[{"data":1,"prerenderedAt":1832},["ShallowReactive",2],{"blog-tag-de-rag":3},[4,88,150,209,273,341,411,466,522,565,614,684,757,825,893,957,1025,1091,1146,1185,1236,1286,1325,1400,1444,1498,1553,1609,1659,1733],{"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":528,"keywords":529,"about":540,"sources":550,"cover":559,"og":560,"expertise":80,"locales":561,"lang":83,"title":562,"description":563,"coverAlt":564},"embedding-quantization-binary-matryoshka",5,[10,13,526,527,11],"Quantization","pgvector",[16,17,8],[530,531,532,533,534,535,536,537,538,539],"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",[541,544,547],{"name":542,"url":543},"Quantization (signal processing)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FQuantization_(signal_processing)",{"name":545,"url":546},"Nearest neighbor search","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FNearest_neighbor_search",{"name":548,"url":549},"Hamming distance","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FHamming_distance",[551,554,557],{"title":552,"url":553},"Hugging Face: Binary and Scalar Embedding Quantization for Significantly Faster and Cheaper Retrieval (Mar 2024)","https:\u002F\u002Fhuggingface.co\u002Fblog\u002Fembedding-quantization",{"title":555,"url":556},"Kusupati et al.: Matryoshka Representation Learning (2022)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.13147",{"title":558,"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":566,"published":567,"minutes":568,"category":8,"tags":569,"tagPages":574,"keywords":576,"about":585,"sources":589,"cover":608,"og":609,"expertise":80,"locales":610,"lang":83,"title":611,"description":612,"coverAlt":613},"zep","2026-10-06",11,[570,571,572,573,11],"Agent memory","Knowledge graph","Temporal graph","Context engineering",[575,8],"context-engineering",[577,578,579,580,581,582,583,584],"zep test","zep agenten-memory","graphiti wissensgraph","zep preise","zep vs mem0 vergleich","langzeitgedächtnis für agenten","temporaler wissensgraph","zep cloud kosten",[586],{"name":587,"url":588},"Zep","https:\u002F\u002Fwww.getzep.com\u002F",[590,593,596,599,602,605],{"title":591,"url":592},"Zep pricing: plans, credits and limits","https:\u002F\u002Fwww.getzep.com\u002Fpricing",{"title":594,"url":595},"Zep documentation","https:\u002F\u002Fhelp.getzep.com\u002F",{"title":597,"url":598},"Graphiti on GitHub","https:\u002F\u002Fgithub.com\u002Fgetzep\u002Fgraphiti",{"title":600,"url":601},"Graphiti product page","https:\u002F\u002Fwww.getzep.com\u002Fplatform\u002Fgraphiti\u002F",{"title":603,"url":604},"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":606,"url":607},"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":615,"published":616,"minutes":617,"category":8,"tags":618,"tagPages":622,"keywords":623,"about":634,"sources":641,"cover":678,"og":679,"expertise":80,"locales":680,"lang":83,"title":681,"description":682,"coverAlt":683},"graphrag-knowledge-graph-rag","2026-10-02",13,[619,620,621,11],"GraphRAG","Knowledge graphs","LightRAG",[8],[624,625,626,627,628,629,630,631,632,633],"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",[635,637,638],{"name":571,"url":636},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FKnowledge_graph",{"name":111,"url":112},{"name":639,"url":640},"Leiden algorithm","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FLeiden_algorithm",[642,645,648,651,654,657,660,663,666,669,672,675],{"title":643,"url":644},"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":646,"url":647},"Microsoft GraphRAG documentation: overview","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002F",{"title":649,"url":650},"Microsoft GraphRAG documentation: default dataflow","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Findex\u002Fdefault_dataflow\u002F",{"title":652,"url":653},"Microsoft GraphRAG