This repository has been archived on 2026-02-15.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/klausur-service/NiBiS-Ingestion-Pipeline/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

2806 lines
69 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/klausur-service/NiBiS-Ingestion-Pipeline/">
<link rel="prev" href="../BYOEH-Developer-Guide/">
<link rel="next" href="../OCR-Labeling-Spec/">
<link rel="icon" href="../../../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.1">
<title>NiBiS Pipeline - 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="#nibis-ingestion-pipeline" 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">
NiBiS Pipeline
</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="../../ki-daten-pipeline/" 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--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_4_1" >
<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="false">
<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="../../ki-daten-pipeline/" class="md-nav__link">
<span class="md-ellipsis">
Uebersicht
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ki-daten-pipeline/architecture/" class="md-nav__link">
<span class="md-ellipsis">
Architektur
</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_2" checked>
<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="true">
<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="../" class="md-nav__link">
<span class="md-ellipsis">
Uebersicht
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../byoeh-system-erklaerung/" class="md-nav__link">
<span class="md-ellipsis">
BYOEH Systemerklaerung
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../BYOEH-Architecture/" class="md-nav__link">
<span class="md-ellipsis">
BYOEH Architektur
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../BYOEH-Developer-Guide/" class="md-nav__link">
<span class="md-ellipsis">
BYOEH Developer Guide
</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">
NiBiS Pipeline
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
NiBiS Pipeline
</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="#overview" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#unterstutzte-daten" class="md-nav__link">
<span class="md-ellipsis">
Unterstützte Daten
</span>
</a>
<nav class="md-nav" aria-label="Unterstützte Daten">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#verzeichnisse" class="md-nav__link">
<span class="md-ellipsis">
Verzeichnisse
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#dokumenttypen" class="md-nav__link">
<span class="md-ellipsis">
Dokumenttypen
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#facher" class="md-nav__link">
<span class="md-ellipsis">
Fächer
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#architektur" class="md-nav__link">
<span class="md-ellipsis">
Architektur
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#verwendung" class="md-nav__link">
<span class="md-ellipsis">
Verwendung
</span>
</a>
<nav class="md-nav" aria-label="Verwendung">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#via-api-empfohlen" class="md-nav__link">
<span class="md-ellipsis">
Via API (empfohlen)
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#via-cli" class="md-nav__link">
<span class="md-ellipsis">
Via CLI
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#via-shell-script" class="md-nav__link">
<span class="md-ellipsis">
Via Shell Script
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#qdrant-schema" class="md-nav__link">
<span class="md-ellipsis">
Qdrant Schema
</span>
</a>
<nav class="md-nav" aria-label="Qdrant Schema">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#collection-bp_nibis_eh" class="md-nav__link">
<span class="md-ellipsis">
Collection: bp_nibis_eh
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#api-endpoints" class="md-nav__link">
<span class="md-ellipsis">
API Endpoints
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#erweiterung-fur-andere-bundeslander" class="md-nav__link">
<span class="md-ellipsis">
Erweiterung für andere Bundesländer
</span>
