python开发milvus2.0.2开发，快速上手，参考文档、手册、案例

最新推荐文章于 2025-06-22 00:48:40 发布

愚昧之山绝望之谷开悟之坡

最新推荐文章于 2025-06-22 00:48:40 发布

阅读量3.1k

点赞数 1

CC 4.0 BY-SA版权

分类专栏：笔记 milvus 文章标签：人工智能

本文链接：https://blog.csdn.net/qq_15821487/article/details/124588680

笔记同时被 2 个专栏收录

742 篇文章

订阅专栏

milvus

21 篇文章

订阅专栏

本文介绍了如何使用Python Milvus库创建集合、设置一致性级别，并创建IVF_FLAT索引。重点讲解了设置consistency_level的重要性和仅支持向量字段的索引创建。适合初学者了解Milvus在搜索加速中的基本操作。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

参考文档

开发案例：
https://gitee.com/AI-Mart/pymilvus/blob/master/examples/hello_milvus.py
https://github.com/milvus-io/pymilvus/blob/master/examples/hello_milvus.py
参考指南：
https://milvus.io/docs/v2.0.x/manage_connection.md
python开发api文档：
https://milvus.io/api-reference/pymilvus/v2.0.2/About.md

代码记录

1、创建集合

hello_milvus = Collection("hello_milvus", schema, consistency_level="Strong")

注意1

Milvus supports setting consistency level while creating a collection (only on PyMilvus currently). In this example, the consistency level of the collection is set as "Strong", meaning Milvus will read the most updated data view at the exact time point when a search or query request comes. By default, a collection created without specifying the consistency level is set with bounded consistency level, under which Milvus reads a less updated data view (usually several seconds earlier) when a search or query request comes. Besides collection creation, you can also set the consistency level specifically for search or query (only on PyMilvus currently). For other consistency level supported by Milvus, see Guarantee Timestamp in Search Requests.

注意2

The collection to create must contain a primary key field and a vector field. INT64 is the only supported data type for the primary key field in current release of Milvus.

2、创建索引

# 4. create index
print(fmt.format("Start Creating index IVF_FLAT"))
index = {
    "index_type": "IVF_FLAT",
    "metric_type": "L2",
    "params": {"nlist": 128},
}

hello_milvus.create_index("embeddings", index)

注意1

# We are going to create an IVF_FLAT index for hello_milvus collection.
# create_index() can only be applied to `FloatVector` and `BinaryVector` fields.

Vector indexes are an organizational unit of metadata used to accelerate vector similarity search. Without index built on vectors, Milvus will perform a brute-force search by default

注意2

Current release of Milvus only supports index on vector field. Future releases will support index on scalar field.
By default, Milvus does not index a segment with less than 1,024 rows. To change this parameter, configure rootCoord.minSegmentSizeToEnableIndex in milvus.yaml.