Hi, I started the nlu server by typing this command in cmd:
rasa run --enable-api -m models/(name of my package).tar
and then in other cmd window typed:
curl localhost:5005/model/parse -d ‘{“text”:“hello”}’
after that I got an error:
{“version”:“1.2.3”,“status”:“failure”,“message”:“An unexpected error occurred. Error: Failed when parsing body as json”,“reason”:“ParsingError”,“details”:{},“help”:null,“code”:500}
What is the reason for it? what should I change to get the normal(200) output?
Can you do the same in debug mode, e.g.
rasa run --enable-api -m models/(name of my package).tar --debug
You should see the stacktrace of the actual exception in debug mode. Can you past it here?
I have seen the same issue when I run the server also. I use RASA 1.3
Ran my NLU server:
(RASA_ENV_python3.6) D:\ML-Chatbot-Cudo\RASA_ENV_python3.6>rasa run --enable-api
-m models/nlu-20190825-161838.tar.gz --debug
2019-08-25 17:24:18 DEBUG rasa.cli.utils - Parameter 'endpoints' not set. Us
ing default location 'endpoints.yml' instead.
2019-08-25 17:24:18 DEBUG rasa.cli.utils - Parameter 'credentials' not set.
Using default location 'credentials.yml' instead.
2019-08-25 17:24:30 INFO numexpr.utils - NumExpr defaulting to 4 threads.
2019-08-25 17:24:35 DEBUG rasa.core.utils - Available web server routes:
/conversations/<conversation_id>/messages POST
add_message
/conversations/<conversation_id>/tracker/events POST
append_events
/webhooks/rasa GET
custom_webhook_RasaChatInput.health
/webhooks/rasa/webhook POST
custom_webhook_RasaChatInput.receive
/webhooks/rest GET
custom_webhook_RestInput.health
/webhooks/rest/webhook POST
custom_webhook_RestInput.receive
/model/test/intents POST
evaluate_intents
/model/test/stories POST
evaluate_stories
/conversations/<conversation_id>/execute POST
execute_action
/domain GET
get_domain
/ GET
hello
/model PUT
load_model
/model/parse POST
parse
/conversations/<conversation_id>/predict POST
predict
/conversations/<conversation_id>/tracker/events PUT
replace_events
/conversations/<conversation_id>/story GET
retrieve_story
/conversations/<conversation_id>/tracker GET
retrieve_tracker
/status GET
status
/model/predict POST
tracker_predict
/model/train POST
train
/model DELETE
unload_model
/version GET
version
2019-08-25 17:24:35 INFO root - Starting Rasa server on http://localhost:50
05
2019-08-25 17:24:35 INFO root - Enabling coroutine debugging. Loop id 39884
5320.
2019-08-25 17:24:35 DEBUG rasa.model - Extracted model to 'C:\Users\arvarma\
AppData\Local\Temp\tmpq1kptth7'.
2019-08-25 17:24:37 DEBUG rasa.core.tracker_store - Connected to InMemoryTra
ckerStore.
2019-08-25 17:24:37 DEBUG rasa.model - Extracted model to 'C:\Users\arvarma\
AppData\Local\Temp\tmpzg9apdmf'.
Now when I run the parse command using curl
curl http://localhost:5005/model/parse -d '{"text":"hello"}'
{"version":"1.3","status":"failure","message":"An unexpected error occurred. Err
or: Failed when parsing body as json","reason":"ParsingError","details":{},"help
":null,"code":500}
Error in console:
2019-08-25 17:25:58 DEBUG rasa.server - Traceback (most recent call last):
File "D:\Anaconda\envs\RASA_ENV_python3.6\lib\site-packages\sanic\request.py
line 149, in load_json
self.parsed_json = loads(self.body)
File "D:\Anaconda\envs\RASA_ENV_python3.6\lib\json\__init__.py", line 354, i
loads
return _default_decoder.decode(s)
File "D:\Anaconda\envs\RASA_ENV_python3.6\lib\json\decoder.py", line 339, in
ecode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "D:\Anaconda\envs\RASA_ENV_python3.6\lib\json\decoder.py", line 357, in
aw_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 "d:\ml-chatbot-cudo\rasa_env_python3.6\rasa\rasa\server.py", line 823,
parse
data = emulator.normalise_request_json(request.json)
File "D:\Anaconda\envs\RASA_ENV_python3.6\lib\site-packages\sanic\request.py
line 143, in json
self.load_json()
File "D:\Anaconda\envs\RASA_ENV_python3.6\lib\site-packages\sanic\request.py
line 153, in load_json
raise InvalidUsage("Failed when parsing body as json")
sanic.exceptions.InvalidUsage: Failed when parsing body as json
2019-08-25 17:29:21 DEBUG rasa.server - Traceback (most recent call last):
File "D:\Anaconda\envs\RASA_ENV_python3.6\lib\site-packages\sanic\request.py
line 149, in load_json
self.parsed_json = loads(self.body)
File "D:\Anaconda\envs\RASA_ENV_python3.6\lib\json\__init__.py", line 354, i
loads
return _default_decoder.decode(s)
File "D:\Anaconda\envs\RASA_ENV_python3.6\lib\json\decoder.py", line 339, in
ecode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "D:\Anaconda\envs\RASA_ENV_python3.6\lib\json\decoder.py", line 357, in
aw_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 "d:\ml-chatbot-cudo\rasa_env_python3.6\rasa\rasa\server.py", line 823,
parse
data = emulator.normalise_request_json(request.json)
File "D:\Anaconda\envs\RASA_ENV_python3.6\lib\site-packages\sanic\request.py
line 143, in json
self.load_json()
File "D:\Anaconda\envs\RASA_ENV_python3.6\lib\site-packages\sanic\request.py
line 153, in load_json
raise InvalidUsage("Failed when parsing body as json")
sanic.exceptions.InvalidUsage: Failed when parsing body as json
Does the same happen if you create a new chatbot with rasa init --no-prompt? I don’t have that problem on the latest version, can you update your Rasa version and try again?