Видео

How can I modify the environment if I am using UI - I get error due to some library not found

the code is not present in discord

Explained beautifully.

I think the code is not on the Discord. Can't find it! Only can find the link to TruLens repo.

Excellent video and demo

i dont see Multi-Agent

@MG I have deployed my Azure Open AI on web app for 200 users where I have Customized the domain. Will this same process help me to log user prompt?? Do I need to use Custom domain as endpoint or I can use default endpoint from Azure Open AI service.

Great information and presentation. Thanks!

Can it be used for other models?

Not working. Seems like this tutorial is abandoned.

it shows insufficient data for pinecone

Can you suggest any opensource ai llm model application for practicing the loadtesting using jmeter.

how to add custom metadata to azure ai search

Excellent tutorial.Please make One video for Azure open AI and azure AI with practical explanation .Also need tutorial work on google cloud for Generative AI

@MG I can’t find a reference in Discord. Did you post it?

Amazing bro! 💙

46:00 I have run the bicep-ado-deploy-infra.yml file but the Prod RG didn’t get created for me. Why is that?

Useful Information. Thanks

I tried using hugging face embeddings with pinecone but it's giving me an error, I couldn't troubleshoot it.

What happen when you try to Anonimiz specific data like a patient ID. Can you specify what data do you want to aninimze?

Super useful Moe 🙌 Great content

How is this different from langsmith and which would you recommend for production?

Wow your chanel is underrated! One question, could you please shortly describe what key components you would suggest to use in combination with chatgpt-4o-mini to categorize a request, collect some data (based on what type of category it is)? Currently I’m using only instructions, but if you have detailed steps chatgpt should follow + different data he should collect, they are getting huge! I was thinking about vector database, like in your videos, but can’t think about how to handle the category steps correctly (without forgetting something, because it only got „chunks“) & how to categorize the request. Any thoughts are highly appreciated! I can only find „how to collect data“ and „how to use vector database for knowledge retrieval“ but not everything combined: categorizing the request, follow multi steps instructions based on that & collect data step by step. (By the way I’m using azure atm)

Another wonderful video. Thank you.

Really appreciate for great content. I have one question may you like to create a video on that. Is categorizing the user question in the first steps (using a prompt to recognize) is an efficient action? specially when you use your company data

please make video on how to mock databricks services like delta live tables and all, for unit testing purpose. in aws we have moto library do we have something in databricks?

What if the PII isn't of a known format? For example if we're dealing with a patient report we need to mask records accordingly i.e if BP is higher than 120mmHg it should say high BP instead of the actual metrics.

looks pydantic even easier than json_format , new features offereed by OpenAI need to write so many details in json schema which is pain.

hi @MG can you please let me know why are we using azure devops as a tool to communicate with Azure ML studio? can't we create this type of pipelines in ML studio?

I edited host file to connect with VPN. But jupyter kernel not connecting with notebook

wonderful playlist. Thanks for this!

Thanks !!!

Which city is that! looks beautiful!

please guide which tool is used by Azure machine learning for model experimentation right now, we are not using Azure machine learning cloud we have our own on-premise solution where we are using mlflow for this process but im eager to know that , which tool they are using for that any link for this knowledge would be very helpful .

Thank you for the very detailed explanation about routing. This is exactly what we do here at Plurally, and we also support more than 2 models! We are currently in an early access stage, but to anyone looking for such a solution or simply want to try it out - reach out to us (we are very responsive), would love to hear about your specific use cases!

Bonjour

do you need to use openapi everywhere instead of using llama 3.1? or even better groq?

Hi! How can i summarize my whole graph ,it is not working using chain.invoke as i asked to summarize the graph or tried multiple user queries for summarization

Is it possible to get the code of those templates or any flow we create? For instance, I'm interested in the code of a memory chatbot

Thanks alot. Getting this error when I try to run the LLM bit. I tried another LLM and still getting same error: NotImplementedError: Unsupported message type: <class 'dict'>

Best ever! Would like to see a combination of semantic search and RAG. :D

stupid

How can I install my custom python package on this spark cluster. The scenario would be I am working on editable python function and want to run spark jobs interactively.

Hello MG, I got this errormessage "---------------------------------------------------------------- TypeError Traceback (most recent call last) Cell In[38], line 26 ------------------ TypeError: azureml.train.automl.automlconfig.AutoMLConfig.__init__() got multiple values for keyword argument 'primary_metric'" I will appreciate your kind assistance.

Thanks for your detailed video on RouteLLM. You are my go-to RUclips channel to implement and learn new techniques in the AI space.

Can you please do a tutorial on adding exogenous variables to the model?

Great explanation 👍

Love the explanation

Good one

no description about how to do the install or how to use the software... any of that would have been helpful