[{"data":1,"prerenderedAt":2329},["ShallowReactive",2],{"blog-category-de-rag":3},[4,88,150,209,273,341,411,466,522,578,621,670,740,813,884,952,1020,1082,1148,1212,1273,1341,1406,1457,1496,1547,1597,1636,1686,1756,1831,1875,1929,1984,2033,2105,2156,2218,2263],{"slug":5,"published":6,"minutes":7,"category":8,"tags":9,"tagPages":15,"keywords":18,"about":31,"sources":41,"cover":78,"og":79,"expertise":80,"locales":81,"lang":83,"title":85,"description":86,"coverAlt":87},"embedding-model-selection-2026","2026-10-17",9,"rag",[10,11,12,13,14],"Embeddings","RAG","MTEB","Vector search","Model selection",[16,8,17],"embeddings","vector-search",[19,20,21,22,23,24,25,26,27,28,29,30],"bestes embedding-modell 2026","embedding-modell auswählen","embedding-modell vergleich","mteb rangliste erklärt","rteb rangliste","open-source embedding-modell","mehrsprachiges embedding-modell","voyage-4 vs openai embeddings vergleich","qwen3-embedding","embeddinggemma","embedding-modell für rag","embedding-modell wechseln neu einbetten",[32,35,38],{"name":33,"url":34},"Word embedding","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FWord_embedding",{"name":36,"url":37},"Information retrieval","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FInformation_retrieval",{"name":39,"url":40},"Discounted cumulative gain","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FDiscounted_cumulative_gain",[42,45,48,51,54,57,60,63,66,69,72,75],{"title":43,"url":44},"Enevoldsen et al.: MMTEB, Massive Multilingual Text Embedding Benchmark (2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.13595",{"title":46,"url":47},"Hugging Face: Introducing RTEB, a new standard for retrieval evaluation (Oct 2025)","https:\u002F\u002Fhuggingface.co\u002Fblog\u002Frteb",{"title":49,"url":50},"OpenAI: Vector embeddings guide","https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fguides\u002Fembeddings",{"title":52,"url":53},"OpenAI: API pricing","https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fpricing",{"title":55,"url":56},"Voyage AI: The Voyage 4 model family, shared embedding space with MoE architecture (Jan 2026)","https:\u002F\u002Fblog.voyageai.com\u002F2026\u002F01\u002F15\u002Fvoyage-4\u002F",{"title":58,"url":59},"Voyage AI: Text embeddings documentation","https:\u002F\u002Fdocs.voyageai.com\u002Fdocs\u002Fembeddings",{"title":61,"url":62},"Voyage AI: Pricing","https:\u002F\u002Fdocs.voyageai.com\u002Fdocs\u002Fpricing",{"title":64,"url":65},"Google: Gemini API embeddings documentation","https:\u002F\u002Fai.google.dev\u002Fgemini-api\u002Fdocs\u002Fembeddings",{"title":67,"url":68},"Google: Gemini API pricing","https:\u002F\u002Fai.google.dev\u002Fgemini-api\u002Fdocs\u002Fpricing",{"title":70,"url":71},"Cohere: Embed models documentation","https:\u002F\u002Fdocs.cohere.com\u002Fdocs\u002Fcohere-embed",{"title":73,"url":74},"Qwen: Qwen3-Embedding-8B model card","https:\u002F\u002Fhuggingface.co\u002FQwen\u002FQwen3-Embedding-8B",{"title":76,"url":77},"Google Developers Blog: Introducing EmbeddingGemma (Sep 2025)","https:\u002F\u002Fdevelopers.googleblog.com\u002Fen\u002Fintroducing-embeddinggemma\u002F","\u002Fimages\u002Fblog\u002Fembedding-model-selection-2026\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fembedding-model-selection-2026\u002Fog.jpg","ai-engineer",[82,83,84],"en","de","hu","Embedding-Modell wählen 2026: Leaderboards, Kosten und ein Vergleichstest mit eigenen Daten","Embedding-Modell 2026 für RAG wählen: was MTEB und RTEB aussagen, API oder offene Gewichte, Preise, Dimensionen und ein einwöchiger Test mit eigenen Daten.","Embedding-Modelle 2026: Drei Kuchen aus drei Formen kühlen ab, eine Gabel probiert gleich einen.",{"slug":89,"published":6,"minutes":90,"category":8,"tags":91,"tagPages":95,"keywords":96,"about":109,"sources":119,"cover":144,"og":145,"expertise":80,"locales":146,"lang":83,"title":147,"description":148,"coverAlt":149},"contextual-retrieval-late-chunking",10,[11,92,10,93,94],"Chunking","Contextual retrieval","Late chunking",[8,16],[97,98,99,100,101,102,103,104,105,106,107,108],"contextual retrieval","anthropic contextual retrieval","late chunking","late chunking anleitung","kontextuelle chunk-embeddings","kontextuelle embeddings rag","contextual bm25 suche","chunk-kontext rag","voyage-context-3","voyage-context-4","late chunking vs contextual retrieval vergleich","rag chunking kontextverlust",[110,113,116],{"name":111,"url":112},"Retrieval-augmented generation","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FRetrieval-augmented_generation",{"name":114,"url":115},"Okapi BM25","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOkapi_BM25",{"name":117,"url":118},"Sentence embedding","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FSentence_embedding",[120,123,126,129,132,135,138,141],{"title":121,"url":122},"Anthropic: Introducing Contextual Retrieval (Sep 2024)","https:\u002F\u002Fwww.anthropic.com\u002Fnews\u002Fcontextual-retrieval",{"title":124,"url":125},"Günther et al.: Late Chunking, Contextual Chunk Embeddings Using Long-Context Embedding Models (2024, rev. 2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.04701",{"title":127,"url":128},"Jina AI: Late Chunking in Long-Context Embedding Models (Aug 2024)","https:\u002F\u002Fjina.ai\u002Fnews\u002Flate-chunking-in-long-context-embedding-models\u002F",{"title":130,"url":131},"Voyage AI: Introducing voyage-context-3 (Jul 2025)","https:\u002F\u002Fblog.voyageai.com\u002F2025\u002F07\u002F23\u002Fvoyage-context-3\u002F",{"title":133,"url":134},"Voyage AI: voyage-context-4 (Jun 2026)","https:\u002F\u002Fblog.voyageai.com\u002F2026\u002F06\u002F29\u002Fvoyage-context-4\u002F",{"title":136,"url":137},"Voyage AI: Contextualized chunk embeddings documentation","https:\u002F\u002Fdocs.voyageai.com\u002Fdocs\u002Fcontextualized-chunk-embeddings",{"title":139,"url":140},"Anthropic: Claude API pricing","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fabout-claude\u002Fpricing",{"title":142,"url":143},"Qu, Tu and Bao: Is Semantic Chunking Worth the Computational Cost? (2024)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.13070","\u002Fimages\u002Fblog\u002Fcontextual-retrieval-late-chunking\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fcontextual-retrieval-late-chunking\u002Fog.jpg",[82,83,84],"Contextual Retrieval und Late Chunking: RAG-Chunks ihren Kontext zurückgeben","Chunks verlieren ihr Dokument. Wie Contextual Retrieval, Late Chunking und kontextuelle Embeddings das beheben, was sie kosten, wann man verzichtet.","Contextual Retrieval: Eine Hand hält ein Puzzleteil mit Anhänger über seine Lücke im Puzzle.",{"slug":151,"published":6,"minutes":7,"category":8,"tags":152,"tagPages":156,"keywords":157,"about":170,"sources":178,"cover":203,"og":204,"expertise":80,"locales":205,"lang":83,"title":206,"description":207,"coverAlt":208},"rag-access-control-permissions",[11,153,154,155,13],"Access control","Security","Multi-tenancy",[8,17],[158,159,160,161,162,163,164,165,166,167,168,169],"rag zugriffskontrolle","berechtigungsbewusstes rag","dokumentebene sicherheit rag","rag mandantenfähigkeit","vektordatenbank zugriffskontrolle","pgvector row-level-security einrichten","security trimming azure ai search einrichten","openfga rag autorisierung","qdrant mandanten","pinecone namespaces mandanten","owasp llm08 embedding-schwächen","rag datenabfluss",[171,174,177],{"name":172,"url":173},"Access-control list","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAccess-control_list",{"name":175,"url":176},"Multitenancy","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FMultitenancy",{"name":111,"url":112},[179,182,185,188,191,194,197,200],{"title":180,"url":181},"OWASP GenAI Security Project: LLM08:2025 Vector and Embedding Weaknesses","https:\u002F\u002Fgenai.owasp.org\u002Fllmrisk\u002Fllm082025-vector-and-embedding-weaknesses\u002F",{"title":183,"url":184},"PostgreSQL documentation: Row Security Policies","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Fddl-rowsecurity.html",{"title":186,"url":187},"pgvector README: filtering and iterative index scans","https:\u002F\u002Fgithub.com\u002Fpgvector\u002Fpgvector",{"title":189,"url":190},"Qdrant: Multitenancy and partitions guide","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fguides\u002Fmultiple-partitions\u002F",{"title":192,"url":193},"Pinecone: Implement multitenancy using namespaces","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Fimplement-multitenancy",{"title":195,"url":196},"Microsoft Learn: Document-level access control in Azure AI Search","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fsearch-document-level-access-overview",{"title":198,"url":199},"OpenFGA: RAG authorization use case","https:\u002F\u002Fopenfga.dev\u002Fdocs\u002Fuse-cases\u002Frag-authorization",{"title":201,"url":202},"Morris et al.: Text Embeddings Reveal (Almost) As Much As Text (EMNLP 2023)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.06816","\u002Fimages\u002Fblog\u002Frag-access-control-permissions\u002Fcover.webp","\u002Fimages\u002Fblog\u002Frag-access-control-permissions\u002Fog.jpg",[82,83,84],"Zugriffskontrolle für RAG: berechtigungsbewusstes Retrieval ohne Datenlecks","Wie RAG-Assistenten Dokumente preisgeben und wie man das stoppt: ACLs an jedem Chunk, Vorfilter, Row-Level Security in pgvector, Rechte-Sync und Lecktests.","Zugriffskontrolle für RAG: Eine Person mit Ausweis nimmt ein Buch, andere bleiben hinter einer verschlossenen Glastür.",{"slug":210,"published":6,"minutes":90,"category":8,"tags":211,"tagPages":216,"keywords":219,"about":231,"sources":239,"cover":266,"og":267,"expertise":268,"locales":269,"lang":83,"title":270,"description":271,"coverAlt":272},"rag-product-catalog-pim-data",[11,212,213,214,215],"PIM","Product data","B2B e-commerce","Metadata filtering",[8,217,218],"pim","b2b-e-commerce",[220,221,222,223,224,225,226,227,228,229,230],"rag produktkatalog","rag pim-daten","ki produktdaten","produktkatalog chatbot","akeneo rag anbindung","pimcore ki-suche","rag strukturierte daten","metadatenfilter rag","produktattribute embeddings","b2b produktassistent","etim-klassifikation ki",[232,235,236],{"name":233,"url":234},"Product information management","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FProduct_information_management",{"name":111,"url":112},{"name":237,"url":238},"ETIM (standard)","https:\u002F\u002Fwww.etim-international.com\u002Fclassification\u002F",[240,243,246,249,251,254,257,260,263],{"title":241,"url":242},"Akeneo API: Products, product values, metric values and product models","https:\u002F\u002Fapi.akeneo.com\u002Fconcepts\u002Fproducts.html",{"title":244,"url":245},"Akeneo Help Center: What about products with variants?","https:\u002F\u002Fhelp.akeneo.com\u002Fserenity-take-the-power-over-your-products\u002Fserenity-what-about-products-with-variants",{"title":247,"url":248},"Pimcore documentation: Classification Store","https:\u002F\u002Fdocs.pimcore.com\u002Fplatform\u002FPimcore\u002FObjects\u002FObject_Classes\u002FData_Types\u002FClassification_Store\u002F",{"title":250,"url":238},"ETIM International: Classification",{"title":252,"url":253},"ETIM International: ETIM releases and the IXF format","https:\u002F\u002Fetim-international.com\u002F?p=754",{"title":255,"url":256},"Reddy et al.: Shopping Queries Dataset, a large-scale ESCI benchmark for improving product search (2022)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.06588",{"title":258,"url":259},"Amazon Science: esci-data repository","https:\u002F\u002Fgithub.com\u002Famazon-science\u002Fesci-data",{"title":261,"url":262},"Qdrant documentation: Filtering","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fconcepts\u002Ffiltering\u002F",{"title":264,"url":265},"Sui et al.: Table Meets LLM, can large language models understand structured table data? (WSDM 2024)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.13062","\u002Fimages\u002Fblog\u002Frag-product-catalog-pim-data\u002Fcover.webp","\u002Fimages\u002Fblog\u002Frag-product-catalog-pim-data\u002Fog.jpg","b2b-ecommerce-developer",[82,83,84],"RAG über Produktkataloge: aus PIM-Daten Antworten machen, die halten","Produktdaten sind strukturiert, Chunking wie bei PDFs scheitert. So serialisiert man PIM-Attribute, leitet Spezifikationsfragen an Filter und bleibt exakt.","RAG über Produktkataloge: Aus einem offenen Produktkatalog steigt eine Sprechblase mit einer Produktkarte auf.",{"slug":274,"published":6,"minutes":275,"category":8,"tags":276,"tagPages":281,"keywords":282,"about":293,"sources":301,"cover":335,"og":336,"expertise":80,"locales":337,"lang":83,"title":338,"description":339,"coverAlt":340},"conversational-search-query-rewriting",12,[277,278,11,279,280],"Conversational search","Query rewriting","HyDE","E-commerce",[8],[283,284,285,286,287,288,289,290,291,292],"konversationelle suche query rewriting","koreferenzauflösung suchanfrage","hyde hypothetische dokument-embeddings","multi-query erweiterung rag","llm filter-extraktion","b2b-produktsuche assistent","konversationelle produktsuche","query rewriting latenz","recall@k bewertung","standalone query generierung",[294,297,300],{"name":295,"url":296},"Query expansion","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FQuery_expansion",{"name":298,"url":299},"Coreference","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FCoreference",{"name":114,"url":115},[302,305,308,311,314,317,320,323,326,329,332],{"title":303,"url":304},"Gao et al.: Precise Zero-Shot Dense Retrieval without Relevance Labels, ACL 2023","https:\u002F\u002Faclanthology.org\u002F2023.acl-long.99\u002F",{"title":306,"url":307},"UTokyo-Hitotsubashi at TREC 2025 RAG Track: HyDE-Enhanced Sparse-Dense Retrieval Fusion with LLM Reranking","https:\u002F\u002Ftrec.nist.gov\u002Fpubs\u002Ftrec34\u002Fpapers\u002FUTokyo.rag.pdf",{"title":309,"url":310},"Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion","https:\u002F\u002Faclanthology.org\u002F2025.findings-acl.980.pdf",{"title":312,"url":313},"ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning","https:\u002F\u002Faclanthology.org\u002F2025.emnlp-main.1349\u002F",{"title":315,"url":316},"CFDA and CLIP at TREC iKAT 2025: Query Reformulation and Rank Fusion","https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.15588",{"title":318,"url":319},"MiniELM: A Lightweight and Adaptive Query Rewriting Framework for E-Commerce Search Optimization","https:\u002F\u002Faclanthology.org\u002F2025.findings-acl.363\u002F",{"title":321,"url":322},"Microsoft Learn: Rewrite queries with semantic ranker in Azure AI Search (preview)","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fsemantic-how-to-query-rewrite",{"title":324,"url":325},"Microsoft Learn: Agentic retrieval overview in Azure AI Search","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fagentic-retrieval-overview",{"title":327,"url":328},"Microsoft Tech Community: Generative query rewriting and a new semantic ranker","https:\u002F\u002Ftechcommunity.microsoft.com\u002Fblog\u002Fazure-ai-services-blog\u002Fraising-the-bar-for-rag-excellence-query-rewriting-and-new-semantic-ranker\u002F4302729\u002F",{"title":330,"url":331},"Amazon Bedrock User Guide: Configure and customize queries and response generation","https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fkb-test-config.html",{"title":333,"url":334},"Ragas documentation: List of available metrics","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fconcepts\u002Fmetrics\u002Favailable_metrics\u002F","\u002Fimages\u002Fblog\u002Fconversational-search-query-rewriting\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fconversational-search-query-rewriting\u002Fog.jpg",[82,83,84],"Query Rewriting für die konversationelle Suche: Kontext, HyDE und Filter","Wie Follow-up-Fragen in einem B2B-Shop-Assistenten umgeschrieben werden: Koreferenz, HyDE, Multi-Query, Filter, Latenz und Evaluation.","Query Rewriting: Eine Sprechblase läuft durch eine Nähmaschine und kommt als ordentliche Notiz mit Lupe heraus.",{"slug":342,"published":6,"minutes":90,"category":8,"tags":343,"tagPages":348,"keywords":350,"about":363,"sources":369,"cover":405,"og":406,"expertise":80,"locales":407,"lang":83,"title":408,"description":409,"coverAlt":410},"synthetic-test-data-rag-evals",[11,344,345,346,347],"Evaluation","Synthetic data","Retrieval","Testing",[8,349],"evaluation",[351,352,353,354,355,356,357,358,359,360,361,362],"synthetische testdaten rag","rag-evaluationsdatensatz","fragengenerierung aus chunks","hard negatives retrieval-evaluation","answerability-filter","rag testset generieren","synthetische qa-paare","rag eval daten kontamination","mehrsprachige rag-evaluation deutsch ungarisch","retrieval-metriken recall ndcg","llm-judge menschliche stichprobe","unbeantwortbare fragen rag",[364,366,368],{"name":111,"url":365},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FRetrieval_augmented_generation",{"name":345,"url":367},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FSynthetic_data",{"name":36,"url":37},[370,373,376,379,382,385,388,391,394,397,400,402],{"title":371,"url":372},"Red Hat Developers: Synthetic data for RAG evaluation (Feb 23, 2026)","https:\u002F\u002Fdevelopers.redhat.com\u002Farticles\u002F2026\u002F02\u002F23\u002Fsynthetic-data-rag-evaluation-why-your-rag-system-needs-better-testing",{"title":374,"url":375},"Ragas docs: Testset Generation for RAG","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fgetstarted\u002Frag_testset_generation\u002F",{"title":377,"url":378},"Ragas docs: Testset generation concepts (query types, scenarios)","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fconcepts\u002Ftest_data_generation\u002Frag\u002F",{"title":380,"url":381},"NVIDIA Technical Blog: Evaluating and Enhancing RAG Pipeline Performance Using Synthetic Data","https:\u002F\u002Fdeveloper.nvidia.com\u002Fblog\u002Fevaluating-and-enhancing-rag-pipeline-performance-using-synthetic-data\u002F",{"title":383,"url":384},"DeepEval docs: Datasets and the Synthesizer","https:\u002F\u002Fdeepeval.com\u002Fdocs\u002Fevaluation-datasets",{"title":386,"url":387},"Rajpurkar, Jia, Liang: Know What You Don't Know: Unanswerable Questions for SQuAD (ACL 2018)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1806.03822",{"title":389,"url":390},"Rahmani et al.: Towards Understanding Bias in Synthetic Data for Evaluation (CIKM 2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.10301",{"title":392,"url":393},"Cheng et al.: A Survey on Data Contamination for Large Language Models","https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.14425",{"title":395,"url":396},"Xu et al.: Infini-gram mini: Exact n-gram Search at the Internet Scale (EMNLP 2025)","https:\u002F\u002Faclanthology.org\u002F2025.emnlp-main.1268\u002F",{"title":398,"url":399},"Panickssery, Bowman, Feng: LLM Evaluators Recognize and Favor Their Own Generations","https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.13076",{"title":401,"url":44},"Enevoldsen et al.: MMTEB, Massive Multilingual Text Embedding Benchmark (ICLR 2025)",{"title":403,"url":404},"Evidently AI: How to align an LLM judge with human labels (Nov 2025)","https:\u002F\u002Fwww.evidentlyai.com\u002Fblog\u002Fhow-to-align-llm-judge-with-human-labels","\u002Fimages\u002Fblog\u002Fsynthetic-test-data-rag-evals\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fsynthetic-test-data-rag-evals\u002Fog.jpg",[82,83,84],"Synthetische Testdaten für RAG-Evaluierungen erzeugen","Fragengeneration aus Chunks, Hard Negatives, Answerability-Labels, deutsche und ungarische Abdeckung, Kontamination und menschliche Stichproben.","Synthetische Testdaten für RAG: Ein Roboter bedient eine Maschine, die aus einem Buch Fragekarten macht.",{"slug":412,"published":413,"minutes":7,"category":8,"tags":414,"tagPages":419,"keywords":421,"about":432,"sources":440,"cover":460,"og":461,"expertise":80,"locales":462,"lang":83,"title":463,"description":464,"coverAlt":465},"pdf-document-parsing-for-rag","2026-10-16",[11,415,416,417,418],"PDF parsing","OCR","Docling","Document AI",[8,420],"document-ai",[422,423,424,425,426,427,428,429,430,431],"pdf-parsing für rag","bester pdf-parser für rag","docling vs marker vergleich","marker vs mineru vergleich","pdf zu markdown für llm","tabellen aus pdf extrahieren rag","ocr für rag-pipeline","olmocr benchmark","gescannte pdfs rag","dokumenten-parsing llm",[433,436,439],{"name":434,"url":435},"PDF","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FPDF",{"name":437,"url":438},"Optical character recognition","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOptical_character_recognition",{"name":111,"url":112},[441,444,447,450,453,456,459],{"title":442,"url":443},"Docling: README, features and license (GitHub)","https:\u002F\u002Fgithub.com\u002Fdocling-project\u002Fdocling",{"title":445,"url":446},"Auer et al.: Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion (2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.17887",{"title":448,"url":449},"Datalab: Marker README, olmOCR-bench results and license (GitHub)","https:\u002F\u002Fgithub.com\u002Fdatalab-to\u002Fmarker",{"title":451,"url":452},"OpenDataLab: MinerU README and license (GitHub)","https:\u002F\u002Fgithub.com\u002Fopendatalab\u002FMinerU",{"title":454,"url":455},"Poznanski et al.: olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models (2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.18443",{"title":457,"url":458},"Claude Platform Docs: PDF support","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fbuild-with-claude\u002Fpdf-support",{"title":121,"url":122},"\u002Fimages\u002Fblog\u002Fpdf-document-parsing-for-rag\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fpdf-document-parsing-for-rag\u002Fog.jpg",[82,83,84],"PDF-Parsing für RAG: Layout-Pipelines, OCR und Vision-Modelle im Vergleich","Warum das PDF-Parsing die RAG-Qualität bestimmt, wie sich Docling, Marker, MinerU und VLM-OCR unterscheiden und wie man einen Parser selbst testet.","PDF-Parsing für RAG: Ein Dokument läuft durch eine Walzenmaschine und kommt als Tabellen-, Bild- und Textkarten heraus.",{"slug":467,"published":413,"minutes":468,"category":8,"tags":469,"tagPages":473,"keywords":474,"about":485,"sources":495,"cover":516,"og":517,"expertise":80,"locales":518,"lang":83,"title":519,"description":520,"coverAlt":521},"multilingual-rag-german-hungarian",7,[11,470,10,471,472],"Multilingual","German","Hungarian",[8,16],[475,476,477,478,479,480,481,482,483,484],"mehrsprachiges rag","rag deutsch embeddings","ungarische nlp suche","sprachübergreifende suche","mehrsprachige embeddings deutsch ungarisch","bge-m3 deutsch","deutsche komposita suche","ungarisch stemming postgres","multilingual-e5-large-instruct","qwen3 embedding mehrsprachig",[486,489,492],{"name":487,"url":488},"Cross-language information retrieval","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FCross-language_information_retrieval",{"name":490,"url":491},"Agglutinative language","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAgglutinative_language",{"name":493,"url":494},"Compound (linguistics)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FCompound_(linguistics)",[496,498,501,504,507,510,513],{"title":497,"url":44},"Enevoldsen et al.: MMTEB: Massive Multilingual Text Embedding Benchmark (2025)",{"title":499,"url":500},"Chen et al.: M3-Embedding (BGE-M3): Multi-Linguality, Multi-Functionality, Multi-Granularity (2024)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.03216",{"title":502,"url":503},"Zhang et al.: Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models (2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.05176",{"title":505,"url":506},"Hugging Face: intfloat\u002Fmultilingual-e5-large-instruct model card","https:\u002F\u002Fhuggingface.co\u002Fintfloat\u002Fmultilingual-e5-large-instruct",{"title":508,"url":509},"Elasticsearch Reference: Hyphenation decompounder token filter","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Ftext-analysis\u002Fanalysis-hyp-decomp-tokenfilter",{"title":511,"url":512},"PostgreSQL 18 Documentation: Text search dictionaries","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Ftextsearch-dictionaries.html",{"title":514,"url":515},"Snowball: stemming algorithms by language","https:\u002F\u002Fsnowballstem.org\u002Falgorithms\u002F","\u002Fimages\u002Fblog\u002Fmultilingual-rag-german-hungarian\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fmultilingual-rag-german-hungarian\u002Fog.jpg",[82,83,84],"Mehrsprachiges RAG für Deutsch und Ungarisch: Embeddings, Komposita und sprachübergreifende Suche","RAG über deutsche und ungarische Inhalte: mehrsprachige Embeddings, Komposita, Stemming, Akzente und Evaluation pro Sprache.","Mehrsprachiges RAG: Eine Person trägt ein Buch über eine kleine Brücke zwischen zwei Bücherregalen.",{"slug":523,"published":413,"minutes":524,"category":8,"tags":525,"tagPages":531,"keywords":533,"about":545,"sources":554,"cover":572,"og":573,"expertise":80,"locales":574,"lang":83,"title":575,"description":576,"coverAlt":577},"text-to-sql-llm-guardrails",8,[526,527,528,529,530],"Text-to-SQL","LLM security","PostgreSQL","Agents","Analytics",[532],"llm-security",[534,535,536,537,538,539,540,541,542,543,544],"text-to-sql