[{"data":1,"prerenderedAt":881},["ShallowReactive",2],{"blog-tag-de-hybrid-search":3},[4,85,161,225,291,344,397,470,519,579,636,685,764,818],{"slug":5,"published":6,"updated":7,"minutes":8,"category":9,"tags":10,"tagPages":16,"keywords":18,"about":29,"sources":38,"cover":75,"og":76,"expertise":77,"locales":78,"lang":80,"title":82,"description":83,"coverAlt":84},"visual-search-shop","2026-10-05","2026-10-17",11,"web",[11,12,13,14,15],"Visual search","Image embeddings","OCR","Part numbers","Hybrid search",[17],"hybrid-search",[19,20,21,22,23,24,25,26,27,28],"visuelle suche b2b-shop","bildsuche produktkatalog","clip siglip bild-embeddings","foto zu teilenummer","visuelle suche shop umsetzen","multimodale embeddings shop","ersatzteile per foto erkennen","ocr teilenummer aus foto","bildähnlichkeitssuche pgvector","visuell in den warenkorb",[30,32,35],{"name":11,"url":31},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FVisual_search",{"name":33,"url":34},"Optical character recognition","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOptical_character_recognition",{"name":36,"url":37},"Contrastive learning","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FContrastive_learning",[39,42,45,48,51,54,57,60,63,66,69,72],{"title":40,"url":41},"CLIP: Learning Transferable Visual Models From Natural Language Supervision (2021)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.00020",{"title":43,"url":44},"Hugging Face: SigLIP 2 release (2025)","https:\u002F\u002Fhuggingface.co\u002Fblog\u002Fsiglip2",{"title":46,"url":47},"MIEB: Massive Image Embedding Benchmark (2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.10471",{"title":49,"url":50},"jina-clip-v2 model card (CC-BY-NC-4.0)","https:\u002F\u002Fhuggingface.co\u002Fjinaai\u002Fjina-clip-v2",{"title":52,"url":53},"pgvector: README","https:\u002F\u002Fgithub.com\u002Fpgvector\u002Fpgvector",{"title":55,"url":56},"Spryker docs: Search by Image","https:\u002F\u002Fdocs.spryker.com\u002Fdocs\u002Fpbc\u002Fall\u002Fai-commerce\u002Flatest\u002Fsearch-by-image",{"title":58,"url":59},"Spryker docs: Visual Add to Cart","https:\u002F\u002Fdocs.spryker.com\u002Fdocs\u002Fdg\u002Fdev\u002Fai\u002Fai-commerce\u002Fvisual-add-to-cart\u002Fvisual-add-to-cart",{"title":61,"url":62},"Google Cloud: Vision API pricing","https:\u002F\u002Fcloud.google.com\u002Fvision\u002Fpricing",{"title":64,"url":65},"Voyage AI: pricing","https:\u002F\u002Fdocs.voyageai.com\u002Fdocs\u002Fpricing",{"title":67,"url":68},"python-stdnum: EAN, UPC and GTIN module","https:\u002F\u002Farthurdejong.org\u002Fpython-stdnum\u002Fdoc\u002F1.20\u002Fstdnum.ean.html",{"title":70,"url":71},"Elasticsearch: fuzzy query","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Fquery-languages\u002Fquery-dsl\u002Fquery-dsl-fuzzy-query",{"title":73,"url":74},"SymSpell (GitHub)","https:\u002F\u002Fgithub.com\u002Fwolfgarbe\u002FSymSpell","\u002Fimages\u002Fblog\u002Fvisual-search-shop\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fvisual-search-shop\u002Fog.jpg","b2b-ecommerce-developer",[79,80,81],"en","de","hu","Visuelle Suche für B2B-Shops: Bildeinbettungen, Teilenummern und ehrliche Grenzen","Visuelle Suche im B2B-Shop: Bildeinbettungen, OCR für Teilenummern, Bild-zu-Text-Suche, Filter, Kosten und Bewertung mit eigenen Fotos.","Visuelle Suche für B2B-Shops: Eine Kamera fotografiert ein Teil und findet die passende Kachel im Raster.",{"slug":86,"published":87,"updated":88,"minutes":89,"category":90,"tags":91,"tagPages":96,"keywords":98,"about":109,"sources":117,"cover":154,"og":155,"expertise":156,"locales":157,"lang":80,"title":158,"description":159,"coverAlt":160},"elasticsearch-opensearch-vector-search","2026-09-30","2026-10-01",8,"rag",[92,93,94,15,95],"Elasticsearch","OpenSearch","Vector search","Licensing",[97,17],"vector-search",[99,100,101,102,103,104,105,106,107,108],"vektorsuche elasticsearch opensearch","knn-suche elasticsearch","opensearch neural search anleitung","hybride suche rrf","elasticsearch bbq quantisierung","opensearch diskann jvector","elasticsearch agpl lizenz","gefilterte knn-suche","elasticsearch vs opensearch vektordatenbank vergleich","suchmaschine als vektorspeicher",[110,112,114],{"name":92,"url":111},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FElasticsearch",{"name":93,"url":113},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOpenSearch_%28software%29",{"name":115,"url":116},"Nearest neighbor search","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FNearest_neighbor_search",[118,121,124,127,130,133,136,139,142,145,148,151],{"title":119,"url":120},"Elastic docs: kNN search","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Fvector\u002Fknn",{"title":122,"url":123},"Elastic docs: filtered kNN search","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Fvector\u002Fknn\u002Ffiltered-knn-search",{"title":125,"url":126},"Elastic docs: dense_vector field