Rasa bot response failure

Rasa Open Source
1

Hello Everyone,

I am facing a issue regarding the bot response.

I only get the first response, but then when I put other questions or even the same question, the bot does not respond unless I restart it (after which it responds to first msg).

Does anyone have any idea about this issue. Please help.

RASA_issue_1
RASA_issue_11636×716 82.8 KB

While running the rasa server I am getting some warning which might help in assessing:-

rasa run --enable-api --cors "*"
yay
2022-02-24 14:48:58 INFO     root  - Starting Rasa server on http://localhost:5005
2022-02-24 14:48:58 INFO     rasa.model  - Loading model models/20220224-132602.tar.gz...
/usr/local/lib/python3.8/site-packages/tensorflow/python/framework/indexed_slices.py:447: UserWarning: Converting sparse IndexedSlices(IndexedSlices(indices=Tensor("gradients/cond_grad/Identity_1:0", shape=(None,), dtype=int64), values=Tensor("gradients/cond_grad/Identity:0", shape=(None,), dtype=float32), dense_shape=Tensor("gradients/cond_grad/Identity_2:0", shape=(1,), dtype=int32))) to a dense Tensor of unknown shape. This may consume a large amount of memory.
  warnings.warn(
/usr/local/lib/python3.8/site-packages/tensorflow/python/framework/indexed_slices.py:447: UserWarning: Converting sparse IndexedSlices(IndexedSlices(indices=Tensor("gradients/cond_1_grad/Identity_1:0", shape=(None,), dtype=int64), values=Tensor("gradients/cond_1_grad/Identity:0", shape=(None,), dtype=float32), dense_shape=Tensor("gradients/cond_1_grad/Identity_2:0", shape=(1,), dtype=int32))) to a dense Tensor of unknown shape. This may consume a large amount of memory.
  warnings.warn(
2022-02-24 14:50:05 WARNING  rasa.shared.utils.common  - The UnexpecTED Intent Policy is currently experimental and might change or be removed in the future 🔬 Please share your feedback on it in the forum (http://forum.rasa.com) to help us make this feature ready for production.
2022-02-24 14:50:15 INFO     root  - Rasa server is up and running.

Rasa Version      :         2.8.17
Minimum Compatible Version: 2.8.9
Rasa SDK Version  :         2.8.4
Rasa X Version    :         None
Python Version    :         3.8.7
Operating System  :         Linux-3.10.0-1127.el7.x86_64-x86_64-with-glibc2.17
Python Path       :         /usr/local/bin/python3.8

Thanks,

Yash Chopda

2

@yashchopda what is your main error can you highlight? and your rasa --version ?

@yashchopda Can you run this command:

rasa run -m models --enable-api --cors "*" --debug

and delete all the previous trained model and train and run again.

3

@nik202 Thank you for the reply. I have highlighted my issue. I am not getting any errors while training or running the bot but, when I run it on shell or an interface it does not respond. The version details are:-

Rasa Version      :         2.8.17
Minimum Compatible Version: 2.8.9
Rasa SDK Version  :         2.8.4
Rasa X Version    :         None
Python Version    :         3.8.7
Operating System  :         Linux-3.10.0-1127.el7.x86_64-x86_64-with-glibc2.17
Python Path       :         /usr/local/bin/python3.8

I will try running the command and delete the pretrained models and train again. It will take a couple of hours and then get back to you. Thanks

4

@yashchopda no worries Yash, take your time and do let me know the output.