mit llms","text-to-sql leitplanken","llm sql-agent sicherheit","natürliche sprache zu sql produktion","read-only datenbankrolle llm","bird benchmark","spider 2.0 benchmark ergebnisse","sqlglot sql validieren","row-level-security llm","mit der datenbank chatten ki","text-to-sql llm",[546,549,552],{"name":547,"url":548},"SQL","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FSQL",{"name":550,"url":551},"Natural language interface to databases","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FNatural-language_user_interface",{"name":528,"url":553},"https:\u002F\u002Fwww.postgresql.org\u002F",[555,558,561,563,566,569],{"title":556,"url":557},"BIRD-bench: leaderboard and dataset description","https:\u002F\u002Fbird-bench.github.io\u002F",{"title":559,"url":560},"Lei et al.: Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows (2024)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.07763",{"title":562,"url":184},"PostgreSQL 18 Documentation: Row Security Policies",{"title":564,"url":565},"PostgreSQL 18 Documentation: Client Connection Defaults (read-only and timeouts)","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Fruntime-config-client.html",{"title":567,"url":568},"SQLGlot: SQL parser, transpiler and optimizer (GitHub)","https:\u002F\u002Fgithub.com\u002Ftobymao\u002Fsqlglot",{"title":570,"url":571},"OWASP Gen AI Security Project: LLM06:2025 Excessive Agency","https:\u002F\u002Fgenai.owasp.org\u002Fllmrisk\u002Fllm062025-excessive-agency\u002F","\u002Fimages\u002Fblog\u002Ftext-to-sql-llm-guardrails\u002Fcover.webp","\u002Fimages\u002Fblog\u002Ftext-to-sql-llm-guardrails\u002Fog.jpg",[82,83,84],"Text-to-SQL mit LLMs: Schema-Kontext, Read-only-Rollen und Validierung, die hält","Wie genau Text-to-SQL wirklich ist, wie das Modell Schema-Kontext bekommt und welche Datenbank- und Code-Leitplanken generiertes SQL sicher machen.","Text-to-SQL: Eine Sprechblase gelangt durch ein vergittertes Fenster in einen Datenbankzylinder, an der Tür ein Schloss.",{"slug":579,"published":413,"minutes":580,"category":8,"tags":581,"tagPages":584,"keywords":585,"about":596,"sources":606,"cover":615,"og":616,"expertise":80,"locales":617,"lang":83,"title":618,"description":619,"coverAlt":620},"embedding-quantization-binary-matryoshka",5,[10,13,582,583,11],"Quantization","pgvector",[16,17,8],[586,587,588,589,590,591,592,593,594,595],"embedding-quantisierung","binäre quantisierung embeddings","int8-embeddings quantisierung","matryoshka-embeddings","vektordatenbank speicher reduzieren","pgvector halfvec","pgvector binary_quantize","embedding-dimensionen reduzieren","rescoring binärer embeddings","vektorindex speicherbedarf",[597,600,603],{"name":598,"url":599},"Quantization (signal processing)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FQuantization_(signal_processing)",{"name":601,"url":602},"Nearest neighbor search","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FNearest_neighbor_search",{"name":604,"url":605},"Hamming distance","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FHamming_distance",[607,610,613],{"title":608,"url":609},"Hugging Face: Binary and Scalar Embedding Quantization for Significantly Faster and Cheaper Retrieval (Mar 2024)","https:\u002F\u002Fhuggingface.co\u002Fblog\u002Fembedding-quantization",{"title":611,"url":612},"Kusupati et al.: Matryoshka Representation Learning (2022)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.13147",{"title":614,"url":187},"pgvector README: halfvec, bit, binary quantization and subvector indexing","\u002Fimages\u002Fblog\u002Fembedding-quantization-binary-matryoshka\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fembedding-quantization-binary-matryoshka\u002Fog.jpg",[82,83,84],"Embedding-Quantisierung: Binär-, int8- und Matryoshka-Vektoren ohne Qualitätsverlust beim Retrieval","Wie Binär- und int8-Quantisierung und Matryoshka-Kürzung Vektorindizes 4- bis 32-mal verkleinern, was das an Recall kostet und wie Rescoring es zurückholt.","Embedding-Quantisierung: Matroschka-Puppen stehen von groß nach klein, die kleinste auf einer Waage.",{"slug":622,"published":623,"minutes":624,"category":8,"tags":625,"tagPages":630,"keywords":632,"about":641,"sources":645,"cover":664,"og":665,"expertise":80,"locales":666,"lang":83,"title":667,"description":668,"coverAlt":669},"zep","2026-10-06",11,[626,627,628,629,11],"Agent memory","Knowledge graph","Temporal graph","Context engineering",[631,8],"context-engineering",[633,634,635,636,637,638,639,640],"zep test","zep agenten-memory","graphiti wissensgraph","zep preise","zep vs mem0 vergleich","langzeitgedächtnis für agenten","temporaler wissensgraph","zep cloud kosten",[642],{"name":643,"url":644},"Zep","https:\u002F\u002Fwww.getzep.com\u002F",[646,649,652,655,658,661],{"title":647,"url":648},"Zep pricing: plans, credits and limits","https:\u002F\u002Fwww.getzep.com\u002Fpricing",{"title":650,"url":651},"Zep documentation","https:\u002F\u002Fhelp.getzep.com\u002F",{"title":653,"url":654},"Graphiti on GitHub","https:\u002F\u002Fgithub.com\u002Fgetzep\u002Fgraphiti",{"title":656,"url":657},"Graphiti product page","https:\u002F\u002Fwww.getzep.com\u002Fplatform\u002Fgraphiti\u002F",{"title":659,"url":660},"Announcing a new direction for Zep's open-source strategy","https:\u002F\u002Fwww.getzep.com\u002Fblog\u002Fannouncing-a-new-direction-for-zeps-open-source-strategy\u002F",{"title":662,"url":663},"Graphiti: temporal knowledge graphs for AI agents (arXiv)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.13956","\u002Fimages\u002Fblog\u002Fzep\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fzep\u002Fog.jpg",[82,83,84],"Zep-Review: Agenten-Memory auf einem temporalen Graphen","Zep im Review: Agenten-Memory auf temporalem Knowledge Graph. Credits beim Schreiben, Retrieval gratis, Flex ab 125 Dollar\u002FMonat, Graphiti selbst hostbar.","Zep: Ein Roboter betrachtet ein Wandschema verbundener Karten, jede mit kleiner Uhr.",{"slug":671,"published":672,"minutes":673,"category":8,"tags":674,"tagPages":678,"keywords":679,"about":690,"sources":697,"cover":734,"og":735,"expertise":80,"locales":736,"lang":83,"title":737,"description":738,"coverAlt":739},"graphrag-knowledge-graph-rag","2026-10-02",13,[675,676,677,11],"GraphRAG","Knowledge graphs","LightRAG",[8],[680,681,682,683,684,685,686,687,688,689],"graphrag erklärt","wissensgraph-rag","graphrag vs vektor-rag vergleich","microsoft graphrag erklärt","lightrag vs graphrag vergleich","graphrag global vs local suche","graphrag indexierungskosten","wann graphrag einsetzen","multi-hop rag fragen","lazygraphrag",[691,693,694],{"name":627,"url":692},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FKnowledge_graph",{"name":111,"url":112},{"name":695,"url":696},"Leiden algorithm","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FLeiden_algorithm",[698,701,704,707,710,713,716,719,722,725,728,731],{"title":699,"url":700},"Edge et al.: From Local to Global: A Graph RAG Approach to Query-Focused Summarization (arXiv:2404.16130)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.16130",{"title":702,"url":703},"Microsoft GraphRAG documentation: overview","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002F",{"title":705,"url":706},"Microsoft GraphRAG documentation: default dataflow","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Findex\u002Fdefault_dataflow\u002F",{"title":708,"url":709},"Microsoft GraphRAG documentation: global search","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Fquery\u002Fglobal_search\u002F",{"title":711,"url":712},"Microsoft GraphRAG documentation: local search","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Fquery\u002Flocal_search\u002F",{"title":714,"url":715},"Microsoft GraphRAG documentation: DRIFT search","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Fquery\u002Fdrift_search\u002F",{"title":717,"url":718},"Microsoft GraphRAG documentation: getting started","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Fget_started\u002F",{"title":720,"url":721},"Microsoft Research: LazyGraphRAG, setting a new standard for quality and cost (25 November 2024)","https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fblog\u002Flazygraphrag-setting-a-new-standard-for-quality-and-cost\u002F",{"title":723,"url":724},"Guo et al.: LightRAG: Simple and Fast Retrieval-Augmented Generation (arXiv:2410.05779)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.05779",{"title":726,"url":727},"HKUDS\u002FLightRAG on GitHub","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FLightRAG",{"title":729,"url":730},"Gutiérrez et al.: HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models (arXiv:2405.14831)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.14831",{"title":732,"url":733},"Xiang et al.: When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation (arXiv:2506.05690)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.05690","\u002Fimages\u002Fblog\u002Fgraphrag-knowledge-graph-rag\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fgraphrag-knowledge-graph-rag\u002Fog.jpg",[82,83,84],"GraphRAG und Knowledge-Graph-RAG: wann ein Graph die Vektorsuche schlägt","GraphRAG und Knowledge-Graph-RAG: was Microsoft GraphRAG und LightRAG tun, was die Indexierung kostet und wann ein Wissensgraph Vektor-RAG schlägt.","Knowledge-Graph-RAG: Eine Lupe über einer Kreuzung auf einem Stadtplan, daneben ein loser Papierstapel.",{"slug":741,"published":742,"updated":413,"minutes":90,"category":8,"tags":743,"tagPages":749,"keywords":750,"about":762,"sources":770,"cover":807,"og":808,"expertise":80,"locales":809,"lang":83,"title":810,"description":811,"coverAlt":812},"multimodal-rag-colpali","2026-10-01",[744,745,746,747,748],"ColPali","Multimodal RAG","Late interaction","Multi-vector embeddings","Visual document retrieval",[],[751,752,753,754,755,756,757,758,759,760,761],"multimodales rag mit colpali","multimodales rag erklärt","colpali","visuelle dokumentensuche","colqwen2","colqwen3","late interaction maxsim erklärt","multi-vektor-embeddings","vidore benchmark ergebnisse","seitenbild-embeddings","multivektor-datenbank",[763,764,767],{"name":111,"url":112},{"name":765,"url":766},"Vector database","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FVector_database",{"name":768,"url":769},"Vision-language model","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FVision-language_model",[771,774,777,780,783,786,789,792,795,798,801,804],{"title":772,"url":773},"ColPali: Efficient Document Retrieval with Vision Language Models (arXiv:2407.01449)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.01449",{"title":775,"url":776},"ViDoRe V2 benchmark (arXiv:2505.17166)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.17166",{"title":778,"url":779},"ViDoRe V3 benchmark (arXiv:2601.08620)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.08620",{"title":781,"url":782},"EVIE: storage and benchmark analysis for ColQwen-family models (arXiv:2610.11553)","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2610.11553v1",{"title":784,"url":785},"Vespa: scaling ColPali to billions","https:\u002F\u002Fblog.vespa.ai\u002Fscaling-colpali-to-billions\u002F",{"title":787,"url":788},"Qdrant documentation: vectors, multivectors and the max_sim comparator","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fconcepts\u002Fvectors\u002F",{"title":790,"url":791},"Qdrant: ColPali optimization with pooling and two-stage retrieval (2024)","https:\u002F\u002Fqdrant.tech\u002Fblog\u002Fcolpali-qdrant-optimization",{"title":793,"url":794},"Qdrant: turbo4 multivector search tutorial","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Ftutorials-search-engineering\u002Fturbo4-multivector-search\u002F",{"title":796,"url":797},"Sentence Transformers v6.0.0 release notes","https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fsentence-transformers\u002Freleases\u002Ftag\u002Fv6.0.0",{"title":799,"url":800},"illuin-tech\u002Fcolpali repository and model table","https:\u002F\u002Fgithub.com\u002Filluin-tech\u002Fcolpali",{"title":802,"url":803},"MUVERA: multi-vector retrieval via fixed dimensional encodings (NeurIPS 2024)","https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2024\u002Ffile\u002Fb71cfefae46909178603b5bc6c11d3ae-Paper-Conference.pdf",{"title":805,"url":806},"VectorChord documentation: indexing with MaxSim operators","https:\u002F\u002Fdocs.vectorchord.ai\u002Fvectorchord\u002Fusage\u002Findexing-with-maxsim-operators.html","\u002Fimages\u002Fblog\u002Fmultimodal-rag-colpali\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fmultimodal-rag-colpali\u002Fog.jpg",[82,83,84],"Multimodales