Chatbot Deployment with Flask and JavaScript
In this tutorial we deploy the chatbot I created in this tutorial with Flask and JavaScript.
This gives 2 deployment options:
- Deploy within Flask app with jinja2 template
- Serve only the Flask prediction API. The used html and javascript files can be included in any Frontend application (with only a slight modification) and can run completely separate from the Flask App then.
Initial Setup:
This repo currently contains the starter files.
Create a virtual environment
$ mkdir chatbot-deployment
$ cd chatbot-deployment
$ python3 -m venv venv
$ . venv/bin/activate
Install dependencies
$ (venv) pip install Flask torch torchvision nltk
Install nltk package
$ (venv) python
>>> import nltk
>>> nltk.download('punkt')
Modify intents.json
with different intents and responses for your Chatbot
Run
$ (venv) python train.py
This will dump data.pth file. And then run the following command to test it in the console.
$ (venv) python chat.py
Now for deployment follow my tutorial to implement app.py
and app.js
.
Credits:
This repo was used for the frontend code: https://github.com/hitchcliff/front-end-chatjs