[Python] Python web app on Azure: using and running Llamaindex Huggingface model

The python app I'm making does LLM computations and requires an embed model. But it cant download the Huggingface embed model:


from llama_index.embeddings.huggingface import HuggingFaceEmbedding

embed_model= HuggingFaceEmbedding(
model_name="BAAI/bge-small-en-v1.5"
)
Settings.embed_model=embed_model


When this part is run, the container just gets 'killed' when its trying to fetch the model files. I tried using a huggingface cache, ONNX optimizer, and Langchain's huggingface model- still no luck. Please help!

Continue reading...