This project involves implementing Hugging Face embedding models with the LangChain ecosystem using a REST API within a Docker environment.
By hosting these embedding models on a GPU server, you can use them from a local PC without a GPU.
It is highly recommended to run this on a Linux server.
Please download docker first: https://www.docker.com/products/docker-desktop/
cd RESTAPI_Docker
docker build -t embedding . --no-cache
docker run --name embedding -p 7777:5000 embedding
After running your embedding container, visit: http://localhost:7777/instruction
for server: simply change localhost to your server's ip address