RAG mit ColPali: Seitenbilder, Multi-Vektor-Kosten und wann sie gewinnen","Multimodales RAG mit ColPali: Seitenbild-Embeddings, MaxSim-Scoring, Speicherkosten für Multi-Vektoren, Kompression und wann sie geparsten Text schlagen.","Multimodales RAG mit ColPali: Eine Seite in kleine Felder geteilt, einige mit einer Lupe verbunden.",{"slug":814,"published":742,"updated":6,"minutes":524,"category":8,"tags":815,"tagPages":819,"keywords":821,"about":832,"sources":842,"cover":878,"og":879,"expertise":80,"locales":880,"lang":83,"title":881,"description":882,"coverAlt":883},"code-rag-repository-indexing",[11,816,817,10,818],"Code search","Tree-sitter","Coding agents",[8,16,820],"coding-agents",[822,823,824,825,826,827,828,829,830,831],"rag über code","ast-chunking code","tree-sitter chunking","repo-map für agenten","code-embeddings","semantische code-suche","codebase indexierung","repo map token-budget","inkrementeller code-index","coir benchmark ergebnisse",[833,834,837,839],{"name":111,"url":112},{"name":835,"url":836},"Abstract syntax tree","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAbstract_syntax_tree",{"name":817,"url":838},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FTree-sitter_%28parser_generator%29",{"name":840,"url":841},"Merkle tree","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FMerkle_tree",[843,846,849,852,855,858,861,864,867,869,872,875],{"title":844,"url":845},"cAST: AST-based chunking for code RAG (arXiv 2506.15655)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.15655",{"title":847,"url":848},"Aider docs: repository map","https:\u002F\u002Faider.chat\u002Fdocs\u002Frepomap.html",{"title":850,"url":851},"Aider blog: building a better repository map with tree-sitter (2023)","https:\u002F\u002Faider.chat\u002F2023\u002F10\u002F22\u002Frepomap.html",{"title":853,"url":854},"Anthropic Engineering: effective context engineering for AI agents (Sep 2025)","https:\u002F\u002Fwww.anthropic.com\u002Fengineering\u002Feffective-context-engineering-for-ai-agents",{"title":856,"url":857},"Cursor blog: securely indexing large codebases (Jan 2026)","https:\u002F\u002Fcursor.com\u002Fblog\u002Fsecure-codebase-indexing",{"title":859,"url":860},"turbopuffer: Cursor customer story","https:\u002F\u002Fturbopuffer.com\u002Fcustomers\u002Fcursor",{"title":862,"url":863},"Kilo Code docs: codebase indexing","https:\u002F\u002Fkilo.ai\u002Fdocs\u002Fcustomize\u002Fcontext\u002Fcodebase-indexing",{"title":865,"url":866},"Serena on GitHub","https:\u002F\u002Fgithub.com\u002Foraios\u002Fserena",{"title":868,"url":62},"Voyage AI docs: pricing",{"title":870,"url":871},"Qwen blog: Qwen3-Embedding (Jun 2025)","https:\u002F\u002Fqwenlm.github.io\u002Fblog\u002Fqwen3-embedding\u002F",{"title":873,"url":874},"CoIR: a benchmark for code information retrieval (arXiv 2407.02883)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.02883",{"title":876,"url":877},"CocoIndex blog: indexing a codebase","https:\u002F\u002Fcocoindex.io\u002Fblogs\u002Findex-codebase-v1","\u002Fimages\u002Fblog\u002Fcode-rag-repository-indexing\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fcode-rag-repository-indexing\u002Fog.jpg",[82,83,84],"RAG über Code: AST-Chunking, Repo-Maps und Code-Embeddings für Agenten","Wie Coding-Agenten Code finden: AST-Chunking mit tree-sitter, Repo-Maps, Merkle-Tree-Sync, Code-Embedding-Modelle 2026 und wann grep einen Index schlägt.","RAG über Code: Ein verzweigter Codebaum speist eine Reihe von Karteikarten.",{"slug":885,"published":886,"updated":742,"minutes":524,"category":8,"tags":887,"tagPages":891,"keywords":892,"about":903,"sources":911,"cover":946,"og":947,"expertise":80,"locales":948,"lang":83,"title":949,"description":950,"coverAlt":951},"reranking-models-compared","2026-09-30",[888,11,889,890,344],"Reranking","Search","Cross-encoders",[8,349],[893,894,895,896,897,898,899,900,901,902],"cross-encoder reranker vergleich","cohere rerank 4 preise","bge-reranker-v2-m3 test","voyage rerank-3 vergleich","jina reranker v3.5 test","colbert vs reranker","llm als reranker","rrf vs reranker","reranking top-k bewertung","reranker selbst hosten onnx cpu",[904,907,910],{"name":905,"url":906},"Learning to rank","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FLearning_to_rank",{"name":908,"url":909},"BERT (language model)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FBERT_%28language_model%29",{"name":36,"url":37},[912,915,918,921,924,927,930,931,934,937,940,943],{"title":913,"url":914},"Sentence-BERT (arXiv 1908.10084)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.10084",{"title":916,"url":917},"Sentence Transformers: retrieve and re-rank","https:\u002F\u002Fsbert.net\u002Fexamples\u002Fsentence_transformer\u002Fapplications\u002Fretrieve_rerank\u002FREADME.html",{"title":919,"url":920},"BAAI\u002Fbge-reranker-v2-m3 model card","https:\u002F\u002Fhuggingface.co\u002FBAAI\u002Fbge-reranker-v2-m3",{"title":922,"url":923},"Cohere docs: reranking best practices","https:\u002F\u002Fdocs.cohere.com\u002Fdocs\u002Freranking-best-practices",{"title":925,"url":926},"Cohere pricing","https:\u002F\u002Fcohere.com\u002Fpricing",{"title":928,"url":929},"Voyage AI blog: rerank-3 (30 Sep 2026)","https:\u002F\u002Fblog.voyageai.com\u002F2026\u002F09\u002F30\u002Frerank-3\u002F",{"title":868,"url":62},{"title":932,"url":933},"Jina AI: Reranker v3.5 (3 Aug 2026)","https:\u002F\u002Fjina.ai\u002Fnews\u002Fjina-reranker-v3-5-faster-listwise-reranking-hybrid-attention-self-distillation\u002F",{"title":935,"url":936},"ColBERTv2 (arXiv 2112.01488)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.01488",{"title":938,"url":939},"Elasticsearch docs: reciprocal rank fusion","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Frest-apis\u002Freciprocal-rank-fusion",{"title":941,"url":942},"Azure AI Search: semantic ranking overview","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fsemantic-search-overview",{"title":944,"url":945},"RankGPT (arXiv 2304.09542)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.09542","\u002Fimages\u002Fblog\u002Freranking-models-compared\u002Fcover.webp","\u002Fimages\u002Fblog\u002Freranking-models-compared\u002Fog.jpg",[82,83,84],"Cross-Encoder-Reranker im Vergleich: Cohere, bge, Voyage, Jina und Late Interaction (2026)","Reranker im Oktober 2026: pointwise, listwise und Late Interaction, Cohere, Voyage, bge, Qwen3, Jina und mxbai, Preise, Self-Hosting und die Wahl von k.","Cross-Encoder-Reranker: Ein Trichter verengt viele Karten auf fünf, eine Karte wird nach vorn gehoben.",{"slug":953,"published":886,"updated":742,"minutes":524,"category":8,"tags":954,"tagPages":959,"keywords":961,"about":972,"sources":978,"cover":1014,"og":1015,"expertise":80,"locales":1016,"lang":83,"title":1017,"description":1018,"coverAlt":1019},"elasticsearch-opensearch-vector-search",[955,956,13,957,958],"Elasticsearch","OpenSearch","Hybrid search","Licensing",[17,960],"hybrid-search",[962,963,964,965,966,967,968,969,970,971],"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",[973,975,977],{"name":955,"url":974},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FElasticsearch",{"name":956,"url":976},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOpenSearch_%28software%29",{"name":601,"url":602},[979,982,985,988,991,993,996,999,1002,1005,1008,1011],{"title":980,"url":981},"Elastic docs: kNN search","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Fvector\u002Fknn",{"title":983,"url":984},"Elastic docs: filtered kNN search","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Fvector\u002Fknn\u002Ffiltered-knn-search",{"title":986,"url":987},"Elastic docs: dense_vector field type","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Fmapping-reference\u002Fdense-vector",{"title":989,"url":990},"Elastic docs: BBQ","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Fmapping-reference\u002Fbbq",{"title":992,"url":939},"Elastic docs: reciprocal rank fusion",{"title":994,"url":995},"Elastic docs: GPU vector indexing","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Fvector\u002Fgpu-vector-indexing",{"title":997,"url":998},"Elastic blog: Elasticsearch is open source again (Aug 2024)","https:\u002F\u002Fwww.elastic.co\u002Fblog\u002Felasticsearch-is-open-source-again",{"title":1000,"url":1001},"OpenSearch docs: methods and engines","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fmappings\u002Fsupported-field-types\u002Fknn-methods-engines\u002F",{"title":1003,"url":1004},"OpenSearch docs: memory-optimized vectors","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fmappings\u002Fsupported-field-types\u002Fknn-memory-optimized\u002F",{"title":1006,"url":1007},"OpenSearch docs: reciprocal rank fusion","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fvector-search\u002Fai-search\u002Fhybrid-search\u002Frrf\u002F",{"title":1009,"url":1010},"OpenSearch docs: version history","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fversion-history\u002F",{"title":1012,"url":1013},"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",[82,83,84],"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":1021,"published":1022,"updated":742,"minutes":524,"category":8,"tags":1023,"tagPages":1026,"keywords":1027,"about":1037,"sources":1042,"cover":1076,"og":1077,"expertise":80,"locales":1078,"lang":83,"title":1079,"description":1080,"coverAlt":1081},"turbopuffer","2026-09-29",[1021,765,1024,1025,957],"Object storage","Pricing",[960],[1021,1028,1029,1030,1031,1032,1033,1034,1035,1036],"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",[1038,1039,1041],{"name":765,"url":766},{"name":1024,"url":1040},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FObject_storage",{"name":601,"url":602},[1043,1046,1049,1052,1055,1058,1061,1064,1067,1070,1073],{"title":1044,"url":1045},"turbopuffer blog: turbopuffer (updated Mar 2026)","https:\u002F\u002Fturbopuffer.com\u002Fblog\u002Fturbopuffer",{"title":1047,"url":1048},"turbopuffer blog: ANN v3 (Jan 2026)","https:\u002F\u002Fturbopuffer.com\u002Fblog\u002Fann-v3",{"title":1050,"url":1051},"SPFresh (SOSP 2023)","https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3600006.3613166",{"title":1053,"url":1054},"turbopuffer blog: native filtering","https:\u002F\u002Fturbopuffer.com\u002Fblog\u002Fnative-filtering",{"title":1056,"url":1057},"turbopuffer docs: hybrid search","https:\u002F\u002Fturbopuffer.com\u002Fdocs\u002Fhybrid",{"title":1059,"url":1060},"turbopuffer blog: native embedding (Sep 2026)","https:\u002F\u002Fturbopuffer.com\u002Fblog\u002Fnative-embedding",{"title":1062,"url":1063},"turbopuffer docs: architecture","https:\u002F\u002Fturbopuffer.com\u002Fdocs\u002Farchitecture",{"title":1065,"url":1066},"turbopuffer pricing","https:\u002F\u002Fturbopuffer.com\u002Fpricing",{"title":1068,"url":1069},"turbopuffer docs: limits","https:\u002F\u002Fturbopuffer.com\u002Fdocs\u002Flimits",{"title":1071,"url":1072},"turbopuffer v3 benchmarks","https:\u002F\u002Fturbopuffer.com\u002Fv3",{"title":1074,"url":1075},"Pinecone pricing","https:\u002F\u002Fwww.pinecone.io\u002Fpricing\u002F","\u002Fimages\u002Fblog\u002Fturbopuffer\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fturbopuffer\u002Fog.jpg",[82,83,84],"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":1083,"published":1022,"updated":413,"minutes":524,"category":8,"tags":1084,"tagPages":1087,"keywords":1088,"about":1099,"sources":1105,"cover":1142,"og":1143,"expertise":80,"locales":1144,"lang":83,"title":1145,"description":1146,"coverAlt":1147},"table-extraction-rag",[11,1085,1086,344,526],"Tables","Document parsing",[8,349],[1089,1090,1091,1092,1093,1094,1095,1096,1097,1098],"tabellenextraktion für rag","tabellen in rag-pipelines","pdfplumber vs camelot vergleich","table transformer pubtables-1m modell","docling tabellenmodus tableformer","azure document intelligence tabellen erkennen","teds metrik grenzen","markdown vs html tabelle für llm","text-to-sql für tabellenfragen","llamaparse tabellen extrahieren",[1100,1101,1104],{"name":111,"url":112},{"name":1102,"url":1103},"Table (information)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FTable_%28information%29",{"name":434,"url":435},[1106,1109,1112,1115,1118,1121,1124,1127,1130,1133,1136,1139],{"title":1107,"url":1108},"Factorial study of parsers, chunkers and retrievers (arXiv 2609.31660)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.31660",{"title":1110,"url":1111},"pdfplumber on GitHub","https:\u002F\u002Fgithub.com\u002Fjsvine\u002Fpdfplumber",{"title":1113,"url":1114},"Camelot