-- coding: utf-8 --

""" @author: Pradeep Yadav """

🤖 Persona Chatbot

A persona-based conversational AI built with Hugging Face Transformers and NLP techniques. This chatbot can switch between different character personas and maintain contextual conversations.

🚀 Features

• Multiple Personas: Switch between different character personas with unique personalities
• Intent Recognition: ML-based intent classification using TF-IDF and Random Forest
• Contextual Responses: Maintains conversation history and context
• NLP Preprocessing: Text cleaning, tokenization, and normalization
• Hugging Face Integration: DialoGPT for state-of-the-art dialogue generation

🛠️ Tech Stack

• Python - Core programming language
• Hugging Face Transformers - Dialogue generation
• Pandas - Data handling and processing
• Scikit-learn - Machine learning for intent classification
• NLTK - Natural language processing
• PyTorch - Deep learning framework

📁 Project Structure

Persona-chatbot/ ├── 📁 chatbot/ # Core chatbot modules │ ├── init.py │ ├── persona_bot.py # Main chatbot class │ ├── intent_classifier.py # ML intent classification │ ├── data_processor.py # NLP preprocessing │ └── config.py # Configuration settings ├── 📁 data/ # Training data │ ├── intents.csv │ └── persona_data.csv ├── 📁 scripts/ # Utility scripts │ ├── create_data_files.py │ ├── enhance_intents.py │ ├── verify_data.py │ └── fix_data_files.py ├── 📁 tests/ # Test files │ ├── test_installation.py │ ├── test_data_processor.py │ ├── test_intents.py │ ├── simple_test.py │ └── test_fixed_chatbot.py ├── 📄 app.py # Main application ├── 📄 demo_chatbot.py # Demo showcase ├── 📄 minimal_chatbot.py # Minimal version ├── 📄 requirements.txt # Dependencies ├── 📄 README.md # Documentation └── 📄 .gitignore # Git ignore file

🎯 Quick Start

Installation

1. Clone the repository:

git clone https://github.com/PRADEEP930/Persona-chatbot.git
cd persona-chatbot

2. Create virtual environment:

conda create -n persona-chatbot python=3.10
conda activate persona-chatbot

3. Install dependencies:

pip install -r requirements.txt

Usage

🔬 Simple Chatbot Version

For a quick start and basic understanding, check out simple_chatbot.py - a minimal implementation using GPT-2 that demonstrates the core concept in less than 20 lines of code.

File: simple_chatbot.py - Basic GPT-2 chatbot for quick testing and learning.

🚀 Quick Start

For Basic Testing (Simple Version):

python simple_chatbot.py

For Full Features (Main Project):

Run the main chatbot:

python app.py

Run the demo:

python demo_chatbot.py

Run tests:

python tests/final_test.py

🎭 Available Personas Alex: Friendly tech support specialist

Dr. Smith: Empathetic medical professional

Professor Davis: Analytical academic researcher

Creative Casey: Enthusiastic artistic designer

🔧 Customization

Adding New Personas Edit data/persona_data.csv:

name,description,personality,expertise Your Persona,a new character,traits,keywords expertise

Adding New Intents Edit data/intents.csv:

tag,patterns,responses new_intent,pattern1|pattern2|pattern3,Response text

📊 Model Details Base Model: Microsoft DialoGPT-small

Intent Classifier: TF-IDF + Random Forest

Training Data: Custom intents and patterns

Response Generation: Conditional text generation with persona context

🤝 Contributing Fork the repository

Create a feature branch (git checkout -b feature/amazing-feature)

Commit your changes (git commit -m 'Add amazing feature')

Push to the branch (git push origin feature/amazing-feature)

Open a Pull Request

📝 License This project is licensed under the MIT License - see the LICENSE file for details.