0

Apart from being open source, what can other Conversational AI platforms (wit.ai, Lex, DialogFlow..) do that Rasa can't?

Gianluca
  • 63
  • 3

1 Answers1

1

These are some of the main differences between Dialog Flow and Rasa:

Dialog Flow:

  • No installation needed, you can start using it immediately.

  • Easy to use, non-tech people can build a bot.

  • Closed system.

  • Web-based interface for building bots.

  • Data is hosted on the cloud.

  • Can’t be hosted on your server or on-premise.

  • Out-of-box integration with Google Assistant, Skype, Slack, Facebook Messenger, etc.

Rasa:

  • Requires installation of multiple components.

  • Requires tech knowledge.

  • Open-source code available in GitHub.

  • No interface provided, write JSON or markdown files.

  • No hosting provided.

  • You can host it on your server.

  • No out-of-box integration.

Eduardo Ortiz
  • 715
  • 3
  • 14
  • Thank you so much! Unfortunately I can't upvote your answer (I'm new). However I'd like to know if there's something specific that Rasa can't do (e.g. "Dialog Flow can handle more complex contexts" / "Dialog Flow has a much better nlu interface") – Gianluca Dec 30 '21 at 09:22
  • If my answer helped you, you could mark it as accepted, I did some research and there's nothing Rasa can't do, but the main difference between the two of the is that the NLU, NLP and NLG does not happen under the hood in the case of Rasa, and DialogFlow needs to sent it to the cloud everytime a transaction happens. – Eduardo Ortiz Dec 30 '21 at 14:04
  • "there's nothing Rasa can't do" - great to know that. Thanks! – Gianluca Dec 30 '21 at 19:47
  • Composite nested entities can't be handled in RASA. It is there in wit.ai – Mritunjay Prasad Apr 20 '22 at 06:05