This repository has been archived on 2026-02-15. You can view files and clone it. You cannot open issues or pull requests or push a commit.
Files
breakpilot-pwa/docs-site/services/ki-daten-pipeline/architecture/index.html
BreakPilot Dev 557305db5d
Some checks failed
ci/woodpecker/push/integration Pipeline failed
ci/woodpecker/push/main Pipeline failed
CI/CD Pipeline / Go Tests (push) Has been cancelled
CI/CD Pipeline / Python Tests (push) Has been cancelled
CI/CD Pipeline / Website Tests (push) Has been cancelled
CI/CD Pipeline / Linting (push) Has been cancelled
CI/CD Pipeline / Security Scan (push) Has been cancelled
CI/CD Pipeline / Docker Build & Push (push) Has been cancelled
CI/CD Pipeline / Integration Tests (push) Has been cancelled
CI/CD Pipeline / Deploy to Staging (push) Has been cancelled
CI/CD Pipeline / Deploy to Production (push) Has been cancelled
CI/CD Pipeline / CI Summary (push) Has been cancelled
Security Scanning / Secret Scanning (push) Has been cancelled
Security Scanning / Dependency Vulnerability Scan (push) Has been cancelled
Security Scanning / Go Security Scan (push) Has been cancelled
Security Scanning / Python Security Scan (push) Has been cancelled
Security Scanning / Node.js Security Scan (push) Has been cancelled
Security Scanning / Docker Image Security (push) Has been cancelled
Security Scanning / Security Summary (push) Has been cancelled
Tests / Go Tests (push) Has been cancelled
Tests / Python Tests (push) Has been cancelled
Tests / Integration Tests (push) Has been cancelled
Tests / Go Lint (push) Has been cancelled
Tests / Python Lint (push) Has been cancelled
Tests / Security Scan (push) Has been cancelled
Tests / All Checks Passed (push) Has been cancelled
feat: Add Academy, Whistleblower, Incidents SDK modules, pitch-deck, blog and CI/CD config
- Academy, Whistleblower, Incidents frontend pages with API proxies and types
- Vendor compliance API proxy route
- Go backend handlers and models for all new SDK modules
- Investor pitch-deck app with interactive slides
- Blog section with DSGVO, AI Act, NIS2, glossary articles
- MkDocs documentation site
- CI/CD pipelines (Woodpecker, GitHub Actions), security scanning config
- Planning and implementation documentation

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-13 21:12:16 +01:00

2930 lines
72 KiB
HTML

<!doctype html>
<html lang="de" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="canonical" href="https://macmini:8008/services/ki-daten-pipeline/architecture/">
<link rel="prev" href="../">
<link rel="next" href="../../klausur-service/">
<link rel="icon" href="../../../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.1">
<title>Architektur - Breakpilot Dokumentation</title>
<link rel="stylesheet" href="../../../assets/stylesheets/main.484c7ddc.min.css">
<link rel="stylesheet" href="../../../assets/stylesheets/palette.ab4e12ef.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<script>__md_scope=new URL("../../..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="teal" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#ki-daten-pipeline-architektur" class="md-skip">
Zum Inhalt
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Kopfzeile">
<a href="../../.." title="Breakpilot Dokumentation" class="md-header__button md-logo" aria-label="Breakpilot Dokumentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
Breakpilot Dokumentation
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Architektur
</span>
</div>
</div>
</div>
<form class="md-header__option" data-md-component="palette">
<input class="md-option" data-md-color-media="" data-md-color-scheme="default" data-md-color-primary="teal" data-md-color-accent="indigo" aria-label="Dark Mode aktivieren" type="radio" name="__palette" id="__palette_0">
<label class="md-header__button md-icon" title="Dark Mode aktivieren" for="__palette_1" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a4 4 0 0 0-4 4 4 4 0 0 0 4 4 4 4 0 0 0 4-4 4 4 0 0 0-4-4m0 10a6 6 0 0 1-6-6 6 6 0 0 1 6-6 6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="teal" data-md-color-accent="indigo" aria-label="Light Mode aktivieren" type="radio" name="__palette" id="__palette_1">
<label class="md-header__button md-icon" title="Light Mode aktivieren" for="__palette_0" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12s-1.44-4.5-3.5-5.45C10.26 6.2 11.11 6 12 6a6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
</form>
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Suche" placeholder="Suche" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Suche">
<button type="reset" class="md-search__icon md-icon" title="Zurücksetzen" aria-label="Zurücksetzen" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
<div class="md-search__suggest" data-md-component="search-suggest"></div>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Suche wird initialisiert
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<nav class="md-tabs" aria-label="Hauptnavigation" data-md-component="tabs">
<div class="md-grid">
<ul class="md-tabs__list">
<li class="md-tabs__item">
<a href="../../.." class="md-tabs__link">
Start
</a>
</li>
<li class="md-tabs__item">
<a href="../../../getting-started/environment-setup/" class="md-tabs__link">
Erste Schritte
</a>
</li>
<li class="md-tabs__item">
<a href="../../../architecture/system-architecture/" class="md-tabs__link">
Architektur
</a>
</li>
<li class="md-tabs__item md-tabs__item--active">
<a href="../" class="md-tabs__link">
Services
</a>
</li>
<li class="md-tabs__item">
<a href="../../../api/backend-api/" class="md-tabs__link">
API
</a>
</li>
<li class="md-tabs__item">
<a href="../../../development/testing/" class="md-tabs__link">
Entwicklung
</a>
</li>
</ul>
</div>
</nav>
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary md-nav--lifted" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../../.." title="Breakpilot Dokumentation" class="md-nav__button md-logo" aria-label="Breakpilot Dokumentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
