VeriWise-Content-Checker is an intelligent, modular Python API system designed to help you validate and verify content efficiently across multiple aspects:
- β Plagiarism Detection: Detect content similarity using TF-IDF & cosine similarity algorithms.
- β Grammar Checking: Identify grammar and spelling issues using LanguageTool.
- β Grammar Suggestion: Provide detailed grammar improvement suggestions.
- β Copyright and Medical Content Verification: Extract text from images using Easyocr and OpenCV to cross-check with a database of copyrighted medical content providers.
π See Documentation
Make sure you have the following Python packages installed:
-
fastapi
-
uvicorn
-
easyocr
-
opencv-python
-
numpy
-
requests
-
Pillow
-
difflib
-
beautifulsoup4
-
language_tool_python
-
scikit-learn
-
pocketbase # Datasource for plagiarism detection
-
PyMuPDF
-
python-dotenv
You can install all dependencies using:
pip install -r requirements.txt
- Clone the repository
git clone https://github.com/SB2318/VeriWise-Content-Checker.git
cd VeriWise-Content-Checker
- Install the dependencies
pip install -r requirements.txt
- Run the application
uvicorn main:app --reload
or
python main.py
- Open your web browser and navigate to
http://127.0.0.1:5000
Easily build and run the Veriwise Content Checker using Docker.
- β Install Docker Desktop
- π Ensure Docker Desktop is running before executing commands.
docker build -t veriwise-content-checker .
# Option 1: (Detached Mode)
docker run -d -p 8000:8000 veriwise-content-checker
# Option 2: Run in Interactive Mode (for development/debugging)
docker run -it -p 8000:8000 veriwise-content-checker /bin/sh
In the terminal enter
uvicorn main:app --reload
Check api documentation at https://uhsocial.in/content-intel/docs
- Plagiarism Detection: Submit text to check for similarity against existing content.
- Grammar Check: Submit text to get a grammar correctness score (predict score).
- Grammar Suggestion: Get detailed suggestions to improve grammar and spelling errors.
- Copyright Checker: Upload images or text to verify against copyrighted medical content provider data.
Feel free to open issues or pull requests to improve the system. For feedback or any queries, you can contact the maintainer, via GitHub or email.