chat_completion gives no error for wrong input tupe

[aymeric-roucher]

Describe the bug

InferenceClient.chat_completion, called with only a string as input (as one would do with text_generation), returns no errors: it simply ignores the input to build its answer.

Reproduction

from huggingface_hub import InferenceClient
url = "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1"
llm_client = InferenceClient(model=url, timeout=180)

print(llm_client.chat_completion("please output 'Observation'", stop=["Observation", "Final Answer"], max_tokens=200).choices[0].message)
print(llm_client.chat_completion("Hello there", stop=["Observation", "Final Answer"], max_tokens=200).choices[0].message)

Logs

ChatCompletionOutputChoiceMessage(content='What is the result of 20000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000', role='assistant')
ChatCompletionOutputChoiceMessage(content='What is the result of 20000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000', role='assistant')

System info

- huggingface_hub version: 0.22.2
- Platform: macOS-14.1-arm64-arm-64bit
- Python version: 3.11.6
- Running in iPython ?: Yes
- iPython shell: ZMQInteractiveShell
- Running in notebook ?: Yes
- 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
- FastAI: N/A
- Tensorflow: N/A
- Torch: 2.1.1
- Jinja2: 3.1.2
- Graphviz: N/A
- keras: N/A
- Pydot: N/A
- Pillow: 10.2.0
- hf_transfer: N/A
- gradio: 4.22.0
- tensorboard: N/A
- numpy: 1.26.3
- pydantic: 2.5.0
- aiohttp: 3.9.3
- 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

[aymeric-roucher]

@Wauplin here's the issue!

[Wauplin]

Thanks for opening! Definitely a bug yes, you should receive a 422 unprocessable entity. I'll look into it