A FastAPI-based Named Entity Recognition (NER) API for detecting bank names using spaCy. The API supports customizable patterns, is Dockerized for easy deployment, and ready for cloud hosting.

• Detects bank names in text using spaCy's EntityRuler.
• Allows adding custom patterns dynamically via the /train/ endpoint.
• Fast and lightweight using FastAPI.
• Dockerized for portability and easy deployment.
• CORS enabled for frontend integration.

bank-ner/
├── bank_patterns.json       # JSON file with default bank patterns
├── main.py                  # FastAPI application
├── requirements.txt         # Python dependencies
├── Dockerfile               # Docker configuration
└── __pycache__/             # Compiled Python files

git clone https://github.com/kishore-144/bank-ner.git

python3 -m venv venv
source venv/bin/activate  # Linux/macOS
venv\Scripts\activate     # Windows

pip install -r requirements.txt

uvicorn main:app --reload --host 0.0.0.0 --port 8000

Open http://localhost:8000/docs for the interactive API documentation.

• Endpoint: /train/
• Method: POST
• Body:

{
  "l1": [
    {
      "label": "BANK",
      "pattern": "UAB"
    },
    {
      "label": "BANK",
      "pattern": "IDBI"
    }
  ]
}

• Response:

{"message": "2 patterns added"}

• Endpoint: /test/
• Method: POST
• Body:

{
  "sentence": "I have accounts in SBI and HDFC Bank."
}

• Response:

[
  ["SBI", "BANK"],
  ["HDFC Bank", "BANK"]
]

docker build -t bank-ner-api .

docker run -d -p 8000:8000 bank-ner-api

docker ps                       # Get container ID
docker stop <container_id>
docker rm <container_id>

• The app can be deployed to Azure App Service, AWS ECS, Google Cloud Run, or any other container-hosting service.
• Ensure the Docker image exposes port 8000 and the container is set to run uvicorn main:app --host 0.0.0.0 --port 8000.

• Python 3.11+
• FastAPI
• spaCy
• Docker (optional, for containerization)

1. Fork the repo
2. Create a new branch (git checkout -b feature/xyz)
3. Make your changes
4. Commit (git commit -m 'Add feature xyz')
5. Push (git push origin feature/xyz)
6. Open a pull request

This project is licensed under the MIT License.

Kishore Passionate about machine learning, web development, and building scalable APIs.