{ "_id": "6a107a86acfb0bcc41cadba5", "Package": "arete", "Title": "Automated REtrieval from TExt", "Version": "0.1", "Date": "2025-09-29", "Author": "Vasco V. Branco [cre, aut]\n(), Vaughn Shirey [ctb]\n(), Thomas Merrien [ctb]\n(), Pedro Cardoso [aut]\n()", "Authors@R": "c(\nperson(\"Vasco V.\", \"Branco\", role = c(\"cre\",\"aut\"),\nemail = \"vasco.branco@helsinki.fi\",\ncomment = c(ORCID = \"0000-0001-7797-3183\")),\nperson(\"Vaughn\", \"Shirey\", role = c(\"ctb\"),\nemail = \"vms55@georgetown.edu\",\ncomment = c(ORCID = \"0000-0002-3589-9699\")),\nperson(\"Thomas\", \"Merrien\", role = c(\"ctb\"),\nemail = \"thomas.merrien@helsinki.fi\",\ncomment = c(ORCID = \"0000-0002-0339-5656\")),\nperson(\"Pedro\", \"Cardoso\", role = c(\"aut\"),\nemail = \"pedro.cardoso@helsinki.fi\",\ncomment = c(ORCID = \"0000-0001-8119-9960\"))\n)", "Maintainer": "Vasco V. Branco ", "Description": "A Python based pipeline for extraction of species\noccurrence data through the usage of large language models.\nIncludes validation tools designed to handle model\nhallucinations for a scientific, rigorous use of LLM. Currently\nsupports usage of GPT with more planned, including local and\nnon-proprietary models. For more details on the methodology\nused please consult the references listed under each function,\nsuch as Kent, A. et al. (1995) ,\nvan Rijsbergen, C.J. (1979, ISBN:978-0408709293, Levenshtein,\nV.I. (1966)\n and\nKlaus Krippendorff (2011)\n.", "License": "GPL-3", "Encoding": "UTF-8", "RoxygenNote": "7.3.2", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-06 08:05:57 UTC", "User": "root" }, "Config/Needs/website": "rmarkdown", "VignetteBuilder": "knitr", "Config/pak/sysreqs": "libabsl-dev cmake libfontconfig1-dev\nlibfreetype6-dev libfribidi-dev libgdal-dev gdal-bin\nlibgeos-dev libglpk-dev libgmp3-dev make libharfbuzz-dev\ndefault-jdk libicu-dev libjpeg-dev libpng-dev libuv1-dev\nlibxml2-dev libssl-dev libpoppler-cpp-dev poppler-data\nlibproj-dev python3 libsqlite3-dev libudunits2-dev", "Repository": "https://vascobranco.r-universe.dev", "Date/Publication": "2025-11-06 17:51:06 UTC", "RemoteUrl": "https://github.com/vascobranco/arete", "RemoteRef": "HEAD", "RemoteSha": "cc738ca101f4ea25df71db19945a2b0c59437ce1", "MD5sum": "5e57bba95bf0ad0e3444f230d23664e5", "_user": "vascobranco", "_type": "src", "_file": "arete_0.1.tar.gz", "_fileid": "d27b56b6f824b2ed3f1a511d47024f36e4f767061e1e71b30c63b1d522303786", "_filesize": 1083653, "_sha256": "d27b56b6f824b2ed3f1a511d47024f36e4f767061e1e71b30c63b1d522303786", "_created": "2026-05-06T08:05:57.000Z", "_published": "2026-05-22T15:47:18.606Z", "_distro": "noble", "_jobs": [ { "job": 77413721460, "time": 422, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "6825527898" }, { "job": 77413721348, "time": 394, "config": "linux-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "6825521372" }, { "job": 77413721738, "time": 458, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "6825530350" }, { "job": 77413721695, "time": 677, "config": "macos-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "6825581883" }, { "job": 77413720889, "time": 321, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "6825418728" }, { "job": 77413720800, "time": 199, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7164645821" }, { "job": 77413721296, "time": 766, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "6825615281" }, { "job": 77413721710, "time": 