The backend of the chatbot is implemented using FastAPI, and the frontend is implemented using Gradio. Langchain is used to index and retrieve text from the LLM.
LLM chat is a chat interface crafted with huggingface-falcon-7B for running Alpaca models. This repository contains the code for a chatbot that uses a large language model (LLM) to generate text responses.
The backend of the chatbot is implemented using FastAPI, and the frontend is implemented using Gradio. Langchain is used to index and retrieve text from the LLM.