--- title: "Small experiment with LLMR" output: rmarkdown::html_vignette vignette: > %\VignetteIndexEntry{Small experiment with LLMR} %\VignetteEngine{knitr::rmarkdown} %\VignetteEncoding{UTF-8} --- ```{r} knitr::opts_chunk$set( collapse = TRUE, comment = "#>", eval = identical(tolower(Sys.getenv("LLMR_RUN_VIGNETTES", "false")), "true") ) ``` We will compare three configurations on two prompts, once unstructured and once with structured output. In choosing models, note that at the time of writing this vignette, Gemini models are not guaranteeing the schema output and is more likely to run into trouble. ```{r} library(LLMR) library(dplyr) cfg_openai <- llm_config("openai", "gpt-5-nano") cfg_cld <- llm_config("anthropic","claude-sonnet-4-20250514", max_tokens = 512) cfg_gem <- llm_config("groq", "openai/gpt-oss-20b") ``` ## Build a factorial design ```{r} experiments <- build_factorial_experiments( configs = list(cfg_openai, cfg_cld, cfg_gem), user_prompts = c("Summarize in one sentence: The Apollo program.", "List two benefits of green tea."), system_prompts = c("Be concise.") ) experiments ``` ## Run unstructured ```{r} setup_llm_parallel(workers = 10) res_unstructured <- call_llm_par(experiments, progress = TRUE) reset_llm_parallel() res_unstructured |> select(provider, model, user_prompt_label, response_text, finish_reason) |> head() ``` ## Structured version ```{r} schema <- list( type = "object", properties = list( answer = list(type="string"), keywords = list(type="array", items = list(type="string")) ), required = list("answer","keywords"), additionalProperties = FALSE ) experiments2 <- experiments experiments2$config <- lapply(experiments2$config, enable_structured_output, schema = schema) setup_llm_parallel(workers = 10) res_structured <- call_llm_par_structured(experiments2 , .fields = c("answer","keywords") ) reset_llm_parallel() res_structured |> select(provider, model, user_prompt_label, structured_ok, answer) |> head() ```