Breakpilot Dokumentation
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../.." class="md-nav__link">
<span class="md-ellipsis">
Start
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_2" >
<label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
<span class="md-ellipsis">
Erste Schritte
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
Erste Schritte
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../getting-started/environment-setup/" class="md-nav__link">
<span class="md-ellipsis">
Umgebung einrichten
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../getting-started/mac-mini-setup/" class="md-nav__link">
<span class="md-ellipsis">
Mac Mini Setup
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_3" >
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0">
<span class="md-ellipsis">
Architektur
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Architektur
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../architecture/system-architecture/" class="md-nav__link">
<span class="md-ellipsis">
Systemuebersicht
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../architecture/auth-system/" class="md-nav__link">
<span class="md-ellipsis">
Auth-System
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../architecture/mail-rbac-architecture/" class="md-nav__link">
<span class="md-ellipsis">
Mail-RBAC
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../architecture/multi-agent/" class="md-nav__link">
<span class="md-ellipsis">
Multi-Agent
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../architecture/secrets-management/" class="md-nav__link">
<span class="md-ellipsis">
Secrets Management
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../architecture/devsecops/" class="md-nav__link">
<span class="md-ellipsis">
DevSecOps
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../architecture/sdk-protection/" class="md-nav__link">
<span class="md-ellipsis">
SDK Protection
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../architecture/environments/" class="md-nav__link">
<span class="md-ellipsis">
Environments
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../architecture/zeugnis-system/" class="md-nav__link">
<span class="md-ellipsis">
Zeugnis-System
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" checked>
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="">
<span class="md-ellipsis">
Services
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Services
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--active md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4_1" checked>
<label class="md-nav__link" for="__nav_4_1" id="__nav_4_1_label" tabindex="">
<span class="md-ellipsis">
KI-Daten-Pipeline
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_4_1_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_4_1">
<span class="md-nav__icon md-icon"></span>
KI-Daten-Pipeline
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../" class="md-nav__link">
<span class="md-ellipsis">
Uebersicht
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
Architektur
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Architektur
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Inhaltsverzeichnis">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Inhaltsverzeichnis
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#systemuebersicht" class="md-nav__link">
<span class="md-ellipsis">
Systemuebersicht
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#komponenten-details" class="md-nav__link">
<span class="md-ellipsis">
Komponenten-Details
</span>
</a>
<nav class="md-nav" aria-label="Komponenten-Details">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#ocr-labeling-modul" class="md-nav__link">
<span class="md-ellipsis">
OCR-Labeling Modul
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#rag-pipeline-modul" class="md-nav__link">
<span class="md-ellipsis">
RAG Pipeline Modul
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#daten-rag-modul" class="md-nav__link">
<span class="md-ellipsis">
Daten &amp; RAG Modul
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#datenmodelle" class="md-nav__link">
<span class="md-ellipsis">
Datenmodelle
</span>
</a>
<nav class="md-nav" aria-label="Datenmodelle">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#ocr-labeling" class="md-nav__link">
<span class="md-ellipsis">
OCR-Labeling
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#rag-pipeline" class="md-nav__link">
<span class="md-ellipsis">
RAG Pipeline
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#legal-corpus" class="md-nav__link">
<span class="md-ellipsis">
Legal Corpus
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#qdrant-collections" class="md-nav__link">
<span class="md-ellipsis">
Qdrant Collections
</span>
</a>
<nav class="md-nav" aria-label="Qdrant Collections">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#konfiguration" class="md-nav__link">
<span class="md-ellipsis">
Konfiguration
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#chunk-strategie" class="md-nav__link">
<span class="md-ellipsis">
Chunk-Strategie
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#api-authentifizierung" class="md-nav__link">
<span class="md-ellipsis">
API-Authentifizierung
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#monitoring-metriken" class="md-nav__link">
<span class="md-ellipsis">
Monitoring &amp; Metriken
</span>
</a>
<nav class="md-nav" aria-label="Monitoring &amp; Metriken">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#verfuegbare-metriken" class="md-nav__link">
<span class="md-ellipsis">
Verfuegbare Metriken
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#logging" class="md-nav__link">
<span class="md-ellipsis">
Logging
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#fehlerbehandlung" class="md-nav__link">
<span class="md-ellipsis">
Fehlerbehandlung
