"huggingface : Connection error, and we cannot find the requested files in the cached path" when I have wifi in and have disabled the cache

Beginners
1

I am trying to launch a container that calls the HuggingFace hub but there seems to be a connection or cache error. why is this happening?

$ sudo docker compose up
...
h2ogpt  | Traceback (most recent call last):
h2ogpt  |   File "/workspace/generate.py", line 16, in <module>
h2ogpt  |     entrypoint_main()
h2ogpt  |   File "/workspace/generate.py", line 12, in entrypoint_main
h2ogpt  |     H2O_Fire(main)
h2ogpt  |   File "/workspace/src/utils.py", line 65, in H2O_Fire
h2ogpt  |     fire.Fire(component=component, command=args)
h2ogpt  |   File "/h2ogpt_conda/lib/python3.10/site-packages/fire/core.py", line 141, in Fire
h2ogpt  |     component_trace = _Fire(component, args, parsed_flag_args, context, name)
h2ogpt  |   File "/h2ogpt_conda/lib/python3.10/site-packages/fire/core.py", line 475, in _Fire
h2ogpt  |     component, remaining_args = _CallAndUpdateTrace(
h2ogpt  |   File "/h2ogpt_conda/lib/python3.10/site-packages/fire/core.py", line 691, in _CallAndUpdateTrace
h2ogpt  |     component = fn(*varargs, **kwargs)
h2ogpt  |   File "/workspace/src/gen.py", line 1664, in main
h2ogpt  |     model=get_embedding(use_openai_embedding, hf_embedding_model=hf_embedding_model,
h2ogpt  |   File "/workspace/src/gpt_langchain.py", line 461, in get_embedding
h2ogpt  |     embedding = HuggingFaceEmbeddings(model_name=hf_embedding_model, model_kwargs=model_kwargs)
h2ogpt  |   File "/h2ogpt_conda/lib/python3.10/site-packages/langchain_community/embeddings/huggingface.py", line 65, in __init__
h2ogpt  |     self.client = sentence_transformers.SentenceTransformer(
h2ogpt  |   File "/h2ogpt_conda/lib/python3.10/site-packages/sentence_transformers/SentenceTransformer.py", line 87, in __init__
h2ogpt  |     snapshot_download(model_name_or_path,
h2ogpt  |   File "/h2ogpt_conda/lib/python3.10/site-packages/sentence_transformers/util.py", line 491, in snapshot_download
h2ogpt  |     path = cached_download(**cached_download_args)
h2ogpt  |   File "/h2ogpt_conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 118, in _inner_fn
h2ogpt  |     return fn(*args, **kwargs)
h2ogpt  |   File "/h2ogpt_conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 770, in cached_download
h2ogpt  |     raise LocalEntryNotFoundError(
h2ogpt  | huggingface_hub.utils._errors.LocalEntryNotFoundError: Connection error, and we cannot find the requested files in the cached path. Please try again or make sure your Internet connection is on.
^X^CGracefully stopping... (press Ctrl+C again to force)
Aborting on container exit...
[+] Stopping 1/1
 ✔ Container h2ogpt  Stopped                                                                                         0.5s 
canceled

Here is my docker-compose.yml:

version: '3'

services:
  h2ogpt:
    image: gcr.io/vorvan/h2oai/h2ogpt-runtime:latest
    container_name: h2ogpt
    shm_size: '2gb'
    environment:
      - ANONYMIZED_TELEMETRY=False
      - HF_DATASETS_OFFLINE=1
      - TRANSFORMERS_OFFLINE=1
    volumes:
       # - $HOME/.cache:/workspace/.cache
       - ./data/models:/workspace/models:ro
       - ./data/save:/workspace/save
       - ./data/user_path:/workspace/user_path
       - ./data/db_dir_UserData:/workspace/db_dir_UserData
       - ./data/users:/workspace/users
       - ./data/db_nonusers:/workspace/db_nonusers
       - ./data/llamacpp_path:/workspace/llamacpp_path
       - ./data/h2ogpt_auth:/workspace/h2ogpt_auth
    ports:
      - 7860:7860
    restart: always
    deploy:
      resources:
        reservations:
          devices:
          - driver: nvidia
            count: all
            capabilities: [gpu]
    command: >
      /workspace/generate.py 
      --base_model=mistralai/Mistral-7B-Instruct-v0.2 
      --hf_embedding_model=intfloat/multilingual-e5-large  
      --load_4bit=True  
      --use_flash_attention_2=True 
      --score_model=None 
      --top_k_docs=10 
      --max_input_tokens=2048  
      --visible_h2ogpt_logo=False 
      --dark=True 
      --visible_tos_tab=True 
      --langchain_modes="['UserData', 'LLM']" 
      --langchain_mode_paths="{'UserData':'/workspace/user_path/sample_docs'}" 
      --langchain_mode_types="{'UserData':'shared'}"  
      --enable_pdf_doctr=off 
      --enable_captions=False 
      --enable_llava=False 
      --use_unstructured=False 
      --enable_doctr=False 
      --enable_transcriptions=False 
      --enable_heap_analytics=False  
      --use_auth_token=hf_XXXX
      --prompt_type=mistral
      --pre_prompt_query="Use the following pieces of informations to answer,  don't try to make up an answer, just say I don't know if you don't know. Answer in the following language: french"
      --prompt_query="Cite relevant passages from context to justify your answer."
      --use_safetensors=False --verbose=True
    networks:
      - h2ogpt-net



networks:
  h2ogpt-net: