"Tried to set non existent slot" error persists after deleting all instances of slots and retraining
See original GitHub issueRasa version: rasa-core==0.13.7 rasa-core-sdk==0.12.2 rasa-nlu==0.14.6
Python version: Python 3.6.7
Operating system (windows, osx, …): Distributor ID: Ubuntu Description: Ubuntu 18.04.2 LTS Release: 18.04 Codename: bionic
Issue: The slots which were used for previous experiments are not resetting even after removing these slots from all files (nlu.md, stories.md, domain.yml and actions.py) I tried deleting the entire model directory and trained the models again. but still it showing the errors with previously used slot. Please find the error message below.
2019-04-22 09:56:44 ERROR rasa_core.trackers - Tried to set non existent slot 'environment'. Make sure you added all your s
lots to your domain file.
2019-04-22 09:56:44 ERROR rasa_core.trackers - Tried to set non existent slot 'platform'. Make sure you added all your slot
s to your domain file.
I just executed a grep command from my project directory to make sure these slots are not using anymore.
~/project/slackbot$ grep "environment" * -R
Notebook/Conversational_Chatbot.ipynb: "# In your environment run:\n",
(sample_bot_env) ubuntu@ip-172-31-21-57:~/project/slackbot$ grep "platform" * -R
Notebook/Conversational_Chatbot.ipynb: "Requirement already satisfied, skipping upgrade: greenlet>=0.4.14; platform_python_implementation == \"CPython\" in /usr/local/lib/python3.6/dist-packages (from gevent->rasa_nlu[spacy]) (0.4.15)\n",
credentials.yml:# This file contains the credentials for the voice & chat platforms
nohup.out:2019-04-03 09:58:46.340534: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
Kindly note that I had used these slots before (not in the current stories) for doing some experiments.
Thank you,
Issue Analytics
- State:
- Created 4 years ago
- Reactions:1
- Comments:47 (18 by maintainers)
Top GitHub Comments
I think I found the culprit. I was using the MongoTrackerStore to store the conversation. When i removed the collection from mongo db, all the unwanted track history (which were used before) disappeared.
But, why this is making an issue? That mean’s, we need to clear the stored collection from mongodb every time when we change/rename an existing entity/slot value? Is there any proper way to handle this?
Hi @erohmensing I am facing a similar issue. I have no slots that are undefined in the domain.yml and I have ensured that the action server is restarted. Furthermore, the form action was working smoothly earlier, and suddenly these errors started showing up despite of making no changes to the code.