1"use strict";(globalThis.webpackChunkmy_website=globalThis.webpackChunkmy_website||[]).push([[15893],{89302(e,t,a){a.r(t),a.d(t,{assets:()=>l,contentTitle:()=>s,default:()=>d,frontMatter:()=>r,metadata:()=>i,toc:()=>g});var i=a(42158),n=a(74848),o=a(28453);const r={title:"The ChatGPT Retrieval Plugin - Weaviate as a Long-term Memory Store for Generative AI",slug:"weaviate-retrieval-plugin",authors:"zain",date:new Date("2023-04-04T00:00:00.000Z"),image:"./img/hero.png",tags:["integrations"],description:"Learn how you can connect Weaviate to ChatGPT to generate customized responses."},s=void 0,l={image:a(15498).A,authorsImageUrls:[void 0]},g=[];function h(e){const t={a:"a",admonition:"admonition",img:"img",p:"p",...(0,o.R)(),...e.components};return(0,n.jsxs)(n.Fragment,{children:[(0,n.jsx)(t.p,{children:(0,n.jsx)(t.img,{alt:"Weaviate Retrieval Plugin",src:a(8647).A+"",width:"1200",height:"630"})}),"\n",(0,n.jsx)(t.admonition,{title:"Historical post: the ChatGPT plugins program is retired",type:"caution",children:(0,n.jsxs)(t.p,{children:["Published 2023-04-04, during the closed alpha for ChatGPT plugins. OpenAI retired the program in 2024, so the Weaviate Retrieval Plugin and the install flow in the screenshots below no longer exist. The idea the post describes, giving a chat model long-term memory by attaching a vector database, became standard ",(0,n.jsx)(t.a,{href:"/blog/introduction-to-rag",children:"RAG"}),", and the equivalent integration today is a ",(0,n.jsx)(t.a,{href:"https://docs.weaviate.io/weaviate/configuration/mcp-server",children:"Model Context Protocol (MCP)"})," server. See ",(0,n.jsx)(t.a,{href:"/blog/coding-assistant-weaviate-mcp",children:"Build a Coding Assistant with Weaviate MCP"})," for the current version of this workflow, and ",(0,n.jsx)(t.a,{href:"/blog/how-to-chatgpt-plugin",children:"How to Create Your Own ChatGPT Plugin"})," for the companion build write-up."]})})]})}function d(e={}){const{wrapper:t}={...(0,o.R)(),...e.components};return t?(0,n.jsx)(t,{...e,children:(0,n.jsx)(h,{...e})}):h(e)}},15498(e,t,a){a.d(t,{A:()=>i});const i=a.p+"assets/images/hero-06988d44e2f9d94bdc8b825f0de94f50.png"},8647(e,t,a){a.d(t,{A:()=>i});const i=a.p+"assets/images/hero-06988d44e2f9d94bdc8b825f0de94f50.png"},42158(e){e.exports=JSON.parse('{"permalink":"/blog/weaviate-retrieval-plugin","editUrl":"https://github.com/weaviate/weaviate-io/tree/main/blog/2023-04-04-weaviate-retrieval-plugin/index.mdx","source":"@site/blog/2023-04-04-weaviate-retrieval-plugin/index.mdx","title":"The ChatGPT Retrieval Plugin - Weaviate as a Long-term Memory Store for Generative AI","description":"Learn how you can connect Weaviate to ChatGPT to generate customized responses.","date":"2023-04-04T00:00:00.000Z","tags":[{"inline":true,"label":"integrations","permalink":"/blog/tags/integrations"}],"readingTime":8.3,"hasTruncateMarker":true,"authors":[{"name":"Zain Hasan","title":"Developer Advocate","url":"https://github.com/zainhas","imageURL":"/img/people/icon/zain.jpg","key":"zain","page":null}],"frontMatter":{"title":"The ChatGPT Retrieval Plugin - Weaviate as a Long-term Memory Store for Generative AI","slug":"weaviate-retrieval-plugin","authors":"zain","date":"2023-04-04T00:00:00.000Z","image":"./img/hero.png","tags":["integrations"],"description":"Learn how you can connect Weaviate to ChatGPT to generate customized responses."},"unlisted":false,"prevItem":{"title":"Ranking Models for Better Search","permalink":"/blog/ranking-models-for-better-search"},"nextItem":{"title":"Monitoring Weaviate in Production","permalink":"/blog/monitoring-weaviate-in-production"}}')}}]);
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.