Interface for Large Language Model APIs in R
Bind tools to a config (provider-agnostic)
Build Factorial Experiment Design
Cache LLM API Calls
Parallel API calls: Fixed Config, Multiple Messages
Parallel API calls: Multiple Configs, Fixed Message
Parallel experiments with structured parsing
Parallel LLM Processing with Tibble-Based Experiments (Core Engine)
Robustly Call LLM API (Simple Retry)
Parallel API calls: Parameter Sweep - Vary One Parameter, Fixed Messag...
Call an LLM (chat/completions or embeddings) with optional multimodal ...
Disable Structured Output (clean provider toggles)
Enable Structured Output (Provider-Agnostic)
Generate Embeddings in Batches
Chat Session Object and Methods
Create an LLM configuration (provider-agnostic)
Vectorized structured-output LLM
Apply an LLM prompt over vectors/data frames
Data-frame mutate with structured output
Mutate a data frame with LLM output
Parse structured fields from a column into typed vectors
Parse structured output emitted by an LLM
Validate structured JSON objects against a JSON Schema (locally)
LLMR Response Object
Log LLMR Errors
Parse Embedding Response into a Numeric Matrix
Reset Parallel Environment
Setup Parallel Environment for LLM Processing
Provides a unified interface to large language models across multiple providers. Supports text generation, structured output with optional JSON Schema validation, and embeddings. Includes tidyverse-friendly helpers, chat session, consistent error handling, and parallel batch tools.
Useful links