---
date: "2023-05-16T09:51:00.000Z"
title: "2023-05-16"
tags: ["language_models","sql"]
draft: false
---

[`LMQL`](https://docs.lmql.ai/en/latest/index.html) is a SQL-like programming language for interacting with LMs.
It takes a declarative approach to specifying the output constraints for a language model, with a SQL flavor.

---

Microsoft created a project called [`guidance`](https://github.com/microsoft/guidance) which is an LLM-agnostic language to "interleave generation, prompting, and logical control into a single continuous flow matching how the language model actually processes the text".
It's based on Handlebars templates and provides in-template notion for system and user messages.

---

[`kor`](https://github.com/eyurtsev/kor) is a prototype used to extract structured data from language model responses.
It takes a more object oriented approach and is Python-specific.

---

[`rebuff`](https://github.com/woop/rebuff) is a multilayer prompt injection defense library that continuously improves and adapts based on previous attacks.