feat: Add tool to get dataset schema so LLMs can understand dataset structure without fetching everything #190
Conversation
This file contains hidden or 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
…tructure without fetching everything (mainly for Zuzka). Placed under storage since that group isn’t enabled by default. Also, I added runId and datasetId injection into context, hopefully it won't break anything affect existing flows.
jirispilka
changed the title
jirispilka
requested review from
MQ37 and
MichalKalita
and removed request for
MichalKalita
MQ37
approved these changes
Jul 25, 2025
Contributor
MQ37
left a comment
MQ37
left a comment
There was a problem hiding this comment.
LGTM, I just do not like the nested try blocks, but it works so it does not matter.
MichalKalita
approved these changes
Jul 25, 2025
Contributor
MichalKalita
left a comment
MichalKalita
left a comment
There was a problem hiding this comment.
👍 for fallbackSchema approach
This was referenced Jul 29, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
feat: Add tool to get dataset schema so LLMs can understand dataset structure without fetching everything (mainly for Zuzka)
Placed under storage since that group isn’t enabled by default.
Also, I added runId and datasetId injection into context, hopefully it won't break anything affect existing flows.