Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ivangael/flask-chatbot-nlp
Flask Chatbot using NLP Libraries
https://github.com/ivangael/flask-chatbot-nlp
chatbot dialoggpt flask huggingface-transformers nlp nlp-library python
Last synced: 2 months ago
JSON representation
Flask Chatbot using NLP Libraries
- Host: GitHub
- URL: https://github.com/ivangael/flask-chatbot-nlp
- Owner: IvanGael
- Created: 2024-06-12T19:16:09.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2024-06-12T19:33:53.000Z (7 months ago)
- Last Synced: 2024-06-14T01:25:34.088Z (7 months ago)
- Topics: chatbot, dialoggpt, flask, huggingface-transformers, nlp, nlp-library, python
- Language: Python
- Homepage:
- Size: 221 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Flask Chatbot using NLP Libraries
This project is a simple chatbot web app built using Python, Flask, and various NLP libraries such as NLTK, SpaCy, and transformers. The chatbot uses the Huggingface `transformers` library with the `microsoft/DialoGPT-medium` model to generate responses to user inputs. It also uses NLTK and SpaCy for additional text processing.
## Table of Contents
- [Installation](#installation)
- [Usage](#usage)
- [How It Works](#how-it-works)
- [Examples](#examples)
- [License](#license)
## Installation
1. **Install the required dependencies:**
```
pip install flask nltk spacy transformers
python -m spacy download en_core_web_sm
```
2. **Download NLTK data:**
```
python -c "import nltk; nltk.download('punkt')"
```
## Usage
1. **Run the Flask application:**
```
py app.py
```
2. **Open your web browser and navigate to:**
```
http://127.0.0.1:5000/
```
3. **Interact with the chatbot by typing messages and clicking 'Send'.**
## How It Works
1. **Flask Server**: The Flask web server renders the HTML template and handles incoming POST requests to generate chatbot responses.
2. **NLP Processing**:
- **NLTK**: Used for tokenizing the input message.
- **SpaCy**: Used for named entity recognition (NER) and part-of-speech (POS) tagging.
- **Transformers**: The chatbot uses the Huggingface `transformers` library with the `microsoft/DialoGPT-medium` model to generate responses to user inputs.
3. **Frontend**: The web interface uses HTML and jQuery to handle user interactions and display the conversation.
## Examples
Here are some example messages you can try with the chatbot:
- "Hello!"
- "What is your name?"
- "Can you tell me a joke?"
- "I like cats."
- "What's the meaning of life?"
## License
This project is licensed under the MIT License.