</span>
</a>
<nav class="md-nav" aria-label="Fehlerbehandlung">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#retry-strategien" class="md-nav__link">
<span class="md-ellipsis">
Retry-Strategien
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#fallback-verhalten" class="md-nav__link">
<span class="md-ellipsis">
Fallback-Verhalten
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#skalierung" class="md-nav__link">
<span class="md-ellipsis">
Skalierung
</span>
</a>
<nav class="md-nav" aria-label="Skalierung">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#aktueller-stand" class="md-nav__link">
<span class="md-ellipsis">
Aktueller Stand
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#geplante-erweiterungen" class="md-nav__link">
<span class="md-ellipsis">
Geplante Erweiterungen
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_4_2" >
<label class="md-nav__link" for="__nav_4_2" id="__nav_4_2_label" tabindex="">
<span class="md-ellipsis">
Klausur-Service
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_4_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4_2">
<span class="md-nav__icon md-icon"></span>
Klausur-Service
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../klausur-service/" class="md-nav__link">
<span class="md-ellipsis">
Uebersicht
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../klausur-service/byoeh-system-erklaerung/" class="md-nav__link">
<span class="md-ellipsis">
BYOEH Systemerklaerung
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../klausur-service/BYOEH-Architecture/" class="md-nav__link">
<span class="md-ellipsis">
BYOEH Architektur
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../klausur-service/BYOEH-Developer-Guide/" class="md-nav__link">
<span class="md-ellipsis">
BYOEH Developer Guide
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../klausur-service/NiBiS-Ingestion-Pipeline/" class="md-nav__link">
<span class="md-ellipsis">
NiBiS Pipeline
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../klausur-service/OCR-Labeling-Spec/" class="md-nav__link">
<span class="md-ellipsis">
OCR Labeling
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../klausur-service/OCR-Compare/" class="md-nav__link">
<span class="md-ellipsis">
OCR Compare
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../klausur-service/RAG-Admin-Spec/" class="md-nav__link">
<span class="md-ellipsis">
RAG Admin
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../klausur-service/Worksheet-Editor-Architecture/" class="md-nav__link">
<span class="md-ellipsis">
Worksheet Editor
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../voice-service/" class="md-nav__link">
<span class="md-ellipsis">
Voice-Service
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../agent-core/" class="md-nav__link">
<span class="md-ellipsis">
Agent-Core
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_4_5" >
<label class="md-nav__link" for="__nav_4_5" id="__nav_4_5_label" tabindex="">
<span class="md-ellipsis">
AI-Compliance-SDK
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_4_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4_5">
<span class="md-nav__icon md-icon"></span>
AI-Compliance-SDK
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../ai-compliance-sdk/" class="md-nav__link">
<span class="md-ellipsis">
Uebersicht
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ai-compliance-sdk/ARCHITECTURE/" class="md-nav__link">
<span class="md-ellipsis">
Architektur
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ai-compliance-sdk/DEVELOPER/" class="md-nav__link">
<span class="md-ellipsis">
Developer Guide
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ai-compliance-sdk/AUDITOR_DOCUMENTATION/" class="md-nav__link">
<span class="md-ellipsis">
Auditor Dokumentation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ai-compliance-sdk/SBOM/" class="md-nav__link">
<span class="md-ellipsis">
SBOM
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_5" >
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
<span class="md-ellipsis">
API
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
API
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../api/backend-api/" class="md-nav__link">
<span class="md-ellipsis">
Backend API
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_6" >
<label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
<span class="md-ellipsis">
Entwicklung
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_6">
<span class="md-nav__icon md-icon"></span>
Entwicklung
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../development/testing/" class="md-nav__link">
<span class="md-ellipsis">
Testing
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../development/documentation/" class="md-nav__link">
<span class="md-ellipsis">
Dokumentation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../development/ci-cd-pipeline/" class="md-nav__link">
<span class="md-ellipsis">
CI/CD Pipeline
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Inhaltsverzeichnis">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Inhaltsverzeichnis
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#systemuebersicht" class="md-nav__link">
<span class="md-ellipsis">
Systemuebersicht
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#komponenten-details" class="md-nav__link">
<span class="md-ellipsis">
Komponenten-Details
</span>
</a>
<nav class="md-nav" aria-label="Komponenten-Details">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#ocr-labeling-modul" class="md-nav__link">
<span class="md-ellipsis">
OCR-Labeling Modul
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#rag-pipeline-modul" class="md-nav__link">
<span class="md-ellipsis">
RAG Pipeline Modul
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#daten-rag-modul" class="md-nav__link">
<span class="md-ellipsis">
Daten &amp; RAG Modul
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#datenmodelle" class="md-nav__link">
