Getting started with Kernel Memory

Ғылым және технология

Kernel Memory is a multi-modal AI service that enables efficient indexing of datasets through custom data pipelines. It supports RAG, synthetic memory, prompt engineering, and custom semantic memory processing.
This video is a gentle introduction to Kernel Memory, and how we can run it in both Serverless and as a Web Service to index data, and use natural language queries to obtain answers from indexed data!
0:00 Introduction
1:22 Difference between Kernel Memory and Semantic Memory
2:46 Serverless mode
3:57 Kernel Memory Web Service
5:25 Demo - Running Kernel Memory in Serverless Mode
15:26 Demo - Running Kernel Memory in a Web Service
27:05 Wrap up
Get the code for this video: github.com/willvelida/kernel-memory-series/tree/main/IntroductionToKernelMemory
Learn more: microsoft.github.io/kernel-memory/
Connect with me!
Twitter: willvelida
GitHub: github.com/willvelida
Bluesky: bsky.app/profile/willvelida.bsky.social

Пікірлер: 14

  • @SilverLion567
    @SilverLion5674 күн бұрын

    Would definitely love to see more from this series. I have learned a lot, you are a great teacher. Could you do a video about combining vector databases, using embeddings, memory, and RAG with semantic kernel?

  • @crazygwancha6221
    @crazygwancha62217 күн бұрын

    Heyy great video here. Will we get more anytime soon ? THNX

  • @JaredWoodruff
    @JaredWoodruff2 ай бұрын

    Great video Will, Thanks for sharing 🙂

  • @willvelida

    @willvelida

    2 ай бұрын

    My pleasure! Thanks for watching 😊

  • @DeepikaAnand087
    @DeepikaAnand087Ай бұрын

    In this example you ask the question the memory so at that point only this document in what the memory aware of. right? And what algo does the memory use to figure out the answers? Is it just Semantic search or is it Hybrid search?

  • @daniduck4723
    @daniduck47232 ай бұрын

    Thanks!! 🎉

  • @willvelida

    @willvelida

    2 ай бұрын

    No worries :)

  • @kai-odie
    @kai-odie2 ай бұрын

    Great video! Would love to see an example of using persistent storage, something like Postgres. Either way, keep up the good work!

  • @willvelida

    @willvelida

    2 ай бұрын

    Thank you! Yeah this is definitely in the pipeline. Will let you know when it's done 😊

  • @omaralejandroibanez83
    @omaralejandroibanez835 күн бұрын

    Does anyone know how I can use km in an api? I ran some tests using this great example video but it still doesn't work for me

  • @natious100
    @natious1002 ай бұрын

    Greate video. Extremely helpful. I would love to see one using Azure OpenAI for the Serverless mode scenario

  • @willvelida

    @willvelida

    Ай бұрын

    Thanks for watching! I'll add it to the backlog 😊

  • @devgenesis6436
    @devgenesis64362 ай бұрын

    Grt video.. how can we change the kernal memeory web service settings which we have configured through powershell.. is there any file created for this

  • @FabioAngela
    @FabioAngela2 ай бұрын

    does it allows you to apply taks to uploaded documents? or custom schemes? e.g. imagine I want to import different kind of documents, like pdf but also emails, can I specify the type of document so that if I ask for email contents it search only into emails and not pdfs?