documentation: global search","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Fquery\u002Fglobal_search\u002F",{"title":655,"url":656},"Microsoft GraphRAG documentation: local search","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Fquery\u002Flocal_search\u002F",{"title":658,"url":659},"Microsoft GraphRAG documentation: DRIFT search","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Fquery\u002Fdrift_search\u002F",{"title":661,"url":662},"Microsoft GraphRAG documentation: getting started","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Fget_started\u002F",{"title":664,"url":665},"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":667,"url":668},"Guo et al.: LightRAG: Simple and Fast Retrieval-Augmented Generation (arXiv:2410.05779)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.05779",{"title":670,"url":671},"HKUDS\u002FLightRAG on GitHub","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FLightRAG",{"title":673,"url":674},"Gutiérrez et al.: HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models (arXiv:2405.14831)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.14831",{"title":676,"url":677},"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":685,"published":686,"updated":6,"minutes":687,"category":8,"tags":688,"tagPages":692,"keywords":694,"about":705,"sources":715,"cover":751,"og":752,"expertise":80,"locales":753,"lang":83,"title":754,"description":755,"coverAlt":756},"code-rag-repository-indexing","2026-10-01",8,[11,689,690,10,691],"Code search","Tree-sitter","Coding agents",[8,16,693],"coding-agents",[695,696,697,698,699,700,701,702,703,704],"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",[706,707,710,712],{"name":111,"url":112},{"name":708,"url":709},"Abstract syntax tree","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAbstract_syntax_tree",{"name":690,"url":711},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FTree-sitter_%28parser_generator%29",{"name":713,"url":714},"Merkle tree","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FMerkle_tree",[716,719,722,725,728,731,734,737,740,742,745,748],{"title":717,"url":718},"cAST: AST-based chunking for code RAG (arXiv 2506.15655)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.15655",{"title":720,"url":721},"Aider docs: repository map","https:\u002F\u002Faider.chat\u002Fdocs\u002Frepomap.html",{"title":723,"url":724},"Aider blog: building a better repository map with tree-sitter (2023)","https:\u002F\u002Faider.chat\u002F2023\u002F10\u002F22\u002Frepomap.html",{"title":726,"url":727},"Anthropic Engineering: effective context engineering for AI agents (Sep 2025)","https:\u002F\u002Fwww.anthropic.com\u002Fengineering\u002Feffective-context-engineering-for-ai-agents",{"title":729,"url":730},"Cursor blog: securely indexing large codebases (Jan 2026)","https:\u002F\u002Fcursor.com\u002Fblog\u002Fsecure-codebase-indexing",{"title":732,"url":733},"turbopuffer: Cursor customer story","https:\u002F\u002Fturbopuffer.com\u002Fcustomers\u002Fcursor",{"title":735,"url":736},"Kilo Code docs: codebase indexing","https:\u002F\u002Fkilo.ai\u002Fdocs\u002Fcustomize\u002Fcontext\u002Fcodebase-indexing",{"title":738,"url":739},"Serena on GitHub","https:\u002F\u002Fgithub.com\u002Foraios\u002Fserena",{"title":741,"url":62},"Voyage AI docs: pricing",{"title":743,"url":744},"Qwen blog: Qwen3-Embedding (Jun 2025)","https:\u002F\u002Fqwenlm.github.io\u002Fblog\u002Fqwen3-embedding\u002F",{"title":746,"url":747},"CoIR: a benchmark for code information retrieval (arXiv 