800, "config": "windows-oldrel", "r": "4.5.3", "check": "NOTE", "artifact": "6825623120" }, { "job": 77413721441, "time": 820, "config": "windows-release", "r": "4.6.0", "check": "NOTE", "artifact": "6825628637" } ], "_buildurl": "https://github.com/r-universe/vascobranco/actions/runs/25423469812", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/vascobranco/arete", "_commit": { "id": "cc738ca101f4ea25df71db19945a2b0c59437ce1", "author": "Vasco Branco ", "committer": "GitHub ", "message": "Update README.md", "time": 1762451466 }, "_maintainer": { "name": "Vasco V. Branco", "email": "vasco.branco@helsinki.fi", "login": "vascobranco", "twitter": "@VV_Branco", "uuid": 56229977, "orcid": "0000-0001-7797-3183" }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.3.0", "role": "Depends" }, { "package": "terra", "role": "Imports" }, { "package": "cld2", "role": "Imports" }, { "package": "stringr", "role": "Imports" }, { "package": "reticulate", "role": "Imports" }, { "package": "pdftools", "role": "Imports" }, { "package": "fedmatch", "role": "Imports" }, { "package": "kableExtra", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "gecko", "role": "Imports" }, { "package": "methods", "role": "Imports" }, { "package": "ggplot2", "role": "Imports" }, { "package": "jsonlite", "role": "Imports" }, { "package": "googledrive", "role": "Imports" }, { "package": "irr", "role": "Imports" }, { "package": "rmarkdown", "role": "Imports" }, { "package": "knitr", "role": "Suggests" } ], "_owner": "vascobranco", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2025-45", "n": 5 } ], "_tags": [], "_topics": [ "ecology", "large-language-models", "wildlife-conservation" ], "_stars": 1, "_contributors": [ { "user": "vascobranco", "count": 5, "uuid": 56229977 } ], "_userbio": { "uuid": 56229977, "type": "user", "name": "Vasco Branco", "description": "Researcher and R programmer uncovering the secrets of the flesh." }, "_downloads": { "count": 217, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/arete" }, "_devurl": "https://github.com/vascobranco/arete", "_searchresults": 3, "_rbuild": "4.6.0", "_assets": [ "extra/arete.html", "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/vascobranco/arete", "_realowner": "vascobranco", "_cranurl": true, "_releases": [ { "version": "0.1", "date": "2025-10-20" } ], "_exports": [ "arete_data", "arete_setup", "aux_string_to_coords", "check_lang", "compare_IUCN", "create_training_data", "file_comparison", "gazetteer", "get_geodata", "install_OCR_packages", "install_python_packages", "labels", "labels_unique", "performance_report", "process_document", "process_species_names", "string_to_coords", "webanno_open", "webanno_summary" ], "_help": [ { "page": "arete_data", "title": "Example data packaged with gecko", "topics": [ "arete_data" ] }, { "page": "ARETE_package", "title": "Summary of methods in the arete package", "topics": [ "arete", "arete_package" ] }, { "page": "arete_setup", "title": "Setup arete", "topics": [ "arete_setup" ] }, { "page": "aux_string_to_coords", "title": "Mechanical coordinate conversion", "topics": [ "aux_string_to_coords" ] }, { "page": "check_lang", "title": "Check if text is language-appropriate", "topics": [ "check_lang" ] }, { "page": "compare_IUCN", "title": "Check EOO differences between two sets of coordinates", "topics": [ "compare_IUCN" ] }, { "page": "create_training_data", "title": "Create training data for GPT", "topics": [ "create_training_data" ] }, { "page": "file_comparison", "title": "Compare