Package: doclingr 0.1.0

Andre Leite

doclingr: Document Intelligence via 'Docling'

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.

Authors:Andre Leite [aut, cre], Marcos Wasilew [aut], Hugo Vasconcelos [aut], Carlos Amorim [aut], Diogo Bezerra [aut]

doclingr_0.1.0.tar.gz
doclingr_0.1.0.tar.gz(r-4.7-any)doclingr_0.1.0.tar.gz(r-4.6-any)
doclingr_0.1.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
doclingr/json (API)

# Install 'doclingr' in R:
install.packages('doclingr', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/strategicprojects/doclingr/issues

Pkgdown/docs site:https://strategicprojects.github.io

On CRAN:

Conda:

3.30 score 13 exports 21 dependencies

Last updated from:827d89d105. Checks:4 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-x86_64OK159
source / vignettesOK274
linux-release-x86_64OK153
wasm-releaseOK125

Exports:as_doctagsas_htmlas_jsonas_markdownas_textdocling_availabledocling_chunkdocling_convertdocling_embeddocling_figuresdocling_n_pagesdocling_tablesinstall_docling

Dependencies:cliglueherejsonlitelatticelifecyclemagrittrMatrixpillarpkgconfigpngrappdirsRcppRcppTOMLreticulaterlangrprojroottibbleutf8vctrswithr

Building a RAG pipeline
1. Convert and chunk | 2. Attach embeddings | 3. Retrieve | 4. Persist | Scaling to many documents
Rendered fromrag.Rmdusingknitr::rmarkdown

Last update: 2026-07-10
Started: 2026-07-10

Conversion options and performance
The Python backend | OCR | Table structure: accurate vs. fast | Hardware acceleration | Images and figures | Batch conversion | A pragmatic recipe
Rendered fromoptions.Rmdusingknitr::rmarkdown

Last update: 2026-07-10
Started: 2026-07-10

Extracting tables from documents
The basics | Accurate vs. fast table structure | Working with the extracted tables | Tips
Rendered fromtables.Rmdusingknitr::rmarkdown

Last update: 2026-07-10
Started: 2026-07-10

From documents to a RAG corpus in R
Overview | One-time setup | Converting a document | Exporting structure | Tables as tibbles | Figures | Chunking for retrieval | From chunks to embeddings | Where to go next
Rendered fromdoclingr.Rmdusingknitr::rmarkdown

Last update: 2026-07-10
Started: 2026-07-10

Readme and manuals

Help Manual

Help pageTopics
Is the Docling backend available?docling_available
Split a document into RAG-ready chunksdocling_chunk
Convert one or more documents with Doclingdocling_convert
Attach embeddings to chunksdocling_embed
Export a converted documentas_doctags as_doctags.docling_document as_html as_html.docling_document as_json as_json.docling_document as_markdown as_markdown.docling_document as_text as_text.docling_document docling_export
Extract figures (pictures) from a converted documentdocling_figures
Number of pages in a converted documentdocling_n_pages
Extract tables as data framesdocling_tables
Install the Docling Python backendinstall_docling