</a>
<nav class="md-nav" aria-label="Erweiterung für andere Bundesländer">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#1-neues-bundesland-hinzufugen" class="md-nav__link">
<span class="md-ellipsis">
1. Neues Bundesland hinzufügen
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#2-neues-verzeichnis-registrieren" class="md-nav__link">
<span class="md-ellipsis">
2. Neues Verzeichnis registrieren
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#3-dokumenttyp-erweiterung" class="md-nav__link">
<span class="md-ellipsis">
3. Dokumenttyp-Erweiterung
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#rechtliche-hinweise" class="md-nav__link">
<span class="md-ellipsis">
Rechtliche Hinweise
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#troubleshooting" class="md-nav__link">
<span class="md-ellipsis">
Troubleshooting
</span>
</a>
<nav class="md-nav" aria-label="Troubleshooting">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#qdrant-nicht-erreichbar" class="md-nav__link">
<span class="md-ellipsis">
Qdrant nicht erreichbar
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#openai-api-fehler" class="md-nav__link">
<span class="md-ellipsis">
OpenAI API Fehler
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#pdf-extraktion-fehlgeschlagen" class="md-nav__link">
<span class="md-ellipsis">
PDF-Extraktion fehlgeschlagen
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#performance" class="md-nav__link">
<span class="md-ellipsis">
Performance
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../OCR-Labeling-Spec/" class="md-nav__link">
<span class="md-ellipsis">
OCR Labeling
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../OCR-Compare/" class="md-nav__link">
<span class="md-ellipsis">
OCR Compare
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../RAG-Admin-Spec/" class="md-nav__link">
<span class="md-ellipsis">
RAG Admin
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../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="#overview" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#unterstutzte-daten" class="md-nav__link">
<span class="md-ellipsis">
Unterstützte Daten
</span>
</a>
<nav class="md-nav" aria-label="Unterstützte Daten">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#verzeichnisse" class="md-nav__link">
<span class="md-ellipsis">
Verzeichnisse
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#dokumenttypen" class="md-nav__link">
<span class="md-ellipsis">
Dokumenttypen
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#facher" class="md-nav__link">
<span class="md-ellipsis">
Fächer
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#architektur" class="md-nav__link">
<span class="md-ellipsis">
Architektur
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#verwendung" class="md-nav__link">
<span class="md-ellipsis">
Verwendung
</span>
</a>
<nav class="md-nav" aria-label="Verwendung">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#via-api-empfohlen" class="md-nav__link">
<span class="md-ellipsis">
Via API (empfohlen)
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#via-cli" class="md-nav__link">
<span class="md-ellipsis">
Via CLI
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#via-shell-script" class="md-nav__link">
<span class="md-ellipsis">
Via Shell Script
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#qdrant-schema" class="md-nav__link">
<span class="md-ellipsis">
Qdrant Schema
</span>
</a>
<nav class="md-nav" aria-label="Qdrant Schema">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#collection-bp_nibis_eh" class="md-nav__link">
<span class="md-ellipsis">
Collection: bp_nibis_eh
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#api-endpoints" class="md-nav__link">
<span class="md-ellipsis">
API Endpoints
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#erweiterung-fur-andere-bundeslander" class="md-nav__link">
<span class="md-ellipsis">
Erweiterung für andere Bundesländer
</span>
</a>
<nav class="md-nav" aria-label="Erweiterung für andere Bundesländer">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#1-neues-bundesland-hinzufugen" class="md-nav__link">
