Automated REtrieval from TExt

---

Documentation for package ‘arete’ version 0.1

• DESCRIPTION file.
• User guides, package vignettes and other documentation.

Help Pages

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