Doc-Ocr-Categorizer

Techniques

• Frontend: React, Antd
• Backend: FastAPI
• Relational database: PostgreSQL
• Storage: MinIO
• OCR: RapidOCR
• NLP: multilingual-e5-large-instruct
• Recommendation Algorithm: pgvector

Overview

The main goal of this project is to design an automatic document recognition and categorization system, using OCR and NLP algorithms, combined with recommendation algorithms, to achieve intelligent processing of documents.

Documentations

• Thorough-Introduction
• Frontend-README
• Backend-README (Including ML & DL Algorithms)