For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Python class

StructuredOutputRegionDelimiters

StructuredOutputRegionDelimiters

class max.pipelines.context.StructuredOutputRegionDelimiters(start_token_ids=None, end_token_ids=None)

source

Bases: object

Token ID sequences that define structured output boundaries.

Used for conditional grammar enforcement: when the start sequence is detected, grammar enforcement activates. When the end sequence is detected, enforcement deactivates.

Parameters:

• start_token_ids (list[int] | None)
• end_token_ids (list[int] | None)

end_token_ids

end_token_ids: list[int] | None = None

source

Token ID sequence marking the end of a structured output region.

start_token_ids

start_token_ids: list[int] | None = None

source

Token ID sequence marking the start of a structured output region.

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit