error when configuring open Api : One or more fields contain incorrect values: Invalid value of the Web service

Great content. if u can kindly show us how we can add data source from online azure db or dynamics db if possible and how can we use this cognitive search through APIs. Thank you

Hi, thank you so much for this. Can I use a database that has thousands of pdf documents?

Is it possible to get pie charts/bar charts using the chatbot? Basically, it should query data from SQL and plot graphs

Hello I have a doubt if I am using RBAC in my azure AI search how can I Create a connection? below code we have to pass Key but if I am using RBAC how can I create Connection acs = AzureSearch( azure_search_endpoint=endpoint, azure_search_key=azureaikey, index_name=index_name, embedding_function=embeddings.embed_query, )

May I know how did you manage to add a custom function to assistant playground? Thanks in advance!

Very interesting!!❤

This is INSANE.

hey can anyone help me with this error ERROR training/train_test.py - TypeError: an integer is required (got type by... ERROR training/train_test.py - TypeError: an integer is required (got type by...

Great Video and congrats on hitting 10k Subscribers, keep going and soon hope you get to 100k

Do you have a example with CI/CD with docker? Or, when I need update my code, I onlye need update my Container Registry? How I do this?

This was incredibly helpful. Great tutorial.

I have a csv file with text data, the data set has 3 columns. One is the main title, then the sub title and third point related to the title. I want to set a QnA bot on it. Basically the bot should be able to handle any queries regarding the dataset whether it is a summary of the points mentioned in it or a complete retreival of all the points. The answers should always be detailed and also gpt should use its own knowledge to enhance on based of the retreived data. I tried RAG but rag just provides me information on the chunks retreived but not able to give summarisation or is not able to give all the points from the sub topic. What is the best way to implement such QnA on such dataset. It only has text data. Please any help would be appreciated. I am really stuck on this. I tried asking this in your discord channel as well

Hi, I tried to consume the Azure AutoML model into the power BI. I got the following error after adding the sample values to the fields. "expression.error: we cannot convert the value "[function]" to type function."

You are awesome MG,unlike DBRX witch doesn't support Arabic language, Any suggestions on open source that supported Arabic and can be deploy locally on-prim? Thanks MG, keep it up

Hey, where can I get one of those jumpers?

How did you connect your Web app with your container registry?

Spelling mistake in your thumbnail… fyi

Hi, excellent job!! I am learning a lot with you.. I would like to know where can I find this dataset that you used in AutoML? I tried to find the same dataset in Kaggle and I did not find it. Could you please share this dataset ?

Hi Mohammed. Could you do the same video of this using LangChain please and also update the video about using Presidio and Faker library for data anonymization? That video showed the LangChain notebook itself which showed the example of polish numbers in both presidio and faker library but it would be really cool if you could show us how can we also implement a wrapper around things that aren't available. For instance, lets say polish numbers werent available in the Faker library.

this is good, but please give the github code access so that it is easy for users to apply it!

"mg, is all you need". thanks for the awesome content.

Thanks. super content

Super content. Thanks

Thanks, super content.

Thanks, Super content.

Super content. Thanks

super content MG. Thanks for making this content on MLOPS.

Thanks for the video! What should we do if we want to add new texts to our existing vector DB? Should we reprocess all the steps from the very begining?

Nice video bro keep it up

thanks for making my ML journey much funner and better

After spending 15 days on search. Finally got sea. As you said in intro. Can I have that code please? That is so amazing if that works for me. please.....................................!

Thanks MG, looking forward to new series. Really like your way of explaining. Thanks

Can assistant API's be used with prompt flow? if yes, how?

MG, I'm so proud of you as an Iranian!

Hi MG, great video..!! I ran the WF and I am gettin this error on NB01 "Load Vector Store" cell: "Request too large for text-embedding-ada-002 in organization oasdcdefghijklmn on tokens per min (TPM): Limit 1000000, Requested 1128920. The input or output tokens must be reduced in order to run successfully.". Do you know how can we reduce the amount of TPM?

Hi MG, would you have an idea if it's safe to connect langchain to databricks tables containing client's data in terms of data security.

MG, you (both) look pretty knowledgeable. Don't waste time on editing. Instead give out more videos

Worst first should have shown github actions

Nice video. I saw you add some pip installation with run pip install librairie I would like to use my own docker image base on microsoft image like you did, but I would like to install from a conda file. Do you have any idea how you would do it?

Could you kindly include the notebook link in the description, please?

only english?

Good one. From your video, I am learning something new everyday ✨

Can it convert voice to voice?

can you do a video on how to setup red teaming chat engine in AZURE Machine learning studio.

Hello sir, can you help me with this: AGENTS TERMINATE Agent Messages (3 messages) | 1 sec userproxy ( to medical_center ) Hey medical_center ( to userproxy ) Hello! How can I assist you with your appointment today? userproxy ( to medical_center ) TERMINATE every time the user proxy returning terminate, can I hide this one?

I am unable to find the reference links in Discord. Any help here?

I have been facing an issue, whenever i try to create a datadrift monitor, the image build dosen't happen, and I keep getting this error AzureMLCompute job failed OrchestrateJobError: Failed to execute command group with error Docker container 'containername' failed with status code `1`. Service 'SECRETS_CAPABILITY' returned capability start response with code: Response { code: "500", error: Some(Error { code: "500", message: "load config failed with error Response error: status: 403 Forbidden, content: <html> <head><title>403 Forbidden</title></head> <body> <center><h1>403 Forbidden</h1></center> <hr><center>nginx</center> </body> </html> ", target: "secrets-capability", node_info: None, category: SystemError, error_details: [], inner_error: None }) } Someone please help me out

Good one ✨

Loved it🎉 but may i know can i get the confidence score for gpt 4 response either the average for all the generated tokens or for each tokens?