LlamaEdge
-
+
diff --git a/docs/assets/js/33630671.25de7a3e.js b/docs/assets/js/33630671.25de7a3e.js
deleted file mode 100644
index c7095a8..0000000
--- a/docs/assets/js/33630671.25de7a3e.js
+++ /dev/null
@@ -1 +0,0 @@
-"use strict";(self.webpackChunkdocs=self.webpackChunkdocs||[]).push([[322],{6931:(e,a,s)=>{s.r(a),s.d(a,{assets:()=>i,contentTitle:()=>l,default:()=>m,frontMatter:()=>t,metadata:()=>r,toc:()=>d});var o=s(4848),n=s(8453);const t={sidebar_position:4},l="LlamaEdge vs Ollama",r={id:"llamaedge_vs_ollama",title:"LlamaEdge vs Ollama",description:'There are several popular tools to run "local LLMs". Ollama is one of the earlist and most popular. Why do people',source:"@site/docs/llamaedge_vs_ollama.md",sourceDirName:".",slug:"/llamaedge_vs_ollama",permalink:"/docs/llamaedge_vs_ollama",draft:!1,unlisted:!1,editUrl:"https://github.com/facebook/docusaurus/tree/main/packages/create-docusaurus/templates/shared/docs/llamaedge_vs_ollama.md",tags:[],version:"current",sidebarPosition:4,frontMatter:{sidebar_position:4},sidebar:"tutorialSidebar",previous:{title:"LlamaEdge vs llama.cpp",permalink:"/docs/llamaedge_vs_llamacpp"},next:{title:"User Guide",permalink:"/docs/category/user-guide"}},i={},d=[];function c(e){const a={a:"a",h1:"h1",li:"li",p:"p",ul:"ul",...(0,n.R)(),...e.components};return(0,o.jsxs)(o.Fragment,{children:[(0,o.jsx)(a.h1,{id:"llamaedge-vs-ollama",children:"LlamaEdge vs Ollama"}),"\n",(0,o.jsx)(a.p,{children:'There are several popular tools to run "local LLMs". Ollama is one of the earlist and most popular. Why do people\nchoose LlamaEdge over them?'}),"\n",(0,o.jsxs)(a.ul,{children:["\n",(0,o.jsx)(a.li,{children:"LlamaEdge is very small. The entire runtime and application is only 30MB. That is about 1/3 of the nearest competitor."}),"\n",(0,o.jsx)(a.li,{children:"LlamaEdge does not need root or sudo permissions It does not install or run any daemon on your system. Hence LlamaEdge can be easily embedded into your own app."}),"\n",(0,o.jsx)(a.li,{children:"LlamaEdge works with model files you download from Huggingface. There is no need for a special download hub."}),"\n",(0,o.jsx)(a.li,{children:"LlamaEdge provides a fully featured API server that supports both chat and embedding models at the same time, which is unique among open source API servers and crucial for RAG use cases."}),"\n"]}),"\n",(0,o.jsx)(a.p,{children:"Finally, LlamaEdge is a developer platform. It provides Rust APIs and components for you to build your own applications.\nIt enables developers to create a single compact and cross-platform binary app that can be easily deployed and orchestrated across clouds."}),"\n",(0,o.jsxs)(a.ul,{children:["\n",(0,o.jsxs)(a.li,{children:["The ",(0,o.jsx)(a.a,{href:"user-guide/server-side-rag/quick-start",children:"server-side RAG"})," API server is built on LlamaEdge components."]}),"\n",(0,o.jsxs)(a.li,{children:["The ",(0,o.jsx)(a.a,{href:"https://github.com/project-robius/moxin",children:"moxin"})," LLM client app uses LlamaEdge as the embedded inference engine."]