Good description and summary of agents. Quick and to the point.
@jeffreyz2196
2 күн бұрын
Thank you for the tutorial. On my computer, I have to change os.getenv() to os.environ.get() to make it work. I am not sure why.
@pedromsb6830
4 күн бұрын
No longer up?
@ultraetf
4 күн бұрын
Great video! Do you mind sharing the source code used? Thanks.
@GrahamFMcElearney
8 күн бұрын
Thanks Aaron this is ace. took me a few goes to figure out how to lpad my api key but figured it out - it's quite magical when you get it going! Thanks again!
@lenonfernandes8584
9 күн бұрын
I really enjoy the way you teach and explain things!
@lenonfernandes8584
12 күн бұрын
Can you teach how to do the same with Gemini?
@abdullahmahir8478
13 күн бұрын
error : No module named 'google' but i downloaded all the requirements. can i know the reason?
@abdullahmahir8478
13 күн бұрын
bro, u nailed it. for past 3 days i'm trying to build a chatbot for myself. Finally i saw this video ❤🔥
@TheMisiekMisiek
16 күн бұрын
great.
@Eric-qz5hz
20 күн бұрын
WOW great video thanks alot!
@Calvinshukla
26 күн бұрын
how am i suppose to access the history?
@vietdihoc
Ай бұрын
How many requests can you make for each key?
@harshrana3012
7 күн бұрын
1500 request as of now
@rryann088
6 күн бұрын
@@harshrana3012 so its free to use and i can get another key if i exceed 1500?
@poojasundar2115
Ай бұрын
Actually, the pretty clear tutorial I've ever seen neat explanation, But I have a doubt What should we do when we prompted the model with pdf? can you make a video for that? and also integrated with UI design?
@vietdihoc
Ай бұрын
huh... Where is the "Whisper-V2" version on your thumbnail screen?
@aarondunn-zt7ev
Ай бұрын
V3 is the most recent version of the Whisper model, and that’s what we are using in this demo. When I specify the model name as ‘whisper-1’ in the API call, it refers to this latest version, V3.
@vietdihoc
Ай бұрын
@@aarondunn-zt7ev thank you for answer
@LanningRon
Ай бұрын
Great tutorial! It was clear and easily reproducible. Thank you!
@aarondunn-zt7ev
Ай бұрын
Thanks you for the comment! I’m glad the video was helpful. I plan to make more so let me know what you would like to see.
@ewg-dasa
Ай бұрын
Thank you sir you helped me a lot!
@aarondunn-zt7ev
Ай бұрын
Thanks for watching. Happy to help! Let me know if there are any specific topics you would like to see covered in future videos.
@Its_Alan_Paul
Ай бұрын
Thankyou so much for this video. Please do make more. Really simple and applicable.
@Its_Alan_Paul
Ай бұрын
Is there something wrong wit Audio ?
@Its_Alan_Paul
Ай бұрын
Nah that was my Laptop.
@siggebjornsson
Ай бұрын
don't you have to hide the keys in the config file?
@rajagurur1978
Ай бұрын
I was struck in Saving the chat history. It helped me sir... thanks a lot...you just got a new subscriber ✨😌
@myquestforknowledge
Ай бұрын
Nice video, crisp and concise. Thanks and you've got a new subscriber.
@aarondunn-zt7ev
Ай бұрын
Thank you. I’m glad you enjoyed the video!
@LoadupBGM
Ай бұрын
Good am a flask developer. Let me try it out will give you more feedback. Great
@ssbookreview6600
2 ай бұрын
Even i tried to make something like this … I also read quarterly results management transcript
@ashimov1970
2 ай бұрын
The most awesome, concise, neat, clean and up-to-date content on how to leverage Gemini API
@aarondunn-zt7ev
2 ай бұрын
Thank you so much for your comment! I’m happy you found the video useful.
@karanshah909
2 ай бұрын
Great explanation and detailed implementation 🙌
@aarondunn-zt7ev
2 ай бұрын
Thank you. I appreciate your comment! Let me know what other types of content you would like to see.
