vdk-smarter: introduce simple open ai plugin #2351
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
antoniivanov
force-pushed
the
person/aivanov/vdk-smarter
branch
from
5d476ff to
11829ae
Compare
Very simple plugin that reviews every query and scores it using OpenAI models. The purpose is to provide easy visibility into queries and their quality for the user. Though technically they could potentially use chatGPT themselves or static code analysis , that is less likely and alsl generally harder A) because some queries are generated dynamically B) lots of queries could be part of a job and takes time to check all. C) the prompt engineering is something that takes time as well and tuning as well. The prompts could be tuned by community pretty well over time. This enables central data team to establish best practices around SQL with proper review model . Signed-off-by: Antoni Ivanov <aivanov@vmware.com>
DeltaMichael
reviewed
Jul 5, 2023
projects/vdk-plugins/vdk-smarter/src/vdk/plugin/smarter/openai_plugin_entry.py
Outdated
Show resolved
Hide resolved
antoniivanov
force-pushed
the
person/aivanov/vdk-smarter
branch
from
4738e0c to
fca3eb1
Compare
Signed-off-by: Antoni Ivanov <aivanov@vmware.com>
antoniivanov
force-pushed
the
person/aivanov/vdk-smarter
branch
from
fca3eb1 to
3056b41
Compare
DeltaMichael
approved these changes
Jul 6, 2023
duyguHsnHsn
approved these changes
Jul 7, 2023
Not at this stage. This is just POC (note the development status of the plugin Pre-Alpha). |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Very simple plugin that reviews every query and scores it using OpenAI models. The purpose is to provide easy visibility into queries and their quality for the user. Though technically they could potentially use chatGPT themselves or static code analysis, that is less likely and and harder for them
A) because some queries are generated dynamically
B) Many queries could be part of a job and take (development) time to check.
C) the prompt engineering is something that takes time as well and tuning as well. The prompts could be tuned by community pretty well over time.
Inside an enterprise, this enables central data team to establish best practices around SQL with proper review model themselves as well.
This is a POC (a Pre-Alpha development status as defined in https://martin-thoma.com/software-development-stages/#2-pre-alpha)