<span class="md-ellipsis">
Datenmodelle
</span>
</a>
<nav class="md-nav" aria-label="Datenmodelle">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#ocr-labeling" class="md-nav__link">
<span class="md-ellipsis">
OCR-Labeling
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#rag-pipeline" class="md-nav__link">
<span class="md-ellipsis">
RAG Pipeline
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#legal-corpus" class="md-nav__link">
<span class="md-ellipsis">
Legal Corpus
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#qdrant-collections" class="md-nav__link">
<span class="md-ellipsis">
Qdrant Collections
</span>
</a>
<nav class="md-nav" aria-label="Qdrant Collections">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#konfiguration" class="md-nav__link">
<span class="md-ellipsis">
Konfiguration
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#chunk-strategie" class="md-nav__link">
<span class="md-ellipsis">
Chunk-Strategie
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#api-authentifizierung" class="md-nav__link">
<span class="md-ellipsis">
API-Authentifizierung
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#monitoring-metriken" class="md-nav__link">
<span class="md-ellipsis">
Monitoring &amp; Metriken
</span>
</a>
<nav class="md-nav" aria-label="Monitoring &amp; Metriken">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#verfuegbare-metriken" class="md-nav__link">
<span class="md-ellipsis">
Verfuegbare Metriken
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#logging" class="md-nav__link">
<span class="md-ellipsis">
Logging
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#fehlerbehandlung" class="md-nav__link">
<span class="md-ellipsis">
Fehlerbehandlung
</span>
</a>
<nav class="md-nav" aria-label="Fehlerbehandlung">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#retry-strategien" class="md-nav__link">
<span class="md-ellipsis">
Retry-Strategien
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#fallback-verhalten" class="md-nav__link">
<span class="md-ellipsis">
Fallback-Verhalten
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#skalierung" class="md-nav__link">
<span class="md-ellipsis">
Skalierung
</span>
</a>
<nav class="md-nav" aria-label="Skalierung">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#aktueller-stand" class="md-nav__link">
<span class="md-ellipsis">
Aktueller Stand
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#geplante-erweiterungen" class="md-nav__link">
<span class="md-ellipsis">
Geplante Erweiterungen
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="ki-daten-pipeline-architektur">KI-Daten-Pipeline Architektur<a class="headerlink" href="#ki-daten-pipeline-architektur" title="Permanent link">&para;</a></h1>
<p>Diese Seite dokumentiert die technische Architektur der KI-Daten-Pipeline im Detail.</p>
<h2 id="systemuebersicht">Systemuebersicht<a class="headerlink" href="#systemuebersicht" title="Permanent link">&para;</a></h2>
<pre class="mermaid"><code>graph TB
subgraph Users["Benutzer"]
U1[Entwickler]
U2[Data Scientists]
U3[Lehrer]
end
subgraph Frontend["Frontend (admin-v2)"]
direction TB
F1["OCR-Labeling&lt;br/&gt;/ai/ocr-labeling"]
F2["RAG Pipeline&lt;br/&gt;/ai/rag-pipeline"]
F3["Daten &amp; RAG&lt;br/&gt;/ai/rag"]
F4["Klausur-Korrektur&lt;br/&gt;/ai/klausur-korrektur"]
end
subgraph Backend["Backend Services"]
direction TB
B1["klausur-service&lt;br/&gt;Port 8086"]
B2["embedding-service&lt;br/&gt;Port 8087"]
end
subgraph Storage["Persistenz"]
direction TB
D1[(PostgreSQL&lt;br/&gt;Metadaten)]
D2[(Qdrant&lt;br/&gt;Vektoren)]
D3[(MinIO&lt;br/&gt;Bilder/PDFs)]
end
subgraph External["Externe APIs"]
E1[OpenAI API]
E2[Ollama]
end
U1 --&gt; F1
U2 --&gt; F2
U3 --&gt; F4
F1 --&gt; B1
F2 --&gt; B1
F3 --&gt; B1
F4 --&gt; B1
B1 --&gt; D1
B1 --&gt; D2
B1 --&gt; D3
B1 --&gt; B2
B2 --&gt; E1
B1 --&gt; E2</code></pre>
<h2 id="komponenten-details">Komponenten-Details<a class="headerlink" href="#komponenten-details" title="Permanent link">&para;</a></h2>
<h3 id="ocr-labeling-modul">OCR-Labeling Modul<a class="headerlink" href="#ocr-labeling-modul" title="Permanent link">&para;</a></h3>
<pre class="mermaid"><code>flowchart TB
subgraph Upload["Upload-Prozess"]
U1[Bilder hochladen] --&gt; U2[MinIO speichern]
U2 --&gt; U3[Session erstellen]
end
subgraph OCR["OCR-Verarbeitung"]
O1[Bild laden] --&gt; O2{Modell wählen}
O2 --&gt;|llama3.2-vision| O3a[Vision LLM]
O2 --&gt;|trocr| O3b[Transformer]
O2 --&gt;|paddleocr| O3c[PaddleOCR]
O2 --&gt;|donut| O3d[Document AI]
O3a --&gt; O4[OCR-Text]
O3b --&gt; O4
O3c --&gt; O4
O3d --&gt; O4
end
subgraph Labeling["Labeling-Prozess"]
L1[Queue laden] --&gt; L2[Item anzeigen]
L2 --&gt; L3{Entscheidung}
L3 --&gt;|korrekt| L4[Bestaetigen]
L3 --&gt;|falsch| L5[Korrigieren]
L3 --&gt;|unklar| L6[Ueberspringen]
L4 --&gt; L7[PostgreSQL]
L5 --&gt; L7
L6 --&gt; L7
end
subgraph Export["Export"]
E1[Gelabelte Items] --&gt; E2{Format}
E2 --&gt;|TrOCR| E3a[Transformer Format]
E2 --&gt;|Llama| E3b[Vision Format]
E2 --&gt;|Generic| E3c[JSON]
end
Upload --&gt; OCR
OCR --&gt; Labeling
Labeling --&gt; Export</code></pre>
<h3 id="rag-pipeline-modul">RAG Pipeline Modul<a class="headerlink" href="#rag-pipeline-modul" title="Permanent link">&para;</a></h3>
<pre class="mermaid"><code>flowchart TB
subgraph Sources["Datenquellen"]
S1[NiBiS PDFs]
S2[Uploads]
S3[Rechtskorpus]
S4[Schulordnungen]
end
subgraph Processing["Verarbeitung"]
direction TB
P1[PDF Parser] --&gt; P2[OCR falls noetig]
P2 --&gt; P3[Text Cleaning]
P3 --&gt; P4[Chunking&lt;br/&gt;1000 chars, 200 overlap]
P4 --&gt; P5[Metadata Extraction]
end
subgraph Embedding["Embedding"]
E1[embedding-service] --&gt; E2[OpenAI API]
E2 --&gt; E3[1536-dim Vektor]
end
subgraph Indexing["Indexierung"]
I1{Collection waehlen}
I1 --&gt;|EH| I2a[bp_nibis_eh]
I1 --&gt;|Custom| I2b[bp_eh]
I1 --&gt;|Legal| I2c[bp_legal_corpus]
I1 --&gt;|Schul| I2d[bp_schulordnungen]
I2a --&gt; I3[Qdrant upsert]