}),"\n",(0,o.jsxs)(a.li,{children:["The ",(0,o.jsx)(a.a,{href:"https://github.com/GaiaNet-AI/gaianet-node",children:"GaiaNet"})," project embeds LlamaEdge to run a large number of decentralized LLM agents across the web."]}),"\n",(0,o.jsxs)(a.li,{children:["The ",(0,o.jsx)(a.a,{href:"https://www.jointerminus.com/",children:"Terminus OS"})," project is a Kubernetes-based personal OS. It embeds LlamaEdge to power AI services such as local search and document QA."]}),"\n"]})]})}function m(e={}){const{wrapper:a}={...(0,n.R)(),...e.components};return a?(0,o.jsx)(a,{...e,children:(0,o.jsx)(c,{...e})}):c(e)}},8453:(e,a,s)=>{s.d(a,{R:()=>l,x:()=>r});var o=s(6540);const n={},t=o.createContext(n);function l(e){const a=o.useContext(t);return o.useMemo((function(){return"function"==typeof e?e(a):{...a,...e}}),[a,e])}function r(e){let a;return a=e.disableParentContext?"function"==typeof e.components?e.components(n):e.components||n:l(e.components),o.createElement(t.Provider,{value:a},e.children)}}}]);
\ No newline at end of file
diff --git a/docs/assets/js/33630671.63c8384f.js b/docs/assets/js/33630671.63c8384f.js
new file mode 100644
index 0000000..2febd91
--- /dev/null
+++ b/docs/assets/js/33630671.63c8384f.js
@@ -0,0 +1 @@
+"use strict";(self.webpackChunkdocs=self.webpackChunkdocs||[]).push([[322],{6931:(e,a,s)=>{s.r(a),s.d(a,{assets:()=>i,contentTitle:()=>t,default:()=>m,frontMatter:()=>l,metadata:()=>r,toc:()=>d});var o=s(4848),n=s(8453);const l={sidebar_position:4},t="LlamaEdge vs Ollama",r={id:"llamaedge_vs_ollama",title:"LlamaEdge vs Ollama",description:'There are several popular tools to run "local LLMs". Ollama is one of the earlist and most popular. Why do people',source:"@site/docs/llamaedge_vs_ollama.md",sourceDirName:".",slug:"/llamaedge_vs_ollama",permalink:"/docs/llamaedge_vs_ollama",draft:!1,unlisted:!1,editUrl:"https://github.com/facebook/docusaurus/tree/main/packages/create-docusaurus/templates/shared/docs/llamaedge_vs_ollama.md",tags:[],version:"current",sidebarPosition:4,frontMatter:{sidebar_position:4},sidebar:"tutorialSidebar",previous:{title:"LlamaEdge vs llama.cpp",permalink:"/docs/llamaedge_vs_llamacpp"},next:{title:"User Guide",permalink:"/docs/category/user-guide"}},i={},d=[];function c(e){const a={a:"a",h1:"h1",li:"li",p:"p",ul:"ul",...(0,n.R)(),...e.components};return(0,o.jsxs)(o.Fragment,{children:[(0,o.jsx)(a.h1,{id:"llamaedge-vs-ollama",children:"LlamaEdge vs Ollama"}),"\n",(0,o.jsx)(a.p,{children:'There are several popular tools to run "local LLMs". Ollama is one of the earlist and most popular. Why do people\nchoose LlamaEdge over them?'}),"\n",(0,o.jsxs)(a.ul,{children:["\n",(0,o.jsx)(a.li,{children:"LlamaEdge is very small. The entire runtime and application is only 30MB. That is about 1/3 of the nearest competitor."}),"\n",(0,o.jsx)(a.li,{children:"LlamaEdge does not need root or sudo permissions It does not install or run any daemon on your system. Hence LlamaEdge can be easily embedded into your own app."}),"\n",(0,o.jsx)(a.li,{children:"LlamaEdge works with model files you download from Huggingface. There is no need for a special download hub."