How to host your own fast Embeddings API | by Stuart Boyle | Medium

This is because almost all GenAI apps that you will build need to make embeddings in one way or another. ... Regarding the question which library to use, I did quite some research and stumbled upon this one: https://github.com/michaelfeil/infinity · All you have to do is start a docker container with: port=7997 docker run -it — gpus all -p $port:$port michaelf34/infinity:latest — model-name-or-path BAAI/bge-small-en-v1.5 — port $port