2407.02883)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.02883",{"title":749,"url":750},"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":758,"published":759,"updated":686,"minutes":687,"category":8,"tags":760,"tagPages":764,"keywords":765,"about":776,"sources":784,"cover":819,"og":820,"expertise":80,"locales":821,"lang":83,"title":822,"description":823,"coverAlt":824},"reranking-models-compared","2026-09-30",[761,11,762,763,344],"Reranking","Search","Cross-encoders",[8,349],[766,767,768,769,770,771,772,773,774,775],"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",[777,780,783],{"name":778,"url":779},"Learning to rank","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FLearning_to_rank",{"name":781,"url":782},"BERT (language model)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FBERT_%28language_model%29",{"name":36,"url":37},[785,788,791,794,797,800,803,804,807,810,813,816],{"title":786,"url":787},"Sentence-BERT (arXiv 1908.10084)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.10084",{"title":789,"url":790},"Sentence Transformers: retrieve and re-rank","https:\u002F\u002Fsbert.net\u002Fexamples\u002Fsentence_transformer\u002Fapplications\u002Fretrieve_rerank\u002FREADME.html",{"title":792,"url":793},"BAAI\u002Fbge-reranker-v2-m3 model card","https:\u002F\u002Fhuggingface.co\u002FBAAI\u002Fbge-reranker-v2-m3",{"title":795,"url":796},"Cohere docs: reranking best practices","https:\u002F\u002Fdocs.cohere.com\u002Fdocs\u002Freranking-best-practices",{"title":798,"url":799},"Cohere pricing","https:\u002F\u002Fcohere.com\u002Fpricing",{"title":801,"url":802},"Voyage AI blog: rerank-3 (30 Sep 2026)","https:\u002F\u002Fblog.voyageai.com\u002F2026\u002F09\u002F30\u002Frerank-3\u002F",{"title":741,"url":62},{"title":805,"url":806},"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":808,"url":809},"ColBERTv2 (arXiv 2112.01488)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.01488",{"title":811,"url":812},"Elasticsearch docs: reciprocal rank fusion","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Frest-apis\u002Freciprocal-rank-fusion",{"title":814,"url":815},"Azure AI Search: semantic ranking overview","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fsemantic-search-overview",{"title":817,"url":818},"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":826,"published":827,"updated":413,"minutes":687,"category":8,"tags":828,"tagPages":832,"keywords":833,"about":844,"sources":850,"cover":887,"og":888,"expertise":80,"locales":889,"lang":83,"title":890,"description":891,"coverAlt":892},"table-extraction-rag","2026-09-29",[11,829,830,344,831],"Tables","Document parsing","Text-to-SQL",[8,349],[834,835,836,837,838,839,840,841,842,843],"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",[845,846,849],{"name":111,"url":112},{"name":847,"url":848},"Table (information)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FTable_%28information%29",{"name":434,"url":435},[851,854,857,860,863,866,869,872,875,878,881,884],{"title":852,"url":853},"Factorial study of parsers, chunkers and retrievers (arXiv 2609.31660)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.31660",{"title":855,"url":856},"pdfplumber on GitHub","https:\u002F\u002Fgithub.com\u002Fjsvine\u002Fpdfplumber",{"title":858,"url":859},"Camelot documentation","https:\u002F\u002Fcamelot-py.readthedocs.io\u002Fen\u002Flatest\u002F",{"title":861,"url":862},"Microsoft Table Transformer (archived)","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftable-transformer",{"title":864,"url":865},"PubTabNet and TEDS (arXiv 1911.10683)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.10683",{"title":867,"url":868},"Semantic evaluation of table extraction (arXiv 2603.18652)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.18652",{"title":870,"url":871},"TableFormer (arXiv 2203.01017)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.01017",{"title":873,"url":874},"Docling docs: advanced options","https:\u002F\u002Fdocling-project.github.io\u002Fdocling\u002Fusage\u002Fadvanced_options\u002F",{"title":876,"url":877},"Azure Document Intelligence: layout