}),"\n",(0,o.jsx)(a.li,{children:"LlamaEdge provides a fully featured API server that supports both chat and embedding models in OpenAI-compatible API formats."}),"\n",(0,o.jsx)(a.li,{children:"LlamaEdge already supports for multimodal vision models. It will soon support text-to-image, and voice models soon through a unified OpenAI-compatible API."}),"\n"]}),"\n",(0,o.jsx)(a.p,{children:"Finally, LlamaEdge is a developer platform. It provides Rust APIs and components for you to build your own applications.\nIt enables developers to create a single compact and cross-platform binary app that can be easily deployed and orchestrated across clouds."}),"\n",(0,o.jsxs)(a.ul,{children:["\n",(0,o.jsxs)(a.li,{children:["The ",(0,o.jsx)(a.a,{href:"user-guide/server-side-rag/quick-start",children:"server-side RAG"})," API server is built on LlamaEdge components."]}),"\n",(0,o.jsxs)(a.li,{children:["The ",(0,o.jsx)(a.a,{href:"https://github.com/project-robius/moxin",children:"moxin"})," LLM client app uses LlamaEdge as the embedded inference engine."]}),"\n",(0,o.jsxs)(a.li,{children:["The ",(0,o.jsx)(a.a,{href:"https://github.com/GaiaNet-AI/gaianet-node",children:"GaiaNet"})," project embeds LlamaEdge to run a large number of decentralized LLM agents across the web."]}),"\n",(0,o.jsxs)(a.li,{children:["The ",(0,o.jsx)(a.a,{href:"https://www.jointerminus.com/",children:"Terminus OS"})," project is a Kubernetes-based personal OS. It embeds LlamaEdge to power AI services such as local search and document QA."]}),"\n"]})]})}function m(e={}){const{wrapper:a}={...(0,n.R)(),...e.components};return a?(0,o.jsx)(a,{...e,children:(0,o.jsx)(c,{...e})}):c(e)}},8453:(e,a,s)=>{s.d(a,{R:()=>t,x:()=>r});var o=s(6540);const n={},l=o.createContext(n);function t(e){const a=o.useContext(l);return o.useMemo((function(){return"function"==typeof e?e(a):{...a,...e}}),[a,e])}function r(e){let a;return a=e.disableParentContext?"function"==typeof e.components?e.components(n):e.components||n:t(e.components),o.createElement(l.Provider,{value:a},e.children)}}}]);
\ No newline at end of file
diff --git a/docs/assets/js/runtime~main.f39d30ca.js b/docs/assets/js/runtime~main.4af2f6d6.js
similarity index 98%
rename from docs/assets/js/runtime~main.f39d30ca.js
rename to docs/assets/js/runtime~main.4af2f6d6.js
index 20c3745..03bc614 100644
--- a/docs/assets/js/runtime~main.f39d30ca.js
+++ b/docs/assets/js/runtime~main.4af2f6d6.js
@@ -1 +1 @@
-(()=>{"use strict";var e,a,t,r,o,c={},d={};function f(e){var a=d[e];if(void 0!==a)return a.exports;var t=d[e]={id:e,loaded:!1,exports:{}};return c[e].call(t.exports,t,t.exports,f),t.loaded=!0,t.exports}f.m=c,f.c=d,e=[],f.O=(a,t,r,o)=>{if(!t){var c=1/0;for(i=0;i=o)&&Object.keys(f.O).every((e=>f.O[e](t[b])))?t.splice(b--,1):(d=!1,o0&&e[i-1][2]>o;i--)e[i]=e[i-1];e[i]=[t,r,o]},f.n=e=>{var a=e&&e.__esModule?()=>e.default:()=>e;return f.d(a,{a:a}),a},t=Object.getPrototypeOf?e=>Object.getPrototypeOf(e):e=>e.__proto__,f.t=function(e,r){if(1&r&&(e=this(e)),8&r)return e;if("object"==typeof e&&e){if(4&r&&e.__esModule)return e;if(16&r&&"function"==typeof e.then)return e}var o=Object.create(null);f.r(o);var c={};a=a||[null,t({}),t([]),t(t)];for(var d=2&r&&e;"object"==typeof d&&!