# outlines

> Structured Outputs

- **URL**: https://www.freshcrate.ai/projects/outlines
- **Author**: dottxt-ai
- **Category**: Prompt Engineering
- **Latest version**: `1.3.0` (2026-05-13)
- **License**: Apache-2.0
- **Source**: https://github.com/dottxt-ai/outlines
- **Homepage**: https://dottxt-ai.github.io/outlines/
- **Language**: Python
- **GitHub**: 13,705 stars, 685 forks
- **Registry**: github
- **Tags**: `cfg`, `generative-ai`, `json`, `llms`, `prompt-engineering`, `python`, `regex`, `structured-generation`, `symbolic-ai`

## Description

Structured Outputs

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `1.3.0` | 2026-05-13 | High | ## What's Changed * Fix error message for model type determination by @Reslan-Tinawi in https://github.com/dottxt-ai/outlines/pull/1862 * Implement uniform exceptions classes across model providers by @plpxsk in https://github.com/dottxt-ai/outlines/pull/1823  ## New Contributors * @Reslan-Tinawi made their first contribution in https://github.com/dottxt-ai/outlines/pull/1862 * @plpxsk made their first contribution in https://github.com/dottxt-ai/outlines/pull/1823  **Full Changelog**: h |
| `1.2.13` | 2026-05-04 | High | ## What's Changed * Fix XDG_CACHE_HOME double .cache in path construction by @jnMetaCode in https://github.com/dottxt-ai/outlines/pull/1828 * fix(llamacpp): correct EOS attention mask and vocab truncation bugs by @giulio-leone in https://github.com/dottxt-ai/outlines/pull/1820 * fix(dsl): add JSON double-quotes to string literals inside container types by @giulio-leone in https://github.com/dottxt-ai/outlines/pull/1821 * fix: accumulate duplicate token IDs in vocabulary construction by @Rolo |
| `1.2.12` | 2026-03-03 | Low | ## What's Changed * Add a link to the audit form in the README and the doc website by @RobinPicard in https://github.com/dottxt-ai/outlines/pull/1822   **Full Changelog**: https://github.com/dottxt-ai/outlines/compare/1.2.11...1.2.12 |
| `1.2.11` | 2026-02-13 | Low | ## What's Changed * Add documentation preview when opening a PR by @RobinPicard in https://github.com/dottxt-ai/outlines/pull/1818   **Full Changelog**: https://github.com/dottxt-ai/outlines/compare/1.2.10...1.2.11 |
| `1.2.10` | 2026-02-06 | Low | ## What's Changed * Correct mlx-lm example unpacking operator by @Anri-Lombard in https://github.com/dottxt-ai/outlines/pull/1786 * Remove todos by @Anri-Lombard in https://github.com/dottxt-ai/outlines/pull/1788 * fix: correct chat format usage by @Ki-Seki in https://github.com/dottxt-ai/outlines/pull/1790 * Add AsyncOllama to __all__ exports by @Anri-Lombard in https://github.com/dottxt-ai/outlines/pull/1791 * fix: Best-effort use of chat completion by @Ki-Seki in https://github.com/dottx |
| `1.2.9` | 2025-11-24 | Low | ## What's Changed * fix: Refactor sampling parameters in VLLMOffline to use StructuredOutputsParams by @Ki-Seki in https://github.com/dottxt-ai/outlines/pull/1779 * docs: clarify use of `SamplingParams` in model response examples by @Ki-Seki in https://github.com/dottxt-ai/outlines/pull/1777 * Update the uv.lock by @RobinPicard in https://github.com/dottxt-ai/outlines/pull/1783  ## New Contributors * @Ki-Seki made their first contribution in https://github.com/dottxt-ai/outlines/pull/1779 |
| `1.2.8` | 2025-10-27 | Low | ## What's Changed * Use uv sync in the CI instead of pip install by @RobinPicard in https://github.com/dottxt-ai/outlines/pull/1767 * Fix error in the batch method of the MLXLM model by @RobinPicard in https://github.com/dottxt-ai/outlines/pull/1772   **Full Changelog**: https://github.com/dottxt-ai/outlines/compare/1.2.7...1.2.8 |
| `1.2.7` | 2025-10-14 | Low | ## What's Changed * Add the device_dtype init parameter to the transformers model by @RobinPicard in https://github.com/dottxt-ai/outlines/pull/1762   **Full Changelog**: https://github.com/dottxt-ai/outlines/compare/1.2.6...1.2.7 |
| `1.2.6` | 2025-10-14 | Low | ## What's Changed * Fix correct handling of chat multimodal inputs in TransformersMM class by @laitifranz in https://github.com/dottxt-ai/outlines/pull/1728 * Add batch generation to the MLXLM model by @RobinPicard in https://github.com/dottxt-ai/outlines/pull/1759 * Feature/mistral ai integration by @yasteven in https://github.com/dottxt-ai/outlines/pull/1755 * Add json type conversion by @RobinPicard in https://github.com/dottxt-ai/outlines/pull/1761 * Fix installation instructions by @Ro |
| `1.2.5` | 2025-09-15 | Low | ## What's Changed * Update the output_type formatting of the llamacpp model by @RobinPicard in https://github.com/dottxt-ai/outlines/pull/1753   **Full Changelog**: https://github.com/dottxt-ai/outlines/compare/1.2.4...1.2.5 |

## Citation

- HTML: https://www.freshcrate.ai/projects/outlines
- Markdown: https://www.freshcrate.ai/projects/outlines.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/outlines/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._