<span class="md-ellipsis">
1. Neues Bundesland hinzufügen
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#2-neues-verzeichnis-registrieren" class="md-nav__link">
<span class="md-ellipsis">
2. Neues Verzeichnis registrieren
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#3-dokumenttyp-erweiterung" class="md-nav__link">
<span class="md-ellipsis">
3. Dokumenttyp-Erweiterung
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#rechtliche-hinweise" class="md-nav__link">
<span class="md-ellipsis">
Rechtliche Hinweise
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#troubleshooting" class="md-nav__link">
<span class="md-ellipsis">
Troubleshooting
</span>
</a>
<nav class="md-nav" aria-label="Troubleshooting">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#qdrant-nicht-erreichbar" class="md-nav__link">
<span class="md-ellipsis">
Qdrant nicht erreichbar
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#openai-api-fehler" class="md-nav__link">
<span class="md-ellipsis">
OpenAI API Fehler
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#pdf-extraktion-fehlgeschlagen" class="md-nav__link">
<span class="md-ellipsis">
PDF-Extraktion fehlgeschlagen
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#performance" class="md-nav__link">
<span class="md-ellipsis">
Performance
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="nibis-ingestion-pipeline">NiBiS Ingestion Pipeline<a class="headerlink" href="#nibis-ingestion-pipeline" title="Permanent link">&para;</a></h1>
<h2 id="overview">Overview<a class="headerlink" href="#overview" title="Permanent link">&para;</a></h2>
<p>Die NiBiS Ingestion Pipeline verarbeitet Abitur-Erwartungshorizonte aus Niedersachsen und indexiert sie in Qdrant für RAG-basierte Klausurkorrektur.</p>
<h2 id="unterstutzte-daten">Unterstützte Daten<a class="headerlink" href="#unterstutzte-daten" title="Permanent link">&para;</a></h2>
<h3 id="verzeichnisse">Verzeichnisse<a class="headerlink" href="#verzeichnisse" title="Permanent link">&para;</a></h3>
<table>
<thead>
<tr>
<th>Verzeichnis</th>
<th>Jahre</th>
<th>Namenskonvention</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>docs/za-download</code></td>
<td>2024, 2025</td>
<td><code>{Jahr}_{Fach}_{niveau}_{Nr}_EWH.pdf</code></td>
</tr>
<tr>
<td><code>docs/za-download-2</code></td>
<td>2016</td>
<td><code>{Jahr}{Fach}{Niveau}Lehrer/{Jahr}{Fach}{Niveau}A{Nr}L.pdf</code></td>
</tr>
<tr>
<td><code>docs/za-download-3</code></td>
<td>2017</td>
<td><code>{Jahr}{Fach}{Niveau}Lehrer/{Jahr}{Fach}{Niveau}A{Nr}L.pdf</code></td>
</tr>
</tbody>
</table>
<h3 id="dokumenttypen">Dokumenttypen<a class="headerlink" href="#dokumenttypen" title="Permanent link">&para;</a></h3>
<ul>
<li><strong>EWH</strong> - Erwartungshorizont (Hauptziel)</li>
<li><strong>Aufgabe</strong> - Prüfungsaufgaben</li>
<li><strong>Material</strong> - Zusatzmaterialien</li>
<li><strong>GBU</strong> - Gefährdungsbeurteilung (Chemie/Biologie)</li>
<li><strong>Bewertungsbogen</strong> - Standardisierte Bewertungsbögen</li>
</ul>
<h3 id="facher">Fächer<a class="headerlink" href="#facher" title="Permanent link">&para;</a></h3>
<p>Deutsch, Englisch, Mathematik, Informatik, Biologie, Chemie, Physik, Geschichte, Erdkunde, Kunst, Musik, Sport, Latein, Griechisch, Französisch, Spanisch, Katholische Religion, Evangelische Religion, Werte und Normen, BRC, BVW, Gesundheit-Pflege</p>
<h2 id="architektur">Architektur<a class="headerlink" href="#architektur" title="Permanent link">&para;</a></h2>
<div class="highlight"><pre><span></span><code><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a>┌─────────────────────────────────────────────────────────────────┐
<a id="__codelineno-0-2" name="__codelineno-0-2" href="#__codelineno-0-2"></a>│ NiBiS Ingestion Pipeline │
<a id="__codelineno-0-3" name="__codelineno-0-3" href="#__codelineno-0-3"></a>├─────────────────────────────────────────────────────────────────┤
<a id="__codelineno-0-4" name="__codelineno-0-4" href="#__codelineno-0-4"></a>│ │
