aliyun-milvus-search

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Category: provider

AliCloud Milvus (Serverless) via PyMilvus

通过PyMilvus使用阿里云Milvus（Serverless版）

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

本技能使用标准PyMilvus API连接阿里云Milvus并执行向量搜索。

Prerequisites

前置条件

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

bash

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
```
)

安装SDK（推荐在虚拟环境中安装以避免PEP 668限制）：

bash

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

通过环境变量提供连接信息：
- ```
MILVUS_URI
```
  （例如
```
http://<host>:19530
```
  ）
- ```
MILVUS_TOKEN
```
  （格式为
```
<username>:<password>
```
  ）
- ```
MILVUS_DB
```
  （默认值：
```
default
```
  ）

Quickstart (Python)

快速入门（Python）

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"),
)

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

1) 创建集合

client.create_collection( collection_name="docs", dimension=768, )

2) Insert data

2) 插入数据

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

3) 搜索

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)

undefined

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)

undefined

Script quickstart

脚本快速入门

bash

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

bash

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

环境变量：

```
MILVUS_URI
```
```
MILVUS_TOKEN
```
```
MILVUS_DB
```
（可选）
```
MILVUS_COLLECTION
```
（可选）
```
MILVUS_DIMENSION
```
（可选）

可选参数：

--collection

、

--dimension

、

--limit

、

--filter

。

Notes for Claude Code/Codex

Claude Code/Codex使用注意事项

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.

插入操作是异步的：搜索新插入的数据前请等待数秒。
请保证向量
```
dimension
```
与你的embedding模型匹配。
使用过滤器强制租户范围或数据集分区。

Error handling

错误处理

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.

认证错误：检查
```
MILVUS_TOKEN
```
和实例权限。
维度不匹配：确保所有向量与集合定义的维度一致。
网络错误：核实实例的VPC/公网访问设置。

Validation

验证

bash

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.

bash

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

通过标准：命令退出码为0且生成

output/aliyun-milvus-search/validate.txt

文件。

Output And Evidence

输出与凭证

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.

将产物、命令输出和API响应摘要保存到
```
output/aliyun-milvus-search/
```
目录下。
在凭证文件中包含关键参数（地域/资源ID/时间范围）以便复现操作。

Workflow

工作流程

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

确认用户意图、地域、标识符，以及操作是只读类型还是变更类型。
首先运行一个最小化的只读查询，验证连通性和权限。
使用明确参数和限定范围执行目标操作。
验证结果并保存输出/凭证文件。

References

参考资料

PyMilvus
```
MilvusClient
```
examples for AliCloud Milvus
Source list:
```
references/sources.md
```

适用于阿里云Milvus的PyMilvus
```
MilvusClient
```
示例
源列表：
```
references/sources.md
```