Lost precision when querying data of type 'FLOAT_VECTOR'

[chendong0120]

No description provided.

[sre-ci-robot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: chendong0120
To complete the pull request process, please assign czs007 after the PR has been reviewed.
You can assign the PR to them by writing /assign @czs007 in a comment when ready.

The full list of commands accepted by this bot can be found here.

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[ponponon]

In Milvus, FLOAT_VECTOR refers to single-precision floats (32-bit floats), not double-precision floats (64-bit floats).

Milvus is an open source vector similarity search engine for efficiently storing and searching large-scale vector data. When you create a collection and specify the field type as FLOAT_VECTOR, Milvus will use single-precision floating-point numbers to store vector data, thus saving storage space and improving search performance.

If you want to store double-precision floating-point vectors, you can use the field type DOUBLE_VECTOR, but in large-scale vector data scenarios, single-precision floating-point is usually sufficient and provides a better balance between storage and performance requirements.