2021-06-22 07:48:24 ERROR rasa.core.agent - Could not load model due to can only concatenate str (not "NoneType") to str

Rasa Open Source
1

Hello, Since I changed the config.yml (DIETClassifier, TEDPolicy instead of EmbeddingIntentClassifier, EmbeddingPolicy) and updated rasa version from 1.10.14 to 2.7.1, it is impossible to load the model.

Has anyone already encountered this problem please?

Here is the full error:

/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 /conversations/<conversation_id>/trigger_intent POST trigger_intent /model DELETE unload_model /version GET version 2021-06-22 07:48:19 INFO root - Starting Rasa server on http://localhost:5005 2021-06-22 07:48:19 DEBUG rasa.core.utils - Using the default number of Sanic workers (1). 2021-06-22 07:48:19 INFO root - Enabling coroutine debugging. Loop id 94913126783232. 2021-06-22 07:48:21 DEBUG rasa.model - Extracted model to ‘/tmp/tmp5lg_kibb’. 2021-06-22 07:48:24 DEBUG root - Could not load interpreter from ‘models’. 2021-06-22 07:48:24 DEBUG rasa.core.tracker_store - Connected to InMemoryTrackerStore. 2021-06-22 07:48:24 DEBUG rasa.core.lock_store - Connected to lock store ‘InMemoryLockStore’. 2021-06-22 07:48:24 DEBUG rasa.model - Extracted model to ‘/tmp/tmpjzkk6mmo’. 2021-06-22 07:48:24 ERROR rasa.core.agent - Could not load model due to can only concatenate str (not “NoneType”) to str. [2021-06-22 07:48:24 +0000] [1] [ERROR] Experienced exception while trying to serve Traceback (most recent call last): File “/opt/venv/lib/python3.7/site-packages/sanic/app.py”, line 1167, in run serve(**server_settings) File “/opt/venv/lib/python3.7/site-packages/sanic/server.py”, line 892, in serve trigger_events(before_start, loop) File “/opt/venv/lib/python3.7/site-packages/sanic/server.py”, line 668, in trigger_events loop.run_until_complete(result) File “uvloop/loop.pyx”, line 1456, in uvloop.loop.Loop.run_until_complete File “/opt/venv/lib/python3.7/site-packages/rasa/core/run.py”, line 257, in load_agent_on_start action_endpoint=endpoints.action, File “/opt/venv/lib/python3.7/site-packages/rasa/core/agent.py”, line 316, in load_agent

2

@Alain Hi, You need to train the model as previous model is trained based on pipeline parameter of version 1.X and now you migrated 2.7.1. Train and run. I guess it will solve your issue.

3

Hello @nik202 , Thanks for your suggestion, the first thing was the generation of a new model. I generated a new model since I maded changes in the config file. The file generation has been completed successfully.

When I launch my docker or try to load manually the model (rasa run). the rasa_core failed .

In my docker log , i can see the following error mentionned in the topic: .

I experienced a lot of process:

  1. Reload image of docker to reload rasa_core and rasa_action_server
  2. Drop image / recreate all.
  3. Resinstall rasa
  4. Reinstall the environnement in where rasa created in anaconda.

Ps: Rasa and python has been updated to newer version.

Rasa Version : 2.7.1 Minimum Compatible Version: 2.6.0 Rasa SDK Version : 2.7.0 Rasa X Version : 0.40.1 Python Version : 3.7.7 Operating System : Windows-10-10.0.17763-SP0