documentation","https:\u002F\u002Fcamelot-py.readthedocs.io\u002Fen\u002Flatest\u002F",{"title":1116,"url":1117},"Microsoft Table Transformer (archived)","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftable-transformer",{"title":1119,"url":1120},"PubTabNet and TEDS (arXiv 1911.10683)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.10683",{"title":1122,"url":1123},"Semantic evaluation of table extraction (arXiv 2603.18652)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.18652",{"title":1125,"url":1126},"TableFormer (arXiv 2203.01017)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.01017",{"title":1128,"url":1129},"Docling docs: advanced options","https:\u002F\u002Fdocling-project.github.io\u002Fdocling\u002Fusage\u002Fadvanced_options\u002F",{"title":1131,"url":1132},"Azure Document Intelligence: layout model","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fai-services\u002Fdocument-intelligence\u002Fprebuilt\u002Flayout",{"title":1134,"url":1135},"Table Meets LLM (WSDM 2024)","https:\u002F\u002Fzmy.io\u002Ffiles\u002Fwsdm24-SUC.pdf",{"title":1137,"url":1138},"TableRAG (arXiv 2410.04739)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.04739",{"title":1140,"url":1141},"Chain-of-Table (arXiv 2401.04398)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.04398","\u002Fimages\u002Fblog\u002Ftable-extraction-rag\u002Fcover.webp","\u002Fimages\u002Fblog\u002Ftable-extraction-rag\u002Fog.jpg",[82,83,84],"Tabellenextraktion für RAG: Extraktionsebenen, Serialisierung und belastbare Abfragen","Tabellen in RAG: warum Chunking sie zerbricht, pdfplumber, Camelot, Docling und Cloud-Extraktoren, was TEDS übersieht, Serialisierung und SQL-Routing.","Tabellenextraktion: Eine Tabelle auf einer Seite wird zu einzelnen Zeilenstreifen, die je einen Kopfreiter behalten.",{"slug":1149,"published":1150,"updated":6,"minutes":524,"category":8,"tags":1151,"tagPages":1154,"keywords":1155,"about":1166,"sources":1172,"cover":1206,"og":1207,"expertise":80,"locales":1208,"lang":83,"title":1209,"description":1210,"coverAlt":1211},"embedding-fine-tuning-domain","2026-09-28",[10,1152,11,344,1153],"Fine-tuning","Sentence Transformers",[16,8,349],[1156,1157,1158,1159,1160,1161,1162,1163,1164,1165],"embedding-modelle feintunen","domain-anpassung embeddings","hard negatives retrieval","multiplenegativesrankingloss","gistembed vs mnrl vergleich","matryoshka embedding dimensionen","qwen3-embedding feintunen","bge-m3 vs embeddinggemma","embedding-bewertung recall@k","katastrophales vergessen dense retrieval",[1167,1168,1171],{"name":33,"url":34},{"name":1169,"url":1170},"Fine-tuning (deep learning)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FFine-tuning_%28deep_learning%29",{"name":36,"url":37},[1173,1176,1179,1182,1185,1188,1191,1192,1195,1198,1201,1203],{"title":1174,"url":1175},"Sentence Transformers: training overview","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fsentence_transformer\u002Ftraining_overview.html",{"title":1177,"url":1178},"Sentence Transformers: loss overview","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fsentence_transformer\u002Floss_overview.html",{"title":1180,"url":1181},"Sentence Transformers: hard negative mining","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fpackage_reference\u002Futil\u002Fhard_negatives.html",{"title":1183,"url":1184},"RocketQA (arXiv 2010.08191)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.08191",{"title":1186,"url":1187},"InPars (arXiv 2202.05144)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.05144",{"title":1189,"url":1190},"Promptagator (arXiv 2209.11755)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.11755",{"title":870,"url":871},{"title":1193,"url":1194},"BAAI\u002Fbge-m3 model card","https:\u002F\u002Fhuggingface.co\u002FBAAI\u002Fbge-m3",{"title":1196,"url":1197},"Google: EmbeddingGemma docs (Oct 2026)","https:\u002F\u002Fai.google.dev\u002Fgemma\u002Fdocs\u002Fembeddinggemma",{"title":1199,"url":1200},"Sentence Transformers: Matryoshka embeddings","https:\u002F\u002Fsbert.net\u002Fexamples\u002Fsentence_transformer\u002Ftraining\u002Fmatryoshka\u002FREADME.html",{"title":1202,"url":44},"MMTEB (arXiv 2502.13595)",{"title":1204,"url":1205},"ANCE-Tele (arXiv 2210.17167)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.17167","\u002Fimages\u002Fblog\u002Fembedding-fine-tuning-domain\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fembedding-fine-tuning-domain\u002Fog.jpg",[82,83,84],"Embedding-Modelle für die eigene Domäne feintunen: Hard Negatives, Losses und Evals","Embeddings für die eigene Domäne feintunen: wann das einen Reranker schlägt, Trainingspaare, Hard Negatives, Losses in sentence-transformers v6 und Kosten.","Embedding-Feintuning: Lose Punkte links werden nach dem Training zu dichten Gruppen rechts.",{"slug":1213,"published":1150,"updated":742,"minutes":524,"category":8,"tags":1214,"tagPages":1218,"keywords":1219,"about":1230,"sources":1236,"cover":1267,"og":1268,"expertise":80,"locales":1269,"lang":83,"title":1270,"description":1271,"coverAlt":1272},"splade-learned-sparse-retrieval",[1215,1216,1217,957,955],"SPLADE","Sparse retrieval","BM25",[960],[1220,1221,1222,1223,1224,1225,1226,1227,1228,1229],"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",[1231,1232,1235],{"name":114,"url":115},{"name":1233,"url":1234},"Inverted index","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FInverted_index",{"name":908,"url":909},[1237,1240,1243,1246,1249,1252,1255,1258,1261,1264],{"title":1238,"url":1239},"naver\u002Fsplade on GitHub","https:\u002F\u002Fgithub.com\u002Fnaver\u002Fsplade",{"title":1241,"url":1242},"SPLADE++ (arXiv 2205.04733)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.04733",{"title":1244,"url":1245},"naver\u002Fsplade-v3 model card","https:\u002F\u002Fhuggingface.co\u002Fnaver\u002Fsplade-v3",{"title":1247,"url":1248},"Static pruning for learned sparse indexes (arXiv 2304.12702)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.12702",{"title":1250,"url":1251},"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":1253,"url":1254},"OpenSearch docs: sparse encoding processor","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fingest-pipelines\u002Fprocessors\u002Fsparse-encoding\u002F",{"title":1256,"url":1257},"Elastic docs: sparse_vector field type","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Fmapping-reference\u002Fsparse-vector",{"title":1259,"url":1260},"Elastic docs: ELSER","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fexplore-analyze\u002Fmachine-learning\u002Fnlp\u002Fml-nlp-elser",{"title":1262,"url":1263},"Elastic Search Labs: ELSER v2, part 2","https:\u002F\u002Fwww.elastic.co\u002Fsearch-labs\u002Fblog\u002Fintroducing-elser-v2-part-2",{"title":1265,"url":1266},"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",[82,83,84],"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":1274,"published":1275,"updated":1276,"minutes":524,"category":8,"tags":1277,"tagPages":1280,"keywords":1281,"about":1292,"sources":1300,"cover":1335,"og":1336,"expertise":80,"locales":1337,"lang":83,"title":1338,"description":1339,"coverAlt":1340},"knowledge-graph-extraction-llm","2026-09-25","2026-10-12",[676,675,1278,11,1279],"Entity resolution","Neo4j",[8],[1282,1283,1284,1285,1286,1287,1288,1289,1290,1291],"wissensgraph mit llm erstellen","graphrag indexierung","entitätsauflösung wissensgraph","triple-extraktion prompt","ontologie-design für llm-extraktion","entitäts-deduplizierung embeddings","wissensgraph provenienz","inkrementelle wissensgraph-updates","graphrag kosten","neo4j simplekgpipeline",[1293,1294,1297],{"name":627,"url":692},{"name":1295,"url":1296},"Record linkage","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FRecord_linkage",{"name":1298,"url":1299},"Ontology (information science)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOntology_%28information_science%29",[1301,1304,1307,1309,1312,1315,1318,1321,1324,1327,1330,1332],{"title":1302,"url":1303},"Microsoft GraphRAG: default dataflow","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fgraphrag\u002Fblob\u002Fmain\u002Fdocs\u002Findex\u002Fdefault_dataflow.md",{"title":1305,"url":1306},"Microsoft GraphRAG on GitHub","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fgraphrag",{"title":1308,"url":721},"Microsoft Research: LazyGraphRAG (Nov 2024)",{"title":1310,"url":1311},"Microsoft Research: GraphRAG auto-tuning (Sep 2024)","https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fblog\u002Fgraphrag-auto-tuning-provides-rapid-adaptation-to-new-domains\u002F",{"title":1313,"url":1314},"neo4j-graphrag-python on GitHub","https:\u002F\u002Fgithub.com\u002Fneo4j\u002Fneo4j-graphrag-python",{"title":1316,"url":1317},"Neo4j GraphRAG: knowledge graph builder guide","https:\u002F\u002Fneo4j.com\u002Fdocs\u002Fneo4j-graphrag-python\u002Fcurrent\u002Fuser_guide_kg_builder.html",{"title":1319,"url":1320},"Splink on GitHub","https:\u002F\u002Fgithub.com\u002Fmoj-analytical-services\u002Fsplink",{"title":1322,"url":1323},"Google LangExtract on GitHub","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Flangextract",{"title":1325,"url":1326},"KGGen (arXiv 2502.09956)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.09956",{"title":1328,"url":1329},"GraphEval (arXiv 2407.10793)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.10793",{"title":1331,"url":663},"Zep temporal knowledge graph (arXiv 2501.13956)",{"title":1333,"url":1334},"Kùzu on GitHub","https:\u002F\u002Fgithub.com\u002Fkuzudb\u002Fkuzu","\u002Fimages\u002Fblog\u002Fknowledge-graph-extraction-llm\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fknowledge-graph-extraction-llm\u002Fog.jpg",[82,83,84],"Wissensgraphen mit LLMs extrahieren: Ontologie, Entitätsauflösung, Herkunft","Einen Wissensgraphen mit LLMs bauen: kleine Ontologie, Extraktionsprompts, Entitätsauflösung, Herkunft, inkrementelle Updates, Evaluierung und Speicher.","Wissensgraphen mit LLMs: Knoten verlassen einen Seitenstapel und bilden ein Netz, in dem zwei Kreise verschmelzen.",{"slug":1342,"published":1275,"updated":6,"minutes":524,"category":8,"tags":1343,"tagPages":1347,"keywords":1348,"about":1359,"sources":1366,"cover":1400,"og":1401,"expertise":80,"locales":1402,"lang":83,"title":1403,"description":1404,"coverAlt":1405},"incremental-indexing-cdc",[11,1344,528,1345,1346],"Change data capture","Vector databases","Data freshness",[8],[1349,1350,1351,1352,1353,1354,1355,1356,1357,1358],"inkrementelles indexieren rag","cdc für rag-index","debezium postgres logische replikation","re-embedding kosten","blue\u002Fgreen index-wechsel vektordatenbank","index-aktualität überwachen","löschungen im vektorindex","rechteänderungen rag-index","qdrant aliase","high water mark änderungserkennung",[1360,1362,1363],{"name":1344,"url":1361},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FChange_data_capture",{"name":111,"url":112},{"name":1364,"url":1365},"Blue–green deployment","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FBlue%E2%80%93green_deployment",[1367,1370,1373,1376,1379,1382,1385,1388,1391,1393,1396,1399],{"title":1368,"url":1369},"PostgreSQL docs: logical decoding concepts","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Flogicaldecoding-explanation.html",{"title":1371,"url":1372},"Debezium docs: PostgreSQL connector","https:\u002F\u002Fdebezium.io\u002Fdocumentation\u002Freference\u002Fstable\u002Fconnectors\u002Fpostgresql.html",{"title":1374,"url":1375},"PostgreSQL docs: CREATE PUBLICATION","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Fsql-createpublication.html",{"title":1377,"url":1378},"PostgreSQL docs: pg_replication_slots","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Fview-pg-replication-slots.html",{"title":1380,"url":1381},"Azure AI Search: changed and deleted blobs","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fsearch-howto-index-changed-deleted-blobs",{"title":1383,"url":1384},"Azure AI Search: scheduling indexers","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fsearch-howto-schedule-indexers",{"title":1386,"url":1387},"Qdrant docs: collections and aliases","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fconcepts\u002Fcollections\u002F",{"title":1389,"url":1390},"Elastic docs: aliases","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fmanage-data\u002Fdata-store\u002Faliases",{"title":1392,"url":187},"pgvector on GitHub",{"title":1394,"url":1395},"GDPR Article 17","https:\u002F\u002Fgdpr-info.eu\u002Fart-17-gdpr\u002F",{"title":1397,"url":1398},"OpenAI API