At the moment, we are using Rasa 2.7.1, Rasa SDK 2.7.0 and Rasa X 0.41.2. We tried to upgrade it up starting 2.8.0 till latest version 2.8.13 without success, on Rasa local/server:
Either there is an error.
or it runs but identifying a small portion of trained examples ex:
Internet slow (trained exampled: slow, slo, int slow, int slo…), it identifies only slow not other values…
Therefore, we had to roll back to the above original versions. Noting that we training again on each version.
Is anyone else facing the same problem, or you are running the latest version without problems? if yes, what was done?
1)- Local:
rasa --version
Rasa Version : 2.7.1
Minimum Compatible Version: 2.6.0
Rasa SDK Version : 2.7.0
Rasa X Version : 0.41.2
Python Version : 3.8.10
Operating System : Linux-5.11.0-40-generic-x86_64-with-glibc2.29
Python Path : /usr/bin/python3
2)- Server:
[root@localhost ~]# docker images
REPOSITORY TAG IMAGE ID CREATED SIZE
x/x chatbot c35c258d5e8c 2 days ago 1.07GB
rasa/rasa-sdk 2.7.0 9681c32b59b0 5 months ago 217MB