LegalQA using SentenceKoBART

Implementation of legal QA system based on SentenceKoBART

Setup

# install git lfs , https://github.com/git-lfs/git-lfs/wiki/Installation
curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash
sudo apt install git-lfs
git clone https://github.com/haven-jeon/LegalQA.git
cd LegalQA
git lfs pull
pip install -r requirements.txt

Index

python app.py -t index

index

GPU-based indexing available as an option

  • pods/encoder.yml - on_gpu: true

With REST API

To start the Jina server for REST API:

python app.py -t query_restful

query

Then use a client to query:

curl --request POST -d '{"top_k": 1, "mode": "search",  "data": ["상속 관련 문의"]}' -H 'Content-Type: application/json' 'http://0.0.0.0:1234/api/search'

Or use Jinabox with endpoint http://127.0.0.1:1234/api/search

From the terminal

python app.py -t query

Demo

![](https://raw.githubusercontent.com/haven-jeon/LegalQA/main/data/demo.gif)

Citation

Model training, data crawling, and demo system were all supported by the AWS Hero program.

@misc{heewon2021,
author = {Heewon Jeon},
title = {LegalQA using SentenceKoBART},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/haven-jeon/LegalQA}}

GitHub

https://github.com/haven-jeon/LegalQA

Source: https://pythonawesome.com/implementation-of-legal-qa-system-based-on-sentencekobart/