pricing","https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fpricing",{"title":868,"url":62},"\u002Fimages\u002Fblog\u002Fincremental-indexing-cdc\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fincremental-indexing-cdc\u002Fog.jpg",[82,83,84],"RAG-Index aktuell halten: inkrementelles Indexieren, CDC und Blue\u002FGreen-Neueinbettung","RAG-Index aktuell halten: Aktualitätsbudget, Änderungserkennung, CDC aus Postgres mit Debezium, Löschungen, Rechte, Blue\u002FGreen-Wechsel und Kosten.","RAG-Index-Updates: Eine Datenbank streamt Änderungen in einen Schrank, daneben ein zweiter Schrank und ein Schalter.",{"slug":1407,"published":1408,"updated":1409,"minutes":7,"category":8,"tags":1410,"tagPages":1412,"keywords":1413,"about":1421,"sources":1426,"cover":1451,"og":1452,"expertise":80,"locales":1453,"lang":83,"title":1454,"description":1455,"coverAlt":1456},"lancedb","2026-09-21","2026-10-07",[13,957,1411,11],"Embedded database",[17,960,8],[1407,1414,1415,1416,1417,1418,1419,1420],"lancedb test","lance vektordatenbank","eingebettete vektordatenbank","lancedb vs qdrant vergleich","hybridsuche rang-fusion","lancedb indexierung","lance datenformat",[1422,1423],{"name":765,"url":766},{"name":1424,"url":1425},"Apache Arrow","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FApache_Arrow",[1427,1430,1433,1436,1439,1442,1445,1448],{"title":1428,"url":1429},"LanceDB quickstart","https:\u002F\u002Fdocs.lancedb.com\u002Fquickstart",{"title":1431,"url":1432},"LanceDB vector indexes","https:\u002F\u002Fdocs.lancedb.com\u002Findexing\u002Fvector-index",{"title":1434,"url":1435},"LanceDB indexing guide","https:\u002F\u002Fdocs.lancedb.com\u002Findexing\u002Findex",{"title":1437,"url":1438},"LanceDB hybrid search","https:\u002F\u002Fdocs.lancedb.com\u002Fsearch\u002Fhybrid-search",{"title":1440,"url":1441},"LanceDB Enterprise","https:\u002F\u002Fdocs.lancedb.com\u002Fenterprise",{"title":1443,"url":1444},"LanceDB frequently asked questions","https:\u002F\u002Fdocs.lancedb.com\u002Ffaq\u002Ffaq-oss",{"title":1446,"url":1447},"LanceDB pricing","https:\u002F\u002Flancedb.com\u002Fpricing",{"title":1449,"url":1450},"LanceDB on PyPI","https:\u002F\u002Fpypi.org\u002Fproject\u002Flancedb\u002F","\u002Fimages\u002Fblog\u002Flancedb\u002Fcover.webp","\u002Fimages\u002Fblog\u002Flancedb\u002Fog.jpg",[82,83,84],"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":583,"published":1408,"updated":742,"minutes":90,"category":8,"tags":1458,"tagPages":1462,"keywords":1463,"about":1471,"sources":1475,"cover":1490,"og":1491,"expertise":80,"locales":1492,"lang":83,"title":1493,"description":1494,"coverAlt":1495},[13,1459,1460,11,1461],"Postgres","HNSW","Quantisation",[17,8],[583,1464,1465,1466,1467,1468,1469,1470],"pgvector vs qdrant vergleich","postgres vektorsuche","hnsw index postgres einrichten","iterative index-scans pgvector","binärquantisierung postgres","vektordatenbank postgres","pgvector test",[1472,1473],{"name":583,"url":187},{"name":528,"url":1474},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FPostgreSQL",[1476,1478,1481,1484,1487],{"title":1477,"url":187},"pgvector README",{"title":1479,"url":1480},"pgvector changelog","https:\u002F\u002Fgithub.com\u002Fpgvector\u002Fpgvector\u002Fblob\u002Fmaster\u002FCHANGELOG.md",{"title":1482,"url":1483},"PostgreSQL news: pgvector 0.8.2 released","https:\u002F\u002Fwww.postgresql.org\u002Fabout\u002Fnews\u002Fpgvector-082-released-3245\u002F",{"title":1485,"url":1486},"AWS: Scale pgvector with binary quantization","https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fdatabase\u002Fscale-pgvector-with-binary-quantization-on-amazon-aurora-postgresql\u002F",{"title":1488,"url":1489},"pgvector licence","https:\u002F\u002Fgithub.com\u002Fpgvector\u002Fpgvector\u002Fblob\u002Fmaster\u002FLICENSE","\u002Fimages\u002Fblog\u002Fpgvector\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fpgvector\u002Fog.jpg",[82,83,84],"pgvector im Review: die Vektordatenbank, die du nicht betreiben musst","pgvector 0.8.7 im Review: iterative Index-Scans für Filter, HNSW und IVFFlat, Binärquantisierung bei 100 Millionen Vektoren und das CVE im Indexaufbau.","pgvector: Ein Elefant trägt eine kleine Kommode mit sortierten Murmeln auf dem Rücken.",{"slug":1497,"published":1498,"updated":742,"minutes":90,"category":8,"tags":1499,"tagPages":1501,"keywords":1502,"about":1509,"sources":1513,"cover":1541,"og":1542,"expertise":80,"locales":1543,"lang":83,"title":1544,"description":1545,"coverAlt":1546},"mem0","2026-09-17",[626,1500,11,13],"Long-term memory",[8,17],[1497,1503,1504,1505,1506,1507,1508],"mem0 test","agent-speicherschicht","mem0 selbst hosten","mem0 kosten","langzeitspeicher für agenten","mem0 alternativen",[1510],{"name":1511,"url":1512},"Mem0","https:\u002F\u002Fmem0.ai",[1514,1517,1520,1523,1526,1529,1532,1535,1538],{"title":1515,"url":1516},"Mem0 documentation","https:\u002F\u002Fdocs.mem0.ai\u002Fintroduction",{"title":1518,"url":1519},"Mem0 quickstart","https:\u002F\u002Fdocs.mem0.ai\u002Fquickstart",{"title":1521,"url":1522},"How Mem0 works","https:\u002F\u002Fdocs.mem0.ai\u002Fcore-concepts\u002Fhow-it-works",{"title":1524,"url":1525},"Mem0 pricing","https:\u002F\u002Fmem0.ai\u002Fpricing",{"title":1527,"url":1528},"Mem0 on GitHub","https:\u002F\u002Fgithub.com\u002Fmem0ai\u002Fmem0",{"title":1530,"url":1531},"mem0ai on PyPI","https:\u002F\u002Fpypi.org\u002Fproject\u002Fmem0ai\u002F",{"title":1533,"url":1534},"Mem0 research and benchmarks","https:\u002F\u002Fmem0.ai\u002Fresearch",{"title":1536,"url":1537},"Mem0 MCP server","https:\u002F\u002Fdocs.mem0.ai\u002Fplatform\u002Fmem0-mcp",{"title":1539,"url":1540},"Mem0 paper on arXiv","https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.19413","\u002Fimages\u002Fblog\u002Fmem0\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fmem0\u002Fog.jpg",[82,83,84],"Mem0: was eine Agent-Speicherschicht pro Runde kostet","Mem0 im Review: extrahierte Fakten pro Runde, die Benchmark-Tabelle vom April 2026 mit Plattform-Vorbehalt, vier Cloud-Stufen und Lücken beim Self-Hosting.","Mem0: Ein Roboter schreibt Notizen neben einer Parkuhr, hinter ihm Haftzettel.",{"slug":1548,"published":1549,"updated":1550,"minutes":90,"category":8,"tags":1551,"tagPages":1554,"keywords":1555,"about":1564,"sources":1572,"cover":1591,"og":1592,"expertise":80,"locales":1593,"lang":83,"title":1594,"description":1595,"coverAlt":1596},"milvus-zilliz","2026-09-08","2026-09-20",[13,957,1552,1553,11],"BM25 full text","Distributed",[17,960,8],[1556,1557,1558,1559,1560,1561,1562,1563],"milvus","milvus vs qdrant vergleich","zilliz cloud preise","vektordatenbank vergleich","milvus hybridsuche","apache milvus selbst hosten","milvus 3.0 neuerungen","rag vektorspeicher",[1565,1568,1571],{"name":1566,"url":1567},"Milvus","https:\u002F\u002Fmilvus.io",{"name":1569,"url":1570},"Zilliz Cloud","https:\u002F\u002Fzilliz.com",{"name":111,"url":112},[1573,1576,1579,1582,1585,1588],{"title":1574,"url":1575},"Milvus architecture overview","https:\u002F\u002Fmilvus.io\u002Fdocs\u002Farchitecture_overview.md",{"title":1577,"url":1578},"Milvus release notes","https:\u002F\u002Fmilvus.io\u002Fdocs\u002Frelease_notes.md",{"title":1580,"url":1581},"Milvus releases on GitHub","https:\u002F\u002Fgithub.com\u002Fmilvus-io\u002Fmilvus\u002Freleases",{"title":1583,"url":1584},"Milvus README: features and licence","https:\u002F\u002Fgithub.com\u002Fmilvus-io\u002Fmilvus",{"title":1586,"url":1587},"Zilliz Cloud pricing","https:\u002F\u002Fzilliz.com\u002Fpricing",{"title":1589,"url":1590},"Zilliz Cloud list price","https:\u002F\u002Fzilliz.com\u002Fpricing\u002Fpricing-guide","\u002Fimages\u002Fblog\u002Fmilvus-zilliz\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fmilvus-zilliz\u002Fog.jpg",[82,83,84],"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":1598,"published":1549,"updated":672,"minutes":90,"category":8,"tags":1599,"tagPages":1603,"keywords":1604,"about":1611,"sources":1615,"cover":1630,"og":1631,"expertise":80,"locales":1632,"lang":83,"title":1633,"description":1634,"coverAlt":1635},"graphrag",[627,11,1600,1601,1602],"Global search","Community summaries","Token cost",[8],[1598,1605,1606,686,1607,1608,1609,1610],"microsoft graphrag test","graphrag vs vektor-rag","graphrag abfragemodi","graphrag lightrag vergleich","wissensgraph rag","graphrag dynamische community-auswahl",[1612,1614],{"name":675,"url":1613},"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fgraphrag\u002F",{"name":111,"url":112},[1616,1618,1620,1622,1625,1627],{"title":1617,"url":1306},"GraphRAG on GitHub",{"title":1619,"url":703},"GraphRAG documentation",{"title":1621,"url":700},"From Local to Global: A Graph RAG Approach to Query-Focused Summarization",{"title":1623,"url":1624},"GraphRAG: Improving global search via dynamic community selection","https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fblog\u002Fgraphrag-improving-global-search-via-dynamic-community-selection\u002F",{"title":1626,"url":721},"LazyGraphRAG: Setting a new standard for quality and cost",{"title":1628,"url":1629},"Graph RAG in 2026: What Actually Works in Production","https:\u002F\u002Fwww.paperclipped.de\u002Fen\u002Fblog\u002Fgraph-rag-production\u002F","\u002Fimages\u002Fblog\u002Fgraphrag\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fgraphrag\u002Fog.jpg",[82,83,84],"Microsoft GraphRAG: ein Wissensgraph-RAG mit Vorabrechnung","Ein Test von Microsoft GraphRAG 3.2.0: MIT, Wartungsmodus und eine Indexrechnung, die vor der ersten Abfrage fällig wird.","Microsoft GraphRAG: Eine Pinnwand mit durch Fäden verbundenen Karten, an der Ecke ein Preisschild.",{"slug":1637,"published":1638,"updated":1639,"minutes":90,"category":8,"tags":1640,"tagPages":1646,"keywords":1648,"about":1654,"sources":1658,"cover":1680,"og":1681,"expertise":80,"locales":1682,"lang":83,"title":1683,"description":1684,"coverAlt":1685},"firecrawl","2026-08-25","2026-09-04",[1641,1642,1643,1644,1645],"Web scraping","RAG ingestion","Crawling","MCP","AGPL",[1647],"mcp",[1637,1649,1650,1651,1652,1653],"firecrawl vs apify vergleich","firecrawl alternativen","web-scraping api für llm","firecrawl selbst hosten","markdown-scraper api",[1655],{"name":1656,"url":1657},"Firecrawl","https:\u002F\u002Fgithub.com\u002Ffirecrawl\u002Ffirecrawl",[1659,1662,1665,1668,1671,1674,1677],{"title":1660,"url":1661},"Firecrawl pricing","https:\u002F\u002Fwww.firecrawl.dev\u002Fpricing",{"title":1663,"url":1664},"Firecrawl crawl documentation","https:\u002F\u002Fdocs.firecrawl.dev\u002Ffeatures\u002Fcrawl",{"title":1666,"url":1667},"Firecrawl self-hosting guide","https:\u002F\u002Fdocs.firecrawl.dev\u002Fcontributing\u002Fself-host",{"title":1669,"url":1670},"Open source or Firecrawl Cloud","https:\u002F\u002Fdocs.firecrawl.dev\u002Fcontributing\u002Fopen-source-or-cloud",{"title":1672,"url":1673},"Firecrawl benchmarks","https:\u002F\u002Fwww.firecrawl.dev\u002Fbenchmarks",{"title":1675,"url":1676},"Apify pricing","https:\u002F\u002Fapify.com\u002Fpricing",{"title":1678,"url":1679},"Browserbase pricing","https:\u002F\u002Fwww.browserbase.com\u002Fpricing","\u002Fimages\u002Fblog\u002Ffirecrawl\u002Fcover.webp","\u002Fimages\u002Fblog\u002Ffirecrawl\u002Fog.jpg",[82,83,84],"Firecrawl: eine Web-Crawling-API für RAG-Pipelines im Test","Firecrawl im Test: sauberes Markdown aus URLs per gehosteter API. Was es kostet, wo das Crawl-Accounting versagt und wann sich der AGPL-Kern lohnt.","Firecrawl: Eine Spinne in einem Netz über einem Browserfenster lässt ordentliche Seiten in einen Korb fallen.",{"slug":1687,"published":1688,"updated":1498,"minutes":673,"category":8,"tags":1689,"tagPages":1693,"keywords":1694,"about":1705,"sources":1711,"cover":1750,"og":1751,"expertise":268,"locales":1752,"lang":83,"title":1753,"description":1754,"coverAlt":1755},"semantic-product-search-b2b","2026-08-21",[1690,957,1691,1692,956],"B2B search","Semantic search","Spryker",[960],[1695,1696,1697,1698,1699,1700,1701,1702,1703,1704],"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",[1706,1708,1709],{"name":1691,"url":1707},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FSemantic_search",{"name":955,"url":974},{"name":956,"url":1710},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOpenSearch",[1712,1715,1718,1721,1724,1727,1730,1733,1736,1739,1742,1745,1747],{"title":1713,"url":1714},"Baymard Institute: E-commerce search query types","https:\u002F\u002Fbaymard.com\u002Fblog\u002Fecommerce-search-query-types",{"title":1716,"url":1717},"Elastic Search Labs: Hybrid search in Elasticsearch","https:\u002F\u002Fwww.elastic.co\u002Fsearch-labs\u002Fblog\u002Fhybrid-search-elasticsearch",{"title":1719,"url":1720},"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":1722,"url":1723},"Elasticsearch