This project implements a Retrieval-Augmented Generation (RAG) based restaurant assistant designed to provide detailed information about the restaurant.
It can answer queries related to the menu, prices, staff, opening hours, and other business-specific details.
The system uses a private knowledge base to store the restaurant’s internal data.
By integrating RAG, the assistant retrieves relevant information and generates accurate, context-aware responses in real time.
A driving time estimation tool is also included to calculate the travel time from the user's location to the restaurant.
- Retrieves accurate, business-specific information using RAG
- Calculates real-time driving time estimates
- Generates contextual and human-like responses using the ReAct (Reasoning + Acting) approach
- LangChain – Framework for building LLM-powered applications
- FAISS – Vector database for similarity search and retrieval
- Hugging Face – Used for generating text embeddings
- Python – Core programming language
- Gradio – Interface for interacting with the assistant
- LLM Model – openai/gpt-oss-20b
- The user submits a query about the restaurant.
- The system retrieves relevant data from the knowledge base using FAISS.
- The LLM generates a response using the retrieved information.
- The assistant can also calculate driving time based on user location.
