{ "_id": "6a5177689b92047c28d509c3", "Package": "doclingr", "Title": "Document Intelligence via 'Docling'", "Version": "0.1.0", "Authors@R": "c(\nperson(\"Andre\", \"Leite\", email = \"leite@castlab.org\", role = c(\"aut\", \"cre\")),\nperson(\"Marcos\", \"Wasilew\", email = \"marcos.wasilew@gmail.com\", role = \"aut\"),\nperson(\"Hugo\", \"Vasconcelos\", email = \"hugo.vasconcelos@ufpe.br\", role = \"aut\"),\nperson(\"Carlos\", \"Amorim\", email = \"carlos.agaf@ufpe.br\", role = \"aut\"),\nperson(\"Diogo\", \"Bezerra\", email = \"diogo.bezerra@ufpe.br\", role = \"aut\"))", "Description": "An interface to 'Docling', a document-understanding\nlibrary that converts 'PDF', 'DOCX', 'PPTX', 'HTML' and image\ndocuments into structured, AI-ready data. The package wraps the\n'Docling' 'Python' package through 'reticulate' to extract\nlayout-aware text, tables and metadata, export to 'Markdown' or\n'JSON', and split documents into context-rich chunks suitable\nfor retrieval-augmented generation (RAG) and embedding\npipelines.", "License": "MIT + file LICENSE", "Language": "en-US", "Encoding": "UTF-8", "RoxygenNote": "8.0.0", "URL": "https://github.com/StrategicProjects/doclingr,\nhttps://strategicprojects.github.io/doclingr/", "BugReports": "https://github.com/StrategicProjects/doclingr/issues", "SystemRequirements": "Python (>= 3.9), docling (>= 2.20.0; tested with\n2.107.0)", "Config/testthat/edition": "3", "VignetteBuilder": "knitr", "NeedsCompilation": "no", "Packaged": { "Date": "2026-07-10 22:48:02 UTC", "User": "root" }, "Author": "Andre Leite [aut, cre], Marcos Wasilew [aut], Hugo Vasconcelos\n[aut], Carlos Amorim [aut], Diogo Bezerra [aut]", "Maintainer": "Andre Leite ", "Config/pak/sysreqs": "python3", "Repository": "https://cran.r-universe.dev", "Date/Publication": "2026-07-10 20:30:26 UTC", "RemoteUrl": "https://github.com/cran/doclingr", "RemoteRef": "HEAD", "RemoteSha": "827d89d1050de616cfab47ea1c80e3b7819eeea8", "_user": "cran", "_type": "src", "_file": "doclingr_0.1.0.tar.gz", "_fileid": "https://r2.ropensci.org/1ee4a3198a9b714d7f550cc147f043c2b851acb7df3b8ef4689e048a51264257", "_filesize": 306732, "_sha256": "1ee4a3198a9b714d7f550cc147f043c2b851acb7df3b8ef4689e048a51264257", "_expires": "2026-10-18T22:51:18.000Z", "_created": "2026-07-10T22:48:02.000Z", "_published": "2026-07-10T22:51:20.613Z", "_jobs": [ { "job": 86479714888, "time": 159, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8241291932" }, { "job": 86479714897, "time": 153, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8241290534" }, { "job": 86479117643, "time": 274, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8241249649" }, { "job": 86479714876, "time": 125, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8241282974" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/cran/actions/runs/29128503945", "_status": "success", "_upstream": "https://github.com/cran/doclingr", "_commit": { "id": "827d89d1050de616cfab47ea1c80e3b7819eeea8", "author": "Andre Leite ", "committer": "cran-robot ", "message": "version 0.1.0\n", "time": 1783715426 }, "_maintainer": { "name": "Andre Leite", "email": "leite@castlab.org" }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "reticulate", "version": ">= 1.34.0", "role": "Imports" }, { "package": "cli", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "tibble", "role": "Imports" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" } ], "_owner": "cran", "_selfowned": false, "_usedby": 0, "_updates": [ { "week": "2026-28", "n": 1 } ], "_tags": [ { "name": "0.1.0", "date": "2026-07-10" } ], "_stars": 0, "_userbio": { "uuid": 6899542, "type": "organization", "name": "cran", "followers": 617, "description": "Unofficial read-only mirror of all CRAN R packages" }, "_downloads": { "count": 0, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/doclingr" }, "_devurl": "https://github.com/strategicprojects/doclingr", "_pkgdown": "https://strategicprojects.github.io/doclingr/", "_searchresults": 0, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/doclingr.html", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "LICENSE", "manual.pdf" ], "_cranurl": false, "_releases": [ { "version": "0.1.0", "date": "2026-07-10" } ], "_exports": [ "as_doctags", "as_html", "as_json", "as_markdown", "as_text", "docling_available", "docling_chunk", "docling_convert", "docling_embed", "docling_figures", "docling_n_pages", "docling_tables", "install_docling" ], "_help": [ { "page": "docling_available", "title": "Is the Docling backend available?", "topics": [ "docling_available" ] }, { "page": "docling_chunk", "title": "Split a document into RAG-ready chunks", "topics": [ "docling_chunk" ] }, { "page": "docling_convert", "title": "Convert one or more documents with Docling", "topics": [ "docling_convert" ] }, { "page": "docling_embed", "title": "Attach embeddings to chunks", "topics": [ "docling_embed" ] }, { "page": "docling_export", "title": "Export a converted document", "topics": [ "as_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" ] }, { "page": "docling_figures", "title": "Extract figures (pictures) from a converted document", "topics": [ "docling_figures" ] }, { "page": "docling_n_pages", "title": "Number of pages in a converted document", "topics": [ "docling_n_pages" ] }, { "page": "docling_tables", "title": "Extract tables as data frames", "topics": [ "docling_tables" ] }, { "page": "install_docling", "title": "Install the Docling Python backend", "topics": [ "install_docling" ] } ], "_pkglogo": "https://github.com/cran/doclingr/raw/HEAD/man/figures/logo.svg", "_readme": "https://github.com/cran/doclingr/raw/HEAD/README.md", "_rundeps": [ "cli", "glue", "here", "jsonlite", "lattice", "lifecycle", "magrittr", "Matrix", "pillar", "pkgconfig", "png", "rappdirs", "Rcpp", "RcppTOML", "reticulate", "rlang", "rprojroot", "tibble", "utf8", "vctrs", "withr" ], "_vignettes": [ { "source": "rag.Rmd", "filename": "rag.html", "title": "Building a RAG pipeline", "engine": "knitr::rmarkdown", "headings": [ "1. Convert and chunk", "2. Attach embeddings", "3. Retrieve", "4. Persist", "Scaling to many documents" ], "created": "2026-07-10 20:30:26", "modified": "2026-07-10 20:30:26", "commits": 1 }, { "source": "options.Rmd", "filename": "options.html", "title": "Conversion options and performance", "engine": "knitr::rmarkdown", "headings": [ "The Python backend", "OCR", "Table structure: accurate vs. fast", "Hardware acceleration", "Images and figures", "Batch conversion", "A pragmatic recipe" ], "created": "2026-07-10 20:30:26", "modified": "2026-07-10 20:30:26", "commits": 1 }, { "source": "tables.Rmd", "filename": "tables.html", "title": "Extracting tables from documents", "engine": "knitr::rmarkdown", "headings": [ "The basics", "Accurate vs. fast table structure", "Working with the extracted tables", "Tips" ], "created": "2026-07-10 20:30:26", "modified": "2026-07-10 20:30:26", "commits": 1 }, { "source": "doclingr.Rmd", "filename": "doclingr.html", "title": "From documents to a RAG corpus in R", "engine": "knitr::rmarkdown", "headings": [ "Overview", "One-time setup", "Converting a document", "Exporting structure", "Tables as tibbles", "Figures", "Chunking for retrieval", "From chunks to embeddings", "Where to go next" ], "created": "2026-07-10 20:30:26", "modified": "2026-07-10 20:30:26", "commits": 1 } ], "_score": 3.3010299956639813, "_indexed": false, "_nocasepkg": "doclingr", "_universes": [ "cran", "strategicprojects" ], "_indexurl": "https://strategicprojects.r-universe.dev/doclingr", "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.0", "date": "2026-07-10T22:50:27.000Z", "distro": "resolute", "commit": "827d89d1050de616cfab47ea1c80e3b7819eeea8", "fileid": "https://r2.ropensci.org/bb05d709ed06f9a46f220f12aad102241bb716f91d384ca54ec2b5384029933a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/29128503945" }, { "r": "4.6.1", "os": "linux", "version": "0.1.0", "date": "2026-07-10T22:50:20.000Z", "distro": "resolute", "commit": "827d89d1050de616cfab47ea1c80e3b7819eeea8", "fileid": "https://r2.ropensci.org/75274d29df4abac5eed324978ab0f85a6506e5053019f3e0cf78f1980c3c00d3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/29128503945" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.0", "date": "2026-07-10T22:50:25.000Z", "commit": "827d89d1050de616cfab47ea1c80e3b7819eeea8", "fileid": "https://r2.ropensci.org/7e0b4e781ae3c93123112ffbca07381f7544bb0d22d9aafdc5884b442794535d", "status": "success", "buildurl": "https://github.com/r-universe/cran/actions/runs/29128503945" } ] }