type","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Fmapping-reference\u002Fdense-vector",{"title":128,"url":129},"Elastic docs: BBQ","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Fmapping-reference\u002Fbbq",{"title":131,"url":132},"Elastic docs: reciprocal rank fusion","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Frest-apis\u002Freciprocal-rank-fusion",{"title":134,"url":135},"Elastic docs: GPU vector indexing","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Fvector\u002Fgpu-vector-indexing",{"title":137,"url":138},"Elastic blog: Elasticsearch is open source again (Aug 2024)","https:\u002F\u002Fwww.elastic.co\u002Fblog\u002Felasticsearch-is-open-source-again",{"title":140,"url":141},"OpenSearch docs: methods and engines","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fmappings\u002Fsupported-field-types\u002Fknn-methods-engines\u002F",{"title":143,"url":144},"OpenSearch docs: memory-optimized vectors","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fmappings\u002Fsupported-field-types\u002Fknn-memory-optimized\u002F",{"title":146,"url":147},"OpenSearch docs: reciprocal rank fusion","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fvector-search\u002Fai-search\u002Fhybrid-search\u002Frrf\u002F",{"title":149,"url":150},"OpenSearch docs: version history","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fversion-history\u002F",{"title":152,"url":153},"AWS Open Source blog: introducing OpenSearch (Apr 2021)","https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fopensource\u002Fintroducing-opensearch\u002F","\u002Fimages\u002Fblog\u002Felasticsearch-opensearch-vector-search\u002Fcover.webp","\u002Fimages\u002Fblog\u002Felasticsearch-opensearch-vector-search\u002Fog.jpg","ai-engineer",[79,80,81],"Vektorsuche in Elasticsearch und OpenSearch: kNN, hybride Suche und die Lizenzfrage","Elasticsearch und OpenSearch als Vektorspeicher: kNN und Filter, BBQ und binäre Quantisierung, hybride Suche mit RRF, GPU-Builds und die Lizenzfrage.","Elasticsearch und OpenSearch: Ein Schrank mit einer Text- und einer Vektorschublade, durchsucht von einer Lupe.",{"slug":162,"published":163,"updated":88,"minutes":89,"category":90,"tags":164,"tagPages":168,"keywords":169,"about":179,"sources":185,"cover":219,"og":220,"expertise":156,"locales":221,"lang":80,"title":222,"description":223,"coverAlt":224},"turbopuffer","2026-09-29",[162,165,166,167,15],"Vector database","Object storage","Pricing",[17],[162,170,171,172,173,174,175,176,177,178],"turbopuffer preise","vektorsuche auf object storage","serverless vektordatenbank test","turbopuffer vs pinecone vergleich","turbopuffer namespaces erklärt","spfresh vektorindex","turbopuffer hybridsuche","abrechnung pro abfrage vektordatenbank","vektordatenbank auf object storage",[180,182,184],{"name":165,"url":181},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FVector_database",{"name":166,"url":183},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FObject_storage",{"name":115,"url":116},[186,189,192,195,198,201,204,207,210,213,216],{"title":187,"url":188},"turbopuffer blog: turbopuffer (updated Mar 2026)","https:\u002F\u002Fturbopuffer.com\u002Fblog\u002Fturbopuffer",{"title":190,"url":191},"turbopuffer blog: ANN v3 (Jan 2026)","https:\u002F\u002Fturbopuffer.com\u002Fblog\u002Fann-v3",{"title":193,"url":194},"SPFresh (SOSP 2023)","https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3600006.3613166",{"title":196,"url":197},"turbopuffer blog: native filtering","https:\u002F\u002Fturbopuffer.com\u002Fblog\u002Fnative-filtering",{"title":199,"url":200},"turbopuffer docs: hybrid search","https:\u002F\u002Fturbopuffer.com\u002Fdocs\u002Fhybrid",{"title":202,"url":203},"turbopuffer blog: native embedding (Sep 2026)","https:\u002F\u002Fturbopuffer.com\u002Fblog\u002Fnative-embedding",{"title":205,"url":206},"turbopuffer docs: architecture","https:\u002F\u002Fturbopuffer.com\u002Fdocs\u002Farchitecture",{"title":208,"url":209},"turbopuffer pricing","https:\u002F\u002Fturbopuffer.com\u002Fpricing",{"title":211,"url":212},"turbopuffer docs: limits","https:\u002F\u002Fturbopuffer.com\u002Fdocs\u002Flimits",{"title":214,"url":215},"turbopuffer v3 benchmarks","https:\u002F\u002Fturbopuffer.com\u002Fv3",{"title":217,"url":218},"Pinecone pricing","https:\u002F\u002Fwww.pinecone.io\u002Fpricing\u002F","\u002Fimages\u002Fblog\u002Fturbopuffer\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fturbopuffer\u002Fog.jpg",[79,80,81],"turbopuffer im Test: Vektorsuche auf Object Storage und was eine Anfrage kostet","turbopuffer im Test: Object Storage als Quelle der Wahrheit, SPFresh, RaBitQ, hybride Suche, Abrechnung pro GB gegenüber Pinecone und wann sich das lohnt.","turbopuffer: Ein großer Speicher-Eimer unten und ein kleines Cache-Fach oben, das einige Karten