~a.indexOf(d);d=t(d))Object.getOwnPropertyNames(d).forEach((a=>c[a]=()=>e[a]));return c.default=()=>e,f.d(o,c),o},f.d=(e,a)=>{for(var t in a)f.o(a,t)&&!f.o(e,t)&&Object.defineProperty(e,t,{enumerable:!0,get:a[t]})},f.f={},f.e=e=>Promise.all(Object.keys(f.f).reduce(((a,t)=>(f.f[t](e,a),a)),[])),f.u=e=>"assets/js/"+({0:"ccb8e574",48:"a94703ab",61:"1f391b9e",74:"89b72d9d",76:"e4f9ea1b",83:"95e1d156",87:"1eac376b",98:"a7bd4aaa",134:"393be207",284:"55fa9a31",286:"d2f61659",322:"33630671",327:"9d0bdc28",401:"17896441",431:"c9e9c5bd",469:"26fe1d28",509:"7c225f1f",511:"ac7af1dc",531:"1429b7e2",548:"247783bb",549:"80891840",550:"d6563973",581:"935f2afb",634:"c4f5d8e4",643:"b75a693e",647:"5e95c892",671:"4c50c399",678:"a7434565",680:"08a17b15",784:"a03793ee",793:"f805ca34",830:"3563a78d",840:"a3b48427",882:"23b1c9b9",899:"e5876591",969:"14eb3368",976:"0e384e19"}[e]||e)+"."+{0:"f099593b",48:"8b0ccadb",61:"85901a5d",74:"ac8ada43",76:"c56929a2",83:"0e598e13",87:"b39ddb1c",98:"fd305e17",134:"f0cfab75",237:"7663bed8",284:"b323bb4c",286:"8169f1cb",322:"25de7a3e",327:"b1d1bb30",401:"b4ff208f",431:"b467df22",469:"e4dcbb5d",509:"e7323d6b",511:"035a73e7",531:"50f42c7c",548:"938ceda8",549:"7ea9a5f0",550:"e51f7086",581:"b00a1758",634:"5241f109",643:"cfc34d34",647:"1dd55255",671:"9f6f2b0c",674:"8da1d51b",678:"a59ef084",680:"c0c34ddf",784:"60abfe00",793:"b2fc7127",830:"e6163d7d",840:"b4068465",882:"af07f6fe",899:"4b1cc9ec",969:"14ef70e8",976:"124bfe7c"}[e]+".js",f.miniCssF=e=>{},f.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||new Function("return this")()}catch(e){if("object"==typeof window)return window}}(),f.o=(e,a)=>Object.prototype.hasOwnProperty.call(e,a),r={},o="docs:",f.l=(e,a,t,c)=>{if(r[e])r[e].push(a);else{var d,b;if(void 0!==t)for(var n=document.getElementsByTagName("script"),i=0;i{d.onerror=d.onload=null,clearTimeout(s);var o=r[e];if(delete r[e],d.parentNode&&d.parentNode.removeChild(d),o&&o.forEach((e=>e(t))),a)return a(t)},s=setTimeout(l.bind(null,void 0,{type:"timeout",target:d}),12e4);d.onerror=l.bind(null,d.onerror),d.onload=l.bind(null,d.onload),b&&document.head.appendChild(d)}},f.r=e=>{"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},f.p="/docs/",f.gca=function(e){return e={17896441:"401",33630671:"322",80891840:"549",ccb8e574:"0",a94703ab:"48","1f391b9e":"61","89b72d9d":"74",e4f9ea1b:"76","95e1d156":"83","1eac376b":"87",a7bd4aaa:"98","393be207":"134","55fa9a31":"284",d2f61659:"286","9d0bdc28":"327",c9e9c5bd:"431","26fe1d28":"469","7c225f1f":"509",ac7af1dc:"511","1429b7e2":"531","247783bb":"548",d6563973:"550","935f2afb":"581",c4f5d8e4:"634",b75a693e:"643","5e95c892":"647","4c50c399":"671",a7434565:"678","08a17b15":"680",a03793ee:"784",f805ca34:"793","3563a78d":"830",a3b48427:"840","23b1c9b9":"882",e5876591:"899","14eb3368":"969","0e384e19":"976"}[e]||e,f.p+f.u(e)},(()=>{var e={354:0,869:0};f.f.j=(a,t)=>{var r=f.o(e,a)?e[a]:void 0;if(0!==r)if(r)t.push(r[2]);else if(/^(354|869)$/.test(a))e[a]=0;else{var o=new Promise(((t,o)=>r=e[a]=[t,o]));t.push(r[2]=o);var c=f.p+f.u(a),d=new Error;f.l(c,(t=>{if(f.o(e,a)&&(0!