documentation: Semantic reranking","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Franking\u002Fsemantic-reranking",{"title":1725,"url":1726},"Elasticsearch documentation: Word delimiter graph token filter","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Ftext-analysis\u002Fanalysis-word-delimiter-graph-tokenfilter",{"title":1728,"url":1729},"Elasticsearch documentation: Synonym graph token filter","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Ftext-analysis\u002Fanalysis-synonym-graph-tokenfilter",{"title":1731,"url":1732},"OpenSearch documentation: Score ranker processor (RRF)","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fsearch-plugins\u002Fsearch-pipelines\u002Fscore-ranker-processor\u002F",{"title":1734,"url":1735},"OpenSearch documentation: Normalization processor","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fsearch-plugins\u002Fsearch-pipelines\u002Fnormalization-processor\u002F",{"title":1737,"url":1738},"Spryker documentation: Search feature overview","https:\u002F\u002Fdocs.spryker.com\u002Fdocs\u002Fpbc\u002Fall\u002Fsearch\u002Flatest\u002Fbase-shop\u002Fsearch-feature-overview\u002Fsearch-feature-overview",{"title":1740,"url":1741},"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":1743,"url":1744},"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":1746,"url":500},"arXiv: M3-Embedding, multilingual, multi-functionality, multi-granularity text embeddings",{"title":1748,"url":1749},"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",[82,83,84],"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":1757,"published":1758,"updated":1759,"minutes":673,"category":8,"tags":1760,"tagPages":1765,"keywords":1766,"about":1777,"sources":1785,"cover":1825,"og":1826,"expertise":80,"locales":1827,"lang":83,"title":1828,"description":1829,"coverAlt":1830},"llm-hallucination-grounding-citations","2026-08-20","2026-09-01",[1761,11,1762,1763,1764],"Hallucinations","Citations","Grounding","Faithfulness",[8],[1767,1768,1769,1770,1771,1772,1773,1774,1775,1776],"llm halluzinationen reduzieren","halluzinationen in produktion vermeiden","halluzinationen rag vermeiden anleitung","llm-zitate api","anthropic citations api nutzen","rag faithfulness metrik","llm abstention nicht antworten","claim-prüfung llm","llm-antworten in quellen verankern","quellen anzeigen ki-chatbot ui",[1778,1781,1782],{"name":1779,"url":1780},"Hallucination (artificial intelligence)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FHallucination_(artificial_intelligence)",{"name":111,"url":112},{"name":1783,"url":1784},"Large language model","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FLarge_language_model",[1786,1789,1792,1795,1798,1801,1804,1807,1810,1813,1816,1819,1822],{"title":1787,"url":1788},"Anthropic: Citations (Claude API documentation)","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fbuild-with-claude\u002Fcitations",{"title":1790,"url":1791},"Anthropic: Search results (Claude API documentation)","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fbuild-with-claude\u002Fsearch-results",{"title":1793,"url":1794},"Anthropic: Reduce hallucinations (Claude API documentation)","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Ftest-and-evaluate\u002Fstrengthen-guardrails\u002Freduce-hallucinations",{"title":1796,"url":1797},"Anthropic: Introducing Citations on the Anthropic API","https:\u002F\u002Fclaude.com\u002Fblog\u002Fintroducing-citations-api",{"title":1799,"url":1800},"Simon Willison: Anthropic's new Citations API (24 January 2025)","https:\u002F\u002Fsimonwillison.net\u002F2025\u002FJan\u002F24\u002Fanthropics-new-citations-api\u002F",{"title":1802,"url":1803},"OpenAI: Web search guide (url_citation annotations and display requirement)","https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fguides\u002Ftools-web-search",{"title":1805,"url":1806},"Cohere: Documents and citations","https:\u002F\u002Fdocs.cohere.com\u002Fdocs\u002Fdocuments-and-citations",{"title":1808,"url":1809},"Google Cloud: Check grounding API","https:\u002F\u002Fdocs.cloud.google.com\u002Fgenerative-ai-app-builder\u002Fdocs\u002Fcheck-grounding",{"title":1811,"url":1812},"AWS: Amazon Bedrock Guardrails contextual grounding check","https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fguardrails-contextual-grounding-check.html",{"title":1814,"url":1815},"Ragas: Faithfulness metric","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fconcepts\u002Fmetrics\u002Favailable_metrics\u002Ffaithfulness\u002F",{"title":1817,"url":1818},"Kalai, Nachum, Vempala, Zhang: Why Language Models Hallucinate (arXiv 2509.04664)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.04664",{"title":1820,"url":1821},"Magesh et al.: Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools (arXiv 2405.20362)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.20362",{"title":1823,"url":1824},"Wallat, Heuss, de Rijke, Anand: Correctness is not Faithfulness in RAG Attributions (arXiv 2412.18004)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.18004","\u002Fimages\u002Fblog\u002Fllm-hallucination-grounding-citations\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fllm-hallucination-grounding-citations\u002Fog.jpg",[82,83,84],"LLM-Halluzinationen in Produktion reduzieren: Grounding, Zitate und das Nein zur richtigen Zeit","LLM-Halluzinationen im RAG senken: Zitier-APIs, Abstention, Claim-Prüfung, Faithfulness-Metriken, Quellen-UI und die Fehler, die durchrutschen.","LLM-Halluzinationen: Ein Heißluftballon ist mit Seilen an einem Bücherstapel verankert.",{"slug":1832,"published":1833,"updated":1834,"minutes":524,"category":8,"tags":1835,"tagPages":1838,"keywords":1839,"about":1848,"sources":1852,"cover":1869,"og":1870,"expertise":80,"locales":1871,"lang":83,"title":1872,"description":1873,"coverAlt":1874},"rag-2026-hybrid-agentic-long-context","2026-07-30","2026-09-22",[11,1836,1837,957,93],"Long context","Agentic search",[8,960],[1840,1841,1842,1843,1844,1845,1846,1847],"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",[1849,1850,1851],{"name":111,"url":112},{"name":1783,"url":1784},{"name":114,"url":115},[1853,1855,1858,1861,1863,1866],{"title":1854,"url":122},"Anthropic: Introducing Contextual Retrieval",{"title":1856,"url":1857},"Chroma: Context Rot","https:\u002F\u002Fwww.trychroma.com\u002Fresearch\u002Fcontext-rot",{"title":1859,"url":1860},"Liu et al., Lost in the Middle (2023)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03172",{"title":1862,"url":140},"Claude docs: Pricing",{"title":1864,"url":1865},"Claude docs: Models overview","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fabout-claude\u002Fmodels\u002Foverview",{"title":1867,"url":1868},"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",[82,83,84],"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":1876,"published":1877,"updated":1833,"minutes":90,"category":8,"tags":1878,"tagPages":1879,"keywords":1880,"about":1890,"sources":1894,"cover":1923,"og":1924,"expertise":80,"locales":1925,"lang":83,"title":1926,"description":1927,"coverAlt":1928},"rag-pipeline-chunking-hybrid-search-reranking","2026-07-24",[11,957,92,888,583],[8,960],[1881,1882,1883,1884,1885,1886,1887,1888,1889],"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",[1891,1892,1893],{"name":111,"url":112},{"name":114,"url":115},{"name":583,"url":187},[1895,1898,1901,1904,1905,1908,1911,1914,1915,1918,1919,1921],{"title":1896,"url":1897},"Lewis et al., Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11401",{"title":1899,"url":1900},"Cormack, Clarke and Büttcher, Reciprocal Rank Fusion (SIGIR 2009)","https:\u002F\u002Fcormack.uwaterloo.ca\u002Fcormacksigir09-rrf.pdf",{"title":1902,"url":1903},"Malkov and Yashunin, HNSW graphs","https:\u002F\u002Farxiv.org\u002Fabs\u002F1603.09320",{"title":1477,"url":187},{"title":1906,"url":1907},"Elasticsearch: similarity settings","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Findex-settings\u002Fsimilarity",{"title":1909,"url":1910},"PostgreSQL: controlling text search","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Ftextsearch-controls.html",{"title":1912,"url":1913},"Chroma: Evaluating Chunking Strategies for Retrieval","https:\u002F\u002Fwww.trychroma.com\u002Fresearch\u002Fevaluating-chunking",{"title":1854,"url":122},{"title":1916,"url":1917},"Sentence Transformers: Cross-Encoders","https:\u002F\u002Fsbert.net\u002Fexamples\u002Fcross_encoder\u002Fapplications\u002FREADME.html",{"title":1859,"url":1860},{"title":1920,"url":1788},"Claude docs: Citations",{"title":1922,"url":1815},"RAGAS: Faithfulness","\u002Fimages\u002Fblog\u002Frag-pipeline-chunking-hybrid-search-reranking\u002Fcover.webp","\u002Fimages\u002Fblog\u002Frag-pipeline-chunking-hybrid-search-reranking\u002Fog.jpg",[82,83,84],"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":1930,"published":1931,"minutes":90,"category":8,"tags":1932,"tagPages":1934,"keywords":1935,"about":1943,"sources":1950,"cover":1978,"og":1979,"expertise":80,"locales":1980,"lang":83,"title":1981,"description":1982,"coverAlt":1983},"chroma","2026-07-20",[13,10,11,957,1933],"Metadata filter",[17,16,8,960],[1936,1937,1938,1939,1940,1941,1942],"chroma vektordatenbank","chroma vs qdrant vergleich","chroma vs pgvector vergleich","hybridsuche reciprocal rank fusion","self-hosted vektordatenbank","chroma cloud preise","metadatenfilter vektorsuche",[1944,1947],{"name":1945,"url":1946},"Chroma","https:\u002F\u002Fgithub.com\u002Fchroma-core\u002Fchroma",{"name":1948,"url":1949},"Apache License 2.0","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FApache_License",[1951,1954,1957,1960,1963,1966,1969,1972,1975],{"title":1952,"url":1953},"Chroma documentation: introduction","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Foverview\u002Fintroduction",{"title":1955,"url":1956},"Chroma architecture overview","https:\u002F\u002Fdocs.trychroma.com\u002Freference\u002Farchitecture\u002Foverview",{"title":1958,"url":1959},"Chroma: getting started with the SDK","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Foverview\u002Fgetting-started",{"title":1961,"url":1962},"Chroma: query and get","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Fquerying-collections\u002Fquery-and-get",{"title":1964,"url":1965},"Chroma: metadata filtering","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Fquerying-collections\u002Fmetadata-filtering",{"title":1967,"url":1968},"Chroma Cloud: Search API overview","https:\u002F\u002Fdocs.trychroma.com\u002Fcloud\u002Fsearch-api\u002Foverview",{"title":1970,"url":1971},"Chroma Cloud: hybrid search with RRF","https:\u002F\u002Fdocs.trychroma.com\u002Fcloud\u002Fsearch-api\u002Fhybrid-search",{"title":1973,"url":1974},"Chroma Cloud: pricing","https:\u002F\u002Fwww.trychroma.com\u002Fpricing",{"title":1976,"url":1977},"Chroma changelog","https:\u002F\u002Fwww.trychroma.com\u002Fchangelog","\u002Fimages\u002Fblog\u002Fchroma\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fchroma\u002Fog.jpg",[82,83,84],"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":1985,"published":1986,"minutes":624,"category":8,"tags":1987,"tagPages":1989,"keywords":1990,"about":1999,"sources":2003,"cover":2027,"og":2028,"expertise":80,"locales":2029,"lang":83,"title":2030,"description":2031,"coverAlt":2032},"pinecone","2026-07-09",[13,10,11,1988,957],"Namespaces",[17,16,8,960],[1991,1992,1993,1994,1995,1996,1997,1998],"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",[2000,2001,2002],{"name":765,"url":766},{"name":601,"url":602},{"name":114,"url":115},[2004,2007,2010,2013,2016,2018,2021,2024],{"title":2005,"url":2006},"Pinecone docs: Index data overview, indexes, namespaces and metadata","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Findexing-overview",{"title":2008,"url":2009},"Pinecone docs: Adopt the Documents API, API version 2026-07","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Fadopt-the-documents-api",{"title":2011,"url":2012},"Pinecone docs: Create an index, schemas, regions and metrics","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Fcreate-an-index",{"title":2014,"url":2015},"Pinecone docs: Understanding Pinecone cost, read units, write units and egress","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Forganizations\u002Fmanage-cost\u002Funderstanding-cost",{"title":2017,"url":1075},"Pinecone pricing: plans, limits and rates",{"title":2019,"url":2020},"Pinecone docs: Semantic search","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Fsearch\u002Fsemantic-search",{"title":2022,"url":2023},"Pinecone