Microsoft today launched Guidance, a guidance language for controlling large language models. Microsoft Guidance’ Syntax is based on Handlebars and it supports both self-hosted LLMs and OpenAI LLMs. According to Microsoft, Guidance enables you to control modern language models more effectively and efficiently than traditional prompting or chaining.
Using Guidance programs, you can interleave generation, prompting, and logical control into a single continuous flow matching how the language model actually processes the text.
- Simple, intuitive syntax, based on Handlebars templating.
- Rich output structure with multiple generations, selections, conditionals, tool use, etc.
- Playground-like streaming in Jupyter/VSCode Notebooks.
- Smart seed-based generation caching.
- Support for role-based chat models (e.g. ChatGPT).
- Easy integration with Hugging Face models, including guidance acceleration for speedups over standard prompting, token healing to optimize prompt boundaries, and regex pattern guides to enforce formats.
You can learn more about Microsoft Guidance from the source link below.