Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Generate structured LLM text with Outlines v1.0.0

Use this resource to get model output that conforms to a JSON schema, a regex or Pydantic

New

  • 460 downloads
  • 154 likes
  • 147 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install structured-llm-output-outlines

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent writes the code that constrains the model's generation to follow your schema. You get valid structured answers, with compatible backends such as Transformers, llama.cpp or vLLM.

Mostly picked by

Updated November 2, 2026

Card for the “Generate structured LLM text with Outlines” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: use cases, installation and quick start with the v1 API
  • references/: backends, examples and JSON generation

Good fit for

  • You run a local model and the output must be valid JSON
  • You need to classify texts into a fixed set of categories

Not for

    Tags

    • outlines
    • json
    • pydantic
    • local llm
    • structured output

    About

    You say

    “Extract the name, date and amount from these invoices into a Pydantic model.”

    Card for the “Generate structured LLM text with Outlines” skill

    Skill published by Orchestra Research under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to get model output that conforms to a JSON schema, a regex or Pydantic
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/backends.md14.1 KB
    • references/examples.md20.7 KB
    • references/json_generation.md14.6 KB
    • SKILL.md16.9 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/nousresearch/hermes-agent/tree/0c74cc682dc81bf78b78a1737b3ee77a820ccb79/optional-skills/mlops/inference/outlines
    Licence
    MIT

    Notice

    « outlines » (Orchestra Research, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.