Tosijs-schema is a super lightweight schema-first LLM-native JSON schema library

[podperson]

I wrote this library this weekend after realizing that Zod was really not designed for the use-cases I want JSON schemas for: 1) defining response formats for LLMs and 2) as a single source of truth for data structures.

[7thpower]

What led you to that conclusion?

[taveras]

Happy to see more tools in the data schema space.

Will you support Standard Schema (https://standardschema.dev)? How does this compare to typebox (https://github.com/sinclairzx81/typebox)?

[kevmo314]

> For large arrays (>97 items) and large dictionaries

How did we end up in a world where 97 items is considered large?

[vages]

Mind your off-by-1s: 97 items is not large, 98 is.

[yunohn]

> It checks a fixed sample of items (roughly 1%) regardless of size

> This provides O(1) performance

Wouldn’t 1% of N still imply O(N) performance?

[podperson]

N is increasing. O(1) means constant (actually capped). We never check more than 100 items.

[bbminner]

While llms accept json schemas for constrained decoding, they might not respect all of the constraints.

[_heimdall]

Had you considered using something like XML as the transport format rather than JSON? If the UX is similar to zod it wouldn't matter what the underlying data format is, and XML is meant to support schemas unlike JSON.

[podperson]

JSON Schema is a schema built on JSON and it’s already being used. Using XML would mean converting the XML into JSON schema to define the response from the LLM.

That said, JSON is “language neutral” but also super convenient for JavaScript developers and typically more convenient for most people than XML.