Unable to inference from space in python using API

Beginners
1

I want to inference via API using gradio_client from https://huggingface.co/spaces/jadechoghari/ferret-demo. I have been unable to do it as I get the following error.
python3.11/site-packages/gradio_client/client.py", line 885, in _get_config raise ValueError(f"Could not fetch config for {self.src}") ValueError: Could not fetch config for https://huggingface.co/spaces/jadechoghari/ferret-demo/

Following is the python code I’m executing:

from gradio_client import Client, handle_file

client = Client("https://huggingface.co/spaces/jadechoghari/ferret-demo")
result = client.predict(
		chatbot=[],
		image_data=handle_file(image_path),
		prompt=prompt,
		model_path="jadechoghari/Ferret-UI-Gemma2b",
		temperature=0.2,
		top_p=0.7,
		max_new_tokens=512,
		api_name="/inference_with_gradio"
)
print(result)
1 Like
2

Your code is a bit wrong, but my local environment is Python 3.9, so I can’t try Gradio5…
Hope it works…

hf_token = "hf_********"
#client = Client("https://huggingface.co/spaces/jadechoghari/ferret-demo")
client = Client("jadechoghari/ferret-demo", hf_token=hf_token)

pip install gradio==5.1.0
pip install -U gradio-client
4

The answer of @John6666 is valuable and understanding by me. It helps a lot.

1 Like
5

@John6666 Not working. here is the log

Loaded as API: https://jadechoghari-ferret-demo.hf.space ✔

Traceback (most recent call last):
  File "/Users/QQAGHN0037/PycharmProjects/FerretUI/main.py", line 13, in <module>
    result = client.predict(
             ^^^^^^^^^^^^^^^
  File "/opt/anaconda3/envs/FerretUI/lib/python3.11/site-packages/gradio_client/client.py", line 476, in predict
    ).result()
      ^^^^^^^^
  File "/opt/anaconda3/envs/FerretUI/lib/python3.11/site-packages/gradio_client/client.py", line 1509, in result
    return super().result(timeout=timeout)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/anaconda3/envs/FerretUI/lib/python3.11/concurrent/futures/_base.py", line 456, in result
    return self.__get_result()
           ^^^^^^^^^^^^^^^^^^^
  File "/opt/anaconda3/envs/FerretUI/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
    raise self._exception
  File "/opt/anaconda3/envs/FerretUI/lib/python3.11/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/anaconda3/envs/FerretUI/lib/python3.11/site-packages/gradio_client/client.py", line 1128, in _inner
    predictions = _predict(*data)
                  ^^^^^^^^^^^^^^^
  File "/opt/anaconda3/envs/FerretUI/lib/python3.11/site-packages/gradio_client/client.py", line 1240, in _predict
    raise AppError(
gradio_client.exceptions.AppError: The upstream Gradio app has raised an exception but has not enabled verbose error reporting. To enable, set show_error=True in launch().
1 Like
6

Hmmm, since I can’t test it, you’ll have to…
You can try the same program in any of the other spaces and see if that doesn’t work, which will determine what you should try next. If it’s a problem with that space, you’ll have to contact the author or duplicate and modify it for your own use. If it’s an error in your environment, changing a setting might fix it.

1 Like