==(r=e[a])&&(e[a]=void 0),r)){var o=t&&("load"===t.type?"missing":t.type),c=t&&t.target&&t.target.src;d.message="Loading chunk "+a+" failed.\n("+o+": "+c+")",d.name="ChunkLoadError",d.type=o,d.request=c,r[1](d)}}),"chunk-"+a,a)}},f.O.j=a=>0===e[a];var a=(a,t)=>{var r,o,c=t[0],d=t[1],b=t[2],n=0;if(c.some((a=>0!==e[a]))){for(r in d)f.o(d,r)&&(f.m[r]=d[r]);if(b)var i=b(f)}for(a&&a(t);n{"use strict";var e,a,t,r,o,c={},d={};function f(e){var a=d[e];if(void 0!==a)return a.exports;var t=d[e]={id:e,loaded:!1,exports:{}};return c[e].call(t.exports,t,t.exports,f),t.loaded=!0,t.exports}f.m=c,f.c=d,e=[],f.O=(a,t,r,o)=>{if(!t){var c=1/0;for(i=0;i=o)&&Object.keys(f.O).every((e=>f.O[e](t[b])))?t.splice(b--,1):(d=!1,o0&&e[i-1][2]>o;i--)e[i]=e[i-1];e[i]=[t,r,o]},f.n=e=>{var a=e&&e.__esModule?()=>e.default:()=>e;return f.d(a,{a:a}),a},t=Object.getPrototypeOf?e=>Object.getPrototypeOf(e):e=>e.__proto__,f.t=function(e,r){if(1&r&&(e=this(e)),8&r)return e;if("object"==typeof e&&e){if(4&r&&e.__esModule)return e;if(16&r&&"function"==typeof e.then)return e}var o=Object.create(null);f.r(o);var c={};a=a||[null,t({}),t([]),t(t)];for(var d=2&r&&e;"object"==typeof d&&!~a.indexOf(d);d=t(d))Object.getOwnPropertyNames(d).forEach((a=>c[a]=()=>e[a]));return c.default=()=>e,f.d(o,c),o},f.d=(e,a)=>{for(var t in a)f.o(a,t)&&!f.o(e,t)&&Object.defineProperty(e,t,{enumerable:!0,get:a[t]})},f.f={},f.e=e=>Promise.all(Object.keys(f.f).reduce(((a,t)=>(f.f[t](e,a),a)),[])),f.u=e=>"assets/js/"+({0:"ccb8e574",48:"a94703ab",61:"1f391b9e",74:"89b72d9d",76:"e4f9ea1b",83:"95e1d156",87:"1eac376b",98:"a7bd4aaa",134:"393be207",284:"55fa9a31",286:"d2f61659",322:"33630671",327:"9d0bdc28",401:"17896441",431:"c9e9c5bd",469:"26fe1d28",509:"7c225f1f",511:"ac7af1dc",531:"1429b7e2",548:"247783bb",549:"80891840",550:"d6563973",581:"935f2afb",634:"c4f5d8e4",643:"b75a693e",647:"5e95c892",671:"4c50c399",678:"a7434565",680:"08a17b15",784:"a03793ee",793:"f805ca34",830:"3563a78d",840:"a3b48427",882:"23b1c9b9",899:"e5876591",969:"14eb3368",976:"0e384e19"}[e]||e)+"."+{0:"f099593b",48:"8b0ccadb",61:"85901a5d",74:"ac8ada43",76:"c56929a2",83:"0e598e13",87:"b39ddb1c",98:"fd305e17",134:"f0cfab75",237:"7663bed8",284:"b323bb4c",286:"8169f1cb",322:"63c8384f",327:"b1d1bb30",401:"b4ff208f",431:"b467df22",469:"e4dcbb5d",509:"e7323d6b",511:"035a73e7",531:"50f42c7c",548:"938ceda8",549:"7ea9a5f0",550:"e51f7086",581:"b00a1758",634:"5241f109",643:"cfc34d34",647:"1dd55255",671:"9f6f2b0c",674:"8da1d51b",678:"a59ef084",680:"c0c34ddf",784:"60abfe00",793:"b2fc7127",830:"e6163d7d",840:"b4068465",882:"af07f6fe",899:"4b1cc9ec",969:"14ef70e8",976:"124bfe7c"}[e]+".js",f.miniCssF=e=>{},f.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||new Function("return this")()}catch(e){if("object"==typeof window)return window}}(),f.o=(e,a)=>Object.prototype.hasOwnProperty.call(e,a),r={},o="docs:",f.l=(e,a,t,c)=>{if(r[e])r[e].push(a);else{var d,b;if(void 0!