Hitonabi/mission-control
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: massive UX and beginner refactoring (Cookbook, Dashboard, Layout, Wording)

Browse Source
This commit is contained in:
Hitonabi
2026-06-20 22:06:04 +02:00
parent 9d05b2d011
commit e3be7fbfb5
11 changed files with 359 additions and 276 deletions
Download Patch File Download Diff File Expand all files Collapse all files
static/js/panels/guides.js
+23 -26
View File
@@ -9,36 +9,39 @@ function render() {
c.innerHTML = `
<div class="grid grid-2">
<div class="card">
<div class="card-h"><h3>Cline / Cursor</h3></div>
<p>Nutze llama-swap als lokalen OpenAI-kompatiblen Provider in Cursor oder Cline.</p>
<label>API Provider</label>
<input class="tokin mono-sm" readonly value="OpenAI Compatible">
<label>Base URL</label>
<div class="card-h"><h3>Cline / Cursor (Juni 2026)</h3></div>
<p>Nutze deine lokalen Modelle kostenlos in Cursor und Cline.</p>
<label>Cursor: Settings -> Models -> Add Custom Model</label>
<input class="tokin mono-sm" readonly value="coder">
<label>Base URL (OpenAI API)</label>
<input class="tokin mono-sm" readonly value="${currentUrl}/v1">
<label>API Key</label>
<input class="tokin mono-sm" readonly value="Dein_Mission_Control_Token_oder_leer">
<input class="tokin mono-sm" readonly value="MissionControl-Token-oder-leer">
<p style="margin-top:12px; font-size:12px; color:var(--mut);">
In Cline: Wähle "OpenAI Compatible" als Provider.
</p>
</div>
<div class="card">
<div class="card-h"><h3>OpenWebUI</h3></div>
<p>Füge llama-swap in OpenWebUI als externe OpenAI-Verbindung hinzu.</p>
<label>Settings -> Connections -> OpenAI API</label>
<div class="card-h"><h3>OpenWebUI (Pipes & Connections)</h3></div>
<p>Verbinde llama-swap nativ in OpenWebUI.</p>
<label>Settings -> Admin Settings -> Connections</label>
<input class="tokin mono-sm" readonly value="${currentUrl}/v1">
<label>API Key</label>
<input class="tokin mono-sm" readonly value="dummy-key">
<p style="margin-top:12px; font-size:12px; color:var(--text-dim);">
OpenWebUI zieht sich danach automatisch alle geladenen Modelle.
<p style="margin-top:12px; font-size:12px; color:var(--mut);">
OpenWebUI erkennt nun vollautomatisch, wenn ein Modell ausgetauscht wird.
</p>
</div>
<div class="card" style="grid-column: span 2;">
<div class="card-h"><h3>Python / LangChain (OpenAI SDK)</h3></div>
<p>Nutze das offizielle <code>openai</code> Package, um mit llama-swap zu sprechen.</p>
<pre style="background: var(--bg); padding: 12px; border-radius: 8px; border: 1px solid var(--border); overflow-x: auto; color: var(--text); font-family: monospace; font-size: 13px;"><code>from openai import OpenAI
<pre style="background: var(--bg); padding: 12px; border-radius: 8px; border: 1px solid var(--line); overflow-x: auto; color: var(--tx); font-family: monospace; font-size: 13px;"><code>from openai import OpenAI
client = OpenAI(
base_url="${currentUrl}/v1",
api_key="Dein_Token" # Optional, falls in Mission Control konfiguriert
api_key="Dein_Token" # Optional
)
response = client.chat.completions.create(
@@ -50,19 +53,13 @@ print(response.choices[0].message.content)</code></pre>
</div>
<div class="card" style="grid-column: span 2;">
<div class="card-h"><h3>n8n / Zapier / HTTP Node</h3></div>
<p>Führe direkte HTTP POST Requests gegen den Endpunkt aus.</p>
<label>Methode & URL</label>
<input class="tokin mono-sm" readonly value="POST ${currentUrl}/v1/chat/completions">
<label>Headers</label>
<input class="tokin mono-sm" readonly value="Content-Type: application/json">
<label>Body (JSON)</label>
<pre style="background: var(--bg); padding: 12px; border-radius: 8px; border: 1px solid var(--border); overflow-x: auto; color: var(--text); font-family: monospace; font-size: 13px;"><code>{
"model": "coder",
"messages": [
{ "role": "user", "content": "Erkläre mir Quantisierung." }
]
}</code></pre>
<div class="card-h"><h3>n8n (AI Agent Nodes)</h3></div>
<p>Nutze den "OpenAI Chat Model" Node in n8n Advanced AI.</p>
<label>Credentials -> OpenAI API -> Custom URL</label>
<input class="tokin mono-sm" readonly value="${currentUrl}/v1">
<p style="margin-top:12px; font-size:12px; color:var(--mut);">
Einfach den Node verbinden, "coder" als Modell-ID (Expression) eintippen und loslegen.
</p>
</div>
</div>
`;