วีดีโอ

Hi please make a video..

Sir please make a video

Hi...can you send the code files used in each of these videos?

Is this same as integrated vectorization available in Azure AI studio?

Ur English is so good Hope you get Success Soon

I waiting for next video sir.

Hi sir In new version of semantic kernel plugin planner do we need config.json,skprompt.txt ?

Hi sir I have followed your video everything is working fine except the create operation. Can you share or update the final source codein your github.

Getting error message "Microsoft.SemanticKernel.KernelException: 'The function identifier is empty'" on var summarize = kernel.CreateFunctionFromPrompt(prompt, executionSettings: new OpenAIPromptExecutionSettings { MaxTokens = 100 }, functionName: "summarize");

thanks

The better way to access those files is to setup build action as *Copy to Output Directory - If Newer* in properties of file. Then you can access them like "Plugins/FunPlugIn"

why so slow ?

the using statement is not correct it wont work. you need a different library using Microsoft.SemanticKernel.Connectors.AzureOpenAI; this ruined my whole day

hi i learn semantic kernel from your videos. i like as you explain in your videos. you did a great job. Thank you for explaining in a such a way.

Are you taking this code from the github notebooks?

Where's the code demo?

Only "Microsoft.KernelMemory.Core" package is fine to implement this. May I know the reason of installing "Microsoft.SemanticKernel" package?

Thanks for the Interesting Playlist ..I wanted to Learn exact same thing but was finding it difficult in the Documentations.

i just started with Semantic kernel and found these videos really helpful. Thanks for creating simple and to the point videos.

Great and to the point!

Your videos have been a lifesaver. I'm a total beginner to C# trying to learn semantic kernel, and these have been incredibly helpful. Thanks Supreet!

Don't know if you've rotated your API keys already, but if not you should or you should delete the resource because you showed the API key briefly at the 5 minute mark

Nice

Totally enjoying your series of AI videos.

Awesome. Where can we get a copy of the code?

Great series, appreciated!

cool, definitely she hates Donna :-)

Thank you so much for the video. Although, i have a problem with the answer being cut off mid sentence. Is that a token issue, or is it the fact that pipeline to OpenAi is not SignalR?. Hope you can help. Thanks

What is the correct/difference between an config.json like { "schema": 1, "type": "completion", "description": "Find the city name from a given prompt.", "completion": { "max_tokens": 512, "temperature": 0.8, "top_p": 0.0, "presence_penalty": 0.0, "frequency_penalty": 0.0 }, "input": { "parameters": [ { "name": "input", "description": "Text from the user to get the city name from.", "defaultValue": "" } ] } } And the one you have, why do I sometimes see execution_settings and other times completions?

Running it twice give always same joke. Why? Temperature is 0.9 but stil....

Is Kernel memory internally using LLM or LLM is nowhere in the picture here. trying to understand if after retrieving the data from PDF, does it automatically pass it to LLM ?

THis bs doesn't work. System.NotSupportedException: Serialization and deserialization of 'System.Type' instances is not supported. Path: $.Function.Metadata.Parameters.ParameterType.

Thanks a ton for this easy to understand tutorial Supreet! I was struggling with env part and it was helpful. However, the code fails and ImportDocumentAsync saying "pipeline start failed". Below is the error message: Microsoft.KernelMemory.Pipeline.BaseOrchestrator[0] Pipeline start failed Azure.RequestFailedException: Service request failed. Status: 303 (See Other) Hope I am missing something. Is the component trying to reach Azure Servers for any validation? I understand serverless meaning "everything happens in local". Pls correct me if I am wrong.

Awesome 🎉, waiting for source code walk-through and I will try to explore the same using Malayalam language. Thanks for the demo

Impressive

Hi. Thanks for the awesome videos. is there a github repo for this code ? thank you.

The SK team on discord is extremely proactive and while I was recording the video and uploading it here, they also logged this bug/ feature request to be solved in their GitHub. If you are seeing this video after a few weeks of posting it you can track the status of the issue here: github.com/microsoft/semantic-kernel/issues/4797 p.s. Forgot mentioning that I was using semantic kernel 1.2.0 stable release when I encountered these issues.

Keep up the good work Supreet :)

Thanks for the (p)review ! This is very interesting. Just thought about, running that on a server you can load into memory on start up and dont need a database.