==t)for(var n=document.getElementsByTagName("script"),i=0;i{d.onerror=d.onload=null,clearTimeout(s);var o=r[e];if(delete r[e],d.parentNode&&d.parentNode.removeChild(d),o&&o.forEach((e=>e(t))),a)return a(t)},s=setTimeout(l.bind(null,void 0,{type:"timeout",target:d}),12e4);d.onerror=l.bind(null,d.onerror),d.onload=l.bind(null,d.onload),b&&document.head.appendChild(d)}},f.r=e=>{"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},f.p="/docs/",f.gca=function(e){return e={17896441:"401",33630671:"322",80891840:"549",ccb8e574:"0",a94703ab:"48","1f391b9e":"61","89b72d9d":"74",e4f9ea1b:"76","95e1d156":"83","1eac376b":"87",a7bd4aaa:"98","393be207":"134","55fa9a31":"284",d2f61659:"286","9d0bdc28":"327",c9e9c5bd:"431","26fe1d28":"469","7c225f1f":"509",ac7af1dc:"511","1429b7e2":"531","247783bb":"548",d6563973:"550","935f2afb":"581",c4f5d8e4:"634",b75a693e:"643","5e95c892":"647","4c50c399":"671",a7434565:"678","08a17b15":"680",a03793ee:"784",f805ca34:"793","3563a78d":"830",a3b48427:"840","23b1c9b9":"882",e5876591:"899","14eb3368":"969","0e384e19":"976"}[e]||e,f.p+f.u(e)},(()=>{var e={354:0,869:0};f.f.j=(a,t)=>{var r=f.o(e,a)?e[a]:void 0;if(0!==r)if(r)t.push(r[2]);else if(/^(354|869)$/.test(a))e[a]=0;else{var o=new Promise(((t,o)=>r=e[a]=[t,o]));t.push(r[2]=o);var c=f.p+f.u(a),d=new Error;f.l(c,(t=>{if(f.o(e,a)&&(0!==(r=e[a])&&(e[a]=void 0),r)){var o=t&&("load"===t.type?"missing":t.type),c=t&&t.target&&t.target.src;d.message="Loading chunk "+a+" failed.\n("+o+": "+c+")",d.name="ChunkLoadError",d.type=o,d.request=c,r[1](d)}}),"chunk-"+a,a)}},f.O.j=a=>0===e[a];var a=(a,t)=>{var r,o,c=t[0],d=t[1],b=t[2],n=0;if(c.some((a=>0!==e[a]))){for(r in d)f.o(d,r)&&(f.m[r]=d[r]);if(b)var i=b(f)}for(a&&a(t);nDeveloper Guide | LlamaEdge
-
+
diff --git a/docs/category/drop-in-replacement-for-openai/index.html b/docs/category/drop-in-replacement-for-openai/index.html
index ebee44b..c6dfd54 100644
--- a/docs/category/drop-in-replacement-for-openai/index.html
+++ b/docs/category/drop-in-replacement-for-openai/index.html
@@ -4,7 +4,7 @@
Drop-in replacement for OpenAI | LlamaEdge
-
+
diff --git a/docs/category/server-side-rag/index.html b/docs/category/server-side-rag/index.html
index 7c77d8e..1b12426 100644
--- a/docs/category/server-side-rag/index.html
+++ b/docs/category/server-side-rag/index.html
@@ -4,7 +4,7 @@
Server-side RAG | LlamaEdge
-
+
diff --git a/docs/category/user-guide/index.html b/docs/category/user-guide/index.html
index fdc383a..8936d98 100644
--- a/docs/category/user-guide/index.html
+++ b/docs/category/user-guide/index.html
@@ -4,7 +4,7 @@
User Guide | LlamaEdge
-
+
diff --git a/docs/developer-guide/basic-llm-app/index.html b/docs/developer-guide/basic-llm-app/index.html
index 5dc12a5..c050741 100644
--- a/docs/developer-guide/basic-llm-app/index.html
+++ b/docs/developer-guide/basic-llm-app/index.html
@@ -4,7 +4,7 @@
Create a basic LLM app | LlamaEdge
-
+
diff --git a/docs/developer-guide/chatbot-llm-app/index.html b/docs/developer-guide/chatbot-llm-app/index.html
index d2fcf8b..8c29d19 100644
--- a/docs/developer-guide/chatbot-llm-app/index.html
+++ b/docs/developer-guide/chatbot-llm-app/index.html
@@ -4,7 +4,7 @@
Create a chatbot LLM app | LlamaEdge
-
+
diff --git a/docs/developer-guide/create-embeddings-collection/index.html b/docs/developer-guide/create-embeddings-collection/index.html
index d28cdbc..80699d1 100644
