mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-13 09:44:26 -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>
140 lines
7.1 KiB
HTML
140 lines
7.1 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> Realtime API</div>
|
|
<h1>The realtime <em>voice loop</em></h1>
|
|
</div>
|
|
<div class="stamp">
|
|
<div class="k">WS</div>
|
|
<div class="s">/ WebRTC</div>
|
|
</div>
|
|
</header>
|
|
<div class="stage"><svg viewBox="0 0 1480 560" id="svg"></svg></div>
|
|
<footer>
|
|
<div class="note">Voice in, voice out: <b>VAD → STT → LLM → TTS</b>, over WebSocket or WebRTC.</div>
|
|
<div class="url">localai.io<span>/features/openai-realtime</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"}));
|
|
}
|
|
|
|
// ============ PIPELINE ROW ============
|
|
// Six stages: mic -> VAD -> STT -> LLM -> TTS -> audio out
|
|
const PY=120, PH=110; // pipeline box top + height
|
|
const PMID=PY+PH/2;
|
|
const stages=[
|
|
{x:24, w:170, n:"Mic audio", s:"caller speaks", fill:PAPER2, edge:false},
|
|
{x:248, w:170, n:"VAD", s:"speech detect", fill:HI, edge:false},
|
|
{x:472, w:170, n:"STT", s:"speech to text",fill:HI, edge:false},
|
|
{x:696, w:170, n:"LLM", s:"reasoning", fill:RUST, edge:true},
|
|
{x:920, w:170, n:"TTS", s:"text to speech",fill:HI, edge:false},
|
|
{x:1144, w:170, n:"Audio out", s:"voice reply", fill:PAPER2, edge:false},
|
|
];
|
|
txt(24,80,"PIPELINE",{w:700,sz:14,ls:".2em",fill:SOFT});
|
|
stages.forEach(st=>{
|
|
shadowRect(st.x,PY,st.w,PH,st.fill);
|
|
const tc = st.edge?PAPER:INK;
|
|
const sc = st.edge?"#F1D9C8":SOFT;
|
|
txt(st.x+st.w/2,PY+52,st.n,{f:"Bricolage Grotesque",w:800,sz:30,a:"middle",fill:tc});
|
|
txt(st.x+st.w/2,PY+82,st.s,{w:700,sz:14,a:"middle",fill:sc});
|
|
});
|
|
// forward arrows between stages
|
|
for(let i=0;i<stages.length-1;i++){
|
|
const a=stages[i], b=stages[i+1];
|
|
arrow(a.x+a.w, PMID, b.x, PMID, INK);
|
|
}
|
|
|
|
// ============ RETURN LOOP (audio out -> mic, loops back to listener) ============
|
|
const lastX = stages[5].x+stages[5].w/2;
|
|
const firstX = stages[0].x+stages[0].w/2;
|
|
const loopY = PY-58;
|
|
// path from audio-out top, up, across, down into mic top
|
|
const lp = `M ${lastX} ${PY} L ${lastX} ${loopY} L ${firstX} ${loopY} L ${firstX} ${PY-11}`;
|
|
svg.appendChild(el("path",{d:lp,fill:"none",stroke:COLD,"stroke-width":3.5,"stroke-linecap":"round","stroke-linejoin":"round","stroke-dasharray":"2 8"}));
|
|
// arrowhead pointing down into mic
|
|
svg.appendChild(el("path",{d:`M ${firstX} ${PY-11} l -7 -11 M ${firstX} ${PY-11} l 7 -11`,fill:"none",stroke:COLD,"stroke-width":3.5,"stroke-linecap":"round"}));
|
|
// loop label
|
|
const llw=216, llx=(lastX+firstX)/2-llw/2;
|
|
svg.appendChild(el("rect",{x:llx,y:loopY-19,width:llw,height:30,fill:PAPER,stroke:COLD,"stroke-width":2.5}));
|
|
txt(llx+llw/2,loopY+2,"streamed back to listener",{w:700,sz:14,a:"middle",fill:COLD});
|
|
|
|
// ============ TRANSPORT BAND ============
|
|
const TY=370, TH=120;
|
|
txt(24,346,"TRANSPORT",{w:700,sz:14,ls:".2em",fill:SOFT});
|
|
const trans=[
|
|
{x:248, w:300, n:"WebSocket", s:"raw PCM frames"},
|
|
{x:592, w:300, n:"WebRTC", s:"Opus · SDP handshake"},
|
|
];
|
|
trans.forEach(t=>{
|
|
shadowRect(t.x,TY,t.w,TH,PAPER,RUSTD,3.5);
|
|
txt(t.x+24,TY+52,t.n,{f:"Bricolage Grotesque",w:800,sz:30,fill:RUSTD});
|
|
txt(t.x+24,TY+84,t.s,{w:700,sz:16,fill:SOFT});
|
|
});
|
|
// transport feeds the pipeline entry (VAD box, the entry into processing)
|
|
const entry = stages[1]; // VAD
|
|
const entryBottomX = entry.x + entry.w/2;
|
|
trans.forEach(t=>{
|
|
arrow(t.x+t.w/2, TY, entryBottomX, PY+PH, RUSTD, "2 8");
|
|
});
|
|
// label on the feed
|
|
txt(entryBottomX+18,(TY+PY+PH)/2+6,"audio in",{w:700,sz:14,fill:RUSTD});
|
|
</script>
|
|
</body>
|
|
</html>
|