model","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fai-services\u002Fdocument-intelligence\u002Fprebuilt\u002Flayout",{"title":879,"url":880},"Table Meets LLM (WSDM 2024)","https:\u002F\u002Fzmy.io\u002Ffiles\u002Fwsdm24-SUC.pdf",{"title":882,"url":883},"TableRAG (arXiv 2410.04739)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.04739",{"title":885,"url":886},"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":894,"published":895,"updated":6,"minutes":687,"category":8,"tags":896,"tagPages":899,"keywords":900,"about":911,"sources":917,"cover":951,"og":952,"expertise":80,"locales":953,"lang":83,"title":954,"description":955,"coverAlt":956},"embedding-fine-tuning-domain","2026-09-28",[10,897,11,344,898],"Fine-tuning","Sentence Transformers",[16,8,349],[901,902,903,904,905,906,907,908,909,910],"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",[912,913,916],{"name":33,"url":34},{"name":914,"url":915},"Fine-tuning (deep learning)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FFine-tuning_%28deep_learning%29",{"name":36,"url":37},[918,921,924,927,930,933,936,937,940,943,946,948],{"title":919,"url":920},"Sentence Transformers: training overview","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fsentence_transformer\u002Ftraining_overview.html",{"title":922,"url":923},"Sentence Transformers: loss overview","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fsentence_transformer\u002Floss_overview.html",{"title":925,"url":926},"Sentence Transformers: hard negative mining","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fpackage_reference\u002Futil\u002Fhard_negatives.html",{"title":928,"url":929},"RocketQA (arXiv 2010.08191)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.08191",{"title":931,"url":932},"InPars (arXiv 2202.05144)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.05144",{"title":934,"url":935},"Promptagator (arXiv 2209.11755)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.11755",{"title":743,"url":744},{"title":938,"url":939},"BAAI\u002Fbge-m3 model card","https:\u002F\u002Fhuggingface.co\u002FBAAI\u002Fbge-m3",{"title":941,"url":942},"Google: EmbeddingGemma docs (Oct 2026)","https:\u002F\u002Fai.google.dev\u002Fgemma\u002Fdocs\u002Fembeddinggemma",{"title":944,"url":945},"Sentence Transformers: Matryoshka embeddings","https:\u002F\u002Fsbert.net\u002Fexamples\u002Fsentence_transformer\u002Ftraining\u002Fmatryoshka\u002FREADME.html",{"title":947,"url":44},"MMTEB (arXiv 2502.13595)",{"title":949,"url":950},"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":958,"published":959,"updated":960,"minutes":687,"category":8,"tags":961,"tagPages":964,"keywords":965,"about":976,"sources":984,"cover":1019,"og":1020,"expertise":80,"locales":1021,"lang":83,"title":1022,"description":1023,"coverAlt":1024},"knowledge-graph-extraction-llm","2026-09-25","2026-10-12",[620,619,962,11,963],"Entity resolution","Neo4j",[8],[966,967,968,969,970,971,972,973,974,975],"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",[977,978,981],{"name":571,"url":636},{"name":979,"url":980},"Record linkage","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FRecord_linkage",{"name":982,"url":983},"Ontology (information science)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOntology_%28information_science%29",[985,988,991,993,996,999,1002,1005,1008,1011,1014,1016],{"title":986,"url":987},"Microsoft GraphRAG: default dataflow","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fgraphrag\u002Fblob\u002Fmain\u002Fdocs\u002Findex\u002Fdefault_dataflow.md",{"title":989,"url":990},"Microsoft GraphRAG on GitHub","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fgraphrag",{"title":992,"url":665},"Microsoft Research: LazyGraphRAG (Nov 2024)",{"title":994,"url":995},"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":997,"url":998},"neo4j-graphrag-python