hosting nlp models for demo purpose
Project description
NLP2GO - hosting nlp models for demo purpose
Example
hosting single model
nlp2go --model model_path --predictor biotag
hosting multiple models
- create a json file as below:
{
"API1_PATH": {
"model": "model1_path",
"predictor": "predictor_tag"
},
"API2_PATH": {
"model": "model2_path",
"predictor": "predictor_tag"
}
}
- run
nlp2go --json json_file_path
Installation
Installing via pip
pip install nlp2go
Running nlprep
Once you've installed nlprep, you can run with
python -m nlp2go.server
# local version
or
nlp2go
# pip installed version
and the following parameter:
$ nlp2go
arguments:
--model model path
or
--json json file include models setting
--outdir processed result output directory
optional arguments:
-h, --help show this help message and exit
--predictor formatting result on different kind of task ['biotag', 'tag', 'default']
--path api path
--port api hosting port
Json file example
{
"API1_PATH": {
"model": "model1_path",
"predictor": "predictor_tag"
},
"API2_PATH": {
"model": "model2_path",
"predictor": "predictor_tag"
}
}
Expose application over the web
I recommend using ngrok to expose this api for demo purpose
Ngrok: https://ngrok.com
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
nlp2go-0.0.2.tar.gz
(3.9 kB
view hashes)
Built Distribution
nlp2go-0.0.2-py3-none-any.whl
(8.6 kB
view hashes)