An interface to 'Docling', a document-understanding library that converts 'PDF', 'DOCX', 'PPTX', 'HTML' and image documents into structured, AI-ready data. The package wraps the 'Docling' 'Python' package through 'reticulate' to extract layout-aware text, tables and metadata, export to 'Markdown' or 'JSON', and split documents into context-rich chunks suitable for retrieval-augmented generation (RAG) and embedding pipelines.
| Version: | 0.1.0 |
| Imports: | reticulate (≥ 1.34.0), cli, rlang, stats, tibble |
| Suggests: | testthat (≥ 3.0.0), knitr, rmarkdown |
| Published: | 2026-07-10 |
| DOI: | 10.32614/CRAN.package.doclingr (may not be active yet) |
| Author: | Andre Leite [aut, cre], Marcos Wasilew [aut], Hugo Vasconcelos [aut], Carlos Amorim [aut], Diogo Bezerra [aut] |
| Maintainer: | Andre Leite <leite at castlab.org> |
| BugReports: | https://github.com/StrategicProjects/doclingr/issues |
| License: | MIT + file LICENSE |
| URL: | https://github.com/StrategicProjects/doclingr, https://strategicprojects.github.io/doclingr/ |
| NeedsCompilation: | no |
| SystemRequirements: | Python (>= 3.9), docling (>= 2.20.0; tested with 2.107.0) |
| Language: | en-US |
| Materials: | README, NEWS |
| CRAN checks: | doclingr results |
| Reference manual: | doclingr.html , doclingr.pdf |
| Vignettes: |
From documents to a RAG corpus in R (source, R code) Conversion options and performance (source, R code) Building a RAG pipeline (source, R code) Extracting tables from documents (source, R code) |
| Package source: | doclingr_0.1.0.tar.gz |
| Windows binaries: | r-devel: not available, r-release: doclingr_0.1.0.zip, r-oldrel: doclingr_0.1.0.zip |
| macOS binaries: | r-release (arm64): doclingr_0.1.0.tgz, r-oldrel (arm64): doclingr_0.1.0.tgz, r-release (x86_64): doclingr_0.1.0.tgz, r-oldrel (x86_64): doclingr_0.1.0.tgz |
Please use the canonical form https://CRAN.R-project.org/package=doclingr to link to this page.