marieai/marie-ai

Complex data extraction and orchestration framework designed for processing unstructured documents. It integrates AI-powered document pipelines (GenAI, LLM, VLLM) into your applications, supporting various tasks such as document cleanup, optical character recognition (OCR), classification, splitting, named entity recognition, and form processing

语言：Python · GitHub 星标：98 · Fork：13

话题：docker · document-layout-analysis · document-parser · icr · intelligent-character-recognition · intelligent-word-recognition · iwr · ocr

在 GitHub 上查看原仓库