on GitHub","https:\u002F\u002Fgithub.com\u002Fneo4j\u002Fneo4j-graphrag-python",{"title":1000,"url":1001},"Neo4j GraphRAG: knowledge graph builder guide","https:\u002F\u002Fneo4j.com\u002Fdocs\u002Fneo4j-graphrag-python\u002Fcurrent\u002Fuser_guide_kg_builder.html",{"title":1003,"url":1004},"Splink on GitHub","https:\u002F\u002Fgithub.com\u002Fmoj-analytical-services\u002Fsplink",{"title":1006,"url":1007},"Google LangExtract on GitHub","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Flangextract",{"title":1009,"url":1010},"KGGen (arXiv 2502.09956)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.09956",{"title":1012,"url":1013},"GraphEval (arXiv 2407.10793)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.10793",{"title":1015,"url":607},"Zep temporal knowledge graph (arXiv 2501.13956)",{"title":1017,"url":1018},"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":1026,"published":959,"updated":6,"minutes":687,"category":8,"tags":1027,"tagPages":1032,"keywords":1033,"about":1044,"sources":1051,"cover":1085,"og":1086,"expertise":80,"locales":1087,"lang":83,"title":1088,"description":1089,"coverAlt":1090},"incremental-indexing-cdc",[11,1028,1029,1030,1031],"Change data capture","PostgreSQL","Vector databases","Data freshness",[8],[1034,1035,1036,1037,1038,1039,1040,1041,1042,1043],"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",[1045,1047,1048],{"name":1028,"url":1046},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FChange_data_capture",{"name":111,"url":112},{"name":1049,"url":1050},"Blue–green deployment","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FBlue%E2%80%93green_deployment",[1052,1055,1058,1061,1064,1067,1070,1073,1076,1078,1081,1084],{"title":1053,"url":1054},"PostgreSQL docs: logical decoding concepts","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Flogicaldecoding-explanation.html",{"title":1056,"url":1057},"Debezium docs: PostgreSQL connector","https:\u002F\u002Fdebezium.io\u002Fdocumentation\u002Freference\u002Fstable\u002Fconnectors\u002Fpostgresql.html",{"title":1059,"url":1060},"PostgreSQL docs: CREATE PUBLICATION","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Fsql-createpublication.html",{"title":1062,"url":1063},"PostgreSQL docs: pg_replication_slots","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Fview-pg-replication-slots.html",{"title":1065,"url":1066},"Azure AI Search: changed and deleted blobs","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fsearch-howto-index-changed-deleted-blobs",{"title":1068,"url":1069},"Azure AI Search: scheduling indexers","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fsearch-howto-schedule-indexers",{"title":1071,"url":1072},"Qdrant docs: collections and aliases","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fconcepts\u002Fcollections\u002F",{"title":1074,"url":1075},"Elastic docs: aliases","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fmanage-data\u002Fdata-store\u002Faliases",{"title":1077,"url":187},"pgvector on GitHub",{"title":1079,"url":1080},"GDPR Article 17","https:\u002F\u002Fgdpr-info.eu\u002Fart-17-gdpr\u002F",{"title":1082,"url":1083},"OpenAI API pricing","https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fpricing",{"title":741,"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":1092,"published":1093,"updated":1094,"minutes":7,"category":8,"tags":1095,"tagPages":1098,"keywords":1100,"about":1108,"sources":1115,"cover":1140,"og":1141,"expertise":80,"locales":1142,"lang":83,"title":1143,"description":1144,"coverAlt":1145},"lancedb","2026-09-21","2026-10-07",[13,1096,1097,11],"Hybrid search","Embedded database",[17,1099,8],"hybrid-search",[1092,1101,1102,1103,1104,1105,1106,1107],"lancedb test","lance vektordatenbank","eingebettete vektordatenbank","lancedb vs qdrant vergleich","hybridsuche