Spatial field location memory for document processing pipelines. Learns field positions, validates extractions, identifies document types by layout, detects drift, and monitors template health. Zero dependencies, pure Python.
YAML-based pattern matching with multi-line capabilities for log normalization using syslog-ng patterndb
End-to-end engineering document parser for detecting title blocks, auto-rotating and cropping drawings, and extracting structured fields with YOLO and Qwen2.5-VL.
Zuva — independent third-party profile of a public API surface, by API Evangelist. Zuva (by Kira Systems) provides a contract and document AI REST API for extracting structured data from unstructured documents. The Zuva DocAI API offers asynchronous OCR, field extraction across 1,400+ pre-built fields, multi-level document classification across 220
To associate your repository with the field-extraction topic, visit your repo's landing page and select "manage topics."