hochholt.",{"slug":226,"published":227,"updated":88,"minutes":89,"category":90,"tags":228,"tagPages":232,"keywords":233,"about":244,"sources":254,"cover":285,"og":286,"expertise":156,"locales":287,"lang":80,"title":288,"description":289,"coverAlt":290},"splade-learned-sparse-retrieval","2026-09-28",[229,230,231,15,92],"SPLADE","Sparse retrieval","BM25",[17],[234,235,236,237,238,239,240,241,242,243],"gelernte sparse-suche","splade erklärt","splade++ vs bm25","neuronale sparse-suche","elasticsearch sparse_vector einrichten","elser elasticsearch","rank_features elasticsearch","opensearch neural sparse anleitung","sparse retrieval indexgröße latenz","sentence-transformers sparse encoder training",[245,248,251],{"name":246,"url":247},"Okapi BM25","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOkapi_BM25",{"name":249,"url":250},"Inverted index","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FInverted_index",{"name":252,"url":253},"BERT (language model)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FBERT_%28language_model%29",[255,258,261,264,267,270,273,276,279,282],{"title":256,"url":257},"naver\u002Fsplade on GitHub","https:\u002F\u002Fgithub.com\u002Fnaver\u002Fsplade",{"title":259,"url":260},"SPLADE++ (arXiv 2205.04733)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.04733",{"title":262,"url":263},"naver\u002Fsplade-v3 model card","https:\u002F\u002Fhuggingface.co\u002Fnaver\u002Fsplade-v3",{"title":265,"url":266},"Static pruning for learned sparse indexes (arXiv 2304.12702)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.12702",{"title":268,"url":269},"OpenSearch blog: faster semantic sparse retrieval in 2.12","https:\u002F\u002Fopensearch.org\u002Fblog\u002FA-deep-dive-into-faster-semantic-sparse-retrieval-in-os-2-12\u002F",{"title":271,"url":272},"OpenSearch docs: sparse encoding processor","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fingest-pipelines\u002Fprocessors\u002Fsparse-encoding\u002F",{"title":274,"url":275},"Elastic docs: sparse_vector field type","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Fmapping-reference\u002Fsparse-vector",{"title":277,"url":278},"Elastic docs: ELSER","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fexplore-analyze\u002Fmachine-learning\u002Fnlp\u002Fml-nlp-elser",{"title":280,"url":281},"Elastic Search Labs: ELSER v2, part 2","https:\u002F\u002Fwww.elastic.co\u002Fsearch-labs\u002Fblog\u002Fintroducing-elser-v2-part-2",{"title":283,"url":284},"Sentence Transformers: sparse encoder usage","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fsparse_encoder\u002Fusage\u002Fusage.html","\u002Fimages\u002Fblog\u002Fsplade-learned-sparse-retrieval\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fsplade-learned-sparse-retrieval\u002Fog.jpg",[79,80,81],"SPLADE und gelernte spärliche Suche in der Praxis: BM25, Indexgröße, Latenz","Gelernte spärliche Suche: wie SPLADE Begriffe erweitert, Modelle und Lizenzen, Indexgröße und Latenz, Engine-Unterstützung und wann es BM25 schlägt.","SPLADE: Ein Wortstreifen fächert sich in viele dünne Balken auf, wenige hohe speisen einen Karteikasten.",{"slug":292,"published":293,"updated":294,"minutes":295,"category":90,"tags":296,"tagPages":299,"keywords":300,"about":308,"sources":313,"cover":338,"og":339,"expertise":156,"locales":340,"lang":80,"title":341,"description":342,"coverAlt":343},"lancedb","2026-09-21","2026-10-07",9,[94,15,297,298],"Embedded database","RAG",[97,17,90],[292,301,302,303,304,305,306,307],"lancedb test","lance vektordatenbank","eingebettete vektordatenbank","lancedb vs qdrant vergleich","hybridsuche rang-fusion","lancedb indexierung","lance datenformat",[309,310],{"name":165,"url":181},{"name":311,"url":312},"Apache Arrow","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FApache_Arrow",[314,317,320,323,326,329,332,335],{"title":315,"url":316},"LanceDB quickstart","https:\u002F\u002Fdocs.lancedb.com\u002Fquickstart",{"title":318,"url":319},"LanceDB vector indexes","https:\u002F\u002Fdocs.lancedb.com\u002Findexing\u002Fvector-index",{"title":321,"url":322},"LanceDB indexing guide","https:\u002F\u002Fdocs.lancedb.com\u002Findexing\u002Findex",{"title":324,"url":325},"LanceDB hybrid search","https:\u002F\u002Fdocs.lancedb.com\u002Fsearch\u002Fhybrid-search",{"title":327,"url":328},"LanceDB Enterprise","https:\u002F\u002Fdocs.lancedb.com\u002Fenterprise",{"title":330,"url":331},"LanceDB frequently asked questions","https:\u002F\u002Fdocs.lancedb.com\u002Ffaq\u002Ffaq-oss",{"title":333,"url":334},"LanceDB pricing","https:\u002F\u002Flancedb.com\u002Fpricing",{"title":336,"url":337},"LanceDB on PyPI","https:\u002F\u002Fpypi.org\u002Fproject\u002Flancedb\u002F","\u002Fimages\u002Fblog\u002Flancedb\u002Fcover.webp","\u002Fimages\u002Fblog\u002Flancedb\u002Fog.jpg",[79,80,81],"LanceDB: Vektorsuche, die als Bibliothek beginnt","LanceDB im Test: eine Apache-2.0-Bibliothek statt Server, die Wahl zwischen IVF und HNSW, Hybridsuche mit Rangfusion und was Enterprise zusätzlich bringt.","LanceDB: Aus einem offenen Buch klappen Regale mit sortierten