@vibingwithgourav
2 ай бұрын
Thank you Aaron ! It so much knowledgable content you've shared with us.
@aarondunn-zt7ev
2 ай бұрын
Thank you very much! I appreciate the comment and glad you found the video useful.
@enmingwang6332
2 ай бұрын
As always, very clear explanation and demo! Really enjoyed your informative lecture, greatly appreciated 👍👍
@aarondunn-zt7ev
2 ай бұрын
Thank you! I’m happy you found the video useful. There will be many more coming.
@enmingwang6332
2 ай бұрын
It is such a beautiful tutorial on function calling👍👍
@aarondunn-zt7ev
2 ай бұрын
Thanks a lot 😊 I appreciate your comment!
@scamorza4786
2 ай бұрын
Thank you so much for the video!! I don't know how to code and I learned how to create inputs thanks to you!
@aarondunn-zt7ev
2 ай бұрын
That’s great! Learning to code is challenging but very rewarding. I hope you will find my future videos helpful as well 😊
@scpresearcherssite1054
2 ай бұрын
going to try it.
@havearelax31401
2 ай бұрын
You are great man cheers
@aarondunn-zt7ev
2 ай бұрын
Thanks! I appreciate the comment. Let me know what other content you would like to see.
@havearelax31401
2 ай бұрын
@@aarondunn-zt7ev It will be great if you use GEMNI API and made a chatbot, which will use custom datasheet from me.
@tankieslayer6927
2 ай бұрын
Is this the latest AGI cope?
@aarondunn-zt7ev
2 ай бұрын
Not at all. This video is about the capabilities of AI Agents today and where they are trending in the near future.
@amazingvideos4824
2 ай бұрын
Please share the github code?
@enmingwang6332
3 ай бұрын
Great tutorial, much appreciated! 👍👍
@enmingwang6332
3 ай бұрын
This is absolutely fantastic, the end of the conversation with the avatar was so funny😂😂! Is it possible to let the bot to be able to evaluate and correct student's pronunciation?
@aarondunn-zt7ev
3 ай бұрын
Thanks for the comment. I appreciate it! I made this video about a year ago and the capabilities of LLMs have skyrocketed since then in many different ways. Gemini AI for example can take in audio and part of its input so it’s possible that it could provide pronunciation assistance. I will do some testing on this in the near future and make an updated video.
@karkids
3 ай бұрын
What google cloud project for API key
@aarondunn-zt7ev
3 ай бұрын
You would select whatever project you want your Gemini code associated with. If you don’t have any Google Cloud projects then you should be able to select a Default option. Let me know if this doesn’t work and I’ll take a closer look.
@karkids
2 ай бұрын
I choose the generative language client and there is a key error every time
@enmingwang6332
3 ай бұрын
Great tutorial, clear and concise👍👍
@aarondunn-zt7ev
3 ай бұрын
Thank you. I’m glad it was helpful!
@MrHanil1
3 ай бұрын
Great video! Thank you!
@aarondunn-zt7ev
3 ай бұрын
Thanks. I appreciate the comment!
@Maxi-789-id
3 ай бұрын
Hi, I am using Autoresponder for Whatsapp together with Gemini AI. Could you please tell me if there's anyway using Gemini to understand and respond to pictures/voice notes/videos sent on Whatsapp?
@judyjudy-jc2ot
3 ай бұрын
Good video, thanks for sharing
@aarondunn-zt7ev
3 ай бұрын
Thanks for watching! Let me know if there are any other topics you would like to see.
@techwithsibro
3 ай бұрын
Thanks a lot!
@aarondunn-zt7ev
3 ай бұрын
You’re welcome! Let me know if there is any specific content that you would be interested in seeing.
@NotAvailableForCommunication
3 ай бұрын
Helpful❤
@AlbertoPhrilance
3 ай бұрын
Great tutorial. Thank you
@aarondunn-zt7ev
3 ай бұрын
I’m glad you enjoyed it. Thanks for the comment.
