The community member asked how to specify that they want to use the GPU when generating embeddings with HuggingFaceEmbeddings. The comments indicate that the GPU is used by default if CUDA is available, and that the device can be optionally specified using device="cuda:0". The community members found this information helpful.
When using HuggingFaceEmbeddings to generate embeddings, how do I specify that I want the GPU to be used? Is there something like langchains model_kwargs?
