[Feature] Allow unconstrained whitespace in JSON schema #123
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
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Outdated suggestions cannot be applied.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.
This PR supports allowing any whitespace by the grammar converted from JSON schema.
Previously the json_schema_converter only allows strictly formatted JSON schema by specifying the indentation and separators. However, some model could tend to generate unformatted JSON schema. Forcing them to generate strictly formatted json may degrade the output quality, because these models will generate a dummy json following the format constraint.
This PR provides an option
any_whitespaceinGrammar.from_json_schemaandGrammarCompiler.compile_json_schema, default true, to allow any whitespace in the generated json, therefore allowing non-strictly formatted json output.Note that this PR changes the behavior of these two functions that the converted grammar will by default allow any whitespace, unless a indentation is specifyed.
It also addresses #122.