Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add support for new VECTOR type #1609

Merged
merged 1 commit into from
Jul 19, 2024

Conversation

dbussink
Copy link
Contributor

@dbussink dbussink commented Jul 18, 2024

Description

MySQL 9.0.0 added support for the VECTOR type. This adds basic support so it can be handled at the protocol level.

See also https://dev.mysql.com/doc/dev/mysql-server/latest/field__types_8h.html

I have not added tests here specifically, since I also don't see any tests for some of the other types like say GEOMETRY and don't know how to add those then in a way that's preferred by the project.

Checklist

  • Code compiles correctly
  • Created tests which fail without the change (if possible)
  • All tests passing
  • Extended the README / documentation, if necessary
  • Added myself / the copyright holder to the AUTHORS file

Summary by CodeRabbit

  • New Features

    • Added support for a new field type VECTOR in various database operations.
  • Chores

    • Included a new contributor, Dirkjan Bussink, in the AUTHORS file.

MySQL 9.0.0 added support for the VECTOR type. This adds basic support
so it can be handled at the protocol level.

Signed-off-by: Dirkjan Bussink <d.bussink@gmail.com>
Copy link

coderabbitai bot commented Jul 18, 2024

Walkthrough

Recent changes introduce a new contributor, Dirkjan Bussink, and expand the fieldType enum with new types: fieldTypeVector, fieldTypeInvalid, and fieldTypeBool. The code handling these field types in fields.go and packets.go has been updated to support fieldTypeVector. This addition enables the handling of vector data types within the impacted functions.

Changes

Files Summary of Changes
AUTHORS Added Dirkjan Bussink as a new contributor with the email d.bussink@gmail.com.
const.go Added fieldTypeVector, fieldTypeInvalid, fieldTypeBool to the fieldType enum.
fields.go Included fieldTypeVector in typeDatabaseName and scanType method cases.
packets.go Added fieldTypeVector handling in the readRow function within binaryRows.

Poem

A new contributor joins the scene,
With vectors added to the field routine.
From types to rows, the code extends,
As Dirkjan’s magic now wends.
Handling data with a vector's grace,
Our codebase finds a new embrace. 🌟


Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

Share
Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai generate interesting stats about this repository and render them as a table.
    • @coderabbitai show all the console.log statements in this repository.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (invoked as PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Additionally, you can add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

Review details

Configuration used: CodeRabbit UI
Review profile: CHILL

Commits

Files that changed from the base of the PR and between 3484db1 and fcb28a6.

Files selected for processing (4)
  • AUTHORS (1 hunks)
  • const.go (1 hunks)
  • fields.go (2 hunks)
  • packets.go (1 hunks)
Additional comments not posted (5)
const.go (1)

128-131: LGTM! But verify the usage of new constants.

The new constants fieldTypeVector, fieldTypeInvalid, and fieldTypeBool are correctly defined.

However, ensure that these new constants are correctly used throughout the codebase.

AUTHORS (1)

36-36: LGTM!

The new contributor Dirkjan Bussink is correctly added.

fields.go (2)

203-204: LGTM! But verify the usage of the method.

The new case fieldTypeVector is correctly added to return scanTypeBytes if charSet is binaryCollationID.

However, ensure that the scanType method is correctly used throughout the codebase.


115-116: LGTM! But verify the usage of the method.

The new case fieldTypeVector is correctly added to return "VECTOR".

However, ensure that the typeDatabaseName method is correctly used throughout the codebase.

packets.go (1)

1332-1333: LGTM! But verify the usage of the method.

The new case fieldTypeVector is correctly added to handle vector data types.

However, ensure that the readRow method is correctly used throughout the codebase.

Verification successful

LGTM! The new case fieldTypeVector is correctly added to handle vector data types.

The readRow method is properly implemented and used throughout the codebase.

  • binaryRows.readRow method includes the new case fieldTypeVector.
  • readRow method is used in rows.go and connection.go without issues.
Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Description: Verify the usage of `readRow` method.

# Test: Search for the usage of `readRow` method. Expect: Occurrences of the method.
rg --type go 'readRow'

Length of output: 294


Script:

#!/bin/bash
# Description: Gather implementations of `readRow` method and inspect its usage.

# Get the implementation of `readRow` method in `binaryRows` struct
ast-grep --lang go --pattern $'func (rows *binaryRows) readRow($_) $_ { $$$ }'

# Get the implementation of `readRow` method in `textRows` struct
ast-grep --lang go --pattern $'func (rows *textRows) readRow($_) $_ { $$$ }'

# Get the usage of `readRow` method in `rows.go`
rg -A 5 'readRow' rows.go

# Get the usage of `readRow` method in `connection.go`
rg -A 5 'readRow' connection.go

Length of output: 11307

@coveralls
Copy link

Coverage Status

coverage: 82.403% (-0.04%) from 82.446%
when pulling fcb28a6 on dbussink:add-vector-support
into 3484db1 on go-sql-driver:master.

@methane methane merged commit 9c20169 into go-sql-driver:master Jul 19, 2024
32 checks passed
@shaozi
Copy link

shaozi commented Sep 10, 2024

Hi,
Can you provide an example on how to use the new vector field? I tried to insert a []float32 as well as an array [768]float32 but ran into error:

db.Exec("insert into vector_table (id, embeddings) values (?,?)",
			id, embeddings,
		)
sql: converting argument $2 type: unsupported type [768]float32, a array

methane pushed a commit to methane/mysql that referenced this pull request Nov 13, 2024
MySQL 9.0.0 added support for the VECTOR type. This adds basic support
so it can be handled at the protocol level.

See also
https://dev.mysql.com/doc/dev/mysql-server/latest/field__types_8h.html
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants