Provides a number of utilities for describing R objects and package documentation in plain text. For interactive use, this is especially powerful for describing relevant pieces of context to large language models. When used programmatically, these utilities can be registered with ellmer chats as tool calls, enabling language models to peruse package documentation and explore your computational environment.
The tidyprompt package allows users to prompt and empower their large language models (LLMs) in a tidy way. It provides a framework to construct LLM prompts using tidyverse-inspired piping syntax, with a library of pre-built prompt wrappers and the option to build custom ones. Additionally, it supports structured LLM output extraction and validation, with automatic feedback and retries if necessary. Moreover, it enables specific LLM reasoning modes, autonomous R function calling for LLMs, and compatibility with any LLM provider.