Overview
RAG is a combination of a dashboard and a backend service that interacts with the LLM (Large Language Model). The dashboard allows users to interact with the LLM and view the results. The backend service is responsible for handling the requests from the dashboard and interacting with the LLM. It can also teach the LLM new things, based on the input files. It is based on LLama v2.
Features
- Dashboard to interact with LLM
- Multiple stream support
Technologies Used
This project utilizes the following technologies:
- Python