PacificChatbot

PacificChatbot is a conversational AI chatbot application built with Python, Flask, and a custom-trained neural network.

Table of Contents

• Features
• Prerequisites
• Installation
• Running Locally with Flask
• Conclusion and Results

Features

• Conversational chatbot interface
• Flask-powered backend
• Easy local development and testing
• Utilities for data collection and cleaning
  • Webpage Data Collection
  • PDF Data Collection
  • Data Cleaning Pipeline
• Formatted question-answer dataset

Prerequisites

• Python 3
• pip

Installation

1. Clone the repository:

   git clone https://github.com/ankhoa1212/PacificChatbot.git
   cd PacificChatbot

2. Create and activate a virtual environment (optional but recommended):

   python -m venv venv
   # On Windows:
   venv\Scripts\activate
   # On macOS/Linux:
   source venv/bin/activate

3. Install dependencies:

   pip install flask
   pip install torch

Running Locally with Flask

1. Set the Flask app environment variable:

   # On Windows:
   set FLASK_APP=app.py
   # On macOS/Linux:
   export FLASK_APP=app.py

2. (Optional) Enable debug mode:

   # On Windows:
   set FLASK_ENV=development
   # On macOS/Linux:
   export FLASK_ENV=development

3. Navigate to the project directory (if not already there):

   cd PacificChatbot

4. Start the Flask server:

   flask run

5. Access the chatbot: Open your browser and go to http://localhost:5000

Conclusion and Results

Implementing a custom neural network can be a preferred solution over a language model when dealing with a specific data for task-specific queries. More details of the project can be found in the research publication.

To explore potential data features and machine learning methodologies, some work was done on binary classification tasks.