--- a/docs/developer-guide/create-embeddings-collection/index.html
+++ b/docs/developer-guide/create-embeddings-collection/index.html
@@ -4,7 +4,7 @@
Create knowledge embeddings using the API server | LlamaEdge
-
+
diff --git a/docs/developer-guide/embedding-app/index.html b/docs/developer-guide/embedding-app/index.html
index 1b43fad..390f678 100644
--- a/docs/developer-guide/embedding-app/index.html
+++ b/docs/developer-guide/embedding-app/index.html
@@ -4,7 +4,7 @@
Create an embedding app | LlamaEdge
-
+
diff --git a/docs/developer-guide/multimodal-app/index.html b/docs/developer-guide/multimodal-app/index.html
index ddebe6a..397ce39 100644
--- a/docs/developer-guide/multimodal-app/index.html
+++ b/docs/developer-guide/multimodal-app/index.html
@@ -4,7 +4,7 @@
Create a multimodal app | LlamaEdge
-
+
diff --git a/docs/developer-guide/rag-api-server/index.html b/docs/developer-guide/rag-api-server/index.html
index 255e471..6f4f1c1 100644
--- a/docs/developer-guide/rag-api-server/index.html
+++ b/docs/developer-guide/rag-api-server/index.html
@@ -4,7 +4,7 @@
Implement your own RAG API server | LlamaEdge
-
+
diff --git a/docs/index.html b/docs/index.html
index a93343a..7e940d8 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -4,7 +4,7 @@
LlamaEdge
-
+
diff --git a/docs/intro/index.html b/docs/intro/index.html
index 084c9ee..bdeacf0 100644
--- a/docs/intro/index.html
+++ b/docs/intro/index.html
@@ -4,7 +4,7 @@
LlamaEdge | LlamaEdge
-
+
diff --git a/docs/llamaedge_vs_llamacpp/index.html b/docs/llamaedge_vs_llamacpp/index.html
index c8a9927..de89ba9 100644
--- a/docs/llamaedge_vs_llamacpp/index.html
+++ b/docs/llamaedge_vs_llamacpp/index.html
@@ -4,7 +4,7 @@
LlamaEdge vs llama.cpp | LlamaEdge
-
+
diff --git a/docs/llamaedge_vs_ollama/index.html b/docs/llamaedge_vs_ollama/index.html
index cdb8576..e3bac26 100644
--- a/docs/llamaedge_vs_ollama/index.html
+++ b/docs/llamaedge_vs_ollama/index.html
@@ -4,7 +4,7 @@
LlamaEdge vs Ollama | LlamaEdge
-
+
@@ -15,7 +15,8 @@
LlamaEdge is very small. The entire runtime and application is only 30MB. That is about 1/3 of the nearest competitor.
LlamaEdge does not need root or sudo permissions It does not install or run any daemon on your system. Hence LlamaEdge can be easily embedded into your own app.
LlamaEdge works with model files you download from Huggingface. There is no need for a special download hub.
-
LlamaEdge provides a fully featured API server that supports both chat and embedding models at the same time, which is unique among open source API servers and crucial for RAG use cases.
+
LlamaEdge provides a fully featured API server that supports both chat and embedding models in OpenAI-compatible API formats.
+
LlamaEdge already supports for multimodal vision models. It will soon support text-to-image, and voice models soon through a unified OpenAI-compatible API.
Finally, LlamaEdge is a developer platform. It provides Rust APIs and components for you to build your own applications.
It enables developers to create a single compact and cross-platform binary app that can be easily deployed and orchestrated across clouds.
