[Python] Having trouble running a trained Rasa model (.tar.gz) due to extraction or path errors

I’m working on a Rasa chatbot project and trying to run a trained model using the command: rasa run --enable-api --cors “*” --model models/20250620-140724-crabby-exchange.tar.gz --port 5006 However, I’m consistently getting this error: Could not load model due to [WinError 123] The filename, directory name, or volume label syntax is incorrect: ‘?\D:\rasa-temp\tmp…train_RulePolicy1’ To troubleshoot, I:

Tried extracting the .tar.gz manually and placed the components/ and metadata into a folder (models/crabby-exchange) Then tried running:rasa run --model models/crabby-exchange But Rasa responded with:No valid model found at models/crabby-exchange! So I’m stuck between archive-related errors and Rasa not accepting manually extracted folders. :backhand_index_pointing_right: Could anyone guide me on how to correctly repackage the model or solve this WinError 123 issue?

I’m on Windows 10, using Anaconda (rasaenv) Thanks in advance for any help!

Continue reading...