<a id="__codelineno-0-5" name="__codelineno-0-5" href="#__codelineno-0-5"></a>│ 1. ZIP Extraction │
<a id="__codelineno-0-6" name="__codelineno-0-6" href="#__codelineno-0-6"></a>│ └── Entpackt 2024.zip, 2025.zip, etc. │
<a id="__codelineno-0-7" name="__codelineno-0-7" href="#__codelineno-0-7"></a>│ │
<a id="__codelineno-0-8" name="__codelineno-0-8" href="#__codelineno-0-8"></a>│ 2. Document Discovery │
<a id="__codelineno-0-9" name="__codelineno-0-9" href="#__codelineno-0-9"></a>│ ├── Parst alte Namenskonvention (2016/2017) │
<a id="__codelineno-0-10" name="__codelineno-0-10" href="#__codelineno-0-10"></a>│ └── Parst neue Namenskonvention (2024/2025) │
<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>│ 3. PDF Processing │
<a id="__codelineno-0-13" name="__codelineno-0-13" href="#__codelineno-0-13"></a>│ ├── Text-Extraktion (PyPDF2) │
<a id="__codelineno-0-14" name="__codelineno-0-14" href="#__codelineno-0-14"></a>│ └── Chunking (1000 chars, 200 overlap) │
<a id="__codelineno-0-15" name="__codelineno-0-15" href="#__codelineno-0-15"></a>│ │
<a id="__codelineno-0-16" name="__codelineno-0-16" href="#__codelineno-0-16"></a>│ 4. Embedding Generation │
<a id="__codelineno-0-17" name="__codelineno-0-17" href="#__codelineno-0-17"></a>│ └── OpenAI text-embedding-3-small (1536 dim) │
<a id="__codelineno-0-18" name="__codelineno-0-18" href="#__codelineno-0-18"></a>│ │
<a id="__codelineno-0-19" name="__codelineno-0-19" href="#__codelineno-0-19"></a>│ 5. Qdrant Indexing │
<a id="__codelineno-0-20" name="__codelineno-0-20" href="#__codelineno-0-20"></a>│ └── Collection: bp_nibis_eh │
<a id="__codelineno-0-21" name="__codelineno-0-21" href="#__codelineno-0-21"></a>│ │
<a id="__codelineno-0-22" name="__codelineno-0-22" href="#__codelineno-0-22"></a>└─────────────────────────────────────────────────────────────────┘
</code></pre></div>
<h2 id="verwendung">Verwendung<a class="headerlink" href="#verwendung" title="Permanent link">&para;</a></h2>
<h3 id="via-api-empfohlen">Via API (empfohlen)<a class="headerlink" href="#via-api-empfohlen" 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="c1"># 1. Vorschau der verfügbaren Dokumente</span>
<a id="__codelineno-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a>curl<span class="w"> </span>http://localhost:8086/api/v1/admin/nibis/discover
<a id="__codelineno-1-3" name="__codelineno-1-3" href="#__codelineno-1-3"></a>
<a id="__codelineno-1-4" name="__codelineno-1-4" href="#__codelineno-1-4"></a><span class="c1"># 2. ZIP-Dateien entpacken</span>
<a id="__codelineno-1-5" name="__codelineno-1-5" href="#__codelineno-1-5"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8086/api/v1/admin/nibis/extract-zips
<a id="__codelineno-1-6" name="__codelineno-1-6" href="#__codelineno-1-6"></a>
<a id="__codelineno-1-7" name="__codelineno-1-7" href="#__codelineno-1-7"></a><span class="c1"># 3. Ingestion starten</span>
<a id="__codelineno-1-8" name="__codelineno-1-8" href="#__codelineno-1-8"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8086/api/v1/admin/nibis/ingest<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-1-9" name="__codelineno-1-9" href="#__codelineno-1-9"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-1-10" name="__codelineno-1-10" href="#__codelineno-1-10"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{&quot;ewh_only&quot;: true}&#39;</span>
<a id="__codelineno-1-11" name="__codelineno-1-11" href="#__codelineno-1-11"></a>
<a id="__codelineno-1-12" name="__codelineno-1-12" href="#__codelineno-1-12"></a><span class="c1"># 4. Status prüfen</span>
<a id="__codelineno-1-13" name="__codelineno-1-13" href="#__codelineno-1-13"></a>curl<span class="w"> </span>http://localhost:8086/api/v1/admin/nibis/status
<a id="__codelineno-1-14" name="__codelineno-1-14" href="#__codelineno-1-14"></a>
<a id="__codelineno-1-15" name="__codelineno-1-15" href="#__codelineno-1-15"></a><span class="c1"># 5. Semantische Suche testen</span>
