A Generative AI chatbot built using Meta LLaMA 2 7B, LangChain, and Gradio that enables conversational AI interactions through a clean web interface.
- LLM inference using Meta LLaMA 2 7B Chat
- Conversational memory using LangChain
- Interactive chat interface using Gradio
- CPU and GPU compatible
- Python
- meta-llama/Llama-2-7b-chat-hf
- Hugging Face Transformers
- LangChain
- Gradio
-
Clone the repository git clone https://github.com/avanthikasreejith8923-a11y/gen-ai-chatbot.git cd gen-ai-chatbot
-
Create virtual environment python -m venv venv venv\Scripts\activate
-
Install dependencies pip install torch transformers gradio langchain langchain-community accelerate
-
Add your HuggingFace token in app.py token = "your_hf_token_here"
-
Run the app python app.py
- Open the Gradio link shown in terminal
- Type your message and press Enter
- The chatbot will respond using LLaMA 2 7B
- HuggingFace account with access to meta-llama/Llama-2-7b-chat-hf
- Minimum 16GB RAM recommended
- GPU recommended for faster inference