| ▲ | Tosijs-schema is a super lightweight schema-first LLM-native JSON schema library(npmjs.com) |
| 37 points by podperson 6 hours ago | 23 comments |
| |
|
| ▲ | kevmo314 an hour ago | parent | next [-] |
| > For large arrays (>97 items) and large dictionaries How did we end up in a world where 97 items is considered large? |
|
| ▲ | podperson 6 hours ago | parent | prev | next [-] |
| 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. |
| |
| ▲ | taveras an hour ago | parent | next [-] | | 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)? | |
| ▲ | 7thpower 5 hours ago | parent | prev [-] | | What led you to that conclusion? | | |
| ▲ | dsabanin 5 hours ago | parent | next [-] | | Zod's validation errors are awful, the json schema it generates for LLM is ugly and and often confusing, the types structures Zod creates are often unintelligible in the and there's even no good way to pretty print a schema when you're debugging. Things are even worse if you're stuck with zod/v3 | | |
| ▲ | sesm 4 hours ago | parent | next [-] | | What's wrong with Zod validation errors? | |
| ▲ | light_hue_1 3 hours ago | parent | prev [-] | | None of this makes a lot of sense. Validation errors are largely irrelevant for LLMs and they can understand them just fine. The type structure looks good for LLMs. You can definitely pretty print a schema at runtime. This all seems pretty uninformed. |
| |
| ▲ | nerdponx 5 hours ago | parent | prev | next [-] | | And what makes this different? What makes it LLM-native? | | |
| ▲ | podperson 4 hours ago | parent [-] | | It generates schemas that are strict by default while Zod requires you to set everything manually. This is actually discussed in the linked article (READ ME file). | | |
| ▲ | halayli 3 hours ago | parent [-] | | That's not true based on zod docs. https://zod.dev/api?id=objects most of the claims you're making against zod is inaccurate. the readme feels like false claims by ai. | | |
| ▲ | podperson 2 hours ago | parent [-] | | It seems to be true to me. And aside from the API stuff (because I am far from an expert user of Zod) all of this has been carefully verified. |
|
|
| |
| ▲ | podperson 4 hours ago | parent | prev [-] | | 1. Zoe’s documentation, such as it is
2. Code examples |
|
|
|
| ▲ | bbminner 3 hours ago | parent | prev | next [-] |
| While llms accept json schemas for constrained decoding, they might not respect all of the constraints. |
|
| ▲ | yunohn 3 hours ago | parent | prev | next [-] |
| > 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 2 hours ago | parent [-] | | N is increasing. O(1) means constant (actually capped). We never check more than 100 items. | | |
| ▲ | SkiFire13 an hour ago | parent [-] | | Then it's not 1%, because if you have 100k items and you check at most 100 you have checked at most 0.1% of items. |
|
|
|
| ▲ | _heimdall 5 hours ago | parent | prev [-] |
| 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 4 hours ago | parent [-] | | 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. | | |
| ▲ | _heimdall 44 minutes ago | parent | next [-] | | Maybe I missed a detail here, sorry if that's the case! Why would we need to concert XML, which already supports schemas and is well understood by LLMs, back to JSON schema? | | |
| ▲ | verdverm 17 minutes ago | parent [-] | | Because most of the world uses JSON and has rich tooling for JSONSchemas, notable many LLM providers allow JSONSchemas to be part of the request when trying to get structured output |
| |
| ▲ | yeasku 3 hours ago | parent | prev [-] | | LLMs are not people. We want a format for LLMs or for people? | | |
|
|
