mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-09 07:48:22 -04:00
7e59a5c7c5
* docs: add 'how LocalAI works' architecture diagram Add a blueprint-style architecture diagram: clients -> small core (API, router, WebUI, agents) -> gRPC -> backend processes pulled on demand as OCI images. Place it on the overview page and replace the stale external architecture image on the reference page. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: add blueprint diagrams across feature, distributed & getting-started docs Add 24 architecture/flow/comparison diagrams (PNG + HTML source) under docs/static/images/diagrams/, wired into their docs pages, from an impact-vs-effort audit of the docs. Broaden the API surface on the overview architecture diagram (OpenAI, Anthropic, ElevenLabs, Ollama, and LocalAI's own API) and move the gRPC boundary label clear of the arrows. Pages: distributed mode (architecture, scheduling, ds4 layer-split), distributed inferencing, MLX, realtime, quantization, MCP, agents, mitm & cloud proxy, middleware, reverse-proxy TLS, VRAM, voice & face recognition, reranker, function calling, fine-tuning (recipe + jobs), diarization, audio transform, quickstart, model resolution. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: add composable-core diagram to README hero Commit the composable-core card (small core + on-demand backend tiles) alongside the other diagrams and reference it from the README hero via a repo-relative path, so it renders on GitHub. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: fix composable-core connectors/badge and federated-vs-worker layout - composable-core: thicken the plug-in connectors so they read clearly, and widen the SEPARATE IMAGE badge so its text no longer overflows the box. - federated-vs-worker: shorten the WHOLE/SPLIT REQUEST pills to fit, and replace the tangled node-to-node activation arrows with a clean fan-out (request split across all sharded nodes), mirroring the federated panel. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
172 lines
8.6 KiB
HTML
172 lines
8.6 KiB
HTML
<!doctype html>
|
|
<html lang="en">
|
|
<head>
|
|
<meta charset="utf-8">
|
|
<link rel="preconnect" href="https://fonts.googleapis.com">
|
|
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
|
|
<link href="https://fonts.googleapis.com/css2?family=Bricolage+Grotesque:opsz,wght@12..96,600;12..96,700;12..96,800&family=Archivo:wght@500;600;700&display=swap" rel="stylesheet">
|
|
<style>
|
|
:root{
|
|
--paper:#F3E8D2; --paper2:#ECDFC2; --ink:#211C14; --ink-soft:#5A5142;
|
|
--rust:#B43A2C; --rust-deep:#8F2C20; --cold:#3F6E73; --hi:#E7D6AE; --dim:#A99F88;
|
|
}
|
|
*{box-sizing:border-box;margin:0;padding:0}
|
|
html,body{width:1600px;height:900px}
|
|
body{
|
|
background:var(--paper);color:var(--ink);font-family:"Archivo",sans-serif;
|
|
position:relative;overflow:hidden;
|
|
background-image:
|
|
linear-gradient(var(--paper2) 1px,transparent 1px),
|
|
linear-gradient(90deg,var(--paper2) 1px,transparent 1px);
|
|
background-size:40px 40px;
|
|
}
|
|
.frame{position:absolute;inset:26px;border:3px solid var(--ink);}
|
|
.wrap{position:absolute;inset:26px;padding:30px 56px 26px;display:flex;flex-direction:column}
|
|
header{display:flex;align-items:flex-end;justify-content:space-between;gap:30px}
|
|
.eyebrow{font-weight:700;letter-spacing:.22em;text-transform:uppercase;font-size:17px;color:var(--rust-deep)}
|
|
.eyebrow b{color:var(--ink)}
|
|
h1{font-family:"Bricolage Grotesque",sans-serif;font-weight:800;font-size:50px;line-height:.98;letter-spacing:-.015em;margin-top:6px}
|
|
h1 em{font-style:normal;color:var(--rust)}
|
|
.stamp{border:3px solid var(--ink);padding:10px 16px 8px;transform:rotate(3deg);text-align:center;background:var(--paper);box-shadow:6px 6px 0 var(--ink);flex:none}
|
|
.stamp .k{font-family:"Bricolage Grotesque";font-weight:800;font-size:21px;letter-spacing:.04em;line-height:1.05}
|
|
.stamp .s{font-weight:700;font-size:11px;letter-spacing:.18em;text-transform:uppercase;color:var(--ink-soft);margin-top:5px}
|
|
.stage{flex:1;margin-top:8px}
|
|
svg{width:100%;height:100%;overflow:visible}
|
|
footer{display:flex;align-items:center;justify-content:space-between;margin-top:6px;gap:24px}
|
|
