alicloud-ai-search-milvus

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Category: provider

分类：服务商

AliCloud Milvus (Serverless) via PyMilvus

通过PyMilvus使用阿里云Milvus（Serverless）

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并执行向量检索。

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（建议在虚拟环境venv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)

快速开始（Python版）

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

脚本快速开始

bash

python skills/ai/search/alicloud-ai-search-milvus/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/alicloud-ai-search-milvus/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

针对Claude Code/Codex的注意事项

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；在检索新插入的数据前请等待几秒。
确保向量
```
dimension
```
与你的嵌入模型保持一致。
使用过滤器来实现租户范围限定或数据集分区。

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的维度一致。
网络错误：验证实例的VPC/公网访问设置。

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
来源列表：
```
references/sources.md
```