diff --git a/docs/llamaedge_vs_python/index.html b/docs/llamaedge_vs_python/index.html
index 36cbb03..ca2bd73 100644
--- a/docs/llamaedge_vs_python/index.html
+++ b/docs/llamaedge_vs_python/index.html
@@ -4,7 +4,7 @@
LlamaEdge vs Python | LlamaEdge
-
+
diff --git a/docs/markdown-page/index.html b/docs/markdown-page/index.html
index 454159c..57c1046 100644
--- a/docs/markdown-page/index.html
+++ b/docs/markdown-page/index.html
@@ -4,7 +4,7 @@
Markdown page example | LlamaEdge
-
+
diff --git a/docs/user-guide/get-started-with-llamaedge/index.html b/docs/user-guide/get-started-with-llamaedge/index.html
index 00637e3..c6b46f6 100644
--- a/docs/user-guide/get-started-with-llamaedge/index.html
+++ b/docs/user-guide/get-started-with-llamaedge/index.html
@@ -4,7 +4,7 @@
LlamaEdge step-by-step | LlamaEdge
-
+
diff --git a/docs/user-guide/llamaedge-docker/index.html b/docs/user-guide/llamaedge-docker/index.html
index ac4d0f5..a2e3458 100644
--- a/docs/user-guide/llamaedge-docker/index.html
+++ b/docs/user-guide/llamaedge-docker/index.html
@@ -4,7 +4,7 @@
Use LlamaEdge in Docker | LlamaEdge
-
+
diff --git a/docs/user-guide/llamaedge-kubernetes/index.html b/docs/user-guide/llamaedge-kubernetes/index.html
index 9173608..2727590 100644
--- a/docs/user-guide/llamaedge-kubernetes/index.html
+++ b/docs/user-guide/llamaedge-kubernetes/index.html
@@ -4,7 +4,7 @@
Use LlamaEdge in Kubernetes | LlamaEdge
-
+
diff --git a/docs/user-guide/llamaedge-lobechat/index.html b/docs/user-guide/llamaedge-lobechat/index.html
index a2afc9b..c8ec63b 100644
--- a/docs/user-guide/llamaedge-lobechat/index.html
+++ b/docs/user-guide/llamaedge-lobechat/index.html
@@ -4,7 +4,7 @@
LobeChat + LlamaEdge | LlamaEdge
-
+
diff --git a/docs/user-guide/openai-api/intro/index.html b/docs/user-guide/openai-api/intro/index.html
index c3e81a4..ef61640 100644
--- a/docs/user-guide/openai-api/intro/index.html
+++ b/docs/user-guide/openai-api/intro/index.html
@@ -4,7 +4,7 @@
Start an LlamaEdge API service | LlamaEdge
-
+
diff --git a/docs/user-guide/openai-api/langchain/index.html b/docs/user-guide/openai-api/langchain/index.html
index e915688..29a2b1f 100644
--- a/docs/user-guide/openai-api/langchain/index.html
+++ b/docs/user-guide/openai-api/langchain/index.html
@@ -4,7 +4,7 @@
LangChain | LlamaEdge
-
+
diff --git a/docs/user-guide/openai-api/lobechat/index.html b/docs/user-guide/openai-api/lobechat/index.html
index 01f5dca..41bf730 100644
--- a/docs/user-guide/openai-api/lobechat/index.html
+++ b/docs/user-guide/openai-api/lobechat/index.html
@@ -4,7 +4,7 @@
LobeChat | LlamaEdge
-
+
diff --git a/docs/user-guide/quick-start-command/index.html b/docs/user-guide/quick-start-command/index.html
index be5d5f6..dfdb4a0 100644
--- a/docs/user-guide/quick-start-command/index.html
+++ b/docs/user-guide/quick-start-command/index.html
@@ -4,7 +4,7 @@
Quick start | LlamaEdge
-
+
diff --git a/docs/user-guide/server-side-rag/markdown/index.html b/docs/user-guide/server-side-rag/markdown/index.html
index 3cb37e5..c92607f 100644
--- a/docs/user-guide/server-side-rag/markdown/index.html
+++ b/docs/user-guide/server-side-rag/markdown/index.html
@@ -4,7 +4,7 @@
Knowledge base from a markdown file | LlamaEdge
-
+
diff --git a/docs/user-guide/server-side-rag/quick-start/index.html b/docs/user-guide/server-side-rag/quick-start/index.html
index bf2bcb8..ddc8127 100644
--- a/docs/user-guide/server-side-rag/quick-start/index.html
+++ b/docs/user-guide/server-side-rag/quick-start/index.html
@@ -4,7 +4,7 @@
Server-side RAG with LlamaEdge | LlamaEdge
-
+
diff --git a/docs/user-guide/server-side-rag/rag-service/index.html b/docs/user-guide/server-side-rag/rag-service/index.html
index 49bb8dd..862e3e1 100644
--- a/docs/user-guide/server-side-rag/rag-service/index.html
+++ b/docs/user-guide/server-side-rag/rag-service/index.html
@@ -4,7 +4,7 @@
Use the API server | LlamaEdge
-
+
diff --git a/docs/user-guide/server-side-rag/text/index.html b/docs/user-guide/server-side-rag/text/index.html
index 0347c8b..01b0f2a 100644
--- a/docs/user-guide/server-side-rag/text/index.html
+++ b/docs/user-guide/server-side-rag/text/index.html
@@ -4,7 +4,7 @@
Knowledge base from a plain text file | LlamaEdge
-
+