{ "_id": "6a51f3cf9b92047c28d52fbe", "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", "Roxygen": "list(markdown = TRUE)", "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", "Config/pak/sysreqs": "libpng-dev python3", "Repository": "https://strategicprojects.r-universe.dev", "Date/Publication": "2026-07-10 20:32:53 UTC", "RemoteUrl": "https://github.com/strategicprojects/doclingr", "RemoteRef": "HEAD", "RemoteSha": "165fcb630ae6f65baa8b9ec13f29095b657b8a68", "NeedsCompilation": "no", "Packaged": { "Date": "2026-07-11 07:38:53 UTC", "User": "root" }, "Author": "Andre Leite [aut, cre],\nMarcos Wasilew [aut],\nHugo Vasconcelos [aut],\nCarlos Amorim [aut],\nDiogo Bezerra [aut]", "Maintainer": "Andre Leite ", "_user": "strategicprojects", "_type": "src", "_file": "doclingr_0.1.0.tar.gz", "_fileid": "https://r2.ropensci.org/209559b3b30ad4bf960341f959580a02ae019ec20cb4d5eac0e958fa078a28f7", "_filesize": 305533, "_sha256": "209559b3b30ad4bf960341f959580a02ae019ec20cb4d5eac0e958fa078a28f7", "_expires": "2026-10-19T07:42:05.000Z", "_created": "2026-07-11T07:38:53.000Z", "_published": "2026-07-11T07:42:07.209Z", "_jobs": [ { "job": 86524534771, "time": 151, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8246419882" }, { "job": 86524534765, "time": 151, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8246420207" }, { "job": 86524534761, "time": 102, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8246412942" }, { "job": 86524534766, "time": 126, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8246416491" }, { "job": 86524304277, "time": 184, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8246396798" }, { "job": 86524534769, "time": 107, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8246413813" }, { "job": 86524534775, "time": 148, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "8246419684" }, { "job": 86524534777, "time": 135, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8246418076" }, { "job": 86524534772, "time": 131, "config": "windows-release", "r": "4.6.1", "check": "OK", "artifact": "8246417083" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/strategicprojects/actions/runs/29144757796", "_status": "success", "_upstream": "https://github.com/strategicprojects/doclingr", "_commit": { "id": "165fcb630ae6f65baa8b9ec13f29095b657b8a68", "author": "André Leite ", "committer": "André Leite ", "message": "Post-acceptance: CRAN badge + install.packages() in README, drop CRAN-SUBMISSION\n\ndoclingr 0.1.0 was accepted on CRAN on 2026-07-10.\n\nCo-Authored-By: Claude Fable 5 \n", "time": 1783715573 }, "_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": "strategicprojects", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-26", "n": 11 }, { "week": "2026-27", "n": 4 }, { "week": "2026-28", "n": 1 } ], "_tags": [ { "name": "v0.1.0", "date": "2026-07-03" } ], "_stars": 0, "_contributors": [ { "user": "milkway", "count": 16, "uuid": 7375849 } ], "_userbio": { "uuid": 127886513, "type": "organization", "name": "Projetos Estratégicos", "followers": 4, "description": "Repositório de código da Assessoria Especial de Projetos Estratégicos." }, "_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" ], "_homeurl": "https://github.com/strategicprojects/doclingr", "_realowner": "strategicprojects", "_cranurl": true, "_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/strategicprojects/doclingr/raw/HEAD/man/figures/logo.svg", "_readme": "https://github.com/strategicprojects/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": "2026-06-27 21:36:32", "modified": "2026-06-27 21:36:32", "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": "2026-06-27 21:36:32", "modified": "2026-06-27 21:36:32", "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": "2026-06-27 21:36:32", "modified": "2026-06-27 21:36:32", "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": "2026-06-27 20:49:23", "modified": "2026-06-27 21:36:32", "commits": 2 } ], "_score": 4.778151250383644, "_indexed": true, "_nocasepkg": "doclingr", "_universes": [ "strategicprojects" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.0", "date": "2026-07-11T07:41:07.000Z", "distro": "resolute", "commit": "165fcb630ae6f65baa8b9ec13f29095b657b8a68", "fileid": "https://r2.ropensci.org/1cd6305f30d082b9b3b733f81dc99962e60beeeb50392c48018c03434e6e24d5", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/strategicprojects/actions/runs/29144757796" }, { "r": "4.6.1", "os": "linux", "version": "0.1.0", "date": "2026-07-11T07:41:06.000Z", "distro": "resolute", "commit": "165fcb630ae6f65baa8b9ec13f29095b657b8a68", "fileid": "https://r2.ropensci.org/ee03d48d3f96466818f6fc290172b1221a014fb34399abea9e3d4ecb4eef740c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/strategicprojects/actions/runs/29144757796" }, { "r": "4.5.3", "os": "mac", "version": "0.1.0", "date": "2026-07-11T07:40:24.000Z", "commit": "165fcb630ae6f65baa8b9ec13f29095b657b8a68", "fileid": "https://r2.ropensci.org/8f052dd19921e7b851833897fad290a1ba7cdbfd386f0f4f780181198f71dd4f", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/strategicprojects/actions/runs/29144757796" }, { "r": "4.6.1", "os": "mac", "version": "0.1.0", "date": "2026-07-11T07:40:39.000Z", "commit": "165fcb630ae6f65baa8b9ec13f29095b657b8a68", "fileid": "https://r2.ropensci.org/783457613216f2af6cb1413640de0902f2dd75112cb4224099c4804c2da2a153", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/strategicprojects/actions/runs/29144757796" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.0", "date": "2026-07-11T07:40:56.000Z", "commit": "165fcb630ae6f65baa8b9ec13f29095b657b8a68", "fileid": "https://r2.ropensci.org/ec245341c61e4a2bb3e534a9e1daaa6fa93f8d1bbf3c22e6526ebb4f1e32d76c", "status": "success", "buildurl": "https://github.com/r-universe/strategicprojects/actions/runs/29144757796" }, { "r": "4.7.0", "os": "win", "version": "0.1.0", "date": "2026-07-11T07:40:16.000Z", "commit": "165fcb630ae6f65baa8b9ec13f29095b657b8a68", "fileid": "https://r2.ropensci.org/dd52ccff0b71a06d56be8f0b730fa503e2f162e76fde6cc8fee585345c56719b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/strategicprojects/actions/runs/29144757796" }, { "r": "4.5.3", "os": "win", "version": "0.1.0", "date": "2026-07-11T07:40:13.000Z", "commit": "165fcb630ae6f65baa8b9ec13f29095b657b8a68", "fileid": "https://r2.ropensci.org/45a008aeb2b9fffb303a73562f9236ee0a3a85b48b5e5104b8cc6dcdfc66cdfd", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/strategicprojects/actions/runs/29144757796" }, { "r": "4.6.1", "os": "win", "version": "0.1.0", "date": "2026-07-11T07:40:00.000Z", "commit": "165fcb630ae6f65baa8b9ec13f29095b657b8a68", "fileid": "https://r2.ropensci.org/db2b1406e774a5e8831052698c9b7c38bd273b0c8088baf5b5b9fff9a1ed9c08", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/strategicprojects/actions/runs/29144757796" } ] }