Skip to content

AdityaRdy71/AI-Enterprise-Document-Classification-System

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

📄 Enterprise Document Classifier

An AI-powered enterprise document classification system built using Vision Transformer (ViT), PyTorch, FastAPI, and Gradio.


Features

✔ Vision Transformer (Google ViT) ✔ 16 Document Classes ✔ FastAPI REST API ✔ Gradio Frontend ✔ Real-time Inference ✔ Confidence Score ✔ Checkpoint Loading ✔ Image Preprocessing ✔ Enterprise-ready Architecture


Tech Stack

  • Python
  • PyTorch
  • Transformers (HuggingFace)
  • FastAPI
  • Gradio
  • Torchvision
  • Pillow

Dataset

RVL-CDIP Dataset 16 Enterprise Document Categories

  • Advertisement
  • Budget
  • Email
  • File Folder
  • Form
  • Handwritten
  • Invoice
  • Letter
  • Memo
  • News Article
  • Presentation
  • Questionnaire
  • Resume
  • Scientific Publication
  • Scientific Report
  • Specification

Project Structure

(project tree)


Demo

(screenshots)


Installation

pip install -r requirements.txt


Run FastAPI

PYTHONPATH=src uvicorn api:app --reload


Run Gradio

PYTHONPATH=src python src/gradio_app.py


API

POST /predict

Returns

{ "predicted_class": "...", "confidence": 99.86 }


Future Improvements

Docker GPU Deployment Top-3 Predictions Batch Inference Cloud Deployment

About

Enterprise AI platform for document classification, OCR, metadata extraction, validation, and intelligent document processing using LayoutLMv3, FastAPI, and Python.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages