Skip to content

Conversation

@bqwu
Copy link

@bqwu bqwu commented Aug 17, 2020

When I am using the trained NER model as service via http port, I found if the input json is something like
query_json = {
"id": 100,
"texts": ["Beijing"]
},
everything is right. However, if the input json is something like
query_json = {
"id": 100,
"texts": ["北京"]
},
then it raises Exception as below:
UnicodeEncodeError: 'ascii' codec can't encode characters in position 23-25: ordinal not in range(128)
I found this error comes from this print func and I think it should be removed here. In hanxiao's Bert-as-service, it does not contain this line (https://github.com/hanxiao/bert-as-service/blob/91bff1c2d0403e1afa9ee1af9dd9cb0dd58fe0d3/server/bert_serving/server/http.py#L57) and it supports Chinese well.
So I suggest removing this print func here.

@bqwu
Copy link
Author

bqwu commented Aug 17, 2020

Hope the author can release a new version for use later. Thanks so much.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant