Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/kendricktan/laice
Train your own Natural Language Processor from a browser 🤖 (Prototype)
https://github.com/kendricktan/laice
Last synced: about 9 hours ago
JSON representation
Train your own Natural Language Processor from a browser 🤖 (Prototype)
- Host: GitHub
- URL: https://github.com/kendricktan/laice
- Owner: kendricktan
- License: mit
- Created: 2016-10-16T00:55:24.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2023-06-08T10:22:05.000Z (over 1 year ago)
- Last Synced: 2024-04-14T11:32:51.336Z (7 months ago)
- Language: JavaScript
- Homepage:
- Size: 265 KB
- Stars: 172
- Watchers: 13
- Forks: 27
- Open Issues: 12
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
Icon by simpleicons
Train your own Natural Language Processor straight from your browser!
---
## What?
Laice allows you to build, train, and classify your own sentences via a Web UI.
Laice can also communicate with your applications through a RESTful API.
In other words, laice aims to be a free, open sourced alternative to api.ai, luis.ai, and wit.ai
Laice turns words into meanings (with enough training data), for example:
- `Jack lives in Berlin` -> `{'person': 'Jack', 'location': 'Berlin'}`
- `Tutu really likes bananas` -> `{'person': 'Tutu', 'food': 'bananas'}`
- `Close the door` -> `{'action': 'close', 'object': 'door'}`
---
## Getting started
```
git clone https://github.com/kendricktan/laice.git
cd laice
npm install -g bower
bower install
pip3 install -r requirements.txt
# Optional, doing this will yeild more accurate
# predictions, however will have a slower startup
# time. Its downloading pre-processed data.
python3 -m spacy.en.download --force all
python3 manage.py migrate
python3 manage.py runserver
```
Then navigate to `http://127.0.0.1:8000` to view your own Natural Language Processor!
---
## Contributing
Currently we're using `React` frontend coupled with a `django` backend. JavaScript files are written in `jsx` and then compiled to `js` using gulp.
### Frontend
To get started with frontend development, make sure you have `npm`, `bower`, `gulp` installed globally.
```
npm install -g bower
npm install -g gulp
npm install
bower install
gulp
```
### Backend
To get started with backend development, make sure you have installed everything in the requirements installed
```
pip install -r requirements
```
---