[Bug]: 运行python client 出错

[cqray1990]

软件环境

- paddlepaddle-gpu: 2.4.2
- paddlenlp: 2.5.2

CUDA 10.2
cudnn  8.7

重复问题

• I have searched the existing issues

错误描述

Traceback (most recent call last):
  File "/PaddleNLP/model_zoo/uie/deploy/serving/simple_serving/client.py", line 28, in <module>
    datas = json.loads(r.text)
  File "anaconda3/lib/python3.10/json/__init__.py", line 346, in loads
    return _default_decoder.decode(s)
  File "anaconda3/lib/python3.10/json/decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
  File "anaconda3/lib/python3.10/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)

稳定复现步骤 & 代码

as https://github.com/PaddlePaddle/PaddleNLP/blob/develop/docs/server.md said
first:
paddlenlp server server:app --host 0.0.0.0 --port 8189 --workers 1
然后在另外的终端运行

python client.py

Traceback (most recent call last):
File "/PaddleNLP/model_zoo/uie/deploy/serving/simple_serving/client.py", line 28, in
datas = json.loads(r.text)
File "anaconda3/lib/python3.10/json/init.py", line 346, in loads
return _default_decoder.decode(s)
File "anaconda3/lib/python3.10/json/decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "anaconda3/lib/python3.10/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)

[LemonNoel]

可以在报错前一行打印下 r.text，可能是返回结果为空

[cqray1990]

可以在报错前一行打印下 r.text，可能是返回结果为空
打印出：r.text
test: Connection error

一个终端运行：
paddlenlp server server:app --host 0.0.0.0 --port 8189 --workers 1:

warnings.warn("Setuptools is replacing distutils.")
[2023-05-11 22:26:57,037] [ INFO] - starting to PaddleNLP SimpleServer...
[2023-05-11 22:26:57,038] [ INFO] - The PaddleNLP SimpleServer is starting, backend component uvicorn arguments as follows:
[2023-05-11 22:26:57,038] [ INFO] - the starting argument [host]=0.0.0.0
[2023-05-11 22:26:57,038] [ INFO] - the starting argument [port]=8189
[2023-05-11 22:26:57,038] [ INFO] - the starting argument [log_level]=None
[2023-05-11 22:26:57,038] [ INFO] - the starting argument [workers]=1
[2023-05-11 22:26:57,038] [ INFO] - the starting argument [limit_concurrency]=None
[2023-05-11 22:26:57,038] [ INFO] - the starting argument [limit_max_requests]=None
[2023-05-11 22:26:57,038] [ INFO] - the starting argument [timeout_keep_alive]=15
[2023-05-11 22:26:57,038] [ INFO] - the starting argument [app_dir]=PaddleNLP/model_zoo/uie/deploy/serving/simple_serving
[2023-05-11 22:26:57,038] [ INFO] - the starting argument [reload]=False
[2023-05-11 22:27:04,787] [ INFO] - We are using <class 'paddlenlp.transformers.ernie.tokenizer.ErnieTokenizer'> to load '../../checkpoint/model_best/'.
[2023-05-11 22:27:04,804] [ INFO] - Taskflow request [path]=/taskflow/uie is genereated.
INFO: Started server process [32534]
[2023-05-11 22:27:04,808] [ INFO] server.py:84 - Started server process [32534]
INFO: Waiting for application startup.
[2023-05-11 22:27:04,809] [ INFO] on.py:45 - Waiting for application startup.
INFO: Application startup complete.
[2023-05-11 22:27:04,809] [ INFO] on.py:59 - Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8189 (Press CTRL+C to quit)
[2023-05-11 22:27:04,809] [ INFO] server.py:217 - Uvicorn running on http://0.0.0.0:8189 (Press CTRL+C to quit)

另外一个：
python client.py 怎么会打印连接错误，双卡，大师默认会用一张的吧

Traceback (most recent call last):
File "/PaddleNLP/model_zoo/uie/deploy/serving/simple_serving/client.py", line 29, in
datas = json.loads(r.text)
File "anaconda3/lib/python3.10/json/init.py", line 346, in loads
return _default_decoder.decode(s)
File "anaconda3/lib/python3.10/json/decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "anaconda3/lib/python3.10/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)

[huangjun11]

你好，请问你的问题解决了吗，我也是遇到这种问题