Package: ragnar
Title: Retrieval-Augmented Generation (RAG) Workflows
Version: 0.1.0
Authors@R: c(
    person("Tomasz", "Kalinowski", , "tomasz@posit.co", role = c("aut", "cre")),
    person("Daniel", "Falbel", , "daniel@posit.co", role = "aut"),
    person("Posit Software, PBC", role = c("cph", "fnd"),
           comment = c(ROR = "03wc8by49"))
  )
Description: Provides tools for implementing Retrieval-Augmented Generation
    (RAG) workflows with Large Language Models (LLM). Includes functions for
    document processing, text chunking, embedding generation, storage
    management, and content retrieval. Supports various document types and
    embedding providers ('Ollama', 'OpenAI'), with 'DuckDB' as the default
    storage backend. Integrates with the 'ellmer' package to equip chat objects
    with retrieval capabilities. Designed to offer both sensible defaults and
    customization options with transparent access to intermediate outputs.
    For a review of retrieval-augmented generation methods, see Gao et al. (2023)
    "Retrieval-Augmented Generation for Large Language Models: A Survey"
    <doi:10.48550/arXiv.2312.10997>.
License: MIT + file LICENSE
Encoding: UTF-8
RoxygenNote: 7.3.2
Depends: R (>= 4.3.0)
Imports: DBI, duckdb (>= 1.2.2), glue, rlang (>= 1.1.0), dplyr, httr2,
        rvest, stringi, tibble, vctrs, tidyr, xml2, methods, S7,
        reticulate (>= 1.42.0), commonmark, blob, cli, curl, withr,
        dotty
Suggests: pandoc, ellmer, knitr, rmarkdown, stringr, dbplyr, testthat
        (>= 3.0.0), paws.common, shiny
Config/Needs/website: tidyverse/tidytemplate, rmarkdown
Config/testthat/edition: 3
URL: http://ragnar.tidyverse.org/, https://github.com/tidyverse/ragnar
VignetteBuilder: knitr
BugReports: https://github.com/tidyverse/ragnar/issues
NeedsCompilation: yes
Packaged: 2025-05-28 14:11:43 UTC; tomasz
Author: Tomasz Kalinowski [aut, cre],
  Daniel Falbel [aut],
  Posit Software, PBC [cph, fnd] (ROR: <https://ror.org/03wc8by49>)
Maintainer: Tomasz Kalinowski <tomasz@posit.co>
Repository: CRAN
Date/Publication: 2025-05-30 09:30:08 UTC