the contents of two WebAnno tsv files.", "topics": [ "file_comparison" ] }, { "page": "gazetteer", "title": "Get geographic coordinates from localities", "topics": [ "gazetteer" ] }, { "page": "get_geodata", "title": "Call a Large Language Model (LLM) to extract species geographic data", "topics": [ "get_geodata" ] }, { "page": "install_OCR_packages", "title": "Update OCR dependencies", "topics": [ "install_OCR_packages" ] }, { "page": "install_python_packages", "title": "Update python dependencies", "topics": [ "install_python_packages" ] }, { "page": "labels", "title": "Labels for model training", "topics": [ "labels" ] }, { "page": "labels_unique", "title": "Get the unique labels of a WebAnno document", "topics": [ "labels_unique" ] }, { "page": "OCR_document", "title": "Scan PDF with optical character recognition (OCR)", "topics": [ "OCR_document" ] }, { "page": "performance_report", "title": "Evaluate the performance of a LLM", "topics": [ "performance_report" ] }, { "page": "process_document", "title": "Extract and process text from a document", "topics": [ "process_document" ] }, { "page": "process_species_names", "title": "Process and fix species names", "topics": [ "process_species_names" ] }, { "page": "string_to_coords", "title": "Convert strings to numerical coordinates", "topics": [ "string_to_coords" ] }, { "page": "webanno_open", "title": "Open a WebAnno TSV v3.3 file.", "topics": [ "webanno_open" ] }, { "page": "webanno_summary", "title": "Summarize the contents of a group of WebAnno tsv files", "topics": [ "webanno_summary" ] }, { "page": "WebAnnoTSV-class", "title": "WebAnno TSV v3.3 class creator.", "topics": [ "WebAnnoTSV-class", "webanno_creator" ] } ], "_pkglogo": "https://github.com/vascobranco/arete/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/vascobranco/arete/raw/HEAD/README.md", "_rundeps": [ "abind", "ape", "askpass", "base64enc", "BAT", "BH", "biomod2", "bit", "bit64", "boot", "bslib", "cachem", "caret", "class", "classInt", "cld2", "cli", "clock", "cluster", "clusterGeneration", "coda", "codetools", "combinat", "cpp11", "crayon", "curl", "data.table", "DBI", "DEoptim", "diagram", "digest", "dismo", "doParallel", "dplyr", "e1071", "evaluate", "expm", "farver", "fastcluster", "fastmap", "fastmatch", "fedmatch", "FNN", "fontawesome", "forcats", "foreach", "fs", "future", "future.apply", "gargle", "gbm", "gdistance", "gecko", "generics", "geometry", "geosphere", "ggplot2", "globals", "glue", "googledrive", "gower", "gtable", "hardhat", "here", "highr", "hitandrun", "hms", "htmltools", "httr", "hypervolume", "igraph", "ipred", "irr", "isoband", "iterators", "jquerylib", "jsonlite", "kableExtra", "kernlab", "KernSmooth", "knitr", "ks", "labeling", "lattice", "lava", "lifecycle", "linprog", "listenv", "lpSolve", "lubridate", "magic", "magrittr", "maps", "MASS", "Matrix", "mclust", "memoise", "mgcv", "mime", "mnormt", "ModelMetrics", "multicool", "mvtnorm", "nlme", "nls2", "nnet", "numDeriv", "openssl", "optimParallel", "palmerpenguins", "parallelly", "pbapply", "pdftools", "pdist", "permute", "phangorn", "phytools", "pillar", "pkgconfig", "PlotTools", "plyr", "png", "pracma", "predicts", "PresenceAbsence", "prettyunits", "pROC", "prodlim", "progress", "progressr", "proto", "proxy", "purrr", "qpdf", "quadprog", "R6", "rappdirs", "raster", "rbibutils", "rcdd", "RColorBrewer", "Rcpp", "RcppArmadillo", "RcppProgress", "RcppTOML", "Rdpack", "recipes", "red", "reshape", "reshape2", "reticulate", "rlang", "rmarkdown", "rpart", "rprojroot", "rstudioapi", "s2", "S7", "sass", "scales", "scatterplot3d", "sf", "shape", "SnowballC", "sp", "sparsevctrs", "SQUAREM", "stringdist", "stringi", "stringr", "survival", "svglite", "sys", "systemfonts", "terra", "textshaping", "tibble", "tidyr", "tidyselect", "timechange", "timeDate", "tinytex", "TreeTools", "tzdb", "units", "utf8", "uuid", "vctrs", "vegan", "viridisLite", "withr", "wk", "xfun", "xml2", "yaml" ], "_vignettes": [ { "source": "request_example.Rmd", "filename": "request_example.html", "title": "Package workflow", "engine": "knitr::rmarkdown", "headings": [ "Data extraction", "Process coordinates", "Process species names", "Process outliers", "Create performance reports" ], "created": "2025-11-06 17:02:00", "modified": "2025-11-06 17:02:00", "commits": 1 } ], "_score": 3.6989700043360187, "_indexed": true, "_nocasepkg": "arete", "_universes": [ "vascobranco" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1", "date": "2026-05-06T08:09:57.000Z", "distro": "noble", "commit": "cc738ca101f4ea25df71db19945a2b0c59437ce1", "fileid": "e9a8b32a7921bf82c5cefa36afc836e14e620d6bdb5e0d159f4d18d6c15af895", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/vascobranco/actions/runs/25423469812" }, { "r": "4.6.0", "os": "linux", "version": "0.1", "date": "2026-05-06T08:09:49.000Z", "distro": "noble", "commit": "cc738ca101f4ea25df71db19945a2b0c59437ce1", "fileid": "a2feb3c1e0c8b64a9e21cda56454dfb782a33fb62baec402133e11feee048c4f", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/vascobranco/actions/runs/25423469812" }, { "r": "4.5.3", "os": "mac", "version": "0.1", "date": "2026-05-06T08:11:42.000Z", "commit": "cc738ca101f4ea25df71db19945a2b0c59437ce1", "fileid": "c5acfd312d3e9aaaf97ed3153e8e1f5f1deca948f67bc126c67ac2e14fa3117d", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/vascobranco/actions/runs/25423469812" }, { "r": "4.6.0", "os": "mac", "version": "0.1", "date": "2026-05-06T08:13:29.000Z", "commit": "cc738ca101f4ea25df71db19945a2b0c59437ce1", "fileid": "47095d9ed626c21ec58b631a815fce91a92a6835aabbeacc5f95997fd1c5eacf", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/vascobranco/actions/runs/25423469812" }, { "r": "4.7.0", "os": "win", "version": "0.1", "date": "2026-05-06T08:15:32.000Z", "commit": "cc738ca101f4ea25df71db19945a2b0c59437ce1", "fileid": "7ac0d48dcd714b4dc8de007eaed27c305a9e7efd9b9dc10ac0d57f228f3a1051", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/vascobranco/actions/runs/25423469812" }, { "r": "4.5.3", "os": "win", "version": "0.1", "date": "2026-05-06T08:16:00.000Z", "commit": "cc738ca101f4ea25df71db19945a2b0c59437ce1", "fileid": "b13a072deb56263fd29acfd63ca68278ff7c4660fda8af09a7dda752ad8759b7", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/vascobranco/actions/runs/25423469812" }, { "r": "4.6.0", "os": "win", "version": "0.1", "date": "2026-05-06T08:15:23.000Z", "commit": "cc738ca101f4ea25df71db19945a2b0c59437ce1", "fileid": "9eac2bc1a656b25a0596aca7f882a77c3bbbf7ae521c146eafc2705f4371237c", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/vascobranco/actions/runs/25423469812" }, { "r": "4.6.0", "os": "wasm", "version": "0.1", "date": "2026-05-22T15:46:52.000Z", "commit": "cc738ca101f4ea25df71db19945a2b0c59437ce1", "fileid": "02b040dfed9b627a987ad02f0715714548e7fa679c4dbd1c965a02acfd76af43", "status": "success", "buildurl": "https://github.com/r-universe/vascobranco/actions/runs/25423469812" } ] }