rang-fusion","lancedb indexierung","lance datenformat",[1109,1112],{"name":1110,"url":1111},"Vector database","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FVector_database",{"name":1113,"url":1114},"Apache Arrow","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FApache_Arrow",[1116,1119,1122,1125,1128,1131,1134,1137],{"title":1117,"url":1118},"LanceDB quickstart","https:\u002F\u002Fdocs.lancedb.com\u002Fquickstart",{"title":1120,"url":1121},"LanceDB vector indexes","https:\u002F\u002Fdocs.lancedb.com\u002Findexing\u002Fvector-index",{"title":1123,"url":1124},"LanceDB indexing guide","https:\u002F\u002Fdocs.lancedb.com\u002Findexing\u002Findex",{"title":1126,"url":1127},"LanceDB hybrid search","https:\u002F\u002Fdocs.lancedb.com\u002Fsearch\u002Fhybrid-search",{"title":1129,"url":1130},"LanceDB Enterprise","https:\u002F\u002Fdocs.lancedb.com\u002Fenterprise",{"title":1132,"url":1133},"LanceDB frequently asked questions","https:\u002F\u002Fdocs.lancedb.com\u002Ffaq\u002Ffaq-oss",{"title":1135,"url":1136},"LanceDB pricing","https:\u002F\u002Flancedb.com\u002Fpricing",{"title":1138,"url":1139},"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":527,"published":1093,"updated":686,"minutes":90,"category":8,"tags":1147,"tagPages":1151,"keywords":1152,"about":1160,"sources":1164,"cover":1179,"og":1180,"expertise":80,"locales":1181,"lang":83,"title":1182,"description":1183,"coverAlt":1184},[13,1148,1149,11,1150],"Postgres","HNSW","Quantisation",[17,8],[527,1153,1154,1155,1156,1157,1158,1159],"pgvector vs qdrant vergleich","postgres vektorsuche","hnsw index postgres einrichten","iterative index-scans pgvector","binärquantisierung postgres","vektordatenbank postgres","pgvector test",[1161,1162],{"name":527,"url":187},{"name":1029,"url":1163},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FPostgreSQL",[1165,1167,1170,1173,1176],{"title":1166,"url":187},"pgvector README",{"title":1168,"url":1169},"pgvector changelog","https:\u002F\u002Fgithub.com\u002Fpgvector\u002Fpgvector\u002Fblob\u002Fmaster\u002FCHANGELOG.md",{"title":1171,"url":1172},"PostgreSQL news: pgvector 0.8.2 released","https:\u002F\u002Fwww.postgresql.org\u002Fabout\u002Fnews\u002Fpgvector-082-released-3245\u002F",{"title":1174,"url":1175},"AWS: Scale pgvector with binary quantization","https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fdatabase\u002Fscale-pgvector-with-binary-quantization-on-amazon-aurora-postgresql\u002F",{"title":1177,"url":1178},"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":1186,"published":1187,"updated":686,"minutes":90,"category":8,"tags":1188,"tagPages":1190,"keywords":1191,"about":1198,"sources":1202,"cover":1230,"og":1231,"expertise":80,"locales":1232,"lang":83,"title":1233,"description":1234,"coverAlt":1235},"mem0","2026-09-17",[570,1189,11,13],"Long-term memory",[8,17],[1186,1192,1193,1194,1195,1196,1197],"mem0 test","agent-speicherschicht","mem0 selbst hosten","mem0 kosten","langzeitspeicher für agenten","mem0 alternativen",[1199],{"name":1200,"url":1201},"Mem0","https:\u002F\u002Fmem0.ai",[1203,1206,1209,1212,1215,1218,1221,1224,1227],{"title":1204,"url":1205},"Mem0 documentation","https:\u002F\u002Fdocs.mem0.ai\u002Fintroduction",{"title":1207,"url":1208},"Mem0 quickstart","https:\u002F\u002Fdocs.mem0.ai\u002Fquickstart",{"title":1210,"url":1211},"How Mem0 works","https:\u002F\u002Fdocs.mem0.ai\u002Fcore-concepts\u002Fhow-it-works",{"title":1213,"url":1214},"Mem0 pricing","https:\u002F\u002Fmem0.ai\u002Fpricing",{"title":1216,"url":1217},"Mem0 on GitHub","https:\u002F\u002Fgithub.com\u002Fmem0ai\u002Fmem0",{"title":1219,"url":1220},"mem0ai on PyPI","https:\u002F\u002Fpypi.org\u002Fproject\u002Fmem0ai\u002F",{"title":1222,"url":1223},"Mem0 research and benchmarks","https:\u002F\u002Fmem0.ai\u002Fresearch",{"title":1225,"url":1226},"Mem0 MCP