Easily increase the capacity of the VnCoreNLP service to handle huge dataset.
Only support for word segmenter.
- Docker.
- Docker Compose.
- Python with
vncorenlp
preinstalled.
- Clone this repository.
git clone https://github.com/duydvu/Scalable-VnCoreNLP.git
cd Scalable-VnCoreNLP
- Build the Docker image:
docker-compose build
- Start the service with 4 instance:
docker-compose up --scale vncorenlp=4
- Connect to the service:
from vncorenlp import VnCoreNLP
wordsegmenter = VnCoreNLP('http://localhost', 8000)
wordsegmenter.tokenize('hôm nay tôi đi học')