Rasa Open Source 2.0 is out now!

@noman do you mind creating a new forum post and tagging me in it? would be easier to separate out various issues we’re trying to figure out

sure that would be great

Any news for a fix for the forms problem to not filling/validating slots from the utterance triggering the form?

hi, how to control or select entity extracted by multi entity extractor? I am using RegexExtracor, CRFextractor, DIETextractor to extract my entity, as a result, the tracker will keep these three extracting results as a list, so how to control the tracker just keep only one result?

This is another difficult issue. Is these slots are for a form, you can write an action to validate the slot. The validation function will get the list of values, and you can select one of them. What I did (for my case) was to remove duplicates, and from the remaining values get the one with most characters.

If you not in a form, you can write a custom action, or a custom component.

@123 could you open a new post so we can address that issue separately?

@petasis could you a post for the issue you were originally talking about with all the details you shared already? this thread has a bunch of different discussions going on, and it’s gotten a little difficult to keep track of the issue/the data you’ve shared. Same goes for the second issue you just mentioned. Feel free to tag myself and/or Tobias

Super excited there is now RasaX support! Will the Deep Dive Webinar be made available for those who missed it? Cheers.

I am using Rasa 2.0. My action server is up and running, my endpoint is uptodate with action_endpoint URL, but there is no response from bot where we have action defined in story. There is no error, but it just listens and expects input from user. Is there any different way I need to handle custom actions in 2.0? this works good in 1.10 for me.

I can’t get API /model/train endpoint working on Rasa 2.0. Even if I copy your example from Rasa Open Source Documentation I’m keep getting 500

{
    "version": "2.0.0",
    "status": "failure",
    "message": "Ran training, but it finished without a trained model.",
    "reason": "TrainingError",
    "details": {},
    "help": null,
    "code": 500
}

and this is in terminal

No training data given. Please provide stories and NLU data in order to train a Rasa model using the '--data' argument.
2020-10-15 09:40:20 ERROR    rasa.server  - Ran training, but it finished without a trained model.

I use rasa run --enable-api.

Edit: Here it is @akelad Rasa 2.0 - API /model/train doesn't work

Yep, will be uploaded to Youtube soon!

Could you create a new post for your issue with the commands you ran etc? will be easier to solve there than in this thread with lots of different posts

Same to you, would be great if you can create a new forum post. Incl. the API call you made please

Thanks. But this has been resolved. In 2.0, NLU is yaml, I was defining entities like like 1.X and that was causing issue. Removing this resolved the issue.

I am stuck at rasa 2.0 regarding the form validation. Could you please send me an example or a link of a project in which it is working, so that I could see the domain and actions file. Thanks in advance

here’s an example: https://github.com/RasaHQ/financial-demo/blob/rasa-2-0/actions/actions.py#L249

If you have any more questions, would be great if you can open a new forum post with all the details of the issue you’re having, and we’ll get back to you there :slight_smile:

Thanks , will do it

I am getting this issue while trying to install Rasa 2.0.0 in Windows version 10.How can this be resolved ,any insights please With Python version 3.7.7 on Windows 10 got the below issue

Shared with CloudApp

Therefore I have reinstalled Python 3.6 to resolve the tensor flow issue ,now facing this

Shared with CloudApp

any suggestions on how to resolve this

Setting up Rasa 2.0 on a windows 10 setup using Python 3.6

Thanks in advance

This is nice,

I have a form where a cellphone number is validated and it does work when a user type letters it throws that ValueError in the actions tab but i want to give a user a message like “wrong input a number is expected”

Hey @skbushula could you open a new post on the forum so we can help figure out whats going on? (easier to keep separate threads for all these issues)

Hi!

I believe there is something amiss with the two stage fallback policy: it clears all slots when rewinding.

When the fallback is triggered, and the user correctly rephrases their input to something the bot recognises, the two stage fallback is supposed to revert the last interaction to prevent confusion when making the next prediction. It also clears all slots however.

I believe this is a bug, and it makes the two stage fallback unusable for my application. I hope this can be resolved quickly, because the fallback is a critical part of the project I am working on.

Thank you