server","https:\u002F\u002Fdocs.mem0.ai\u002Fplatform\u002Fmem0-mcp",{"title":1228,"url":1229},"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":1237,"published":1238,"updated":1239,"minutes":90,"category":8,"tags":1240,"tagPages":1243,"keywords":1244,"about":1253,"sources":1261,"cover":1280,"og":1281,"expertise":80,"locales":1282,"lang":83,"title":1283,"description":1284,"coverAlt":1285},"milvus-zilliz","2026-09-08","2026-09-20",[13,1096,1241,1242,11],"BM25 full text","Distributed",[17,1099,8],[1245,1246,1247,1248,1249,1250,1251,1252],"milvus","milvus vs qdrant vergleich","zilliz cloud preise","vektordatenbank vergleich","milvus hybridsuche","apache milvus selbst hosten","milvus 3.0 neuerungen","rag vektorspeicher",[1254,1257,1260],{"name":1255,"url":1256},"Milvus","https:\u002F\u002Fmilvus.io",{"name":1258,"url":1259},"Zilliz Cloud","https:\u002F\u002Fzilliz.com",{"name":111,"url":112},[1262,1265,1268,1271,1274,1277],{"title":1263,"url":1264},"Milvus architecture overview","https:\u002F\u002Fmilvus.io\u002Fdocs\u002Farchitecture_overview.md",{"title":1266,"url":1267},"Milvus release notes","https:\u002F\u002Fmilvus.io\u002Fdocs\u002Frelease_notes.md",{"title":1269,"url":1270},"Milvus releases on GitHub","https:\u002F\u002Fgithub.com\u002Fmilvus-io\u002Fmilvus\u002Freleases",{"title":1272,"url":1273},"Milvus README: features and licence","https:\u002F\u002Fgithub.com\u002Fmilvus-io\u002Fmilvus",{"title":1275,"url":1276},"Zilliz Cloud pricing","https:\u002F\u002Fzilliz.com\u002Fpricing",{"title":1278,"url":1279},"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":1287,"published":1238,"updated":616,"minutes":90,"category":8,"tags":1288,"tagPages":1292,"keywords":1293,"about":1300,"sources":1304,"cover":1319,"og":1320,"expertise":80,"locales":1321,"lang":83,"title":1322,"description":1323,"coverAlt":1324},"graphrag",[571,11,1289,1290,1291],"Global search","Community summaries","Token cost",[8],[1287,1294,1295,630,1296,1297,1298,1299],"microsoft graphrag test","graphrag vs vektor-rag","graphrag abfragemodi","graphrag lightrag vergleich","wissensgraph rag","graphrag dynamische community-auswahl",[1301,1303],{"name":619,"url":1302},"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fgraphrag\u002F",{"name":111,"url":112},[1305,1307,1309,1311,1314,1316],{"title":1306,"url":990},"GraphRAG on GitHub",{"title":1308,"url":647},"GraphRAG documentation",{"title":1310,"url":644},"From Local to Global: A Graph RAG Approach to Query-Focused Summarization",{"title":1312,"url":1313},"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":1315,"url":665},"LazyGraphRAG: Setting a new standard for quality and cost",{"title":1317,"url":1318},"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":1326,"published":1327,"updated":1328,"minutes":617,"category":8,"tags":1329,"tagPages":1334,"keywords":1335,"about":1346,"sources":1354,"cover":1394,"og":1395,"expertise":80,"locales":1396,"lang":83,"title":1397,"description":1398,"coverAlt":1399},"llm-hallucination-grounding-citations","2026-08-20","2026-09-01",[1330,11,1331,1332,1333],"Hallucinations","Citations","Grounding","Faithfulness",[8],[1336,1337,1338,1339,1340,1341,1342,1343,1344,1345],"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",[1347,1350,1351],{"name":1348,"url":1349},"Hallucination (artificial intelligence)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FHallucination_(artificial_intelligence)",{"name":111,"url":112},{"name":1352,"url":1353},"Large language model","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FLarge_language_model",[1355,1358,1361,1364,1367,1370,1373,1376,1379,1382,1385,1388,1391],{"title":1356,"url":1357},"Anthropic: Citations (Claude API documentation)","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fbuild-with-claude\u002Fcitations",{"title":1359,"url":1360},"Anthropic: Search