I2b --&gt; I3
I2c --&gt; I3
I2d --&gt; I3
end
Sources --&gt; Processing
Processing --&gt; Embedding
Embedding --&gt; Indexing</code></pre>
<h3 id="daten-rag-modul">Daten &amp; RAG Modul<a class="headerlink" href="#daten-rag-modul" title="Permanent link">&para;</a></h3>
<pre class="mermaid"><code>flowchart TB
subgraph Query["Suchanfrage"]
Q1[User Query] --&gt; Q2[Query Embedding]
Q2 --&gt; Q3[1536-dim Vektor]
end
subgraph Search["Qdrant Suche"]
S1[Collection waehlen] --&gt; S2[Vector Search]
S2 --&gt; S3[Top-k Results]
S3 --&gt; S4[Score Filtering]
end
subgraph Results["Ergebnisse"]
R1[Chunks] --&gt; R2[Metadata anreichern]
R2 --&gt; R3[Source URLs]
R3 --&gt; R4[Response]
end
Query --&gt; Search
Search --&gt; Results</code></pre>
<h2 id="datenmodelle">Datenmodelle<a class="headerlink" href="#datenmodelle" title="Permanent link">&para;</a></h2>
<h3 id="ocr-labeling">OCR-Labeling<a class="headerlink" href="#ocr-labeling" title="Permanent link">&para;</a></h3>
<div class="highlight"><pre><span></span><code><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a><span class="kd">interface</span><span class="w"> </span><span class="nx">OCRSession</span><span class="w"> </span><span class="p">{</span>
<a id="__codelineno-0-2" name="__codelineno-0-2" href="#__codelineno-0-2"></a><span class="w"> </span><span class="nx">id</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-0-3" name="__codelineno-0-3" href="#__codelineno-0-3"></a><span class="w"> </span><span class="nx">name</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-0-4" name="__codelineno-0-4" href="#__codelineno-0-4"></a><span class="w"> </span><span class="nx">source_type</span><span class="o">:</span><span class="w"> </span><span class="s1">&#39;klausur&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;handwriting_sample&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;scan&#39;</span>
<a id="__codelineno-0-5" name="__codelineno-0-5" href="#__codelineno-0-5"></a><span class="w"> </span><span class="nx">ocr_model</span><span class="o">:</span><span class="w"> </span><span class="s1">&#39;llama3.2-vision:11b&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;trocr&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;paddleocr&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;donut&#39;</span>
<a id="__codelineno-0-6" name="__codelineno-0-6" href="#__codelineno-0-6"></a><span class="w"> </span><span class="nx">total_items</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span>
<a id="__codelineno-0-7" name="__codelineno-0-7" href="#__codelineno-0-7"></a><span class="w"> </span><span class="nx">labeled_items</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span>
<a id="__codelineno-0-8" name="__codelineno-0-8" href="#__codelineno-0-8"></a><span class="w"> </span><span class="nx">status</span><span class="o">:</span><span class="w"> </span><span class="s1">&#39;active&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;completed&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;archived&#39;</span>
<a id="__codelineno-0-9" name="__codelineno-0-9" href="#__codelineno-0-9"></a><span class="w"> </span><span class="nx">created_at</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-0-10" name="__codelineno-0-10" href="#__codelineno-0-10"></a><span class="p">}</span>
<a id="__codelineno-0-11" name="__codelineno-0-11" href="#__codelineno-0-11"></a>
<a id="__codelineno-0-12" name="__codelineno-0-12" href="#__codelineno-0-12"></a><span class="kd">interface</span><span class="w"> </span><span class="nx">OCRItem</span><span class="w"> </span><span class="p">{</span>
<a id="__codelineno-0-13" name="__codelineno-0-13" href="#__codelineno-0-13"></a><span class="w"> </span><span class="nx">id</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-0-14" name="__codelineno-0-14" href="#__codelineno-0-14"></a><span class="w"> </span><span class="nx">session_id</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-0-15" name="__codelineno-0-15" href="#__codelineno-0-15"></a><span class="w"> </span><span class="nx">image_path</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-0-16" name="__codelineno-0-16" href="#__codelineno-0-16"></a><span class="w"> </span><span class="nx">ocr_text</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="kc">null</span>
<a id="__codelineno-0-17" name="__codelineno-0-17" href="#__codelineno-0-17"></a><span class="w"> </span><span class="nx">ocr_confidence</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="kc">null</span>
<a id="__codelineno-0-18" name="__codelineno-0-18" href="#__codelineno-0-18"></a><span class="w"> </span><span class="nx">ground_truth</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="kc">null</span>
<a id="__codelineno-0-19" name="__codelineno-0-19" href="#__codelineno-0-19"></a><span class="w"> </span><span class="nx">status</span><span class="o">:</span><span class="w"> </span><span class="s1">&#39;pending&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;confirmed&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;corrected&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;skipped&#39;</span>
<a id="__codelineno-0-20" name="__codelineno-0-20" href="#__codelineno-0-20"></a><span class="w"> </span><span class="nx">label_time_seconds</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="kc">null</span>
<a id="__codelineno-0-21" name="__codelineno-0-21" href="#__codelineno-0-21"></a><span class="p">}</span>
</code></pre></div>
<h3 id="rag-pipeline">RAG Pipeline<a class="headerlink" href="#rag-pipeline" title="Permanent link">&para;</a></h3>
<div class="highlight"><pre><span></span><code><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></a><span class="kd">interface</span><span class="w"> </span><span class="nx">TrainingJob</span><span class="w"> </span><span class="p">{</span>
