ragR: Retrieval-Augmented Generation and RAG Evaluation Tools

Provides tools for document ingestion, embedding storage, retrieval-augmented generation (RAG), and evaluation of question-answering systems. The package includes an R-native vector store, wrappers for OpenAI embedding and chat-completion application programming interfaces (APIs), question-answering logging utilities, and large language model (LLM)-based evaluation metrics for context precision, context recall, answer relevance, and faithfulness. These metrics are based on the Retrieval-Augmented Generation Assessment (RAGAS) framework. The retrieval-augmented generation methodology is described by Lewis et al. (2020) "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks" <doi:10.48550/arXiv.2005.11401>. The evaluation metrics are based on Es et al. (2024) "RAGAS: Automated Evaluation of Retrieval Augmented Generation" <doi:10.18653/v1/2024.eacl-demo.16>.

Version:	0.1.0
Depends:	R (≥ 4.1.0)
Imports:	dplyr, httr2, jsonlite, pdftools, readtext, tibble
Suggests:	plumber, stringr, yaml, testthat (≥ 3.0.0)
Published:	2026-07-22
DOI:	10.32614/CRAN.package.ragR (may not be active yet)
Author:	Muhammad Aimal Rehman [aut, cre], Zhili Lu [aut], Chi-Kuang Yeh [aut]
Maintainer:	Muhammad Aimal Rehman <rehman.aimal at gmail.com>
BugReports:	https://github.com/aimalrehman92/ragR/issues
License:	GPL-3
URL:	https://github.com/aimalrehman92/ragR
NeedsCompilation:	no
Language:	en-US
Materials:	README
CRAN checks:	ragR results

Documentation:

Reference manual:

ragR.html , ragR.pdf

Downloads:

Package source:	ragR_0.1.0.tar.gz
Windows binaries:	r-devel: not available, r-release: ragR_0.1.0.zip, r-oldrel: not available
macOS binaries:	r-release (arm64): ragR_0.1.0.tgz, r-oldrel (arm64): ragR_0.1.0.tgz, r-release (x86_64): ragR_0.1.0.tgz, r-oldrel (x86_64): ragR_0.1.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=ragR to link to this page.