Package index • tidyprompt

Prompt wrapping and evaluation

Functions to create and handle tidyprompt objects.

Functions for creating prompt wraps.

prompt_wrap(): Wrap a prompt with functions for modification and handling the LLM response
provider_prompt_wrap() experimental: Create a provider-level prompt wrap
llm_feedback(): Create an llm_feedback object
llm_break(): Create an llm_break object
llm_break_soft(): Create an llm_break_soft object

Function to evaluate prompts with an LLM provider.

A library of pre-built prompt wraps for common use cases.

Functions to have LLMs answer in a specific format (structured output).

answer_as_boolean(): Make LLM answer as a boolean (TRUE or FALSE)
answer_as_category(): Make LLM answer as a category
answer_as_integer(): Make LLM answer as an integer (between min and max)
answer_as_json(): Make LLM answer as JSON (with optional schema; structured output)
answer_as_key_value(): Make LLM answer as a list of key-value pairs
answer_as_list(): Make LLM answer as a list of items
answer_as_multi_category(): Build prompt for categorizing a text into multiple categories
answer_as_named_list(): Make LLM answer as a named list
answer_as_regex_match(): Make LLM answer match a specific regex
answer_as_text(): Make LLM answer as a constrained text response

Functions to have LLMs answer in a specific way.

Functions that give LLMs access to tools (function-calling) and code

answer_using_r(): Enable LLM to draft and execute R code
answer_using_sql(): Enable LLM to draft and execute SQL queries on a database
answer_using_tools(): Enable LLM to call R functions (and/or MCP server tools)
tools_add_docs(): Add tidyprompt function documentation to a function
tools_get_docs(): Extract documentation from a function

add_text(): Add text to a tidyprompt
quit_if(): Make evaluation of a prompt stop if LLM gives a specific response
user_verify(): Have user check the result of a prompt (human-in-the-loop)
llm_verify(): Have LLM check the result of a prompt (LLM-in-the-loop)

Functions to interact with LLM providers and manage chat history.

llm_provider_ellmer() experimental: Create a new LLM provider from an ellmer::chat() object
llm_provider_google_gemini() superseded: Create a new Google Gemini LLM provider
llm_provider_groq(): Create a new Groq LLM provider
llm_provider_mistral(): Create a new Mistral LLM provider
llm_provider_ollama(): Create a new Ollama LLM provider
llm_provider_openai(): Create a new OpenAI LLM provider
llm_provider_openrouter(): Create a new OpenRouter LLM provider
llm_provider_xai(): Create a new XAI (Grok) LLM provider

A helper class to have a persistent, manual conversation with a LLM provider.

Functions to create text to be used in prompts.

df_to_string(): Convert a dataframe to a string representation
vector_list_to_string(): Convert a named or unnamed list/vector to a string representation
skim_with_labels_and_levels(): Skim a dataframe and include labels and levels

extract_from_return_list(): Function to extract a specific element from a list
r_json_schema_to_example(): Generate an example object from a JSON schema