<a id="__codelineno-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a><span class="w"> </span><span class="nx">id</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-1-3" name="__codelineno-1-3" href="#__codelineno-1-3"></a><span class="w"> </span><span class="nx">name</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-1-4" name="__codelineno-1-4" href="#__codelineno-1-4"></a><span class="w"> </span><span class="nx">status</span><span class="o">:</span><span class="w"> </span><span class="s1">&#39;queued&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;preparing&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;training&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;validating&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;completed&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;failed&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;paused&#39;</span>
<a id="__codelineno-1-5" name="__codelineno-1-5" href="#__codelineno-1-5"></a><span class="w"> </span><span class="nx">progress</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span>
<a id="__codelineno-1-6" name="__codelineno-1-6" href="#__codelineno-1-6"></a><span class="w"> </span><span class="nx">current_epoch</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span>
<a id="__codelineno-1-7" name="__codelineno-1-7" href="#__codelineno-1-7"></a><span class="w"> </span><span class="nx">total_epochs</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span>
<a id="__codelineno-1-8" name="__codelineno-1-8" href="#__codelineno-1-8"></a><span class="w"> </span><span class="nx">documents_processed</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span>
<a id="__codelineno-1-9" name="__codelineno-1-9" href="#__codelineno-1-9"></a><span class="w"> </span><span class="nx">total_documents</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span>
<a id="__codelineno-1-10" name="__codelineno-1-10" href="#__codelineno-1-10"></a><span class="w"> </span><span class="nx">config</span><span class="o">:</span><span class="w"> </span><span class="p">{</span>
<a id="__codelineno-1-11" name="__codelineno-1-11" href="#__codelineno-1-11"></a><span class="w"> </span><span class="nx">batch_size</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span>
<a id="__codelineno-1-12" name="__codelineno-1-12" href="#__codelineno-1-12"></a><span class="w"> </span><span class="nx">bundeslaender</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span><span class="p">[]</span>
<a id="__codelineno-1-13" name="__codelineno-1-13" href="#__codelineno-1-13"></a><span class="w"> </span><span class="nx">mixed_precision</span><span class="o">:</span><span class="w"> </span><span class="kt">boolean</span>
<a id="__codelineno-1-14" name="__codelineno-1-14" href="#__codelineno-1-14"></a><span class="w"> </span><span class="p">}</span>
<a id="__codelineno-1-15" name="__codelineno-1-15" href="#__codelineno-1-15"></a><span class="p">}</span>
<a id="__codelineno-1-16" name="__codelineno-1-16" href="#__codelineno-1-16"></a>
<a id="__codelineno-1-17" name="__codelineno-1-17" href="#__codelineno-1-17"></a><span class="kd">interface</span><span class="w"> </span><span class="nx">DataSource</span><span class="w"> </span><span class="p">{</span>
<a id="__codelineno-1-18" name="__codelineno-1-18" href="#__codelineno-1-18"></a><span class="w"> </span><span class="nx">id</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-1-19" name="__codelineno-1-19" href="#__codelineno-1-19"></a><span class="w"> </span><span class="nx">name</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-1-20" name="__codelineno-1-20" href="#__codelineno-1-20"></a><span class="w"> </span><span class="nx">collection</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-1-21" name="__codelineno-1-21" href="#__codelineno-1-21"></a><span class="w"> </span><span class="nx">document_count</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span>
<a id="__codelineno-1-22" name="__codelineno-1-22" href="#__codelineno-1-22"></a><span class="w"> </span><span class="nx">chunk_count</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span>
<a id="__codelineno-1-23" name="__codelineno-1-23" href="#__codelineno-1-23"></a><span class="w"> </span><span class="nx">status</span><span class="o">:</span><span class="w"> </span><span class="s1">&#39;active&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;pending&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;error&#39;</span>
<a id="__codelineno-1-24" name="__codelineno-1-24" href="#__codelineno-1-24"></a><span class="w"> </span><span class="nx">last_updated</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="kc">null</span>
<a id="__codelineno-1-25" name="__codelineno-1-25" href="#__codelineno-1-25"></a><span class="p">}</span>
</code></pre></div>
<h3 id="legal-corpus">Legal Corpus<a class="headerlink" href="#legal-corpus" title="Permanent link">&para;</a></h3>
<div class="highlight"><pre><span></span><code><a id="__codelineno-2-1" name="__codelineno-2-1" href="#__codelineno-2-1"></a><span class="kd">interface</span><span class="w"> </span><span class="nx">RegulationStatus</span><span class="w"> </span><span class="p">{</span>
<a id="__codelineno-2-2" name="__codelineno-2-2" href="#__codelineno-2-2"></a><span class="w"> </span><span class="nx">code</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-2-3" name="__codelineno-2-3" href="#__codelineno-2-3"></a><span class="w"> </span><span class="nx">name</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-2-4" name="__codelineno-2-4" href="#__codelineno-2-4"></a><span class="w"> </span><span class="nx">fullName</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-2-5" name="__codelineno-2-5" href="#__codelineno-2-5"></a><span class="w"> </span><span class="kr">type</span><span class="o">:</span><span class="w"> </span><span class="s1">&#39;eu_regulation&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;eu_directive&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;de_law&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;bsi_standard&#39;</span>