<a id="__codelineno-1-16" name="__codelineno-1-16" href="#__codelineno-1-16"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8086/api/v1/admin/nibis/search<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-1-17" name="__codelineno-1-17" href="#__codelineno-1-17"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-1-18" name="__codelineno-1-18" href="#__codelineno-1-18"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{&quot;query&quot;: &quot;Analyse literarischer Texte&quot;, &quot;subject&quot;: &quot;Deutsch&quot;, &quot;limit&quot;: 5}&#39;</span>
</code></pre></div>
<h3 id="via-cli">Via CLI<a class="headerlink" href="#via-cli" 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="c1"># Dry-Run (nur analysieren)</span>
<a id="__codelineno-2-2" name="__codelineno-2-2" href="#__codelineno-2-2"></a><span class="nb">cd</span><span class="w"> </span>klausur-service/backend
<a id="__codelineno-2-3" name="__codelineno-2-3" href="#__codelineno-2-3"></a>python<span class="w"> </span>nibis_ingestion.py<span class="w"> </span>--dry-run
<a id="__codelineno-2-4" name="__codelineno-2-4" href="#__codelineno-2-4"></a>
<a id="__codelineno-2-5" name="__codelineno-2-5" href="#__codelineno-2-5"></a><span class="c1"># Vollständige Ingestion</span>
<a id="__codelineno-2-6" name="__codelineno-2-6" href="#__codelineno-2-6"></a>python<span class="w"> </span>nibis_ingestion.py
<a id="__codelineno-2-7" name="__codelineno-2-7" href="#__codelineno-2-7"></a>
<a id="__codelineno-2-8" name="__codelineno-2-8" href="#__codelineno-2-8"></a><span class="c1"># Nur bestimmtes Jahr</span>
<a id="__codelineno-2-9" name="__codelineno-2-9" href="#__codelineno-2-9"></a>python<span class="w"> </span>nibis_ingestion.py<span class="w"> </span>--year<span class="w"> </span><span class="m">2024</span>
<a id="__codelineno-2-10" name="__codelineno-2-10" href="#__codelineno-2-10"></a>
<a id="__codelineno-2-11" name="__codelineno-2-11" href="#__codelineno-2-11"></a><span class="c1"># Nur bestimmtes Fach</span>
<a id="__codelineno-2-12" name="__codelineno-2-12" href="#__codelineno-2-12"></a>python<span class="w"> </span>nibis_ingestion.py<span class="w"> </span>--subject<span class="w"> </span>Deutsch
<a id="__codelineno-2-13" name="__codelineno-2-13" href="#__codelineno-2-13"></a>
<a id="__codelineno-2-14" name="__codelineno-2-14" href="#__codelineno-2-14"></a><span class="c1"># Manifest erstellen</span>
<a id="__codelineno-2-15" name="__codelineno-2-15" href="#__codelineno-2-15"></a>python<span class="w"> </span>nibis_ingestion.py<span class="w"> </span>--manifest<span class="w"> </span>/tmp/nibis_manifest.json
</code></pre></div>
<h3 id="via-shell-script">Via Shell Script<a class="headerlink" href="#via-shell-script" 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>./klausur-service/scripts/run_nibis_ingestion.sh<span class="w"> </span>--dry-run
<a id="__codelineno-3-2" name="__codelineno-3-2" href="#__codelineno-3-2"></a>./klausur-service/scripts/run_nibis_ingestion.sh<span class="w"> </span>--year<span class="w"> </span><span class="m">2024</span><span class="w"> </span>--subject<span class="w"> </span>Deutsch
</code></pre></div>
<h2 id="qdrant-schema">Qdrant Schema<a class="headerlink" href="#qdrant-schema" title="Permanent link">&para;</a></h2>
<h3 id="collection-bp_nibis_eh">Collection: <code>bp_nibis_eh</code><a class="headerlink" href="#collection-bp_nibis_eh" 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="p">{</span>
<a id="__codelineno-4-2" name="__codelineno-4-2" href="#__codelineno-4-2"></a><span class="w"> </span><span class="nt">&quot;id&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;nibis_2024_deutsch_ea_1_abc123_chunk_0&quot;</span><span class="p">,</span>
<a id="__codelineno-4-3" name="__codelineno-4-3" href="#__codelineno-4-3"></a><span class="w"> </span><span class="nt">&quot;vector&quot;</span><span class="p">:</span><span class="w"> </span><span class="p">[</span><span class="mi">1536</span><span class="w"> </span><span class="err">dime</span><span class="kc">ns</span><span class="err">io</span><span class="kc">ns</span><span class="p">],</span>
<a id="__codelineno-4-4" name="__codelineno-4-4" href="#__codelineno-4-4"></a><span class="w"> </span><span class="nt">&quot;payload&quot;</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
