@RasaHQ Is Rasa Open Source still compatible with Google Assistant? Additionally, I've been attempting to connect my Telegram bot with Rasa, but it's throwing an Event Loop Error. I tried raising an issue on the Jira board, but I haven't seen a serious response to people who have posted queries and highlighted issues on the board.
Thanks, this is very good. 2 feedbacks only. Your voice level is low compared to the effects at the end. Also other thing is the examples and forum entries I have found so far. All approaches are about the rules and not about learning. So if user ask something then rasa answer something. If user aks this again with other question in 1 sentence then need a new rule for that case. So as far as I see soon or later this will be too complex and difficult to keep it up to date. This is my experience so far. I would expect to fetch the keywords (what the user asking that can be more than 1 queston) and chose answers, however as per the examples so far this is not the case. :-(
Hi Zoltan! It sounds like you're looking for multi intent classification: rasa.com/docs/rasa/tuning-your-model/#doing-multi-intent-classification - Rachael
It would be great if you give a broad introduction about the ML pipielines you can use in Rasa. What works best and why? What is best to start with,...
@@RasaHQ Well, yes I have seen this. But what I am missing is a more broader overview. Especially how to start the pipeline tuning, which pipeline to start with and how pretrained models can be used. This is such an important topic and I think it was not covered enough
@@Raminber (Vincent here) The pipeline tuning, so far, seems hard to say anything general about. In my experience though, it seems like in most cases gridsearch is a pre-mature optimisation. Unless you're absolutely sure you've got a representative dataset with actual users giving you actual data ... I might focus on getting more data first.
(Vincent again) That said, if you have a specific issue in your pipeline you're free to ping me @koaning in our forum. I'll gladly have a look. forum.rasa.com
An open-source neural network similar to TOR? What if we make an open-source neural network that would work as a swarm, in the spirit of the Tor network or torrents, crypto? So that all computers would be part of its "consciousness", and not some servers?
I was right. The second I heard "deep learning" neural networks. I realized they were gonna try to make a chatbot....language...... so i got a degree in lingustics. I don't have a clue about python.....but i instantly understand the LLM part....somehow.
Is this an updated playlist to the former one, "Rasa Master Class" because the former uses depreciated data formats like JSON and Markdown and rasa stated they'll drop support for it.
Yep, this is intended to be an updated version of the master class! (Although as a note, if you're using Rasa 1.x then the master class is still relevant for that.) -R
@@shashigharti5137 (Vincent here) That can be implemented with a custom action in Rasa and you'd be free to use any backend you like. You might like neo4j, but you're free to pick whatever you like.
@@RasaHQ I want to create a chatbot for my college website but how can I add information about different courses and also these are divided into M-tech and B-tech courses
My name is mifta iam from Ethiopia. i want to develop chatbot for amharic language by using RASA. Is that possible because RASA doesnot support amharic
(Vincent here) I'm not familiar with Amharic, so I can't know for sure. The standard pipeline that you get when using `rasa init` should work for most whitespace tokenizable languages though.
Hi i had been folowing up with the other rasa masterclass lately, i am having great trouble installing the rasa x actually, i have kind of read all the blogs out there, would u be able to help me out, if i follow the official docs, my terminal says Requirement already satisfied: rasa-x in c (sys is Windows), but rasa --version shows it to be None, i also tried it on google colab with same result, rasa x ends up being MissingDependencyException. Any help from anybody is extreeeemly appreciated !!!!!!!
To properly follow up, it might be helpful to ask the question on our forum. That way we'd more easily be able to exchange code. You can ping me @koaning on forum.rasa.com
Thank you for sharing the video with us. I really appreciate it
@RasaHQ Is Rasa Open Source still compatible with Google Assistant? Additionally, I've been attempting to connect my Telegram bot with Rasa, but it's throwing an Event Loop Error. I tried raising an issue on the Jira board, but I haven't seen a serious response to people who have posted queries and highlighted issues on the board.