<a id="__codelineno-2-6" name="__codelineno-2-6" href="#__codelineno-2-6"></a><span class="w"> </span><span class="nx">chunkCount</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span>
<a id="__codelineno-2-7" name="__codelineno-2-7" href="#__codelineno-2-7"></a><span class="w"> </span><span class="nx">status</span><span class="o">:</span><span class="w"> </span><span class="s1">&#39;ready&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;empty&#39;</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="s1">&#39;error&#39;</span>
<a id="__codelineno-2-8" name="__codelineno-2-8" href="#__codelineno-2-8"></a><span class="p">}</span>
<a id="__codelineno-2-9" name="__codelineno-2-9" href="#__codelineno-2-9"></a>
<a id="__codelineno-2-10" name="__codelineno-2-10" href="#__codelineno-2-10"></a><span class="kd">interface</span><span class="w"> </span><span class="nx">SearchResult</span><span class="w"> </span><span class="p">{</span>
<a id="__codelineno-2-11" name="__codelineno-2-11" href="#__codelineno-2-11"></a><span class="w"> </span><span class="nx">text</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-2-12" name="__codelineno-2-12" href="#__codelineno-2-12"></a><span class="w"> </span><span class="nx">regulation_code</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-2-13" name="__codelineno-2-13" href="#__codelineno-2-13"></a><span class="w"> </span><span class="nx">regulation_name</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-2-14" name="__codelineno-2-14" href="#__codelineno-2-14"></a><span class="w"> </span><span class="nx">article</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="kc">null</span>
<a id="__codelineno-2-15" name="__codelineno-2-15" href="#__codelineno-2-15"></a><span class="w"> </span><span class="nx">paragraph</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span><span class="w"> </span><span class="o">|</span><span class="w"> </span><span class="kc">null</span>
<a id="__codelineno-2-16" name="__codelineno-2-16" href="#__codelineno-2-16"></a><span class="w"> </span><span class="nx">source_url</span><span class="o">:</span><span class="w"> </span><span class="kt">string</span>
<a id="__codelineno-2-17" name="__codelineno-2-17" href="#__codelineno-2-17"></a><span class="w"> </span><span class="nx">score</span><span class="o">:</span><span class="w"> </span><span class="kt">number</span>
<a id="__codelineno-2-18" name="__codelineno-2-18" href="#__codelineno-2-18"></a><span class="p">}</span>
</code></pre></div>
<h2 id="qdrant-collections">Qdrant Collections<a class="headerlink" href="#qdrant-collections" title="Permanent link">&para;</a></h2>
<h3 id="konfiguration">Konfiguration<a class="headerlink" href="#konfiguration" title="Permanent link">&para;</a></h3>
<table>
<thead>
<tr>
<th>Collection</th>
<th>Vektor-Dimension</th>
<th>Distanz-Metrik</th>
<th>Payload</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>bp_nibis_eh</code></td>
<td>1536</td>
<td>COSINE</td>
<td>bundesland, fach, aufgabe</td>
</tr>
<tr>
<td><code>bp_eh</code></td>
<td>1536</td>
<td>COSINE</td>
<td>user_id, klausur_id</td>
</tr>
<tr>
<td><code>bp_legal_corpus</code></td>
<td>1536</td>
<td>COSINE</td>
<td>regulation, article, source_url</td>
</tr>
<tr>
<td><code>bp_schulordnungen</code></td>
<td>1536</td>
<td>COSINE</td>
<td>bundesland, typ, datum</td>
</tr>
</tbody>
</table>
<h3 id="chunk-strategie">Chunk-Strategie<a class="headerlink" href="#chunk-strategie" title="Permanent link">&para;</a></h3>
<div class="highlight"><pre><span></span><code><a id="__codelineno-3-1" name="__codelineno-3-1" href="#__codelineno-3-1"></a>┌─────────────────────────────────────────────────────────────┐
<a id="__codelineno-3-2" name="__codelineno-3-2" href="#__codelineno-3-2"></a>│ Originaldokument │
<a id="__codelineno-3-3" name="__codelineno-3-3" href="#__codelineno-3-3"></a>│ Lorem ipsum dolor sit amet, consectetur adipiscing elit... │
<a id="__codelineno-3-4" name="__codelineno-3-4" href="#__codelineno-3-4"></a>└─────────────────────────────────────────────────────────────┘
<a id="__codelineno-3-5" name="__codelineno-3-5" href="#__codelineno-3-5"></a>
<a id="__codelineno-3-6" name="__codelineno-3-6" href="#__codelineno-3-6"></a>
<a id="__codelineno-3-7" name="__codelineno-3-7" href="#__codelineno-3-7"></a>┌──────────────────────┐ ┌──────────────────────┐ ┌──────────────────────┐
<a id="__codelineno-3-8" name="__codelineno-3-8" href="#__codelineno-3-8"></a>│ Chunk 1 │ │ Chunk 2 │ │ Chunk 3 │
<a id="__codelineno-3-9" name="__codelineno-3-9" href="#__codelineno-3-9"></a>│ 0-1000 chars │ │ 800-1800 chars │ │ 1600-2600 chars │
<a id="__codelineno-3-10" name="__codelineno-3-10" href="#__codelineno-3-10"></a>│ │ │ (200 overlap) │ │ (200 overlap) │
<a id="__codelineno-3-11" name="__codelineno-3-11" href="#__codelineno-3-11"></a>└──────────────────────┘ └──────────────────────┘ └──────────────────────┘
</code></pre></div>
<h2 id="api-authentifizierung">API-Authentifizierung<a class="headerlink" href="#api-authentifizierung" title="Permanent link">&para;</a></h2>
<p>Alle Endpunkte nutzen die zentrale Auth-Middleware:</p>
<pre class="mermaid"><code>sequenceDiagram
participant C as Client
participant A as API Gateway
participant S as klausur-service
participant D as Datenbank
C-&gt;&gt;A: Request + JWT Token
A-&gt;&gt;A: Token validieren
A-&gt;&gt;S: Forwarded Request
S-&gt;&gt;D: Daten abfragen
D-&gt;&gt;S: Response
S-&gt;&gt;C: JSON Response</code></pre>
<h2 id="monitoring-metriken">Monitoring &amp; Metriken<a class="headerlink" href="#monitoring-metriken" title="Permanent link">&para;</a></h2>
<h3 id="verfuegbare-metriken">Verfuegbare Metriken<a class="headerlink" href="#verfuegbare-metriken" title="Permanent link">&para;</a></h3>
<table>
<thead>
<tr>
<th>Metrik</th>
<th>Beschreibung</th>
<th>Endpoint</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>ocr_items_total</code></td>
<td>Gesamtzahl OCR-Items</td>