.note{font-weight:600;font-size:18px;color:var(--ink-soft);line-height:1.3;max-width:1080px}
|
|
.note b{color:var(--ink)}
|
|
.url{font-family:"Bricolage Grotesque";font-weight:800;font-size:22px;color:var(--rust-deep);letter-spacing:.01em;flex:none}
|
|
.url span{color:var(--ink)}
|
|
</style>
|
|
</head>
|
|
<body>
|
|
<div class="frame"></div>
|
|
<div class="wrap">
|
|
<header>
|
|
<div>
|
|
<div class="eyebrow">LocalAI <b>·</b> SmartRouter</div>
|
|
<h1>How the router <em>places a request</em></h1>
|
|
</div>
|
|
<div class="stamp">
|
|
<div class="k">IDLE</div>
|
|
<div class="s">first</div>
|
|
</div>
|
|
</header>
|
|
<div class="stage"><svg viewBox="0 0 1480 560" id="svg"></svg></div>
|
|
<footer>
|
|
<div class="note">Idle-first placement with <b>preemptive least-recently-used eviction.</b></div>
|
|
<div class="url">localai.io<span>/features/distributed-mode</span></div>
|
|
</footer>
|
|
</div>
|
|
<script>
|
|
const INK="#211C14", PAPER="#F3E8D2", PAPER2="#ECDFC2", HI="#E7D6AE", SOFT="#5A5142", RUST="#B43A2C", RUSTD="#8F2C20", COLD="#3F6E73", DIM="#A99F88";
|
|
function el(t,a,x){const e=document.createElementNS("http://www.w3.org/2000/svg",t);for(const k in a)e.setAttribute(k,a[k]);if(x!=null)e.textContent=x;return e;}
|
|
const svg=document.getElementById("svg");
|
|
function shadowRect(x,y,w,h,fill,stroke,sw,dash){
|
|
svg.appendChild(el("rect",{x:x+7,y:y+7,width:w,height:h,fill:INK}));
|
|
svg.appendChild(el("rect",{x,y,width:w,height:h,fill,stroke:stroke||INK,"stroke-width":sw||3.5,"stroke-dasharray":dash||"none"}));
|
|
}
|
|
function txt(x,y,s,o){o=o||{};svg.appendChild(el("text",{x,y,"font-family":o.f||"Archivo","font-weight":o.w||700,"font-size":o.sz||15,"letter-spacing":o.ls||"0","text-anchor":o.a||"start",fill:o.fill||INK},s));}
|
|
function arrow(x1,y1,x2,y2,color,dash){
|
|
const mx=(x1+x2)/2;
|
|
svg.appendChild(el("path",{d:`M ${x1} ${y1} C ${mx} ${y1}, ${mx} ${y2}, ${x2-11} ${y2}`,fill:"none",stroke:color,"stroke-width":3.5,"stroke-linecap":"round","stroke-dasharray":dash||"none"}));
|
|
const a=7;
|
|
svg.appendChild(el("path",{d:`M ${x2-11} ${y2} l -${a+4} -${a} M ${x2-11} ${y2} l -${a+4} ${a}`,fill:"none",stroke:color,"stroke-width":3.5,"stroke-linecap":"round"}));
|
|
}
|
|
// straight arrow with explicit endpoint arrowhead (any direction)
|
|
function lineArrow(x1,y1,x2,y2,color,dash){
|
|
svg.appendChild(el("line",{x1,y1,x2,y2,stroke:color,"stroke-width":3.5,"stroke-linecap":"round","stroke-dasharray":dash||"none"}));
|
|
const ang=Math.atan2(y2-y1,x2-x1), a=8, sp=0.5;
|
|
const ax=x2-Math.cos(ang)*2, ay=y2-Math.sin(ang)*2;
|
|
svg.appendChild(el("path",{d:`M ${ax} ${ay} l ${-(a+5)*Math.cos(ang-sp)} ${-(a+5)*Math.sin(ang-sp)} M ${ax} ${ay} l ${-(a+5)*Math.cos(ang+sp)} ${-(a+5)*Math.sin(ang+sp)}`,fill:"none",stroke:color,"stroke-width":3.5,"stroke-linecap":"round"}));
|
|
}
|
|
|
|
// ---------- DIAMOND (decision) ----------
|
|
function diamond(cx,cy,hw,hh,lines,o){
|
|
o=o||{};
|
|
const pts=`${cx},${cy-hh} ${cx+hw},${cy} ${cx},${cy+hh} ${cx-hw},${cy}`;
|
|
// hard offset shadow
|
|
svg.appendChild(el("polygon",{points:`${cx+7},${cy-hh+7} ${cx+hw+7},${cy+7} ${cx+7},${cy+hh+7} ${cx-hw+7},${cy+7}`,fill:INK}));
|
|
svg.appendChild(el("polygon",{points:pts,fill:o.fill||HI,stroke:INK,"stroke-width":o.sw||3.5}));
|
|
const n=lines.length, lh=o.lh||21, start=cy-((n-1)*lh)/2+6;
|
|
lines.forEach((ln,i)=>txt(cx,start+i*lh,ln,{f:"Bricolage Grotesque",w:700,sz:o.sz||17,a:"middle"}));
|
|
}
|
|
// ---------- OUTCOME RECT ----------
|
|
function outcome(cx,cy,w,h,lines,o){
|
|
o=o||{};
|
|
shadowRect(cx-w/2,cy-h/2,w,h,o.fill||PAPER2,o.stroke,o.sw);
|
|
const n=lines.length, lh=o.lh||23, start=cy-((n-1)*lh)/2+7;
|
|
lines.forEach((ln,i)=>txt(cx,start+i*lh,ln,{f:"Bricolage Grotesque",w:o.w||800,sz:o.sz||19,a:"middle",fill:o.tfill||INK}));
|
|
}
|
|
// branch label pill
|
|
function label(x,y,s,color){
|
|
const w=s.length*8.5+22, h=24;
|
|
svg.appendChild(el("rect",{x:x-w/2,y:y-h/2,width:w,height:h,fill:PAPER,stroke:color,"stroke-width":2.5}));
|
|
txt(x,y+6,s,{w:700,sz:13,ls:".06em",a:"middle",fill:color});
|
|
}
|
|
|
|
// ===== LAYOUT =====
|
|
// Left column: the decision spine (diamonds). Right side at each level: the YES outcome.
