I have used docker to start several instances running rasa_nlu.Now I want to know how to update the model which is now running on the server without restart it.The documentionsays rasa can fetch the model from server every few seconds.
Is this what I exactly want.And I still want to know ,in this case, how to start a server like “http://my-server.com/models/default@latest” which mentioned in the documention.Anyone knows or any suggestions about my problem . Thank youToday ,I config he endpoints.yml like this
Then I start a server by flask.The code is as this
It seems I find the problem and I opened a issue here issue
You can replace the current model without restarting the server
{ “model_file”: “/models/20190512.tar.gz”, “model_server”: { “url”: “string”, “params”: {}, “headers”: {}, “basic_auth”: {}, “token”: “string”, “token_name”: “string”, “wait_time_between_pulls”: 0 }, “remote_storage”: “aws” }
Please refer the url given below for your reference