Where are the conversations stored?

Hello everyone,

I want to transfer my chatbot’s conversations on RASA X to another version of the same chatbot (separate projects). I would like to know where the conversations are stored in RASA X ? I’ve read this note in the documentation:

Within the Rasa X service, the event service consumes conversation events data from the events broker and stores it in the Rasa X database (SQL DB). The Rasa X backend also stores training data and metadata, like conversation tags and flagged messages, in the SQL DB.

Is there a way to access this DB ? Or can we export the conversation ?


Anyone please ?

1 Like

Have you deployed the bot on a server? Or been conversing with it locally?

Hello Gaurav, thank you for your reply. I’ve been using RASA X locally !

You can use RASA X and you can check the conversations that you had been having with your bot .Each conversational flow will have a sessionID allocated

Hello @martinavalogia, thank you for replying ! I am aware of this, what I need is to export the conversations from RASA X or access the SQL DB they’re supposed to be in (as mentionned in the documentation).

@forwitai -You can use the parameters mentioned here- Configure you db and start accessing the conversations as needed too Tracker Stores

Yes, I know. But the thing is I haven’t done, and I need to access my previous conversations, so I was wondering if there is a way to do it. I can see them on Rasa X, soo they must be stored somewhere.

Check for rasa.db file in the folder containing your project. It is the default path to store conversations. Now, if you haven’t configured anything in your endpoints.yml file InMemoryTrackerStore is used as the default tracker store. It stores the conversation history in memory, the entire history is lost if you restart the Rasa server. If you want to really store the data then, I’d suggest you use a different tracker store.

how do guys retrieve previous conversation into mobile app?

example scenario: today I’m chatting with bot, tomorrow the conversational still have inside the app

how can we achieve this ?