|
|
const DX=430; // diamond center x
|
|
const DHW=178, DHH=58; // diamond half-width / half-height
|
|
const OX=1090; // outcome center x
|
|
const OW=300, OH=66; // outcome size
|
|
const rowY=[70,200,330,460]; // first 4 diamonds
|
|
// vertical positions
|
|
const dY=[68,196,324,452];
|
|
|
|
// diamonds (decisions) - cold teal accent stroke fill
|
|
const decisions=[
|
|
["model already","loaded on a node?"],
|
|
["node with","free VRAM?"],
|
|
["idle node","available?"],
|
|
["can evict an LRU node","with zero in-flight?"],
|
|
];
|
|
const dCX=DX, dHW=176, dHH=52;
|
|
const dCY=[88,210,332,454];
|
|
|
|
// YES outcomes (right)
|
|
const yesOut=[
|
|
{l:["route there","(done)"],fill:"#EFE0BF"},
|
|
{l:["load there"],fill:"#EFE0BF"},
|
|
{l:["load there"],fill:"#EFE0BF"},
|
|
{l:["evict + load"],fill:"#EFE0BF"},
|
|
];
|
|
const oW=290, oH=60;
|
|
|
|
// bottom row geometry (wait-then-evict + terminal action)
|
|
const botY=556;
|
|
const waitCX=dCX, waitCY=botY, waitW=330, waitH=58;
|
|
const taW=360, taH=64, taCX=OX, taCY=botY;
|
|
|
|
// ========== 1) CONNECTORS (drawn first, shapes sit on top) ==========
|
|
// NO spine: diamond i bottom -> diamond i+1 top
|
|
for(let i=0;i<3;i++) lineArrow(dCX, dCY[i]+dHH, dCX, dCY[i+1]-dHH, INK);
|
|
// final NO: last diamond bottom -> wait-then-evict box
|
|
lineArrow(dCX, dCY[3]+dHH, dCX, waitCY-waitH/2, RUST);
|
|
// YES connectors: diamond right vertex -> yes outcome left edge
|
|
for(let i=0;i<4;i++) lineArrow(dCX+dHW, dCY[i], OX-oW/2, dCY[i], i<3?COLD:RUST);
|
|
// funnel the load/evict outcomes (idx 1,2,3) downward into the terminal action
|
|
[1,2,3].forEach(i=>{
|
|
lineArrow(OX, dCY[i]+oH/2, OX, (i===3? taCY-taH/2 : dCY[i+1]-oH/2), COLD, "2 7");
|
|
});
|
|
// wait-then-evict -> terminal action
|
|
lineArrow(waitCX+waitW/2, waitCY, taCX-taW/2, taCY, RUST);
|
|
|
|
// ========== 2) SHAPES ==========
|
|
decisions.forEach((d,i)=> diamond(dCX,dCY[i],dHW,dHH,d,{fill:i<3?HI:"#E9D2B0",sz:18}) );
|
|
yesOut.forEach((o,i)=> outcome(OX,dCY[i],oW,oH,o.l,{fill:o.fill,sz:21}) );
|
|
outcome(waitCX,waitCY,waitW,waitH,["wait, then evict"],{fill:PAPER,stroke:RUST,sw:3.5,sz:21,tfill:RUSTD});
|
|
outcome(taCX,taCY,taW,taH,["backend.install","+ LoadModel"],{fill:RUST,sz:22,tfill:PAPER,lh:25});
|
|
|
|
// ========== 3) BRANCH LABELS (on top) ==========
|
|
for(let i=0;i<3;i++) label(dCX, (dCY[i]+dHH+dCY[i+1]-dHH)/2, "NO", RUSTD);
|
|
label(dCX, (dCY[3]+dHH+waitCY-waitH/2)/2, "NO", RUST);
|
|
for(let i=0;i<4;i++) label((dCX+dHW+OX-oW/2)/2, dCY[i]-16, "YES", i<3?COLD:RUST);
|
|
|
|
// request tag (left of the first diamond, clear of the spine)
|
|
txt(dCX-dHW-14, dCY[0]+5, "REQUEST", {w:700,sz:13,ls:".16em",a:"end",fill:SOFT});
|
|
</script>
|
|
</body>
|
|
</html>
|