<td><code>/api/v1/ocr-label/stats</code></td>
</tr>
<tr>
<td><code>ocr_accuracy_rate</code></td>
<td>OCR-Genauigkeit</td>
<td><code>/api/v1/ocr-label/stats</code></td>
</tr>
<tr>
<td><code>rag_chunk_count</code></td>
<td>Anzahl indexierter Chunks</td>
<td><code>/api/legal-corpus/status</code></td>
</tr>
<tr>
<td><code>rag_collection_status</code></td>
<td>Collection-Status</td>
<td><code>/api/legal-corpus/status</code></td>
</tr>
</tbody>
</table>
<h3 id="logging">Logging<a class="headerlink" href="#logging" title="Permanent link">&para;</a></h3>
<div class="highlight"><pre><span></span><code><a id="__codelineno-4-1" name="__codelineno-4-1" href="#__codelineno-4-1"></a><span class="c1"># Strukturiertes Logging im klausur-service</span>
<a id="__codelineno-4-2" name="__codelineno-4-2" href="#__codelineno-4-2"></a><span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;OCR processing started&quot;</span><span class="p">,</span> <span class="n">extra</span><span class="o">=</span><span class="p">{</span>
<a id="__codelineno-4-3" name="__codelineno-4-3" href="#__codelineno-4-3"></a> <span class="s2">&quot;session_id&quot;</span><span class="p">:</span> <span class="n">session_id</span><span class="p">,</span>
<a id="__codelineno-4-4" name="__codelineno-4-4" href="#__codelineno-4-4"></a> <span class="s2">&quot;item_count&quot;</span><span class="p">:</span> <span class="n">item_count</span><span class="p">,</span>
<a id="__codelineno-4-5" name="__codelineno-4-5" href="#__codelineno-4-5"></a> <span class="s2">&quot;model&quot;</span><span class="p">:</span> <span class="n">ocr_model</span>
<a id="__codelineno-4-6" name="__codelineno-4-6" href="#__codelineno-4-6"></a><span class="p">})</span>
</code></pre></div>
<h2 id="fehlerbehandlung">Fehlerbehandlung<a class="headerlink" href="#fehlerbehandlung" title="Permanent link">&para;</a></h2>
<h3 id="retry-strategien">Retry-Strategien<a class="headerlink" href="#retry-strategien" title="Permanent link">&para;</a></h3>
<table>
<thead>
<tr>
<th>Operation</th>
<th>Max Retries</th>
<th>Backoff</th>
</tr>
</thead>
<tbody>
<tr>
<td>OCR-Verarbeitung</td>
<td>3</td>
<td>Exponentiell (1s, 2s, 4s)</td>
</tr>
<tr>
<td>Embedding-API</td>
<td>5</td>
<td>Exponentiell mit Jitter</td>
</tr>
<tr>
<td>Qdrant-Upsert</td>
<td>3</td>
<td>Linear (1s)</td>
</tr>
</tbody>
</table>
<h3 id="fallback-verhalten">Fallback-Verhalten<a class="headerlink" href="#fallback-verhalten" title="Permanent link">&para;</a></h3>
<pre class="mermaid"><code>flowchart TD
A[Embedding Request] --&gt; B{OpenAI verfuegbar?}
B --&gt;|Ja| C[OpenAI API]
B --&gt;|Nein| D{Lokales Modell?}
D --&gt;|Ja| E[Ollama Embedding]
D --&gt;|Nein| F[Error + Queue]</code></pre>
<h2 id="skalierung">Skalierung<a class="headerlink" href="#skalierung" title="Permanent link">&para;</a></h2>
<h3 id="aktueller-stand">Aktueller Stand<a class="headerlink" href="#aktueller-stand" title="Permanent link">&para;</a></h3>
<ul>
<li><strong>Single Node</strong>: Alle Services auf Mac Mini</li>
<li><strong>Qdrant</strong>: Standalone, ~50k Chunks</li>
<li><strong>PostgreSQL</strong>: Shared mit anderen Services</li>
</ul>
<h3 id="geplante-erweiterungen">Geplante Erweiterungen<a class="headerlink" href="#geplante-erweiterungen" title="Permanent link">&para;</a></h3>
<ol>
<li><strong>Qdrant Cluster</strong>: Bei &gt; 1M Chunks</li>
<li><strong>Worker Queue</strong>: Redis-basiert fuer Batch-Jobs</li>
<li><strong>GPU-Offloading</strong>: OCR auf vast.ai GPU-Instanzen</li>
</ol>
</article>
</div>
<script>var tabs=__md_get("__tabs");if(Array.isArray(tabs))e:for(var set of document.querySelectorAll(".tabbed-set")){var labels=set.querySelector(".tabbed-labels");for(var tab of tabs)for(var label of labels.getElementsByTagName("label"))if(label.innerText.trim()===tab){var input=document.getElementById(label.htmlFor);input.checked=!0;continue e}}</script>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
<button type="button" class="md-top md-icon" data-md-component="top" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8z"/></svg>
Zurück zum Seitenanfang
</button>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
<div class="md-social">
<a href="http://macmini:3003/breakpilot/breakpilot-pwa" target="_blank" rel="noopener" title="macmini:3003" class="md-social__link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M173.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6m-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3m44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9M252.8 8C114.1 8 8 113.3 8 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C436.2 457.8 504 362.9 504 252 504 113.3 391.5 8 252.8 8M105.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1m-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7m32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1m-11.4-14.7c-1.6 1-1.6 3.6 0 5.9s4.3 3.3 5.6 2.3c1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2"/></svg>
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"annotate": null, "base": "../../..", "features": ["search.highlight", "search.suggest", "navigation.tabs", "navigation.sections", "navigation.expand", "navigation.top", "content.code.copy", "content.tabs.link", "toc.follow"], "search": "../../../assets/javascripts/workers/search.2c215733.min.js", "tags": null, "translations": {"clipboard.copied": "In Zwischenablage kopiert", "clipboard.copy": "In Zwischenablage kopieren", "search.result.more.one": "1 weiteres Suchergebnis auf dieser Seite", "search.result.more.other": "# weitere Suchergebnisse auf dieser Seite", "search.result.none": "Keine Suchergebnisse", "search.result.one": "1 Suchergebnis", "search.result.other": "# Suchergebnisse", "search.result.placeholder": "Suchbegriff eingeben", "search.result.term.missing": "Es fehlt", "select.version": "Version ausw\u00e4hlen"}, "version": null}</script>
<script src="../../../assets/javascripts/bundle.79ae519e.min.js"></script>
</body>
</html>