Retrieve.py throwing error when following training example on Custom diffusion on hugging face

[nighting0le01]

Describe the bug

Retrieve.py script has issues

Reproduction

follow the instructions on custom diffusion training and run it in a python 3.8 conda env.
https://huggingface.co/docs/diffusers/main/en/training/custom_diffusion

Logs

(diff) ubuntu@ip-96-107-149-234:~/project/custom-diffusion_expts/diffusers/examples/custom_diffusion$ python retrieve.py --class_prompt cat --class_data_dir real_reg/samples_cat --num_class_images 200
Traceback (most recent call last):
  File "/opt/conda/envs/diff/lib/python3.8/site-packages/requests/models.py", line 971, in json
    return complexjson.loads(self.text, **kwargs)
  File "/opt/conda/envs/diff/lib/python3.8/json/__init__.py", line 357, in loads
    return _default_decoder.decode(s)
  File "/opt/conda/envs/diff/lib/python3.8/json/decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
  File "/opt/conda/envs/diff/lib/python3.8/json/decoder.py", line 355, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "retrieve.py", line 87, in <module>
    retrieve(args.class_prompt, args.class_data_dir, args.num_class_images)
  File "retrieve.py", line 37, in retrieve
    class_images = client.query(text=class_prompt)
  File "/opt/conda/envs/diff/lib/python3.8/site-packages/clip_retrieval/clip_client.py", line 84, in query
    return self.__search_knn_api__(text=text)
  File "/opt/conda/envs/diff/lib/python3.8/site-packages/clip_retrieval/clip_client.py", line 131, in __search_knn_api__
    return requests.post(
  File "/opt/conda/envs/diff/lib/python3.8/site-packages/requests/models.py", line 975, in json
    raise RequestsJSONDecodeError(e.msg, e.doc, e.pos)
requests.exceptions.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

System Info

Python version 3.8

[sayakpaul]

Thanks for reporting. It seems like an issue with the clip_client though.

I tried the following:

from clip_retrieval.clip_client import ClipClient

num_images = 5
client = ClipClient(
    url="https://knn.laion.ai/knn-service", indice_name="laion_400m", num_images=num_images, aesthetic_weight=0.1
)

results = client.query(text="a an image of a dog")

and reproduced the error.

Would you mind opening an issue here https://github.com/rom1504/clip-retrieval ?

[hosein-moayedi]

results = client.query(text="a an image of a dog")

This is not working also!

[sayakpaul]

I didn't say mine was working. I said:

and reproduced the error.

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

[Sandeep-Narahari]

I this issue resolved , I am getting the same issue

[nighting0le01]

It Should work with a different indice_name when you are instantiating ClipClient

[Sandeep-Narahari]

Could you please share here if possible, how to make it work , Actually I don't understand AI things much @arpitsahni04

[EduPP]

Has anyone been able to fix this issue? It's been a while since it's been there without any solution.

[sayakpaul]

It unfortunately lies with the CLIP retrieval service being used and we cannot control it.

[mukesh1996-ds]

any once can help me in solving this issue

[mukesh1996-ds]

Trying to Inference Hugging face model using API

[asomoza]

the clip retrieval service from laion has been now, I think, not working for at least over 1 year, you error just points out there's an error in the json returned, probably because there's no json returned from a dead service (https://knn.laion.ai/)