Package index • ecoextract

Workflow

Main document processing pipeline

process_documents(): Complete Document Processing Workflow
process_single_document(): Process Single Document Through Complete Pipeline

Database Setup

Initialize and configure databases

init_ecoextract_database(): Initialize EcoExtract database
init_ecoextract(): Initialize ecoextract Project Configuration

Data Access

Query and export extracted data

get_documents(): Get Documents
get_records(): Get Records
get_ocr_markdown(): Data Access Functions
get_ocr_html_preview(): Get OCR HTML Preview
get_db_stats(): Get database statistics
export_db(): Export Database
export_bibtex(): Export Bibliography to BibTeX Format

Review and Accuracy

Human review workflow and accuracy metrics

save_document(): Save Document After Human Review
calculate_accuracy(): Calculate extraction accuracy metrics from verified documents