docs: Local development with Pinecone Local","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Foperations\u002Flocal-development",{"title":2025,"url":2026},"Pinecone docs: 2026 release notes","https:\u002F\u002Fdocs.pinecone.io\u002Frelease-notes\u002F2026","\u002Fimages\u002Fblog\u002Fpinecone\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fpinecone\u002Fog.jpg",[82,83,84],"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":2034,"published":2035,"updated":742,"minutes":673,"category":8,"tags":2036,"tagPages":2038,"keywords":2039,"about":2049,"sources":2053,"cover":2099,"og":2100,"expertise":80,"locales":2101,"lang":83,"title":2102,"description":2103,"coverAlt":2104},"pgvector-vs-vector-databases","2026-06-15",[583,1345,11,957,2037],"EU hosting",[8,960],[2040,2041,2042,2043,2044,591,2045,2046,2047,2048],"pgvector oder vektordatenbank","pgvector vs vektordatenbank vergleich","pgvector vs pinecone vergleich","beste vektordatenbank 2026","pgvector hnsw iterative scan erklärt","opensearch vs elasticsearch vektorsuche","vektordatenbank eu-hosting","hybridsuche postgres","weaviate vs milvus vergleich",[2050,2051,2052],{"name":765,"url":766},{"name":528,"url":1474},{"name":111,"url":112},[2054,2057,2059,2062,2063,2066,2069,2072,2075,2078,2081,2084,2086,2088,2091,2094,2096],{"title":2055,"url":2056},"pgvector README (index limits, HNSW defaults, iterative scans, filtering, halfvec)","https:\u002F\u002Fgithub.com\u002Fpgvector\u002Fpgvector\u002Fblob\u002Fmaster\u002FREADME.md",{"title":2058,"url":1480},"pgvector CHANGELOG (0.4.0 to 0.8.7)",{"title":2060,"url":2061},"pgvectorscale: StreamingDiskANN, statistical binary quantization, filtered search","https:\u002F\u002Fgithub.com\u002Ftimescale\u002Fpgvectorscale",{"title":261,"url":262},{"title":2064,"url":2065},"Qdrant documentation: Hybrid queries","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fconcepts\u002Fhybrid-queries\u002F",{"title":2067,"url":2068},"Qdrant documentation: Create a cluster (providers, free tier, Hybrid Cloud)","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fcloud\u002Fcreate-cluster\u002F",{"title":2070,"url":2071},"Weaviate documentation: Hybrid search","https:\u002F\u002Fdocs.weaviate.io\u002Fweaviate\u002Fconcepts\u002Fsearch\u002Fhybrid-search",{"title":2073,"url":2074},"Weaviate documentation: Vector index types","https:\u002F\u002Fdocs.weaviate.io\u002Fweaviate\u002Fconcepts\u002Fvector-index",{"title":2076,"url":2077},"Weaviate Cloud pricing and deployment options","https:\u002F\u002Fweaviate.io\u002Fpricing",{"title":2079,"url":2080},"Milvus documentation: Overview","https:\u002F\u002Fmilvus.io\u002Fdocs\u002Foverview.md",{"title":2082,"url":2083},"Pinecone documentation: Database architecture","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Fget-started\u002Fdatabase-architecture",{"title":2085,"url":2012},"Pinecone documentation: Create an index (clouds, regions, sparse and hybrid)",{"title":2087,"url":1001},"OpenSearch documentation: Methods and engines",{"title":2089,"url":2090},"OpenSearch documentation: Efficient k-NN filtering","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fvector-search\u002Ffilter-search-knn\u002Fefficient-knn-filtering\u002F",{"title":2092,"url":2093},"Elasticsearch documentation: Dense vector search","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Fvector\u002Fdense-vector",{"title":2095,"url":1720},"Elasticsearch documentation: kNN query (filter as pre-filter)",{"title":2097,"url":2098},"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",[82,83,84],"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":2106,"published":2107,"updated":1409,"minutes":90,"category":8,"tags":2108,"tagPages":2109,"keywords":2110,"about":2118,"sources":2127,"cover":2150,"og":2151,"expertise":80,"locales":2152,"lang":83,"title":2153,"description":2154,"coverAlt":2155},"weaviate","2026-06-02",[13,957,1460,582,155],[17,960],[2106,2111,2112,2113,2114,2115,2116,2117],"weaviate vs qdrant vergleich","weaviate vs pinecone vergleich","weaviate vs pgvector vergleich","hnsw vs hfresh vergleich","weaviate cloud preise","weaviate vektordatenbank test","weaviate hybridsuche",[2119,2122,2124],{"name":2120,"url":2121},"Weaviate","https:\u002F\u002Fgithub.com\u002Fweaviate\u002Fweaviate",{"name":2123,"url":602},"Hierarchical Navigable Small World",{"name":2125,"url":2126},"SPFresh","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2410.14452",[2128,2130,2133,2136,2139,2142,2144,2147],{"title":2129,"url":2074},"Weaviate documentation: Vector indexing",{"title":2131,"url":2132},"Weaviate documentation: ANN benchmark","https:\u002F\u002Fdocs.weaviate.io\u002Fweaviate\u002Fbenchmarks\u002Fann",{"title":2134,"url":2135},"Weaviate 1.39 release notes","https:\u002F\u002Fweaviate.io\u002Fblog\u002Fweaviate-1-39-release",{"title":2137,"url":2138},"Weaviate 1.38 release notes","https:\u002F\u002Fweaviate.io\u002Fblog\u002Fweaviate-1-38-release",{"title":2140,"url":2141},"Weaviate documentation: MCP server","https:\u002F\u002Fdocs.weaviate.io\u002Fweaviate\u002Fconfiguration\u002Fmcp-server",{"title":2143,"url":2077},"Weaviate Cloud pricing",{"title":2145,"url":2146},"weaviate\u002Fweaviate: LICENSE","https:\u002F\u002Fgithub.com\u002Fweaviate\u002Fweaviate\u002Fblob\u002Fmain\u002FLICENSE",{"title":2148,"url":2149},"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",[82,83,84],"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":2157,"published":2158,"updated":2159,"minutes":90,"category":8,"tags":2160,"tagPages":2162,"keywords":2163,"about":2171,"sources":2175,"cover":2212,"og":2213,"expertise":80,"locales":2214,"lang":83,"title":2215,"description":2216,"coverAlt":2217},"qdrant","2026-05-26","2026-10-05",[13,1460,1461,957,2161],"Filtering",[17,960],[2157,2164,2165,2166,2167,2168,2169,2170],"qdrant vs pinecone vergleich","vektordatenbanken im vergleich","hnsw index erklärt","gefilterte vektorsuche","vektor-quantisierung","hybridsuche qdrant","qdrant rag",[2172,2173,2174],{"name":765,"url":766},{"name":601,"url":602},{"name":111,"url":112},[2176,2179,2182,2184,2187,2190,2193,2196,2198,2200,2203,2206,2209],{"title":2177,"url":2178},"Qdrant documentation","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002F",{"title":2180,"url":2181},"Qdrant: points","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fmanage-data\u002Fpoints\u002F",{"title":2183,"url":1387},"Qdrant: collections",{"title":2185,"url":2186},"Qdrant: indexing","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F",{"title":2188,"url":2189},"Qdrant: quantisation","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F",{"title":2191,"url":2192},"Qdrant: capacity planning","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fcapacity-planning\u002F",{"title":2194,"url":2195},"Qdrant: optimise performance","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fops-optimization\u002Foptimize\u002F",{"title":2197,"url":2065},"Qdrant: hybrid and multi-stage queries",{"title":2199,"url":262},"Qdrant: filtering",{"title":2201,"url":2202},"Qdrant: security and access control","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fsecurity\u002F",{"title":2204,"url":2205},"Qdrant pricing","https:\u002F\u002Fqdrant.tech\u002Fpricing\u002F",{"title":2207,"url":2208},"Qdrant on GitHub","https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant",{"title":2210,"url":2211},"Qdrant vector search benchmarks","https:\u002F\u002Fqdrant.tech\u002Fbenchmarks\u002F","\u002Fimages\u002Fblog\u002Fqdrant\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fqdrant\u002Fog.jpg",[82,83,84],"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.",{"slug":2219,"published":2220,"minutes":624,"category":8,"tags":2221,"tagPages":2224,"keywords":2225,"about":2234,"sources":2238,"cover":2257,"og":2258,"expertise":80,"locales":2259,"lang":83,"title":2260,"description":2261,"coverAlt":2262},"unstructured","2026-05-21",[1086,1642,2222,92,2223],"PDF extraction","ETL",[],[2226,2227,2228,2229,2230,2231,2232,2233],"unstructured.io","unstructured bibliothek python","unstructured vs llamaparse vergleich","dokumente parsen für rag","pdf partitioning hi_res einstellung","unstructured preise","chunk by title erklärt","dokumenten-ingestion pipeline",[2235],{"name":2236,"url":2237},"Unstructured","https:\u002F\u002Funstructured.io\u002F",[2239,2242,2245,2248,2251,2254],{"title":2240,"url":2241},"Unstructured documentation: pipelines overview","https:\u002F\u002Fdocs.unstructured.io\u002Fwelcome",{"title":2243,"url":2244},"Unstructured documentation: transform quickstart","https:\u002F\u002Fdocs.unstructured.io\u002Fapi-reference\u002Ftransform\u002Fquickstart\u002Foverview",{"title":2246,"url":2247},"Unstructured pricing: free pages, rate per page and plans","https:\u002F\u002Funstructured.io\u002Fpricing",{"title":2249,"url":2250},"Unstructured benchmarks: 1,000+ enterprise pages against other parsers","https:\u002F\u002Funstructured.io\u002Fbenchmarks",{"title":2252,"url":2253},"Unstructured library on GitHub","https:\u002F\u002Fgithub.com\u002FUnstructured-IO\u002Funstructured",{"title":2255,"url":2256},"Unstructured partition endpoint container","https:\u002F\u002Fgithub.com\u002FUnstructured-IO\u002Funstructured-api","\u002Fimages\u002Fblog\u002Funstructured\u002Fcover.webp","\u002Fimages\u002Fblog\u002Funstructured\u002Fog.jpg",[82,83,84],"Unstructured-Review: Dokumente für RAG parsen","Unstructured: typisierte Elemente für RAG aus PDFs, Word und Bildern. Apache-2.0-Bibliothek, Plattform: 0,015 Dollar pro Seite, die ersten 10.000 gratis.","Unstructured: Hände sortieren einen unordentlichen Stapel Papiere und Fotos in drei Ablagen.",{"slug":2264,"published":2265,"updated":672,"minutes":275,"category":8,"tags":2266,"tagPages":2272,"keywords":2273,"about":2284,"sources":2290,"cover":2323,"og":2324,"expertise":80,"locales":2325,"lang":83,"title":2326,"description":2327,"coverAlt":2328},"rag-evaluation-metrics","2026-05-13",[2267,2268,2269,2270,2271],"RAG evaluation","Retrieval metrics","LLM-as-judge","Golden set","Ragas",[],[2274,2275,2276,2277,2278,2279,2280,2281,2282,2283],"rag evaluierung","rag evaluieren anleitung","rag evaluation metriken","recall@k mrr ndcg erklärt","faithfulness vs antwortrelevanz","golden dataset für rag","llm als richter kalibrierung","ragas vs deepeval vs trulens vergleich","rag-evals in ci","retrieval vs generierung fehler",[2285,2286,2287],{"name":111,"url":112},{"name":39,"url":40},{"name":2288,"url":2289},"Mean reciprocal rank","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FMean_reciprocal_rank",[2291,2294,2297,2299,2301,2304,2307,2310,2313,2316,2318,2320],{"title":2292,"url":2293},"Es et al.: RAGAS, Automated Evaluation of Retrieval Augmented Generation (arXiv 2309.15217)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.15217",{"title":2295,"url":2296},"Zheng et al.: Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena (arXiv 2306.05685)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.05685",{"title":2298,"url":334},"Ragas documentation: available metrics",{"title":2300,"url":1815},"Ragas documentation: faithfulness",{"title":2302,"url":2303},"Ragas documentation: context precision","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fconcepts\u002Fmetrics\u002Favailable_metrics\u002Fcontext_precision\u002F",{"title":2305,"url":2306},"Ragas documentation: context recall","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fconcepts\u002Fmetrics\u002Favailable_metrics\u002Fcontext_recall\u002F",{"title":2308,"url":2309},"DeepEval documentation: metrics introduction","https:\u002F\u002Fdeepeval.com\u002Fdocs\u002Fmetrics-introduction",{"title":2311,"url":2312},"TruLens","https:\u002F\u002Fwww.trulens.org\u002F",{"title":2314,"url":2315},"Arize Phoenix documentation","https:\u002F\u002Farize.com\u002Fdocs\u002Fphoenix",{"title":2317,"url":40},"Wikipedia: Discounted cumulative gain",{"title":2319,"url":2289},"Wikipedia: Mean reciprocal rank",{"title":2321,"url":2322},"Wikipedia: Cohen's kappa","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FCohen%27s_kappa","\u002Fimages\u002Fblog\u002Frag-evaluation-metrics\u002Fcover.webp","\u002Fimages\u002Fblog\u002Frag-evaluation-metrics\u002Fog.jpg",[82,83,84],"RAG evaluieren: Retrieval-Metriken, Faithfulness und wie du erkennst, welche Hälfte versagt hat","RAG evaluieren: Recall at k, MRR und nDCG vs. Faithfulness und Antwortrelevanz, ein Golden Set aus echten Anfragen, kalibrierter LLM-Judge und Evals in CI.","RAG-Evaluation: Eine Angel zieht ein Buch aus einem Teich, eine Waage wiegt eine Sprechblase.",1793451238739]