Murmeln auf.",{"slug":345,"published":346,"updated":347,"minutes":348,"category":90,"tags":349,"tagPages":352,"keywords":353,"about":362,"sources":372,"cover":391,"og":392,"expertise":156,"locales":393,"lang":80,"title":394,"description":395,"coverAlt":396},"milvus-zilliz","2026-09-08","2026-09-20",10,[94,15,350,351,298],"BM25 full text","Distributed",[97,17,90],[354,355,356,357,358,359,360,361],"milvus","milvus vs qdrant vergleich","zilliz cloud preise","vektordatenbank vergleich","milvus hybridsuche","apache milvus selbst hosten","milvus 3.0 neuerungen","rag vektorspeicher",[363,366,369],{"name":364,"url":365},"Milvus","https:\u002F\u002Fmilvus.io",{"name":367,"url":368},"Zilliz Cloud","https:\u002F\u002Fzilliz.com",{"name":370,"url":371},"Retrieval-augmented generation","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FRetrieval-augmented_generation",[373,376,379,382,385,388],{"title":374,"url":375},"Milvus architecture overview","https:\u002F\u002Fmilvus.io\u002Fdocs\u002Farchitecture_overview.md",{"title":377,"url":378},"Milvus release notes","https:\u002F\u002Fmilvus.io\u002Fdocs\u002Frelease_notes.md",{"title":380,"url":381},"Milvus releases on GitHub","https:\u002F\u002Fgithub.com\u002Fmilvus-io\u002Fmilvus\u002Freleases",{"title":383,"url":384},"Milvus README: features and licence","https:\u002F\u002Fgithub.com\u002Fmilvus-io\u002Fmilvus",{"title":386,"url":387},"Zilliz Cloud pricing","https:\u002F\u002Fzilliz.com\u002Fpricing",{"title":389,"url":390},"Zilliz Cloud list price","https:\u002F\u002Fzilliz.com\u002Fpricing\u002Fpricing-guide","\u002Fimages\u002Fblog\u002Fmilvus-zilliz\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fmilvus-zilliz\u002Fog.jpg",[79,80,81],"Milvus-Review: die vollständigste Vektordatenbank im Betrieb","Milvus 3.0.2 im Review: die vollständigste Open-Source-Vektordatenbank und die aufwendigste im Betrieb. Architektur, Hybridsuche, Kosten, Einsatzgrenzen.","Milvus und Zilliz: Ein Lager mit hohen Regalen und Gabelstapler, eine Person mit Schraubenschlüssel am Schaltpult.",{"slug":398,"published":399,"updated":400,"minutes":401,"category":90,"tags":402,"tagPages":406,"keywords":407,"about":418,"sources":424,"cover":464,"og":465,"expertise":77,"locales":466,"lang":80,"title":467,"description":468,"coverAlt":469},"semantic-product-search-b2b","2026-08-21","2026-09-17",13,[403,15,404,405,93],"B2B search","Semantic search","Spryker",[17],[408,409,410,411,412,413,414,415,416,417],"semantische produktsuche b2b","b2b onlineshop suche","hybride suche bm25 und vektoren","artikelnummern suche onlineshop","spryker suche elasticsearch","opensearch hybride suche rrf","mehrsprachige produktsuche deutsch englisch ungarisch","null-treffer-quote shop-suche","llm query-verständnis ecommerce","ki-produktsuche für b2b-shops",[419,421,422],{"name":404,"url":420},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FSemantic_search",{"name":92,"url":111},{"name":93,"url":423},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOpenSearch",[425,428,431,434,437,440,443,446,449,452,455,458,461],{"title":426,"url":427},"Baymard Institute: E-commerce search query types","https:\u002F\u002Fbaymard.com\u002Fblog\u002Fecommerce-search-query-types",{"title":429,"url":430},"Elastic Search Labs: Hybrid search in Elasticsearch","https:\u002F\u002Fwww.elastic.co\u002Fsearch-labs\u002Fblog\u002Fhybrid-search-elasticsearch",{"title":432,"url":433},"Elasticsearch documentation: kNN query (pre-filters and post-filters)","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Fquery-languages\u002Fquery-dsl\u002Fquery-dsl-knn-query",{"title":435,"url":436},"Elasticsearch documentation: Semantic reranking","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Franking\u002Fsemantic-reranking",{"title":438,"url":439},"Elasticsearch documentation: Word delimiter graph token filter","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Ftext-analysis\u002Fanalysis-word-delimiter-graph-tokenfilter",{"title":441,"url":442},"Elasticsearch documentation: Synonym graph token filter","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Ftext-analysis\u002Fanalysis-synonym-graph-tokenfilter",{"title":444,"url":445},"OpenSearch documentation: Score ranker processor (RRF)","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fsearch-plugins\u002Fsearch-pipelines\u002Fscore-ranker-processor\u002F",{"title":447,"url":448},"OpenSearch documentation: Normalization processor","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fsearch-plugins\u002Fsearch-pipelines\u002Fnormalization-processor\u002F",{"title":450,"url":451},"Spryker documentation: Search feature overview","https:\u002F\u002Fdocs.spryker.com\u002Fdocs\u002Fpbc\u002Fall\u002Fsearch\u002Flatest\u002Fbase-shop\u002Fsearch-feature-overview\u002Fsearch-feature-overview",{"title":453,"url":454},"Spryker documentation: Migrate from OpenSearch 1.3 to 