maxent-ai/ocrpy
OCR, Archive, Index and Search: Implementation agnostic OCR framework.
Provides a unified Python interface across multiple OCR backends (Tesseract, AWS Textract, Google Vision, Azure Computer Vision) with abstraction over their different APIs. Exposes both low-level engine access and a declarative Pipeline API that supports YAML configuration for processing documents from cloud storage sources (S3, GCS) with credential management built-in. Designed for end-to-end workflows spanning document parsing, archival, indexing, and search operations.
224 stars and 167 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
224
Forks
11
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 03, 2023
Monthly downloads
167
Commits (30d)
0
Dependencies
17
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/maxent-ai/ocrpy"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
haven-jeon/LegalQA
Korean LegalQA using SentenceKoBART
ametnes/nesis
Your AI Powered Enterprise Knowledge Partner. Designed to be used at scale from ingesting large...
foxminchan/LawKnowledge
A legal knowledge search and Q&A application based on Vietnam's Legal Code and legal document database ⚖️
utachicodes/PyDocEnhancer
An AI-powered Python plugin to enhance documentation with summaries, code explanations,...
ryanlane/document-manager
Local-first document archive assistant for semantic search and RAG using local LLMs and embeddings.