[go: up one dir, main page]
Scribd
Upload
14 views5 pages

Introduction To Kernel Memory

Kernel Memory is a multi-model AI service designed for efficient dataset indexing, supporting various features like RAG and custom semantic memory processing. It can be deployed as a Web Service, Docker Container, or plugin for various platforms, and operates effectively in serverless mode. The document also contrasts Kernel Memory with Semantic Memory, highlighting its .NET codebase and broader compatibility across tools and languages.

Uploaded by

aipcd3311
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
14 views5 pages

Introduction To Kernel Memory

Kernel Memory is a multi-model AI service designed for efficient dataset indexing, supporting various features like RAG and custom semantic memory processing. It can be deployed as a Web Service, Docker Container, or plugin for various platforms, and operates effectively in serverless mode. The document also contrasts Kernel Memory with Semantic Memory, highlighting its .NET codebase and broader compatibility across tools and languages.

Uploaded by

aipcd3311
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 5

Introduction to Kernel Memory

• Multi-model AI service for


efficient indexing of datasets
through hybrid pipelines.
• Support for RAG, synthetic
memory, prompt
engineering, and custom
semantic memory
processing.
• Available as a Web Service,
Docker Container, plugin for
ChatGPT/Copilot/Semantic
Kernel, and .NET library.
Difference between Kernel Memory and Semantic
Memory

Kernel Memory Semantic Memory


• Provides features such as • Library for C#, Python,
storing files, extracting and Java.
text from files, secure • Wraps direct calls to DBs
data etc. and supports vector
• Codebase is entirely search.
in .NET • Part of Semantic Kernel
• Can be used from any project.
tool, language, platform.
Kernel Memory in Serverless Mode
• Kernel Memory works and
scales best when running
as a Web Service.
• However, we can use it in
serverless mode.
• By default, this is volatile
and keeps all data only in
memory.
Using Kernel Memory Service
• You can run your code locally inside your process, or
remotely through an asynchronous service.
• Deploy Kernel Memory as a service, plugging in default
handlers, using non-blocking processes etc.
• Deploy Kernel Memory as a Service if you’re:
• Importing Data and sending queries to your web service
• App is written in another language
• Define custom pipelines mixing multiple languages
• Importing big documents without blocking UI.
• Running memory imports independently, supporting failures
and retry logic.
Demo
Running Kernel Memory in Serverless Mode and as a Web Service

You might also like