I have struggle working with HuggingFaceInstructEmbeddings. I would like to work with the model multilangual-e5-large-instruct from HuggingFace. This works fine if I use it with the HuggingFaceEmbeddings class from LllamaIndex for document embeddings. However, for query embeddings I need to add the instruction. I thought that this could be accomplished using HuggingfaceInstructEmbeddings class - however, this class seems to expect one of the "instruct" models from the "InstructorEmbedding" library, as I am constantly hit with the error: FileNotFoundError: [Errno 2] No such file or directory: '"/root/.cache/torch/sentence_transformers/intfloat_multilingual-e5-large-instruct/sentence_xlnet_config.json'" Therefore, the question is: How can I add the query-instruction to the HuggingFaceEmbedding class for query embedding?

Hi guys, I am wondering whether there is a way to use replicate for embeddings? The background is that I can use Google Colab for creating the embeddings for my documents using an open source model, but how would I go about to use the open source model for query embedding in a deployment scenario? Having an instance running only to embed user queries does not some viable for a side project. I would appreciate any ideas 🙂 Thanks in advance!