This project builds an AI Agent that acts as a virtual restaurant waiter. The agent interacts with customers, answers their menu-related queries, and provides friendly responses. The system is built using LangChain and LangGraph, integrating OpenAI's GPT-based language models to process user inputs effectively.
- Conversational AI: Uses OpenAI's GPT models to generate human-like responses.
- Menu Assistance: Provides detailed information about restaurant menu items.
- Agentic Workflow: Utilizes LangGraph to manage interactions efficiently.
- RAG Integration: Implements a Retrieval-Augmented Generation (RAG) system to fetch relevant menu details.
- Python
- LangChain & LangGraph
- OpenAI API
- FAISS (for vector similarity search)
- Unstructured (for document processing)
- Clone the repository:
git clone https://github.com/yourusername/Agentic_RAG_Waiter.git cd Agentic_RAG_Waiter - Install dependencies:
pip install -r requirements.txt
- Set up your OpenAI API key in the environment variables.
Run the Jupyter Notebook to initialize the agent:
jupyter notebook Agentic_RAG_Project.ipynb- Extend the agent to support multi-modal interactions (voice & text).
- Enhance menu understanding using structured databases.
- Deploy as a chatbot service.
Feel free to open issues or submit pull requests for improvements.
This project is licensed under the MIT License.