Видео

Hello ,thanks a lot for this video that helped me to understand some and the video is very helpful.🙌 excuse me I've 2 questions. real-time means that i get response streamed and instantly only ? or this docs will make Gpt remember the previously created response and continue on it [as how we are chatting with him, but i want to implement that inside my app ] because if i call "response.create" twice , he says that he doesn't know if I've asked him about something before or not

Sam be like: Mujhe Q toda😂

First 30 Seconds Must Watch😅🤪

Ok, so none of the examples worked so far, but the whole video is constantly interrupted by loud, stupid meme sounds and stickers. Who is this for? You’ve lost me mid-way, sorry.

Do you have this project available in github?

Great Content! 👏

This might be very useful..

First

Hi - I'm having issues installing the speaker package. In the error logs it says 'You need to install the latest version of Visual Studio including the "Desktop development with C++" workload' which I have done but it still doesn't work. Did you encounter anything like this? I am working in VS code

When python version of realtime Api comes

Appreciated best video

Great Explanation He deserve Subscribers and likes

Wowie I didn't know realtime API is than fun

Where is part 4 which calls OpenAI Model?

Where is code link

Informative 👍

is there a way to hook it up to a database on the cloud?

how is the way to do it with credentials

Perfect...would be good to see next video how we can do through the microphone

Why does Codestral show 'free trial' in the "Continue" plug-in panel?

good video. would be good to see next video and see how microphone can be used. it would be good to also see how to get RAG+voicebot

best one brother. please make next video as soon as possible

Is it possible to use this api for realtime transcribing tool in replacement of whisper api which is not really realtime?

Excellent Tutorial! what do you think, using openai build-in file search or using like others third party softwares like Pinecone ?

Since the API was released, I've been watching all the videos on RUclips about this topic and your channel is one of the best ones. Why not use Python too?

where is part 4?

Nice one! Clean explanation No BS... Quick free suggestions 1. Start video with the hook - API Talking Something funny or sarcastic (Can use to distribute as short content as well) 2. Use a drawing tool to explain the algo (To avoid up and down to explain the Code). 3. Use the drawn algo on the split with the code for a quick walk through 4. Plus keep the algo drawing of other video on which you built this so that a new user can see what exactly they missed

Awesome vid. You're a great teacher.

Very good video, thank you for sharing. Is it possible to make the assistant maintain the context of the conversation?

Struggled all day with this code and you uploaded this. Thanks a lot man!

Why so many people care about AI having real emotions? most of the same people asking that don't care if their fast food clerk has emotions or if their roofing contractor has emotions...

Cool Stuff!

Great Sir! Best video on o1 model

Hi, my use case is to create a python code based on the conditions which are available in the file. This file is uploaded to vector store but i am not getting the exact code from the ai after uploading file to vector store and updated the same to assistant. I have used the same code provided by you. Can you help me in this.

🦙🌳

Nice! so Mistral AI agent doesnt have a capability to download database as a pdf or docs?

man this is best tutorial i found on fast API in entirety of yt

which interface/python libraries you are using for this project?

that wasn't a pdf though...

sdr should look for another job then?

Checkout Gridscpace's offerings here www.gridspace.com/emotion

Clearly powerful but do you guys also feel that OpenAI is slow at responding ? These are simple questions though, what about complex join queries and correlations that need to be done. Is there any way for OpenAI to actually do this without having to give it too much information ? Which would defeat the point

This creates new vector stores and files every time i run the script. How can i modify it to make it use one specific vector store and not create a new one every time?

This war will gonna be fierce soon i guess...nice vid

That's great news when you think that Google search UI model has not been seriously challenged since 26 years 🎉 good video 👍

Is there a way to constantly update the database with new data? or we have to create a new store with the updated information?

can you please provide the code for your application?

What about pictures in files? Is it a good idea to also store pictures in the files or can't the vector storage "read" the pictures?

brother your english accent is super.. plz make tutorial for this also :)

thanks quick question do you have any video for beginners of how to run mistral nemo please? thars from hf