Glad to hear, thanks! Since that video I already learned some new things about handling multi-language assistants. Will make a new video again some time soon :)
Nice one brother I’ve been having issues with this same bro Really nice solution of using Response AI instead of message. It will just need thorough prompting
@@GregSchaf initially thought I was the only one having this language barrier issue but phew, seems a lot of us had the same issue. Also if you don’t mind maybe we can connect I’m always having crazy ideas to practice myself but seems a lot of people aren’t there yet so , I don’t know if we are able to connect
Nice video! some feedback: could've done it in 10 mins. I assume people coming on here to see if we can make multi lingual bots are mostly people who already know the steps you spent quite a lot of time explaining. either way thanks for making a clear video to follow nonetheless!
Thanks for the feedback! I do intentionally make these videos suitable for beginners as well. However in the future I will probably try to structure my videos in a way that the beginner part can be skipped more easily, so those who don't need that can more easily skip it. Thanks again for letting me know!
I'm building an assitant for a real estate business that offers the website in 3 languages, this was really helpful but I was thinking of making the chatbot itself 3 times the same in the languages it offers and then just at the beginning the client would need to choose in what language they speak. Do you think this will be to expensive in terms of tokens or is this to chaotic? Anyways thanks for the vid!
This solution works well if you limit the assistant to only 3 languages and it won't cause additional token usage. I also did this in the beginning. You can consider not allowing any free input before the language is selected, so that the bot does not get confused. Just consider that this approach leads to a lot of duplication (you need to do everything 3 times)
nice video brother! I did it differently, created a system in English then copying pasted it twice for two other languages, so I have three pathways in different languages with some differences. What should I do if it jumps from one intent to another? Let’s say I asked question is in english but he goes to the russian pathway
I actually switched my approach a bit. More recently I use an AI prompt to determine the language of the users last message and then send them on a path accordingly. While the video is not specifically about the topic, I mention here ruclips.net/video/k235Um3q1mg/видео.htmlsi=8l4_KYdZp5R3Yo0t&t=213 You can then forward the user on a path according to the value of that variable. And as a fallback if the language path is not defined you can just send it to the english path. Hope that helps :)
it was really useful to me, thank you Gregor
Glad to hear, thanks!
Since that video I already learned some new things about handling multi-language assistants. Will make a new video again some time soon :)
@@GregSchaf Awesome, i'll have a look
Nice one brother
I’ve been having issues with this same bro
Really nice solution of using Response AI instead of message.
It will just need thorough prompting
Thanks
Yes that's true :)
@@GregSchaf initially thought I was the only one having this language barrier issue but phew, seems a lot of us had the same issue.
Also if you don’t mind maybe we can connect
I’m always having crazy ideas to practice myself but seems a lot of people aren’t there yet so , I don’t know if we are able to connect
@@McFeeTakeout Sure send me a message over on X x.com/gregorschafroth :)
Nice video!
some feedback: could've done it in 10 mins. I assume people coming on here to see if we can make multi lingual bots are mostly people who already know the steps you spent quite a lot of time explaining. either way thanks for making a clear video to follow nonetheless!
Thanks for the feedback!
I do intentionally make these videos suitable for beginners as well.
However in the future I will probably try to structure my videos in a way that the beginner part can be skipped more easily, so those who don't need that can more easily skip it.
Thanks again for letting me know!
@@GregSchaf thanks man! Keep it going!
I'm building an assitant for a real estate business that offers the website in 3 languages, this was really helpful but I was thinking of making the chatbot itself 3 times the same in the languages it offers and then just at the beginning the client would need to choose in what language they speak. Do you think this will be to expensive in terms of tokens or is this to chaotic? Anyways thanks for the vid!
This solution works well if you limit the assistant to only 3 languages and it won't cause additional token usage. I also did this in the beginning.
You can consider not allowing any free input before the language is selected, so that the bot does not get confused.
Just consider that this approach leads to a lot of duplication (you need to do everything 3 times)
nice
Thanks!
nice video brother!
I did it differently, created a system in English then copying pasted it twice for two other languages, so I have three pathways in different languages with some differences. What should I do if it jumps from one intent to another? Let’s say I asked question is in english but he goes to the russian pathway
I actually switched my approach a bit. More recently I use an AI prompt to determine the language of the users last message and then send them on a path accordingly.
While the video is not specifically about the topic, I mention here ruclips.net/video/k235Um3q1mg/видео.htmlsi=8l4_KYdZp5R3Yo0t&t=213
You can then forward the user on a path according to the value of that variable. And as a fallback if the language path is not defined you can just send it to the english path.
Hope that helps :)
@ thanks brother, your content deserves much more attention. I’m amazed how people recently watch a lot of garbage
@@magardr2 Thanks for the kind words 😊
Nice video
Thank you :)