Package: arete 0.1

arete: Automated REtrieval from TExt

A Python based pipeline for extraction of species occurrence data through the usage of large language models. Includes validation tools designed to handle model hallucinations for a scientific, rigorous use of LLM. Currently supports usage of GPT with more planned, including local and non-proprietary models. For more details on the methodology used please consult the references listed under each function, such as Kent, A. et al. (1995) <doi:10.1002/asi.5090060209>, van Rijsbergen, C.J. (1979, ISBN:978-0408709293, Levenshtein, V.I. (1966) <https://nymity.ch/sybilhunting/pdf/Levenshtein1966a.pdf> and Klaus Krippendorff (2011) <https://repository.upenn.edu/handle/20.500.14332/2089>.

Authors:Vasco V. Branco [cre, aut], Vaughn Shirey [ctb], Thomas Merrien [ctb], Pedro Cardoso [aut]

arete_0.1.tar.gz
arete_0.1.zip(r-4.7-any)arete_0.1.zip(r-4.6-any)arete_0.1.zip(r-4.5-any)
arete_0.1.tgz(r-4.6-any)arete_0.1.tgz(r-4.5-any)
arete_0.1.tar.gz(r-4.7-any)arete_0.1.tar.gz(r-4.6-any)
arete_0.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION
card.svg |card.png
arete/json (API)

# Install 'arete' in R:

install.packages('arete', repos = c('https://vascobranco.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/vascobranco/arete/issues

On CRAN:

ecology large-language-models wildlife-conservation

3.70 score 1 stars 4 scripts 447 downloads 19 exports 195 dependencies

Last updated from:cc738ca101. Checks:7 NOTE, 2 OK. Indexed: yes.

Target	Result	Time
linux-devel	NOTE	587
source / vignettes	OK	333
linux-release	NOTE	417
macos-release	NOTE	445
macos-oldrel	NOTE	400
windows-devel	NOTE	515
windows-release	NOTE	437
windows-oldrel	NOTE	329
wasm-release	OK	186

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

Dependencies: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

Package workflow

Data extraction | Process coordinates | Process species names | Process outliers | Create performance reports

Rendered fromrequest_example.Rmdusingknitr::rmarkdown

Last update: 2025-11-06
Started: 2025-11-06

Help page	Topics
Example data packaged with gecko	arete_data
Summary of methods in the arete package	arete arete_package
Setup arete	arete_setup
Mechanical coordinate conversion	aux_string_to_coords
Check if text is language-appropriate	check_lang
Check EOO differences between two sets of coordinates	compare_IUCN
Create training data for GPT	create_training_data
Compare the contents of two WebAnno tsv files.	file_comparison
Get geographic coordinates from localities	gazetteer
Call a Large Language Model (LLM) to extract species geographic data	get_geodata
Update OCR dependencies	install_OCR_packages
Update python dependencies	install_python_packages
Labels for model training	labels
Get the unique labels of a WebAnno document	labels_unique
Scan PDF with optical character recognition (OCR)	OCR_document
Evaluate the performance of a LLM	performance_report
Extract and process text from a document	process_document
Process and fix species names	process_species_names
Convert strings to numerical coordinates	string_to_coords
Open a WebAnno TSV v3.3 file.	webanno_open
Summarize the contents of a group of WebAnno tsv files	webanno_summary
WebAnno TSV v3.3 class creator.	WebAnnoTSV-class webanno_creator

Package: arete 0.1

arete: Automated REtrieval from TExt

Citation

Development and contributors

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)