Milvus serverless with PyMilvus to create collections, insert vectors, and run filtered similarity search.

Files

SKILL.mdMarkdownGitHub ↗

Category: provider

AliCloud Milvus (Serverless) via PyMilvus

This skill uses standard PyMilvus APIs to connect to AliCloud Milvus and run vector search.

Prerequisites

Install SDK (recommended in a venv to avoid PEP 668 limits):

python3 -m venv .venv
. .venv/bin/activate
python -m pip install --upgrade pymilvus

Provide connection via environment variables:
MILVUS_URI (e.g. http://<host>:19530)
MILVUS_TOKEN (<username>:<password>)
MILVUS_DB (default: default)

Quickstart (Python)

import os
from pymilvus import MilvusClient

client = MilvusClient(
    uri=os.getenv("MILVUS_URI"),
    token=os.getenv("MILVUS_TOKEN"),
    db_name=os.getenv("MILVUS_DB", "default"),
)

# 1) Create a collection
client.create_collection(
    collection_name="docs",
    dimension=768,
)

# 2) Insert data
items = [
    {"id": 1, "vector": [0.01] * 768, "source": "kb", "chunk": 0},
    {"id": 2, "vector": [0.02] * 768, "source": "kb", "chunk": 1},
]
client.insert(collection_name="docs", data=items)

# 3) Search
query_vectors = [[0.01] * 768]
res = client.search(
    collection_name="docs",
    data=query_vectors,
    limit=5,
    filter='source == "kb" and chunk >= 0',
    output_fields=["source", "chunk"],
)
print(res)

Script quickstart

python skills/ai/search/aliyun-milvus-search/scripts/quickstart.py

Environment variables:

MILVUS_URI
MILVUS_TOKEN
MILVUS_DB (optional)
MILVUS_COLLECTION (optional)
MILVUS_DIMENSION (optional)

Optional args: --collection, --dimension, --limit, --filter.

Notes for Claude Code/Codex

Insert is async; wait a few seconds before searching newly inserted data.
Keep vector dimension aligned with your embedding model.
Use filters to enforce tenant scoping or dataset partitions.

Error handling

Auth errors: check MILVUS_TOKEN and instance permissions.
Dimension mismatch: ensure all vectors match collection dimension.
Network errors: verify VPC/public access settings on the instance.

Validation

mkdir -p output/aliyun-milvus-search
for f in skills/ai/search/aliyun-milvus-search/scripts/*.py; do
  python3 -m py_compile "$f"
done
echo "py_compile_ok" > output/aliyun-milvus-search/validate.txt

Pass criteria: command exits 0 and output/aliyun-milvus-search/validate.txt is generated.

Output And Evidence

Save artifacts, command outputs, and API response summaries under output/aliyun-milvus-search/.
Include key parameters (region/resource id/time range) in evidence files for reproducibility.

Workflow

1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating. 2) Run one minimal read-only query first to verify connectivity and permissions. 3) Execute the target operation with explicit parameters and bounded scope. 4) Verify results and save output/evidence files.

References

PyMilvus MilvusClient examples for AliCloud Milvus

Source list: references/sources.md

interface:
  display_name: "Alibaba Cloud AI Search Milvus"
  short_description: "Milvus collection and vector query"
  default_prompt: "Use $aliyun-milvus-search to complete this ai/search task on Alibaba Cloud."

import argparse
import os
import sys

from pymilvus import MilvusClient


def get_env(name: str, default: str | None = None) -> str:
    value = os.getenv(name, default)
    if not value:
        print(f"Missing env var: {name}", file=sys.stderr)
        sys.exit(1)
    return value


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(description="AliCloud Milvus quickstart")
    parser.add_argument("--collection", default=os.getenv("MILVUS_COLLECTION", "docs"))
    parser.add_argument("--dimension", type=int, default=int(os.getenv("MILVUS_DIMENSION", "8")))
    parser.add_argument("--limit", type=int, default=5)
    parser.add_argument("--filter", default='source == "kb" and chunk >= 0')
    return parser.parse_args()


def main() -> None:
    args = parse_args()
    client = MilvusClient(
        uri=get_env("MILVUS_URI"),
        token=get_env("MILVUS_TOKEN"),
        db_name=get_env("MILVUS_DB", "default"),
    )

    print("Creating collection...")
    client.create_collection(collection_name=args.collection, dimension=args.dimension)

    print("Inserting data...")
    items = [
        {"id": 1, "vector": [0.01] * args.dimension, "source": "kb", "chunk": 0},
        {"id": 2, "vector": [0.02] * args.dimension, "source": "kb", "chunk": 1},
    ]
    client.insert(collection_name=args.collection, data=items)

    print("Searching...")
    query_vectors = [[0.01] * args.dimension]
    res = client.search(
        collection_name=args.collection,
        data=query_vectors,
        limit=args.limit,
        filter=args.filter,
        output_fields=["source", "chunk"],
    )
    print(res)


if __name__ == "__main__":
    main()