Is there any ways to use "HuggingFaceEmbedding" for private repository? I tried doing something like "model = AutoModel.from_pretrained(model, token="")" but appears to have an error "Bert Model does not have an attribute get_text_embedding.".

Hello, is there any ways to get the "total and last token usage" in SubQuestionQueryEngine? I added a callback token counter in service context and added into "SubQuestionQueryEngine.default(service_context=...)" but I'm not seeing the token counts. Thanks in advance.

Currently using PGVectorStore to store the vectors. When I try to make and run a query several times (like 10 times), I am getting "DefaultCPUAllocator: not enough memory" error. I am seeing memory usage going up as I make each query and the process gets killed once it reaches memory usage of 100. Guess it is using in-memory somewhere else. Any suggestions would be appreciated. Thanks in advance.

Hey guys, I am trying to generate a "unified query framework" (one of the llamaindex tutorials). During the testing phase, I am getting "Failed to select query engine" error (compare query). There are multiple choices being selected during the process. Should I be doing some sort of prompt engineering to just choose one? or is there any other ways that I could try? Thanks in advance.