CoolFace
Apppublic

Ferr0/structured-output-playground

sourceHugging Facemitupdated 3mo agoView on Hugging Face
0likes
App README

๐Ÿ”’ Structured Output Playground

Lock any LLM's output to a JSON schema. Paste free text, pick (or write) a schema, and a local model returns structured data that is guaranteed to conform โ€” because the decoder is constrained to the schema at generation time, not asked nicely afterwards.

The point isn't the model. It's that schema-conformance is a property of the decoder. Right keys, right types, valid enums โ€” every time.

The toggle is the demo

There's a Constraints ON / OFF switch.

  • โ€”ON โ€” the JSON Schema becomes a grammar; the model can only emit tokens that keep the output valid and conformant. You always get the right shape, the right types, and valid enums.
  • โ€”OFF โ€” the same model just tries. A good model often succeeds, but "often" isn't "always": watch it wrap the JSON in a markdown fence, or โ€” more subtly โ€” return valid JSON that violates the schema (a string where you asked for an integer, a value outside your enum). The Event example is built to show exactly this.

How it works

  • โ€”Model โ€” Qwen2.5-3B-Instruct.
  • โ€”Inference โ€” transformers on ZeroGPU (H200).
  • โ€”Constraint โ€” Outlines turns the JSON Schema into a grammar, so only schema-valid token sequences are allowed.
  • โ€”Validation โ€” every output is checked with jsonschema so you can see conformant vs. broken.

Four presets (contact, product, job posting, event) plus a Custom mode where you paste your own JSON Schema. All example texts are fictional.

About

Built by [Ferr0](https://huggingface.co/Ferr0) โ€” infra-minded AI: local LLM inference, structured generation & tool-calling, offline RAG, defensive AI security. More at [pixelium.win](https://pixelium.win) ยท [GitHub](https://github.com/ferr079).

License: MIT.