This project implements a chatbot capable of answering questions about me. The chatbot leverages a custom-trained model and is deployed using a Streamlit web application for an intuitive user interface. Check it out here:
- Custom Intent Recognition: Understands user intents defined in
intents.json. - Deep Learning Model: Uses a neural network for processing and responding to user inputs.
- Streamlit Integration: Provides a user-friendly web interface for interaction.
- Expandable: Easily customizable intents and responses for additional functionality.
| File/Folder | Description |
|---|---|
app.py |
The main file for running the Streamlit-based chatbot application. |
chat.py |
Contains core logic for processing user queries and generating responses. |
data.pth |
Saved PyTorch model file containing the trained chatbot model. |
intents.json |
JSON file defining chatbot intents and corresponding responses. |
model.py |
Script for building and training the neural network model. |
nltk_utils.py |
Utility functions for text preprocessing, including tokenization and stemming. |
requirements.txt |
List of required Python libraries for setting up the environment. |
Follow the steps below to set up the project on your local machine:
Ensure you have Python 3.8+ installed.
-
Clone the repository:
git clone https://github.com/VanshajR/ChatBot.git cd ChatBot -
Install dependencies: Use the provided
requirements.txtto install all necessary packages:pip install -r requirements.txt
-
Run the app: Start the chatbot interface with Streamlit:
streamlit run app.py
-
Interact with the bot: Open the Streamlit app URL in your browser and start chatting with the bot.
- Modify the
intents.jsonfile to customize the chatbot's understanding of queries and responses. - Train the chatbot model using
model.pyto suit your data.
The Streamlit app can be deployed using platforms like Streamlit Community Cloud, Heroku, or Docker.
This project is open-source and available under the MIT License.