<a id="__codelineno-4-5" name="__codelineno-4-5" href="#__codelineno-4-5"></a><span class="w"> </span><span class="nt">&quot;doc_id&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;nibis_2024_deutsch_ea_1_abc123&quot;</span><span class="p">,</span>
<a id="__codelineno-4-6" name="__codelineno-4-6" href="#__codelineno-4-6"></a><span class="w"> </span><span class="nt">&quot;chunk_index&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">0</span><span class="p">,</span>
<a id="__codelineno-4-7" name="__codelineno-4-7" href="#__codelineno-4-7"></a><span class="w"> </span><span class="nt">&quot;text&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;Der Erwartungshorizont...&quot;</span><span class="p">,</span>
<a id="__codelineno-4-8" name="__codelineno-4-8" href="#__codelineno-4-8"></a><span class="w"> </span><span class="nt">&quot;year&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">2024</span><span class="p">,</span>
<a id="__codelineno-4-9" name="__codelineno-4-9" href="#__codelineno-4-9"></a><span class="w"> </span><span class="nt">&quot;subject&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;Deutsch&quot;</span><span class="p">,</span>
<a id="__codelineno-4-10" name="__codelineno-4-10" href="#__codelineno-4-10"></a><span class="w"> </span><span class="nt">&quot;niveau&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;eA&quot;</span><span class="p">,</span>
<a id="__codelineno-4-11" name="__codelineno-4-11" href="#__codelineno-4-11"></a><span class="w"> </span><span class="nt">&quot;task_number&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">1</span><span class="p">,</span>
<a id="__codelineno-4-12" name="__codelineno-4-12" href="#__codelineno-4-12"></a><span class="w"> </span><span class="nt">&quot;doc_type&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;EWH&quot;</span><span class="p">,</span>
<a id="__codelineno-4-13" name="__codelineno-4-13" href="#__codelineno-4-13"></a><span class="w"> </span><span class="nt">&quot;bundesland&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;NI&quot;</span><span class="p">,</span>
<a id="__codelineno-4-14" name="__codelineno-4-14" href="#__codelineno-4-14"></a><span class="w"> </span><span class="nt">&quot;variant&quot;</span><span class="p">:</span><span class="w"> </span><span class="kc">null</span><span class="p">,</span>
<a id="__codelineno-4-15" name="__codelineno-4-15" href="#__codelineno-4-15"></a><span class="w"> </span><span class="nt">&quot;source&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;nibis&quot;</span><span class="p">,</span>
<a id="__codelineno-4-16" name="__codelineno-4-16" href="#__codelineno-4-16"></a><span class="w"> </span><span class="nt">&quot;training_allowed&quot;</span><span class="p">:</span><span class="w"> </span><span class="kc">true</span>
<a id="__codelineno-4-17" name="__codelineno-4-17" href="#__codelineno-4-17"></a><span class="w"> </span><span class="p">}</span>
<a id="__codelineno-4-18" name="__codelineno-4-18" href="#__codelineno-4-18"></a><span class="p">}</span>
</code></pre></div>
<h2 id="api-endpoints">API Endpoints<a class="headerlink" href="#api-endpoints" title="Permanent link">&para;</a></h2>
<table>
<thead>
<tr>
<th>Methode</th>
<th>Endpoint</th>
<th>Beschreibung</th>
</tr>
</thead>
<tbody>
<tr>
<td>GET</td>
<td><code>/api/v1/admin/nibis/status</code></td>
<td>Ingestion-Status</td>
</tr>
<tr>
<td>POST</td>
<td><code>/api/v1/admin/nibis/extract-zips</code></td>
<td>ZIP-Dateien entpacken</td>
</tr>
<tr>
<td>GET</td>
<td><code>/api/v1/admin/nibis/discover</code></td>
<td>Dokumente finden</td>
</tr>
<tr>
<td>POST</td>
<td><code>/api/v1/admin/nibis/ingest</code></td>
<td>Ingestion starten</td>
</tr>
<tr>
<td>POST</td>
<td><code>/api/v1/admin/nibis/search</code></td>
<td>Semantische Suche</td>
</tr>
<tr>
<td>GET</td>
<td><code>/api/v1/admin/nibis/stats</code></td>
<td>Statistiken</td>
</tr>
<tr>
<td>GET</td>
<td><code>/api/v1/admin/nibis/collections</code></td>
<td>Qdrant Collections</td>
</tr>
<tr>
<td>DELETE</td>
