😊😊😊

Interesting demonstration of capabilities. However, didnt understand why we created a group with 2 functions within, and WE wrote the logic of mapping the LLM-discovered-intent to the actual function-to-be-called! Wouldnt it be possible to have 2 (lambda) functions that each performs ONE separate task and LLM discovers which (lambda) function to call, and what parameters to provide?

great video

What a great technical data streams detailed overview! Thank you.

I😅

Thank you ! It was really helpful!

where is the code?

what does the 1536 represent, where did you get that?

Hey, thanks for that video! What is the difference between Agent and Runtime? E.g., why not use BedrockAgentClient?

can i get the code ??

Great video! Thanks!

59:38 where is the link to the utility?

can i directly get a schema without manual work using langchain

Thanks for this informative video. The presentation is excellent.

I see a lot of value in this tool for my company. I will reach out to you guys to help structure a robust document processing architecture.

awesome 🤓

It’s so awesome that Amazon provides tools like this for free! Thanks AWS Team!!!

Sorry but this is not an intro to getting started on genAI with sagemaker. A better title would have been "How to use Hugging Face On Sagemaker". Personally i feel it has far too complex topics to explain to someone new trying to understand how to use sagemaker for genai workloads.

When will OpenAI models be available on Sagemaker?

AWS is dumbed and fucked....created one junk one after another...looks like these guys have ran out of innovation...all these folks are getting free salary by creating all junk

0:10

Honestly what a useless tool just has bunch of UI to do drag and drop. ideally to build complex solutions you would require many agents. This can only solve rag types of systems a typical Q&A system.

You're missing "import datetime" in the Lambda function code

Great job. Loved this explanation of Agents. Thanks!

MORE THAN REALLY GOOD! THX

Note: You also need to add permissions to your user to not get errors in VS Aws explorer IAM -> Users -> MyUser >Add permissions

Can the model take the function output and build a response based upon it? E.g if you was to ask what time was it 2 hours ago - can it get the time from the function and perform its own logic on how to respond to the user? Or does it just return anything from the lambda exactly?

Ccc

Can I get the deck without all the click tracking?

Why are we calling it serverless as opposed to autoscalling?

Thanks for the details. Why do we use serverless term where it is just autoscaling?

This tutorial is a good general overview of SageMaker for those who already have quite a lot of experience in ML. But it is definitely not suitable for beginners. The first part was easy to follow but the second part was more confusing.

`InvokeModelCommand` doesn't exist anymore and there's absolutely nothing in the docs that tells us what replaced it. Can you let us know how it's done, been lost in pages and pages of docs that have revealed absolutely nothing. Aside: always have this problem with AWS SDKs. Would feel bad complaining but this isn't some tiny FOSS project.

Good one

What is Cut Over ?

Great job. Very easy to follow!

Excellent plain English explanations, and a real live demonstration, instead of pre-recorded cheating videos. Excellent!

I'm a manager for the team responsible for all of my company's GenAi features. I'll definitely be asking everyone on my team to watch this video and any others related to this. Looking forward to seeing more vids like this one.

How to select OpenAI models like gpt4?

Thank you. How do we get the Falcon Tokenizer?

Awesome explanation !

Amazing

where are access keys defined?

where can I find the definetion of these client.ConnectedAsync += Client_ConnectedAsync; client.DisconnectedAsync += Client_ConnectedAsync; client.ApplicationMessageProcessedAsync += Client_ApplicationMessageProcessedAsync; var brokerSettings = GetBrokerSettings(); and also Task<IManagedMqttClient> GetClient() { return clientHolder.Task; } Task Severity Code Description Project File Line Suppression State Details Error CS1061 'AsyncLazy<IManagedMqttClient>' does not contain a definition for 'Task' and no accessible extension method 'Task' accepting a first argument of type 'AsyncLazy<IManagedMqttClient>' could be found (are you missing a using directive or an assembly reference?) FloorDetectonMqttApp1 C:\Users\alaa.alnasef\Documents\projects\visualStudio\FloorDetectonMqttApp\FloorDetectonMqttApp\Program.cs 26 Active could you include the full project for noobs like us?

Thank you -- it is very useful and helpful !!

What about a demo using multiple agents, multiple llm, langchain and langsmith to do tracing?

Can I get the lab manual please?

Really insightful

Mike speaks very fast but he uses very simple english so any non-native speaker can easily understand him. Thanks Mike!