Rasa in Docker: Could not load model due to Error deserializing graph schema

更新日期: 2023-10-09 阅读次数: 648 字数: 150 分类: AI

When deploying Rasa service in production Docker environment, error show:

rasa.core.agent - Could not load model due to Error deserializing graph schema. Can't find class for graph component type 'rasa.graph_components.providers.forms_provider.FormsProvider'

Reason

This error typically occurs when there is a mismatch between the version of Rasa used to train the model and the version used to load the model. It's possible that the model was trained with a newer version of Rasa that introduced a new graph component type (in this case, 'FormsProvider'), which is not recognized by the older version used to load the model.

e.g.

  • dev: 3.6.7
  • docker: 3.1.0

Solution

Pull new version of Rasa docker same as dev enviroment.

Check Rasa Version

> rasa --version

Rasa Version      :         3.4.6
Minimum Compatible Version: 3.0.0
Rasa SDK Version  :         3.4.1
Python Version    :         3.8.5
Operating System  :         Linux-4.4.0-22621-Microsoft-x86_64-with-glibc2.29
Python Path       :         /usr/bin/python3

tags: rasa

关于作者 🌱

我是来自山东烟台的一名开发者,有敢兴趣的话题,或者软件开发需求,欢迎加微信 zhongwei 聊聊, 查看更多联系方式