An intelligent chatbot powered by LLM (Large Language Model) technology that provides comprehensive knowledge about Infosys. The bot uses advanced vector storage and natural language processing to deliver accurate and contextual responses.
- 🎯 Modern, responsive chat interface
- 💡 Intelligent responses using LLM technology
- 🔍 Vector-based semantic search using Qdrant
- 🔄 Real-time text processing
- 💾 PDF document integration
- 🎨 Glass-morphism UI design
- Frontend: Streamlit
- Vector Store: Qdrant
- Embeddings: Sentence Transformers (all-MiniLM-L6-v2)
- LLM: FLAN-T5
- Data Processing: PyPDF2, LangChain
- Python 3.8+
- Docker (for Qdrant)
- Git
- Clone the repository:
git clone https://github.com/Supriya2903/infosys-knowledge-bot.git
cd infosys-knowledge-bot- Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate- Install required packages:
pip install -r requirements.txt- Start Qdrant server using Docker:
docker run -p 6333:6333 qdrant/qdrant- Process and index the PDF document:
python integration.py- Start the chatbot interface:
streamlit run streamlitUI.py- Access the chatbot in your browser at
http://localhost:8501
streamlitUI.py: Main chatbot interface with Streamlitintegration.py: PDF processing and vector store integrationinteractive.py: Interactive components and utilitiesscrapping.py: Data scraping utilitiesformatted30042024.pdf: Source data file
The chatbot uses Qdrant vector database to store and search through document embeddings, enabling semantic search capabilities that understand the context of user queries.
- Glass-morphism design
- Responsive chat bubbles
- Real-time message updates
- Professional color scheme
- Smooth animations
- Automatic PDF text extraction
- Text chunking for optimal processing
- Vector embeddings generation
- Efficient storage and retrieval
Feel free to submit issues and enhancement requests!
This project is licensed under the MIT License - see the LICENSE file for details.