Skip to content

handle json docs containing an object per line #1

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

Merged
merged 1 commit into from
Feb 29, 2024

Conversation

cloudnautique
Copy link
Collaborator

Large datasets in JSON sometimes come in files with an object entry per line. When looking for the schema, the tool could quickly list enough entries to fill the context window.

This updates the tool to try and process larger files with the slurp functionality and treat all entries in the file as items in an array. This lets lenght functions work, and grabbing a single entry.

Large datasets in JSON sometimes come in files with
an object entry per line. When looking for the schema, the tool
could quickly list enough entries to fill the context window.

This updates the tool to try and process larger files with
the slurp functionality and treat all entries in the file as items
in an array. This lets lenght functions work, and grabbing a single
entry.

Signed-off-by: Bill Maxwell <[email protected]>
@cloudnautique
Copy link
Collaborator Author

Needs system tool in: gptscript-ai/gptscript#72

@cloudnautique cloudnautique merged commit 52980e2 into gptscript-ai:main Feb 29, 2024
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.

1 participant