telecomsxchange/opentextshield repository overview

⁠Open Text Shield (OTS)

Open Text Shield (OTS) is an open-source, real-time, high-performance filtering and classification tool for SMS and messaging traffic, designed to deliver responses in under a second on standard hardware. It detects and blocks spam, phishing, and malicious content in 10 languages, making it a powerful solution for telecom operators, messaging providers, and any application handling message traffic, including those using SMPP, SIP, RCS, or SMTP.

OTS version 2.1 now proudly offers text classification predictions across 10 diverse languages, reaffirming our commitment to breaking language barriers and enhancing global communication:

🇬🇧 English 🇸🇦 Arabic 🇮🇩 Indonesian 🇩🇪 German 🇮🇹 Italian 🇪🇸 Spanish 🇷🇺 Russian 🇫🇷 French 🇱🇰 Sinhala 🇮🇳 Tamil

⁠Features

• Real-Time Detection: Instantly classify and block spam, phishing, and other unwanted messages.
• Machine Learning Models: Leverages advanced models like multi-lingual BERT to ensure high accuracy.
• Flexible Integration: Compatible with any application capable of making HTTP requests, including those using SMPP, SIP, RCS, and SMTP.
• Web API: Simple and efficient API for message analysis and predictions.
• Open Source: Free to use and modify, with commercial support available for advanced use cases.

⁠Quick Start with Docker

Setting up Open Text Shield is quick and easy with Docker. Follow these steps to get started:

Note: Our Dockerized version currently supports only ARM architecture. We plan to release a version for AMD/Intel architectures soon.

⁠1. Pull the Latest Docker Image

docker pull telecomsxchange/opentextshield:latest

⁠2. Run the Docker Container

docker run -d -p 8002:8002 telecomsxchange/opentextshield:latest

⁠3. Send a Message for Prediction

Once the container is running, you can send HTTP requests to the API to classify messages.

Example curl request:

curl -X POST "http://localhost:8002/predict/" \
-H "accept: application/json" \
-H "Content-Type: application/json" \
-d "{\"text\":\"Your SMS content here\",\"model\":\"bert\"}"

⁠Example Response:

{
  "label": "ham",
  "probability": 0.9971883893013,
  "processing_time": 0.6801116466522217,
  "Model_Name": "OTS_mBERT",
  "Model_Version": "bert-base-uncased",
  "Model_Author": "TelecomsXChange (TCXC)",
  "Last_Training": "2024-03-20"
}

⁠Learn More

For full documentation and source code, visit the Open Text Shield GitHub repository⁠.