Local Implementation of RAG (Retrieval Augmented Generation) with Mistral 7B Chat Model (4bit Sharded)
conda create -n my_env python=3.10
conda activate my_env
pip install -r requiremnts.txt
You may need these in case pip fails to build llama-cpp-python
Visual Studio Community
Install devleopment kit for C++ and Python
Cmake
Nvidia Cuda Toolkit