Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/guhan-tofu/chatbot
This is a chatbot made for any website. By manipulating the intents.json file you can change this chatbot to answer as desired specific to your website
https://github.com/guhan-tofu/chatbot
chatbot css html javascipt python pytorch
Last synced: 4 days ago
JSON representation
This is a chatbot made for any website. By manipulating the intents.json file you can change this chatbot to answer as desired specific to your website
- Host: GitHub
- URL: https://github.com/guhan-tofu/chatbot
- Owner: guhan-tofu
- License: mit
- Created: 2024-06-24T11:29:24.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2024-06-24T12:55:30.000Z (7 months ago)
- Last Synced: 2024-11-13T17:51:10.353Z (2 months ago)
- Topics: chatbot, css, html, javascipt, python, pytorch
- Language: CSS
- Homepage:
- Size: 35.2 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ChatBot
A chatbot made using predefined intents and a pytorch model which can be manipulated by just changing the contents of the intents.json as well as some minor tweaking in model if necessary.# Gathering Data
In order to gather data, either use my web-scraper and get info on your desired website or if you have the info use chatgpt to enter this prompt"Make me a json file with clearly defined tags, intents and responses based on (____insert your information___) and make it suitable for a chatbot"
It should return the correct prompt, if not use the json template given.
# Installing Dependencies
`pip install flask``pip install flask-cors`
`pip install torch`
`pip install nltk`
`pip install numpy`
# Running the Code
`python nltk_utils.py` - uncomment the third line on the first run`python model.py`
`python train.py`
`flask run` - let the chatbot file run in background
Open the [frontend-standalone](https://github.com/guhan-tofu/ChatBot/tree/main/standalone-frontend) file in another window and run with debugging