This project is an adapted fork of the Repository https://github.com/jovotech/snips-nlu-server. Some minor changes have been made to make it fit to the Voice QL project.
This docker image allows you to run an open source Snips NLU server right in your local development environment. Snips comes with a number of advantages compared to NLP.js which is the default engine for Jovo.
This is why Voice-QL comes preconfigured to run with Snips instead of NLPjs.
Voice-QL will automatically push changes in the language model to snips. To make this work it is important to keep ports as configured in this setting or adjust setting in Voice-QL and this Docker installation in sync.
$ git clone https://github.com/fboerncke/voice-ql-snips-nlu-server.git
$ cd voice-ql-snips-nlu-server
Now build and run the service:
$ sudo docker build -t snips-nlu-server .
This may take some time and there is a lot of stuff happening on the console. Let it happen ...
$ sudo docker run -p 5000:5000 snips-nlu-server
On the console you should then see something like this:
```
* Serving Flask app '/app/server/__init__.py' (lazy loading)
* Environment: development
* Debug mode: on
* Running on all addresses.
WARNING: This is a development server. Do not use it in a production deployment.
* Running on http://172.17.0.2:5001/ (Press CTRL+C to quit)
* Restarting with stat
* Debugger is active!
* Debugger PIN: 207-980-342
```
Alive check:
http://172.17.0.2:5001/
http://172.17.0.2:5001/engine/parse
If for some reason the setup does not work for you then you might want to follow the much more detailled instructions which can be found here: https://github.com/jovotech/snips-nlu-server
This project receives funding from the German Federal Ministry of Education and Research (FKZ 01IS22S30)
The Prototype Fund is a project of the Open Knowledge Foundation Germany, funded by the German Federal Ministry of Education and Research (BMBF).