I am trying to change the policy in RASA from max_history: 5 to FullDialogueTrackerFeaturizer - rasa-nlu

Question

I am new to using RASA and I was able to follow this guide:
https://rasa.com/docs/rasa/user-guide/installation/
to set up RASA on Ubunto 18.04 on windows. I am now following a second guide:
https://rasa.com/docs/rasa/user-guide/rasa-tutorial/
and am at step 3, running the code in step 3 on Ubuntu cane back with the following result:
# Configuration for Rasa NLU.
# https://rasa.com/docs/rasa/nlu/components/
language: en
pipeline:
- name: WhitespaceTokenizer
- name: RegexFeaturizer
- name: LexicalSyntacticFeaturizer
- name: CountVectorsFeaturizer
- name: CountVectorsFeaturizer
analyzer: "char_wb"
min_ngram: 1
max_ngram: 4
- name: DIETClassifier
epochs: 100
- name: EntitySynonymMapper
- name: ResponseSelector
epochs: 100
# Configuration for Rasa Core.
# https://rasa.com/docs/rasa/core/policies/
policies:
- name: MemoizationPolicy
- name: TEDPolicy
max_history: 5
epochs: 100
- name: MappingPolicy
Near the bottom, where it lists max_history: 5 I would like to change the policy to FullDialogueTrackerFeaturizer so that the entire dialog is considered for the bots production. I have tried reading this article:
https://rasa.com/docs/rasa/api/core-featurization/#featurization-conversations
although the article explains the function of the policy, I could not how to switch the policy.
My question is, how do I change the policy from max_history: 5 to FullDialogueTrackerFeaturizer?

Answer 1

FullDialogueTrackerFeaturizer is not a policy it's a featurizer. What you're describing is infinite max_history. This is not a good idea, as your model will become enormous and very slow. Instead, set max_history high enough to account for any patterns in your training data. If you need to save data for use at an arbitrary point in a conversation, set a slot instead.