3.5","https:\u002F\u002Fdocs.spryker.com\u002Fdocs\u002Fpbc\u002Fall\u002Fsearch\u002Flatest\u002Fbase-shop\u002Finstall-and-upgrade\u002Fmigrate-from-opensearch-1.3-to-3.5.html",{"title":456,"url":457},"Instacart via ZenML: Rebuilding query understanding for e-commerce search with LLMs","https:\u002F\u002Fwww.zenml.io\u002Fllmops-database\u002Frebuilding-query-understanding-for-e-commerce-search-with-llms",{"title":459,"url":460},"arXiv: M3-Embedding, multilingual, multi-functionality, multi-granularity text embeddings","https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.03216",{"title":462,"url":463},"Algolia documentation: Search analytics metrics","https:\u002F\u002Fwww.algolia.com\u002Fdoc\u002Fguides\u002Fsearch-analytics\u002Fconcepts\u002Fmetrics\u002F","\u002Fimages\u002Fblog\u002Fsemantic-product-search-b2b\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fsemantic-product-search-b2b\u002Fog.jpg",[79,80,81],"Semantische Produktsuche für B2B-Shops: Artikelnummern, Hybrid-Retrieval und was du messen solltest","Semantische B2B-Produktsuche, ohne die Artikelnummern-Suche zu zerstören: Hybrid aus BM25 und Vektoren, Filter, DE\u002FEN\u002FHU, LLM-Query-Parsing, Metriken.","Semantische Produktsuche: Eine Lupe schwebt über einem Schraubenfach im Baumarktregal.",{"slug":471,"published":472,"updated":473,"minutes":89,"category":90,"tags":474,"tagPages":478,"keywords":479,"about":488,"sources":494,"cover":513,"og":514,"expertise":156,"locales":515,"lang":80,"title":516,"description":517,"coverAlt":518},"rag-2026-hybrid-agentic-long-context","2026-07-30","2026-09-22",[298,475,476,15,477],"Long context","Agentic search","Contextual retrieval",[90,17],[480,481,482,483,484,485,486,487],"rag 2026","long context oder rag","agentisches rag","hybride suche rag","kontextuelles retrieval","ist rag tot","agentische suche vs vektorsuche","rag vs 1m-token-kontextfenster",[489,490,493],{"name":370,"url":371},{"name":491,"url":492},"Large language model","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FLarge_language_model",{"name":246,"url":247},[495,498,501,504,507,510],{"title":496,"url":497},"Anthropic: Introducing Contextual Retrieval","https:\u002F\u002Fwww.anthropic.com\u002Fnews\u002Fcontextual-retrieval",{"title":499,"url":500},"Chroma: Context Rot","https:\u002F\u002Fwww.trychroma.com\u002Fresearch\u002Fcontext-rot",{"title":502,"url":503},"Liu et al., Lost in the Middle (2023)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03172",{"title":505,"url":506},"Claude docs: Pricing","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fabout-claude\u002Fpricing",{"title":508,"url":509},"Claude docs: Models overview","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fabout-claude\u002Fmodels\u002Foverview",{"title":511,"url":512},"Awesome Agentic Patterns: Agentic search over vector embeddings","https:\u002F\u002Fgithub.com\u002Fnibzard\u002Fawesome-agentic-patterns\u002Fblob\u002Fmain\u002Fpatterns\u002Fagentic-search-over-vector-embeddings.md","\u002Fimages\u002Fblog\u002Frag-2026-hybrid-agentic-long-context\u002Fcover.webp","\u002Fimages\u002Fblog\u002Frag-2026-hybrid-agentic-long-context\u002Fog.jpg",[79,80,81],"RAG im Jahr 2026: hybrides Retrieval, agentisches Suchen oder Long Context?","RAG 2026: wann ein gecachter 1M-Token-Kontext das Retrieval schlägt, wann hybride Suche gewinnt, wann agentische Suche passt und was jede Anfrage kostet.","RAG 2026: Eine Person wählt zwischen Wegen zu einem Bücherregal, einem Roboter mit Taschenlampe und einer langen Rolle.",{"slug":520,"published":521,"updated":472,"minutes":348,"category":90,"tags":522,"tagPages":526,"keywords":527,"about":537,"sources":541,"cover":573,"og":574,"expertise":156,"locales":575,"lang":80,"title":576,"description":577,"coverAlt":578},"rag-pipeline-chunking-hybrid-search-reranking","2026-07-24",[298,15,523,524,525],"Chunking","Reranking","pgvector",[90,17],[528,529,530,531,532,533,534,535,536],"rag-pipeline","rag-pipeline aufbauen","chunking-strategie für rag","hybride suche bm25 vektor","reciprocal rank fusion erklärt","cross-encoder re-ranking","pgvector hybride suche","rag-pipeline evaluieren","rag-pipeline in produktion",[538,539,540],{"name":370,"url":371},{"name":246,"url":247},{"name":525,"url":53},[542,545,548,551,553,556,559,562,563,566,567,570],{"title":543,"url":544},"Lewis et al., Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11401",{"title":546,"url":547},"Cormack, Clarke and Büttcher, Reciprocal Rank Fusion (SIGIR 2009)","https:\u002F\u002Fcormack.uwaterloo.ca\u002Fcormacksigir09-rrf.pdf",{"title":549,"url":550},"Malkov and Yashunin, HNSW graphs","https:\u002F\u002Farxiv.org\u002Fabs\u002F1603.09320",{"title":552,"url":53},"pgvector README",{"title":554,"url":555},"Elasticsearch: similarity settings","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Findex-settings\u002Fsimilarity",{"title":557,"url":558},"PostgreSQL: controlling text