All - Activity - jloutz - Rasa Community Forum

Fallback intents for context-sensitive fallbacks

Hi - glad it was useful for you! I just added a python file/module with the component class. You can structure this however you please, just as long as the name you use in the nlu config (for my case : "components.fallback_intent_filter.FallbackIntentFilter") points to the package/module/class that...

ConsoleInputChannel no longer exist

Hi there - not really something I have special knowledge about other than the rasa docs. I am sure the rasa team will be able to help. Good luck!

Utterance based on slot value

Hi, I would say this is not the naive way, but the ONLY way :) If you create enough example stories with differing slot values leading to different bot actions, eventually your dialog model will learn the difference. Might take quite a bit of training data before this starts to work reliably though.

Memoization Policy

The Memoization Policy treats your stories not as ML training data, but as specific, literal instructions. That is, if the dialog so far matches a configured story exactly and the dialog engine needs to find the next action, the memoization policy will just use the next action in the story with confidence based on the match.

Fallback intents for context-sensitive fallbacks (Cont'd)

Hi everyone. I thought I would share an extension that I made to enable context-specific fallback/error handling. Context-specific error handling is really good for things like:

B: "for how many people should I make the reservation?"
U: "oh you are a clever little bot aren't you!"
B: "Sorry, didn't get..."

Implementing Default Fallback Actions

Hi there. To add the Fallback Policy, you need to create an Agent yourself and use that Agent when training the dialog engine. So you need to do a small bit of Python coding, you cannot just use the FallbackPolicy from the command line. What does all this mean? I have a script which wraps common dev...

ConsoleInputChannel no longer exist (Cont'd)

Similarly, I had code to start interactive training from my script. This broke in V11 because of ConsoleInputChannel. So my V9 Version was:
agent = Agent("domain.yml", policies=[KerasPolicy()])
stories_file = "data/stories.md"
stories_data = agent.load_data(stories_file)
output_path = "models/dialo…"

ConsoleInputChannel no longer exist (Cont'd)

So I know you have all already figured this out, but I will share this anyway. I have a python script which wraps common tasks like training running etc. Migrating from core 9 to core 11 caused me a small amount of work to get that going again. My custom “run” method for command line (in my script)...

ConsoleInputChannel no longer exist (Cont'd)

thank you!

Introduce yourself!

Howdy! John Loutzenhiser here. I am a machine learning consultant and software architect. My main client is the German government, mostly the Bundesagentur für Arbeit (Federal Employment Commission). I am employed by the German software consultancy firm msg-systems. I have been using Rasa stack for...

ConsoleInputChannel no longer exist (Cont'd)

Hi there. Same issue. Migration Guide is no help. I will investigate and post a solution if I find one.