@mohamedashiq8248
3 ай бұрын
Hi can we create a customized data and it should answer only for customized data not should answer all the data
@iftekharansari5558
3 ай бұрын
In the model give a system instruction like, (system instruction= "Give response only from the file uploaded and not from outside the pdf or csv file provided" ) . This will limit it to answer only from the knowledge base given, feel free to customise your system instructions.
@aarondunn-zt7ev
3 ай бұрын
There are 2 approaches you can take. One is to just put all your data inside the prompt. This is possible nowadays even with big datasets as models now have huge context windows (up to 2 million tokens for Gemini 1.5 Pro). However, adding too much data to the prompt can be costly and even result in lower quality answers. The other approach is RAG (Retrieval Augmented Generation) which extracts smaller chunks of your dataset that are similar to your input query / question and then uses that data to produce an answer. This is much more efficient and when done properly may even result in better outputs. With either method, you would include in the prompt an instruction to only consider the data you provided when generating the response. This doesn’t work 100% of the time but overall it’s pretty reliable. I put out a video a little while back that demonstrated RAG for a chatbot and how to restrict the model to the data you provide. Check out the video here: kzitem.info/news/bejne/xKajmGyefqh4dHYsi=qAX6wM0ytI_VSu7v
@EchoesofHeartbreak
3 ай бұрын
Can you make this gemini able to recognize images, create titles and tags and subjects (metadata), thanks
@aarondunn-zt7ev
3 ай бұрын
Yes, definitely! Gemini 1.5 is multimodal and can take images, audio and video in the prompt with text. I am working on a video on Gemini for vision / images right now and will let you know when it’s posted.
@EchoesofHeartbreak
3 ай бұрын
@@aarondunn-zt7ev okay, ty
@aarondunn-zt7ev
3 ай бұрын
I just uploaded my video on Gemini for vision. Check it out here: kzitem.info/news/bejne/uZmDyYJ4k5OodIosi=6p93NAlB6o9DePnz
@rustcartoonmovies302
3 ай бұрын
tq sir it was good help to bulid my mini project for college
@mohamedmosad1117
3 ай бұрын
great video , thanks for this video
@aarondunn-zt7ev
3 ай бұрын
Thanks. Happy to hear it was useful.
@parthmahadik6038
4 ай бұрын
How can we feed it our customised data so that it behaves based on the data and response accordingly
@aarondunn-zt7ev
3 ай бұрын
There are 2 approaches you can take. One is to just put all your data inside the prompt. This is possible nowadays even with big datasets as models now have huge context windows (up to 2 million tokens for Gemini 1.5 Pro). However, adding too much data to the prompt can be costly and even result in lower quality answers. The other approach is RAG (Retrieval Augmented Generation) which extracts smaller chunks of your dataset that are similar to your input query / question and then uses that data to produce an answer. This is much more efficient and when done properly may even result in better outputs. With either method, you would include in the prompt an instruction to only consider the data you provided when generating the response. This doesn’t work 100% of the time but overall it’s pretty reliable. I put out a video a little while back that demonstrated RAG for a chatbot and how to restrict the model to the data you provide. Check out the video here: kzitem.info/news/bejne/xKajmGyefqh4dHYsi=qAX6wM0ytI_VSu7v
@tawanbaohlopet9034
4 ай бұрын
How do I add germini with my Facebook page?
@aarondunn-zt7ev
4 ай бұрын
I don’t have any experience creating Facebook apps, but I can look to do some more research on it. From what I’ve discovered so far, to add a Gemini-powered chatbot to your Facebook page, you'll need to integrate it using Facebook Messenger's API. This involves setting up a Facebook Developer account, creating a Facebook app, and configuring a webhook to handle messages. You'd then connect the Gemini API to process and respond to these messages. It would be an interesting project and video!
Пікірлер