search","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Ftextsearch-controls.html",{"title":560,"url":561},"Chroma: Evaluating Chunking Strategies for Retrieval","https:\u002F\u002Fwww.trychroma.com\u002Fresearch\u002Fevaluating-chunking",{"title":496,"url":497},{"title":564,"url":565},"Sentence Transformers: Cross-Encoders","https:\u002F\u002Fsbert.net\u002Fexamples\u002Fcross_encoder\u002Fapplications\u002FREADME.html",{"title":502,"url":503},{"title":568,"url":569},"Claude docs: Citations","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fbuild-with-claude\u002Fcitations",{"title":571,"url":572},"RAGAS: Faithfulness","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fconcepts\u002Fmetrics\u002Favailable_metrics\u002Ffaithfulness\u002F","\u002Fimages\u002Fblog\u002Frag-pipeline-chunking-hybrid-search-reranking\u002Fcover.webp","\u002Fimages\u002Fblog\u002Frag-pipeline-chunking-hybrid-search-reranking\u002Fog.jpg",[79,80,81],"RAG-Pipeline in Produktion, Schritt für Schritt: Chunking, hybride Suche und Reranking","Eine RAG-Pipeline Schritt für Schritt bauen: Parsing, Chunking, pgvector, BM25 plus Vektoren mit RRF, Reranking, Quellenangaben und Evals.","RAG-Pipeline: Ein Brot wird geschnitten, die Scheiben gehen durch ein Sieb und liegen geordnet auf dem Teller.",{"slug":580,"published":581,"minutes":348,"category":90,"tags":582,"tagPages":585,"keywords":587,"about":595,"sources":602,"cover":630,"og":631,"expertise":156,"locales":632,"lang":80,"title":633,"description":634,"coverAlt":635},"chroma","2026-07-20",[94,583,298,15,584],"Embeddings","Metadata filter",[97,586,90,17],"embeddings",[588,589,590,591,592,593,594],"chroma vektordatenbank","chroma vs qdrant vergleich","chroma vs pgvector vergleich","hybridsuche reciprocal rank fusion","self-hosted vektordatenbank","chroma cloud preise","metadatenfilter vektorsuche",[596,599],{"name":597,"url":598},"Chroma","https:\u002F\u002Fgithub.com\u002Fchroma-core\u002Fchroma",{"name":600,"url":601},"Apache License 2.0","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FApache_License",[603,606,609,612,615,618,621,624,627],{"title":604,"url":605},"Chroma documentation: introduction","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Foverview\u002Fintroduction",{"title":607,"url":608},"Chroma architecture overview","https:\u002F\u002Fdocs.trychroma.com\u002Freference\u002Farchitecture\u002Foverview",{"title":610,"url":611},"Chroma: getting started with the SDK","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Foverview\u002Fgetting-started",{"title":613,"url":614},"Chroma: query and get","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Fquerying-collections\u002Fquery-and-get",{"title":616,"url":617},"Chroma: metadata filtering","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Fquerying-collections\u002Fmetadata-filtering",{"title":619,"url":620},"Chroma Cloud: Search API overview","https:\u002F\u002Fdocs.trychroma.com\u002Fcloud\u002Fsearch-api\u002Foverview",{"title":622,"url":623},"Chroma Cloud: hybrid search with RRF","https:\u002F\u002Fdocs.trychroma.com\u002Fcloud\u002Fsearch-api\u002Fhybrid-search",{"title":625,"url":626},"Chroma Cloud: pricing","https:\u002F\u002Fwww.trychroma.com\u002Fpricing",{"title":628,"url":629},"Chroma changelog","https:\u002F\u002Fwww.trychroma.com\u002Fchangelog","\u002Fimages\u002Fblog\u002Fchroma\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fchroma\u002Fog.jpg",[79,80,81],"Chroma: einfache Vektorsuche mit einem Haken","Chroma im Test: eine Apache-2.0-Vektordatenbank, eingebettet, als Einzelknoten oder Cloud. Wo sie angenehm ist und wo die Suche an der Cloud-Grenze endet.","Chroma: Ein Schubladenschrank mit sortierten Murmeln, obenauf ein Kiesel mit Riss.",{"slug":637,"published":638,"minutes":8,"category":90,"tags":639,"tagPages":641,"keywords":642,"about":651,"sources":655,"cover":679,"og":680,"expertise":156,"locales":681,"lang":80,"title":682,"description":683,"coverAlt":684},"pinecone","2026-07-09",[94,583,298,640,15],"Namespaces",[97,586,90,17],[643,644,645,646,647,648,649,650],"pinecone vektordatenbank","pinecone preise","pinecone read units kosten","pinecone namespaces erklärt","pinecone vs qdrant vergleich","pinecone vs pgvector vergleich","pinecone documents api nutzen","serverless vektordatenbank kosten",[652,653,654],{"name":165,"url":181},{"name":115,"url":116},{"name":246,"url":247},[656,659,662,665,668,670,673,676],{"title":657,"url":658},"Pinecone docs: Index data overview, indexes, namespaces and metadata","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Findexing-overview",{"title":660,"url":661},"Pinecone docs: Adopt the Documents API, API version 2026-07","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Fadopt-the-documents-api",{"title":663,"url":664},"Pinecone docs: Create an index, schemas, regions and metrics","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Fcreate-an-index",{"title":666,"url":667},"Pinecone docs: Understanding Pinecone cost, read