1"use strict";(self.webpackChunkjohnnyreilly_com=self.webpackChunkjohnnyreilly_com||[]).push([["16912"],{43245(e,t,n){n.r(t),n.d(t,{assets:()=>l,contentTitle:()=>s,default:()=>m,frontMatter:()=>a,metadata:()=>r,toc:()=>c});var r=n(96983),i=n(74848),o=n(28453);let a={slug:"using-kernel-memory-to-chunk-documents-into-azure-ai-search",title:"Using Kernel Memory to Chunk Documents into Azure AI Search",authors:"johnnyreilly",date:new Date("2024-04-21T00:00:00.000Z"),image:"./title-image.png",tags:["azure","c#","asp.net","ai"],description:"To build RAG (Retrieval Augmented Generation) experiences, where LLMs can query documents, you need a strategy to chunk those documents. Kernel Memory supports this.",hide_table_of_contents:!1,atUri:"at://did:plc:yy3apqjlms24kso7ahn7lbmb/site.standard.document/3mr5bseiuna2b"},s,l={image:n(19779).A,authorsImageUrls:[void 0]},c=[];function u(e){let t={a:"a",img:"img",p:"p",...(0,o.R)(),...e.components};return(0,i.jsxs)(i.Fragment,{children:[(0,i.jsxs)(t.p,{children:["I've recently been working on building retrieval augmented generation (RAG) experiences into applications; building systems where large language models (LLMs) can query documents. To achieve this, we first need a strategy to chunk those documents and make them LLM-friendly. ",(0,i.jsx)(t.a,{href:"https://github.com/microsoft/kernel-memory",children:"Kernel Memory"}),", a sister project of ",(0,i.jsx)(t.a,{href:"https://github.com/microsoft/semantic-kernel",children:"Semantic Kernel"})," supports this."]}),"\n",(0,i.jsx)(t.p,{children:(0,i.jsx)(t.img,{alt:"title image reading "Using Kernel Memory to Chunk Documents into Azure AI Search" with the Azure Open AI / Azure AI Search logos",src:`https://res.cloudinary.com/priou/image/fetch/f_auto,q_auto,w_auto,dpr_auto/https://johnnyreilly.com${n(12138).A}`,width:"800",height:"450",loading:"eager",fetchpriority:"high"})})]})}function m(e={}){let{wrapper:t}={...(0,o.R)(),...e.components};return t?(0,i.jsx)(t,{...e,children:(0,i.jsx)(u,{...e})}):u(e)}},19779(e,t,n){n.d(t,{A:()=>r});let r=n.p+"assets/images/title-image-337c58e5e55f92f59a1d1db49366ec04.png"},12138(e,t,n){n.d(t,{A:()=>r});let r=n.p+"assets/images/title-image-337c58e5e55f92f59a1d1db49366ec04.png"},28453(e,t,n){n.d(t,{R:()=>a,x:()=>s});var r=n(96540);let i={},o=r.createContext(i);function a(e){let t=r.useContext(o);return r.useMemo(function(){return"function"==typeof e?e(t):{...t,...e}},[t,e])}function s(e){let t;return t=e.disableParentContext?"function"==typeof e.components?e.components(i):e.components||i:a(e.components),r.createElement(o.Provider,{value:t},e.children)}},96983(e){e.exports=JSON.parse('{"permalink":"/using-kernel-memory-to-chunk-documents-into-azure-ai-search","editUrl":"https://github.com/johnnyreilly/blog.johnnyreilly.com/edit/main/blog-website/blog/2024-04-21-using-kernel-memory-to-chunk-documents-into-azure-ai-search/index.md","source":"@site/blog/2024-04-21-using-kernel-memory-to-chunk-documents-into-azure-ai-search/index.md","title":"Using Kernel Memory to Chunk Documents into Azure AI Search","description":"To build RAG (Retrieval Augmented Generation) experiences, where LLMs can query documents, you need a strategy to chunk those documents. Kernel Memory supports this.","date":"2024-04-21T00:00:00.000Z","tags":[{"inline":false,"label":"Azure","permalink":"/tags/azure","description":"The Microsoft cloud platform."},{"inline":false,"label":"C#","permalink":"/tags/csharp","description":"The C# programming language."},{"inline":false,"label":"ASP.NET","permalink":"/tags/asp-net","description":"The web framework built by Microsoft."},{"inline":false,"label":"AI","permalink":"/tags/ai","description":"All things AI - Artificial Intelligence, Large Language Models and the like."}],"readingTime":16.47,"hasTruncateMarker":true,"authors":[{"name":"John Reilly","title":"OSS Engineer - TypeScript, Azure, React, Node.js, .NET","url":"https://johnnyreilly.com/about","imageURL":"https://johnnyreilly.com/img/profile-2025.jpg","key":"johnnyreilly","page":null}],"frontMatter":{"slug":"using-kernel-memory-to-chunk-documents-into-azure-ai-search","title":"Using Kernel Memory to Chunk Documents into Azure AI Search","authors":"johnnyreilly","date":"2024-04-21T00:00:00.000Z","image":"./title-image.png","tags":["azure","c#","as
1p.net","ai"],"description":"To build RAG (Retrieval Augmented Generation) experiences, where LLMs can query documents, you need a strategy to chunk those documents. Kernel Memory supports this.","hide_table_of_contents":false,"atUri":"at://did:plc:yy3apqjlms24kso7ahn7lbmb/site.standard.document/3mr5bseiuna2b"},"unlisted":false,"prevItem":{"title":"Large Language Models, Open API, View Models and the Backend for Frontend Pattern","permalink":"/large-language-models-view-models-backend-for-frontend"},"nextItem":{"title":"Overview of webpack, a JavaScript bundler","permalink":"/webpack-overview"}}')}}]);
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.