<td><code>/api/v1/admin/nibis/collection</code></td>
<td>Collection löschen</td>
</tr>
</tbody>
</table>
<h2 id="erweiterung-fur-andere-bundeslander">Erweiterung für andere Bundesländer<a class="headerlink" href="#erweiterung-fur-andere-bundeslander" title="Permanent link">&para;</a></h2>
<p>Die Pipeline ist so designed, dass sie leicht erweitert werden kann:</p>
<h3 id="1-neues-bundesland-hinzufugen">1. Neues Bundesland hinzufügen<a class="headerlink" href="#1-neues-bundesland-hinzufugen" title="Permanent link">&para;</a></h3>
<div class="highlight"><pre><span></span><code><a id="__codelineno-5-1" name="__codelineno-5-1" href="#__codelineno-5-1"></a><span class="c1"># In nibis_ingestion.py</span>
<a id="__codelineno-5-2" name="__codelineno-5-2" href="#__codelineno-5-2"></a>
<a id="__codelineno-5-3" name="__codelineno-5-3" href="#__codelineno-5-3"></a><span class="c1"># Bundesland-Code (ISO 3166-2:DE)</span>
<a id="__codelineno-5-4" name="__codelineno-5-4" href="#__codelineno-5-4"></a><span class="n">BUNDESLAND_CODES</span> <span class="o">=</span> <span class="p">{</span>
<a id="__codelineno-5-5" name="__codelineno-5-5" href="#__codelineno-5-5"></a> <span class="s2">&quot;NI&quot;</span><span class="p">:</span> <span class="s2">&quot;Niedersachsen&quot;</span><span class="p">,</span>
<a id="__codelineno-5-6" name="__codelineno-5-6" href="#__codelineno-5-6"></a> <span class="s2">&quot;BE&quot;</span><span class="p">:</span> <span class="s2">&quot;Berlin&quot;</span><span class="p">,</span>
<a id="__codelineno-5-7" name="__codelineno-5-7" href="#__codelineno-5-7"></a> <span class="s2">&quot;BY&quot;</span><span class="p">:</span> <span class="s2">&quot;Bayern&quot;</span><span class="p">,</span>
<a id="__codelineno-5-8" name="__codelineno-5-8" href="#__codelineno-5-8"></a> <span class="c1"># ...</span>
<a id="__codelineno-5-9" name="__codelineno-5-9" href="#__codelineno-5-9"></a><span class="p">}</span>
<a id="__codelineno-5-10" name="__codelineno-5-10" href="#__codelineno-5-10"></a>
<a id="__codelineno-5-11" name="__codelineno-5-11" href="#__codelineno-5-11"></a><span class="c1"># Parsing-Funktion für neues Format</span>
<a id="__codelineno-5-12" name="__codelineno-5-12" href="#__codelineno-5-12"></a><span class="k">def</span><span class="w"> </span><span class="nf">parse_filename_berlin</span><span class="p">(</span><span class="n">filename</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">file_path</span><span class="p">:</span> <span class="n">Path</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">]:</span>
<a id="__codelineno-5-13" name="__codelineno-5-13" href="#__codelineno-5-13"></a> <span class="c1"># Berlin-spezifische Namenskonvention</span>
<a id="__codelineno-5-14" name="__codelineno-5-14" href="#__codelineno-5-14"></a> <span class="k">pass</span>
</code></pre></div>
<h3 id="2-neues-verzeichnis-registrieren">2. Neues Verzeichnis registrieren<a class="headerlink" href="#2-neues-verzeichnis-registrieren" title="Permanent link">&para;</a></h3>
<div class="highlight"><pre><span></span><code><a id="__codelineno-6-1" name="__codelineno-6-1" href="#__codelineno-6-1"></a><span class="c1"># docs/za-download-berlin/ hinzufügen</span>
<a id="__codelineno-6-2" name="__codelineno-6-2" href="#__codelineno-6-2"></a><span class="n">ZA_DOWNLOAD_DIRS</span> <span class="o">=</span> <span class="p">[</span>
<a id="__codelineno-6-3" name="__codelineno-6-3" href="#__codelineno-6-3"></a> <span class="s2">&quot;za-download&quot;</span><span class="p">,</span>
<a id="__codelineno-6-4" name="__codelineno-6-4" href="#__codelineno-6-4"></a> <span class="s2">&quot;za-download-2&quot;</span><span class="p">,</span>
<a id="__codelineno-6-5" name="__codelineno-6-5" href="#__codelineno-6-5"></a> <span class="s2">&quot;za-download-3&quot;</span><span class="p">,</span>
<a id="__codelineno-6-6" name="__codelineno-6-6" href="#__codelineno-6-6"></a> <span class="s2">&quot;za-download-berlin&quot;</span><span class="p">,</span> <span class="c1"># NEU</span>
<a id="__codelineno-6-7" name="__codelineno-6-7" href="#__codelineno-6-7"></a><span class="p">]</span>