units, write units and egress","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Forganizations\u002Fmanage-cost\u002Funderstanding-cost",{"title":669,"url":218},"Pinecone pricing: plans, limits and rates",{"title":671,"url":672},"Pinecone docs: Semantic search","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Fsearch\u002Fsemantic-search",{"title":674,"url":675},"Pinecone docs: Local development with Pinecone Local","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Foperations\u002Flocal-development",{"title":677,"url":678},"Pinecone docs: 2026 release notes","https:\u002F\u002Fdocs.pinecone.io\u002Frelease-notes\u002F2026","\u002Fimages\u002Fblog\u002Fpinecone\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fpinecone\u002Fog.jpg",[79,80,81],"Pinecone: ein Test der verwalteten Vektordatenbank","Pinecone im Test: Read Units wachsen mit der Namespace-Größe, ein Schema ist nachträglich nicht änderbar, und wo eine eigene Vektordatenbank besser passt.","Pinecone: Ein Kiefernzapfen auf einer Wolke hält Murmeln zwischen den Schuppen, darunter ein Schlüssel.",{"slug":686,"published":687,"updated":88,"minutes":401,"category":90,"tags":688,"tagPages":691,"keywords":692,"about":703,"sources":709,"cover":758,"og":759,"expertise":156,"locales":760,"lang":80,"title":761,"description":762,"coverAlt":763},"pgvector-vs-vector-databases","2026-06-15",[525,689,298,15,690],"Vector databases","EU hosting",[90,17],[693,694,695,696,697,698,699,700,701,702],"pgvector oder vektordatenbank","pgvector vs vektordatenbank vergleich","pgvector vs pinecone vergleich","beste vektordatenbank 2026","pgvector hnsw iterative scan erklärt","pgvector halfvec","opensearch vs elasticsearch vektorsuche","vektordatenbank eu-hosting","hybridsuche postgres","weaviate vs milvus vergleich",[704,705,708],{"name":165,"url":181},{"name":706,"url":707},"PostgreSQL","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FPostgreSQL",{"name":370,"url":371},[710,713,716,719,722,725,728,731,734,737,740,743,745,747,750,753,755],{"title":711,"url":712},"pgvector README (index limits, HNSW defaults, iterative scans, filtering, halfvec)","https:\u002F\u002Fgithub.com\u002Fpgvector\u002Fpgvector\u002Fblob\u002Fmaster\u002FREADME.md",{"title":714,"url":715},"pgvector CHANGELOG (0.4.0 to 0.8.7)","https:\u002F\u002Fgithub.com\u002Fpgvector\u002Fpgvector\u002Fblob\u002Fmaster\u002FCHANGELOG.md",{"title":717,"url":718},"pgvectorscale: StreamingDiskANN, statistical binary quantization, filtered search","https:\u002F\u002Fgithub.com\u002Ftimescale\u002Fpgvectorscale",{"title":720,"url":721},"Qdrant documentation: Filtering","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fconcepts\u002Ffiltering\u002F",{"title":723,"url":724},"Qdrant documentation: Hybrid queries","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fconcepts\u002Fhybrid-queries\u002F",{"title":726,"url":727},"Qdrant documentation: Create a cluster (providers, free tier, Hybrid Cloud)","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fcloud\u002Fcreate-cluster\u002F",{"title":729,"url":730},"Weaviate documentation: Hybrid search","https:\u002F\u002Fdocs.weaviate.io\u002Fweaviate\u002Fconcepts\u002Fsearch\u002Fhybrid-search",{"title":732,"url":733},"Weaviate documentation: Vector index types","https:\u002F\u002Fdocs.weaviate.io\u002Fweaviate\u002Fconcepts\u002Fvector-index",{"title":735,"url":736},"Weaviate Cloud pricing and deployment options","https:\u002F\u002Fweaviate.io\u002Fpricing",{"title":738,"url":739},"Milvus documentation: Overview","https:\u002F\u002Fmilvus.io\u002Fdocs\u002Foverview.md",{"title":741,"url":742},"Pinecone documentation: Database architecture","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Fget-started\u002Fdatabase-architecture",{"title":744,"url":664},"Pinecone documentation: Create an index (clouds, regions, sparse and hybrid)",{"title":746,"url":141},"OpenSearch documentation: Methods and engines",{"title":748,"url":749},"OpenSearch documentation: Efficient k-NN filtering","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fvector-search\u002Ffilter-search-knn\u002Fefficient-knn-filtering\u002F",{"title":751,"url":752},"Elasticsearch documentation: Dense vector search","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Fvector\u002Fdense-vector",{"title":754,"url":433},"Elasticsearch documentation: kNN query (filter as pre-filter)",{"title":756,"url":757},"GitHub releases: Qdrant, Weaviate, Milvus, OpenSearch, pgvectorscale (versions as of 1 October 2026)","https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant\u002Freleases","\u002Fimages\u002Fblog\u002Fpgvector-vs-vector-databases\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fpgvector-vs-vector-databases\u002Fog.jpg",[79,80,81],"pgvector oder Vektordatenbank? So wählst du 2026 den Vektorspeicher","pgvector oder eigene Vektordatenbank? Qdrant, Weaviate, Milvus, Pinecone, OpenSearch, Elasticsearch: