Guidance is an efficient programming paradigm for steering language models. With Guidance, you can control how output is structured and get high-quality output for your use case—while reducing latency and cost vs. conventional prompting or fine-tuning. It allows users to constrain generation (e.g. with regex and CFGs) as well as to interleave control (conditionals, loops, tool use) and generation seamlessly.
Features
- Write pure Python, with additional LM functionality
- Constrain generation with selects (i.e., sets of options), regular expressions, and context-free grammars, as well as with pre-built components
- Documentation available
- Examples available
- Call and deploy tools easily with automatic interleaving of control and generation
- Gain speed with stateful control + generation functions—no need for intermediate parsers
Project Samples
Categories
Large Language Models (LLM)License
MIT LicenseFollow Guidance
You Might Also Like
Gen AI apps are built with MongoDB Atlas
MongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Guidance!