</code></pre></div>
<h3 id="3-dokumenttyp-erweiterung">3. Dokumenttyp-Erweiterung<a class="headerlink" href="#3-dokumenttyp-erweiterung" title="Permanent link">&para;</a></h3>
<p>Für Zeugnisgeneration oder andere Dokumenttypen:</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-7-1" name="__codelineno-7-1" href="#__codelineno-7-1"></a><span class="n">DOC_TYPES</span> <span class="o">=</span> <span class="p">{</span>
<a id="__codelineno-7-2" name="__codelineno-7-2" href="#__codelineno-7-2"></a> <span class="s2">&quot;EWH&quot;</span><span class="p">:</span> <span class="s2">&quot;Erwartungshorizont&quot;</span><span class="p">,</span>
<a id="__codelineno-7-3" name="__codelineno-7-3" href="#__codelineno-7-3"></a> <span class="s2">&quot;ZEUGNIS_VORLAGE&quot;</span><span class="p">:</span> <span class="s2">&quot;Zeugnisvorlage&quot;</span><span class="p">,</span>
<a id="__codelineno-7-4" name="__codelineno-7-4" href="#__codelineno-7-4"></a> <span class="s2">&quot;NOTENSPIEGEL&quot;</span><span class="p">:</span> <span class="s2">&quot;Notenspiegel&quot;</span><span class="p">,</span>
<a id="__codelineno-7-5" name="__codelineno-7-5" href="#__codelineno-7-5"></a> <span class="s2">&quot;BEMERKUNG&quot;</span><span class="p">:</span> <span class="s2">&quot;Bemerkungstexte&quot;</span><span class="p">,</span>
<a id="__codelineno-7-6" name="__codelineno-7-6" href="#__codelineno-7-6"></a><span class="p">}</span>
</code></pre></div>
<h2 id="rechtliche-hinweise">Rechtliche Hinweise<a class="headerlink" href="#rechtliche-hinweise" title="Permanent link">&para;</a></h2>
<ul>
<li>NiBiS-Daten sind unter den <a href="https://nibis.de">NiBiS-Nutzungsbedingungen</a> frei nutzbar</li>
<li><code>training_allowed: true</code> - Strukturelles Wissen darf für KI-Training genutzt werden</li>
<li>Für Lehrer-eigene Erwartungshorizonte (BYOEH) gilt: <code>training_allowed: false</code></li>
</ul>
<h2 id="troubleshooting">Troubleshooting<a class="headerlink" href="#troubleshooting" title="Permanent link">&para;</a></h2>
<h3 id="qdrant-nicht-erreichbar">Qdrant nicht erreichbar<a class="headerlink" href="#qdrant-nicht-erreichbar" title="Permanent link">&para;</a></h3>
<div class="highlight"><pre><span></span><code><a id="__codelineno-8-1" name="__codelineno-8-1" href="#__codelineno-8-1"></a><span class="c1"># Prüfen ob Qdrant läuft</span>
<a id="__codelineno-8-2" name="__codelineno-8-2" href="#__codelineno-8-2"></a>curl<span class="w"> </span>http://localhost:6333/health
<a id="__codelineno-8-3" name="__codelineno-8-3" href="#__codelineno-8-3"></a>
<a id="__codelineno-8-4" name="__codelineno-8-4" href="#__codelineno-8-4"></a><span class="c1"># Docker starten</span>
<a id="__codelineno-8-5" name="__codelineno-8-5" href="#__codelineno-8-5"></a>docker-compose<span class="w"> </span>up<span class="w"> </span>-d<span class="w"> </span>qdrant
</code></pre></div>
<h3 id="openai-api-fehler">OpenAI API Fehler<a class="headerlink" href="#openai-api-fehler" title="Permanent link">&para;</a></h3>
<div class="highlight"><pre><span></span><code><a id="__codelineno-9-1" name="__codelineno-9-1" href="#__codelineno-9-1"></a><span class="c1"># API Key setzen</span>
<a id="__codelineno-9-2" name="__codelineno-9-2" href="#__codelineno-9-2"></a><span class="nb">export</span><span class="w"> </span><span class="nv">OPENAI_API_KEY</span><span class="o">=</span>sk-...
</code></pre></div>
<h3 id="pdf-extraktion-fehlgeschlagen">PDF-Extraktion fehlgeschlagen<a class="headerlink" href="#pdf-extraktion-fehlgeschlagen" title="Permanent link">&para;</a></h3>
<p>Einige PDFs können problematisch sein (gescannte Dokumente ohne OCR). Diese werden übersprungen und im Error-Log protokolliert.</p>
<h2 id="performance">Performance<a class="headerlink" href="#performance" title="Permanent link">&para;</a></h2>
<ul>
<li>~500-1000 Chunks pro Minute (abhängig von OpenAI API)</li>
<li>~2-3 GB Qdrant Storage für alle NiBiS-Daten (2016-2025)</li>
<li>Embeddings werden nur einmal generiert (idempotent via Hash)</li>
</ul>
</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>