## -----------------------------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE, comment = "#>",
  eval = identical(tolower(Sys.getenv("LLMR_RUN_VIGNETTES", "false")), "true") )

## -----------------------------------------------------------------------------
# safe <- function(expr) tryCatch(expr, error = function(e) {message("ERROR: ", e$message); NULL})

## -----------------------------------------------------------------------------
# safe({
#   library(LLMR)
#   cfg <- llm_config(
#     provider = "openai",                # try "groq" or "together" too
#     model    = "gpt-4.1-nano",
#     temperature = 0
#   )
# 
#   # Flip JSON mode on (OpenAI-compat shape)
#   cfg_json <- enable_structured_output(cfg, schema = NULL)
# 
#   res    <- call_llm(cfg_json, 'Give me a JSON object {"ok": true, "n": 3}.')
#   parsed <- llm_parse_structured(res)
# 
#   cat("Raw text:\n", as.character(res), "\n\n")
#   str(parsed)
# })

## -----------------------------------------------------------------------------
# safe({
#   library(LLMR); library(dplyr)
# 
#   # Schema: make every property required to satisfy Groq's stricter check
#   schema <- list(
#     type = "object",
#     additionalProperties = FALSE,
#     properties = list(
#       title = list(type = "string"),
#       year  = list(type = "integer"),
#       tags  = list(type = "array", items = list(type = "string"))
#     ),
#     required = list("title","year","tags")
#   )
# 
#   cfg <- llm_config(
#     provider = "groq",
#     model    = "qwen-2.5-72b-instruct",   # a Qwen Instruct model on Groq
#     temperature = 0
#   )
#   cfg_strict <- enable_structured_output(cfg, schema = schema, strict = TRUE)
# 
#   df  <- tibble(x = c("BERT paper", "Vision Transformers"))
#   out <- llm_fn_structured(
#     df,
#     prompt   = "Return JSON about '{x}' with fields title, year, tags.",
#     .config  = cfg_strict,
#     .schema  = schema,          # send schema to provider
#     .fields  = c("title","year","tags"),
#     .validate_local = TRUE
#   )
# 
#   out %>% select(structured_ok, structured_valid, title, year, tags) %>% print(n = Inf)
# })

## -----------------------------------------------------------------------------
# safe({
#   library(LLMR)
#   schema <- list(
#     type="object",
#     properties=list(answer=list(type="string"), confidence=list(type="number")),
#     required=list("answer","confidence"),
#     additionalProperties=FALSE
#   )
# 
#   cfg <- llm_config("anthropic","claude-3-5-haiku-latest", temperature = 0)
#   cfg <- enable_structured_output(cfg, schema = schema, name = "llmr_schema")
# 
#   res <- call_llm(cfg, c(
#     system = "Return only the tool result that matches the schema.",
#     user   = "Answer: capital of Japan; include confidence in [0,1]."
#   ))
# 
#   parsed <- llm_parse_structured(res)
#   str(parsed)
# })

## -----------------------------------------------------------------------------
# safe({
#   library(LLMR)
# 
#   cfg <- llm_config(
#     "gemini", "gemini-2.5-flash-lite",
#     response_mime_type = "application/json"  # ask for JSON back
#     # Optionally: gemini_enable_response_schema = TRUE, response_schema = <your JSON Schema>
#   )
# 
#   res <- call_llm(cfg, c(
#     system = "Reply as JSON only.",
#     user   = "Produce fields name and score about 'MNIST'."
#   ))
#   str(llm_parse_structured(res))
# })

## -----------------------------------------------------------------------------
# safe({
#   library(LLMR); library(tibble)
# 
#   messy <- c(
#     '```json\n{"x": 1, "y": [1,2,3]}\n```',
#     'Sure! Here is JSON: {"x":"1","y":"oops"} trailing words',
#     '{"x":1, "y":[2,3,4]}'
#   )
# 
#   tibble(response_text = messy) |>
#     llm_parse_structured_col(
#       fields = c(x = "x", y = "/y/0")   # dot/bracket or JSON Pointer
#     ) |>
#     print(n = Inf)
# })

## ----eval=FALSE---------------------------------------------------------------
# library(LLMR); library(dplyr)
# 
# cfg_with_schema = llm_config('openai','gpt-4.1-nano')
# 
# setup_llm_parallel(workers = 10)
# 
# ### Assuming there is a large data frame large_df
# 
# large_df |>
#   llm_mutate_structured(
#     result,
#     prompt = "Extract: {text}",
#     .config = cfg_with_schema,
#     .schema = schema,
#     .fields = c("label", "score"),
#     tries = 3  # auto-retry failures
#   )
# 
# reset_llm_parallel()