Thanks, this is very good. 2 feedbacks only. Your voice level is low compared to the effects at the end. Also other thing is the examples and forum entries I have found so far. All approaches are about the rules and not about learning. So if user ask something then rasa answer something. If user aks this again with other question in 1 sentence then need a new rule for that case. So as far as I see soon or later this will be too complex and difficult to keep it up to date. This is my experience so far. I would expect to fetch the keywords (what the user asking that can be more than 1 queston) and chose answers, however as per the examples so far this is not the case. :-(
Hi Zoltan! It sounds like you're looking for multi intent classification: rasa.com/docs/rasa/tuning-your-model/#doing-multi-intent-classification - Rachael
I like the sound of this.
It would be great if you give a broad introduction about the ML pipielines you can use in Rasa. What works best and why? What is best to start with,...
Have you seen our Algorithm Whiteboard Channel? ruclips.net/p/PL75e0qA87dlG-za8eLI6t0_Pbxafk-cxb
@@RasaHQ Well, yes I have seen this. But what I am missing is a more broader overview. Especially how to start the pipeline tuning, which pipeline to start with and how pretrained models can be used. This is such an important topic and I think it was not covered enough
@@Raminber (Vincent here) The pipeline tuning, so far, seems hard to say anything general about. In my experience though, it seems like in most cases gridsearch is a pre-mature optimisation. Unless you're absolutely sure you've got a representative dataset with actual users giving you actual data ... I might focus on getting more data first.
(Vincent again) That said, if you have a specific issue in your pipeline you're free to ping me @koaning in our forum. I'll gladly have a look. forum.rasa.com
An open-source neural network similar to TOR?
What if we make an open-source neural network that would work as a swarm, in the spirit of the Tor network or torrents, crypto? So that all computers would be part of its "consciousness", and not some servers?
how can we use text flies in look up tables and what are the procudures/gudelines
can't wait to join!
Thank you so much for this video!
Has Rasa stopped updating since 2001? It seems like the official videos stopped updating two to three years ago.
I see some posted on RUclips from this past week?
Fantastic! Thank you.
Hello, thank you for this great video. I wanted to know whether we can implement a Knowledge Graph into a Rasa Chatbot?
Yes you can! You'll need to use a custom action for it. -R
I was right. The second I heard "deep learning" neural networks. I realized they were gonna try to make a chatbot....language...... so i got a degree in lingustics. I don't have a clue about python.....but i instantly understand the LLM part....somehow.
Is this an updated playlist to the former one, "Rasa Master Class" because the former uses depreciated data formats like JSON and Markdown and rasa stated they'll drop support for it.
Yep, this is intended to be an updated version of the master class! (Although as a note, if you're using Rasa 1.x then the master class is still relevant for that.) -R
@@RasaHQ Is RASA open source completely a ghost project ? No more video, nothing..... Playground broken since months. Should we go somewhere else ?
Hi Racheal, Thank you! I am new to Rasa and I want to use graph database with Rasa. Which graph database would you recommend to use?
(Vincent here).
Just to clarify, what do you want to use a graph database for?
@@RasaHQ To store the domain information(universities) and use action to query the data and respond to the user.
@@shashigharti5137 (Vincent here)
That can be implemented with a custom action in Rasa and you'd be free to use any backend you like. You might like neo4j, but you're free to pick whatever you like.
@@RasaHQ I want to create a chatbot for my college website but how can I add information about different courses and also these are divided into M-tech and B-tech courses
My name is mifta iam from Ethiopia. i want to develop chatbot for amharic language by using RASA. Is that possible because RASA doesnot support amharic
(Vincent here)
I'm not familiar with Amharic, so I can't know for sure. The standard pipeline that you get when using `rasa init` should work for most whitespace tokenizable languages though.
I think the audio is too small
I WISH I CONVERT MY JARVIS AI
Thank you for this interesting video, but why do you speak so fast? Are you in a hurry?
Hi i had been folowing up with the other rasa masterclass lately, i am having great trouble installing the rasa x actually, i have kind of read all the blogs out there, would u be able to help me out, if i follow the official docs, my terminal says Requirement already satisfied: rasa-x in c (sys is Windows), but rasa --version shows it to be None, i also tried it on google colab with same result, rasa x ends up being MissingDependencyException. Any help from anybody is extreeeemly appreciated !!!!!!!
To properly follow up, it might be helpful to ask the question on our forum. That way we'd more easily be able to exchange code. You can ping me @koaning on forum.rasa.com
@@RasaHQ Thanks will sure do
👉universe from 🕵️👉God 😮