Everytime I send a message to the bot, it stucks for a long time when it prints DEBUG rasa_core.policies.memoization - Launch DeLorean… , maybe around a minute or more. I am already using a small max_history. This is my policy: policies: name: KerasPolicy epochs: 100 max_history: 5 name: AugmentedMemoizationPolicy max_history: 2 name: FormPolicy name: MappingPolicy And my log: 2019-06-17 22:13:18 DEBUG rasa_core.processor - Action ‘utter_introduce’ ended with events ‘’ 2019-06-17 22:13:18 DEBUG rasa_core.processor - Bot utterance >‘BotUttered(text: hello, data: { “elements”: null, “buttons”: null, “attachment”: null })’ 2019-06-17 22:13:19 DEBUG rasa_core.policies.memoization - Current tracker state [{‘slot_ex_0’: 1.0, ‘slot_utterance_id_0’: 1.0, ‘slot_respondent_0’: 1.0, ‘entity_epic_id’: 1.0, ‘entity_utterance_id’: 1.0, ‘slot_enquirer_0’: 1.0, ‘slot_epic_id_0’: 1.0, ‘prev_action_listen’: 1.0, ‘intent_greet’: 1.0, ‘slot_mc_answer_1’: 1.0}, {‘slot_ex_0’: 1.0, ‘slot_utterance_id_0’: 1.0, ‘slot_respondent_0’: 1.0, ‘entity_epic_id’: 1.0, ‘entity_utterance_id’: 1.0, ‘slot_enquirer_0’: 1.0, ‘slot_epic_id_0’: 1.0, ‘intent_greet’: 1.0, ‘slot_mc_answer_1’: 1.0, ‘prev_utter_introduce’: 1.0}] 2019-06-17 22:13:19 DEBUG rasa_core.policies.memoization - Launch DeLorean… Do you know what makes it so slow and how to make it faster?

Problems solved. It is my mistake. It is because I have not specified max_event_history when I define my custom tracker store. So, when I ahve more then 10k records, the McFly update function iterates through all of them. After I set max_event_history to 100, the memorization policy is much faster. The thread below shows how to limit the tracker history size: [image] Size of trackers in custom tracker store Rasa Open Source Hello! I’ve created a custom tracker store object to connect my bot to a centralized key/value store. That store has limits on the size of values and is also remote to my bot. When do trackers get reset or pop old information off of the conversation? Is that configurable? I’d like to ensure trackers don’t exceed my store’s limits. Also, are trackers retrieved/saved for every new user message/bot response? Since it’s remote, larger trackers could eventually impact my bot’s performance. Thanks…

Rasa core memorization policy is very slow when it "launches DeLorean"

Rasa Open Source

psfr937 (Raymond) June 24, 2019, 2:34pm 2

Problems solved. It is my mistake.

It is because I have not specified max_event_history when I define my custom tracker store.

So, when I ahve more then 10k records, the McFly update function iterates through all of them.

After I set max_event_history to 100, the memorization policy is much faster.

The thread below shows how to limit the tracker history size:

Topic		Replies	Views
Adding TED policy in config. Bot does not respond Rasa Open Source	20	2314	November 23, 2020
Help needed! Issue with dererministic policies and payloads Rasa Open Source	4	810	August 13, 2019
Long conversations get misunderstood Rasa Open Source	8	614	March 1, 2019
Rasa default example stops listening Tutorials, Resources & Videos	13	870	March 16, 2021
Talk to your bot (Interactive Learning) doesn't answerme [Deprecated] Rasa X Community Edition	0	377	August 25, 2020

Rasa core memorization policy is very slow when it "launches DeLorean"

Related Topics