Error not reported correctly by hf_raise_for_status in create_inference_endpoint

[aymeric-roucher]

Describe the bug

When running this snippet:

from huggingface_hub.hf_api import HfApi
from huggingface_hub import login

login("HF_TOKEN")

hf_api = HfApi()

endpoint = hf_api.create_inference_endpoint(
    "test",
    repository="meta-llama/Meta-Llama-3.1-8B",
    framework="pytorch",
    accelerator="gpu",
    instance_size="xlarge",
    instance_type="g6",
    region="us-east-1",
    vendor="aws",
)

The task parameter is left undefined.
The error I get is empty after 'Bad request:'

File "/Users/aymeric/Documents/Code/endpoint-snooper/.venv/lib/python3.12/site-packages/huggingface_hub/hf_api.py", line 7484, in create_inference_endpoint
    hf_raise_for_status(response)
  File "/Users/aymeric/Documents/Code/endpoint-snooper/.venv/lib/python3.12/site-packages/huggingface_hub/utils/_errors.py", line 358, in hf_raise_for_status
    raise BadRequestError(message, response=response) from e
huggingface_hub.utils._errors.BadRequestError:  (Request ID: WWttaQ)

Bad request:

But it should contain some useful information: if we add a print(response.text) just before running hf_raise_for_status(response) in create_inference_endpoint we get precious info : Failed to parse the request body as JSON: model.task: expected value at line 1 column 257 that allows to correct the issue.

So the error seems improperly handled (error 400) in hf_raise_for_status, causing it to lose the content of the error.

Reproduction

No response

Logs

No response

System info

- huggingface_hub version: 0.24.6
- Platform: macOS-14.1-arm64-arm-64bit
- Python version: 3.12.0
- Running in iPython ?: No
- Running in notebook ?: No
- Running in Google Colab ?: No
- Token path ?: /Users/aymeric/.cache/huggingface/token
- Has saved token ?: True
- Who am I ?: m-ric
- Configured git credential helpers: osxkeychain, store
- FastAI: N/A
- Tensorflow: N/A
- Torch: N/A
- Jinja2: N/A
- Graphviz: N/A
- keras: N/A
- Pydot: N/A
- Pillow: N/A
- hf_transfer: N/A
- gradio: N/A
- tensorboard: N/A
- numpy: N/A
- pydantic: N/A
- aiohttp: N/A
- ENDPOINT: https://huggingface.co
- HF_HUB_CACHE: /Users/aymeric/.cache/huggingface/hub
- HF_ASSETS_CACHE: /Users/aymeric/.cache/huggingface/assets
- HF_TOKEN_PATH: /Users/aymeric/.cache/huggingface/token
- HF_HUB_OFFLINE: False
- HF_HUB_DISABLE_TELEMETRY: False
- HF_HUB_DISABLE_PROGRESS_BARS: None
- HF_HUB_DISABLE_SYMLINKS_WARNING: False
- HF_HUB_DISABLE_EXPERIMENTAL_WARNING: False
- HF_HUB_DISABLE_IMPLICIT_TOKEN: False
- HF_HUB_ENABLE_HF_TRANSFER: False
- HF_HUB_ETAG_TIMEOUT: 10
- HF_HUB_DOWNLOAD_TIMEOUT: 10

[Wauplin]

Hi @aymeric-roucher, thanks for reporting this! As a matter of fact, it has been a annoying issue since quite some time but we've fixed it since 2 weeks ago in #2474. It will be shipped in next release.