Filter, Hybridsuche, Skalierung, Kosten, EU-Hosting.","pgvector oder Vektordatenbank: Eine Person an einer Weggabelung wählt zwischen Elefant mit Kommode und hohem Lager.",{"slug":765,"published":766,"updated":294,"minutes":348,"category":90,"tags":767,"tagPages":771,"keywords":772,"about":780,"sources":789,"cover":812,"og":813,"expertise":156,"locales":814,"lang":80,"title":815,"description":816,"coverAlt":817},"weaviate","2026-06-02",[94,15,768,769,770],"HNSW","Quantization","Multi-tenancy",[97,17],[765,773,774,775,776,777,778,779],"weaviate vs qdrant vergleich","weaviate vs pinecone vergleich","weaviate vs pgvector vergleich","hnsw vs hfresh vergleich","weaviate cloud preise","weaviate vektordatenbank test","weaviate hybridsuche",[781,784,786],{"name":782,"url":783},"Weaviate","https:\u002F\u002Fgithub.com\u002Fweaviate\u002Fweaviate",{"name":785,"url":116},"Hierarchical Navigable Small World",{"name":787,"url":788},"SPFresh","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2410.14452",[790,792,795,798,801,804,806,809],{"title":791,"url":733},"Weaviate documentation: Vector indexing",{"title":793,"url":794},"Weaviate documentation: ANN benchmark","https:\u002F\u002Fdocs.weaviate.io\u002Fweaviate\u002Fbenchmarks\u002Fann",{"title":796,"url":797},"Weaviate 1.39 release notes","https:\u002F\u002Fweaviate.io\u002Fblog\u002Fweaviate-1-39-release",{"title":799,"url":800},"Weaviate 1.38 release notes","https:\u002F\u002Fweaviate.io\u002Fblog\u002Fweaviate-1-38-release",{"title":802,"url":803},"Weaviate documentation: MCP server","https:\u002F\u002Fdocs.weaviate.io\u002Fweaviate\u002Fconfiguration\u002Fmcp-server",{"title":805,"url":736},"Weaviate Cloud pricing",{"title":807,"url":808},"weaviate\u002Fweaviate: LICENSE","https:\u002F\u002Fgithub.com\u002Fweaviate\u002Fweaviate\u002Fblob\u002Fmain\u002FLICENSE",{"title":810,"url":811},"weaviate\u002Fweaviate v1.40.0 release notes","https:\u002F\u002Fgithub.com\u002Fweaviate\u002Fweaviate\u002Freleases\u002Ftag\u002Fv1.40.0","\u002Fimages\u002Fblog\u002Fweaviate\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fweaviate\u002Fog.jpg",[79,80,81],"Weaviate: eine Vektordatenbank, die bei der Suche gewinnen muss, nicht nur bei der Ähnlichkeit","Weaviate im Test: hybride BM25- und Vektorsuche in einer Abfrage, HNSW und HFresh, Quantisierungsentscheidungen, eingebauter MCP-Server, Lizenzschlüssel.","Weaviate: Ein Magnet und eine Lupe kreuzen sich über Murmeln, einige haften am Magnet.",{"slug":819,"published":820,"updated":6,"minutes":348,"category":90,"tags":821,"tagPages":824,"keywords":825,"about":833,"sources":837,"cover":875,"og":876,"expertise":156,"locales":877,"lang":80,"title":878,"description":879,"coverAlt":880},"qdrant","2026-05-26",[94,768,822,15,823],"Quantisation","Filtering",[97,17],[819,826,827,828,829,830,831,832],"qdrant vs pinecone vergleich","vektordatenbanken im vergleich","hnsw index erklärt","gefilterte vektorsuche","vektor-quantisierung","hybridsuche qdrant","qdrant rag",[834,835,836],{"name":165,"url":181},{"name":115,"url":116},{"name":370,"url":371},[838,841,844,847,850,853,856,859,861,863,866,869,872],{"title":839,"url":840},"Qdrant documentation","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002F",{"title":842,"url":843},"Qdrant: points","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fmanage-data\u002Fpoints\u002F",{"title":845,"url":846},"Qdrant: collections","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fconcepts\u002Fcollections\u002F",{"title":848,"url":849},"Qdrant: indexing","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F",{"title":851,"url":852},"Qdrant: quantisation","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F",{"title":854,"url":855},"Qdrant: capacity planning","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fcapacity-planning\u002F",{"title":857,"url":858},"Qdrant: optimise performance","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fops-optimization\u002Foptimize\u002F",{"title":860,"url":724},"Qdrant: hybrid and multi-stage queries",{"title":862,"url":721},"Qdrant: filtering",{"title":864,"url":865},"Qdrant: security and access control","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fsecurity\u002F",{"title":867,"url":868},"Qdrant pricing","https:\u002F\u002Fqdrant.tech\u002Fpricing\u002F",{"title":870,"url":871},"Qdrant on GitHub","https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant",{"title":873,"url":874},"Qdrant vector search benchmarks","https:\u002F\u002Fqdrant.tech\u002Fbenchmarks\u002F","\u002Fimages\u002Fblog\u002Fqdrant\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fqdrant\u002Fog.jpg",[79,80,81],"Qdrant: eine Vektordatenbank, gebaut um Filtern","Qdrant im Test: filterbares HNSW, vier Quantisierungsmethoden, die Memory-Tier in Version 1.19 und der Betrieb, den niemand mehr publiziert.","Qdrant-Vektorsuche: Ein mehrlagiges Sieb sortiert Murmeln in eine Schale.",1793451238674]