An advanced RAG (Retrieval-Augmented Generation) based Bengali FAQ chatbot that uses GitHub-hosted OpenAI models and FAISS vector database. Bangla FAQ Chatbot is an advanced AI-powered web application designed to answer user queries in Bengali. It is dynamic animated frontend, and context-aware responses using vector-based retrieval for accurate and natural answers.

screenshot

• Bengali Language Support: Complete question-answer system in Bengali
• RAG System: Accurate information retrieval through FAISS vector database
• Topic Filtering: 5 categories - Education, Health, Travel, Technology, Sports
• Difficulty Levels: Separate filters for easy and difficult questions
• Modern UI: Beautiful and user-friendly interface built with Tailwind CSS
• Bengali Embeddings: Uses l3cube-pune/bengali-sentence-similarity-sbert model

• Python 3.8+
• pip (Python package manager)

# 1. Clone the repository
git clone https://github.com/Aronno1920/FAQ-Chatbot.git
cd BanglaChatbot
# 2. Create a virtual environment
python -m venv venv
# 3. Activate the environment
# Windows
venv\Scripts\activate
# macOS/Linux
source venv/bin/activate
# 4. Install dependencies
pip install -r [requirements.txt]
# 5. Configure API keys
cp [config.example.py] [config.py]
# Edit [config.py](http://_vscodecontentref_/4) and replace GITHUB_TOKEN with your personal token
# 6. Start the Flask app
python [app.py]

To test if all system components are working correctly:

python test_models.py

This script will test:

• GitHub Model API connection
• HuggingFace embedding model
• FAISS vector database
• RAG system integration

BanglaChatbot/
├── app.py # Main Flask application
├── rag_core.py # RAG system and FAQ data
├── utils.py # Utility functions
├── test_models.py # Testing script
├── requirements.txt # Python dependencies
├── templates/
│ └── index.html # Frontend UI
└── README.md # This file

1. Go to GitHub and create a Personal Access Token
2. Update the token in app.py
3. The following model is used: openai/gpt-4.1-nano

Add new question-answer pairs in the FAQ_DATA list in rag_core.py:

FAQ_DATA = [
 {
 'topic': 'শিক্ষা', 
 'difficulty': 'সহজ', 
 'question': 'Your question', 
 'answer': 'Answer'
 },
 # More questions...
]

1. Select Topic: Choose desired subject from the top menu
2. Set Difficulty: Filter for easy or difficult questions
3. Ask Questions: Type your question in Bengali in the text box below
4. Get Answers: Receive relevant answers from the RAG system

• Backend: Flask (Python)
• AI/ML:
  • GitHub-hosted OpenAI GPT-4.1-nano
  • HuggingFace Transformers
  • FAISS (Facebook AI Similarity Search)
  • LangChain
• Frontend: HTML5, Tailwind CSS, JavaScript
• Vector Database: FAISS
• Embeddings: Bengali Sentence-BERT

1. Data Preparation: Create documents from FAQ data
2. Embedding: Generate vectors using Bengali Sentence-BERT
3. Indexing: Create vector database with FAISS
4. Retrieval: Find documents matching user queries
5. Generation: Generate relevant answers using OpenAI model

• GET / - Main chat interface
• POST /chat - Process chat messages
• POST /filter - Update topic/difficulty filter

1. GitHub API Error: Check if token is correct
2. Model Loading Error: Check internet connection
3. FAISS Error: Reinstall with pip install faiss-cpu

You can see detailed logs in the console while running the application.

1. Fork this repository
2. Create a feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

This project is licensed under the MIT License.

Create an issue for questions or suggestions.

Bangla FAQ Chatbot - Smart Q&A service in Bengali using AI 🤖