results (Claude API documentation)","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fbuild-with-claude\u002Fsearch-results",{"title":1362,"url":1363},"Anthropic: Reduce hallucinations (Claude API documentation)","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Ftest-and-evaluate\u002Fstrengthen-guardrails\u002Freduce-hallucinations",{"title":1365,"url":1366},"Anthropic: Introducing Citations on the Anthropic API","https:\u002F\u002Fclaude.com\u002Fblog\u002Fintroducing-citations-api",{"title":1368,"url":1369},"Simon Willison: Anthropic's new Citations API (24 January 2025)","https:\u002F\u002Fsimonwillison.net\u002F2025\u002FJan\u002F24\u002Fanthropics-new-citations-api\u002F",{"title":1371,"url":1372},"OpenAI: Web search guide (url_citation annotations and display requirement)","https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fguides\u002Ftools-web-search",{"title":1374,"url":1375},"Cohere: Documents and citations","https:\u002F\u002Fdocs.cohere.com\u002Fdocs\u002Fdocuments-and-citations",{"title":1377,"url":1378},"Google Cloud: Check grounding API","https:\u002F\u002Fdocs.cloud.google.com\u002Fgenerative-ai-app-builder\u002Fdocs\u002Fcheck-grounding",{"title":1380,"url":1381},"AWS: Amazon Bedrock Guardrails contextual grounding check","https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fguardrails-contextual-grounding-check.html",{"title":1383,"url":1384},"Ragas: Faithfulness metric","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fconcepts\u002Fmetrics\u002Favailable_metrics\u002Ffaithfulness\u002F",{"title":1386,"url":1387},"Kalai, Nachum, Vempala, Zhang: Why Language Models Hallucinate (arXiv 2509.04664)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.04664",{"title":1389,"url":1390},"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":1392,"url":1393},"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":1401,"published":1402,"updated":1403,"minutes":687,"category":8,"tags":1404,"tagPages":1407,"keywords":1408,"about":1417,"sources":1421,"cover":1438,"og":1439,"expertise":80,"locales":1440,"lang":83,"title":1441,"description":1442,"coverAlt":1443},"rag-2026-hybrid-agentic-long-context","2026-07-30","2026-09-22",[11,1405,1406,1096,93],"Long context","Agentic search",[8,1099],[1409,1410,1411,1412,1413,1414,1415,1416],"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",[1418,1419,1420],{"name":111,"url":112},{"name":1352,"url":1353},{"name":114,"url":115},[1422,1424,1427,1430,1432,1435],{"title":1423,"url":122},"Anthropic: Introducing Contextual Retrieval",{"title":1425,"url":1426},"Chroma: Context Rot","https:\u002F\u002Fwww.trychroma.com\u002Fresearch\u002Fcontext-rot",{"title":1428,"url":1429},"Liu et al., Lost in the Middle (2023)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03172",{"title":1431,"url":140},"Claude docs: Pricing",{"title":1433,"url":1434},"Claude docs: Models overview","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fabout-claude\u002Fmodels\u002Foverview",{"title":1436,"url":1437},"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":1445,"published":1446,"updated":1402,"minutes":90,"category":8,"tags":1447,"tagPages":1448,"keywords":1449,"about":1459,"sources":1463,"cover":1492,"og":1493,"expertise":80,"locales":1494,"lang":83,"title":1495,"description":1496,"coverAlt":1497},"rag-pipeline-chunking-hybrid-search-reranking","2026-07-24",[11,1096,92,761,527],[8,1099],[1450,1451,1452,1453,1454,1455,1456,1457,1458],"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",[1460,1461,1462],{"name":111,"url":112},{"name":114,"url":115},{"name":527,"url":187},[1464,1467,1470,1473,1474,1477,1480,1483,1484,1487,1488,1490],{"title":1465,"url":1466},"Lewis et al., Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11401",{"title":1468,"url":1469},"Cormack, Clarke and Büttcher, Reciprocal Rank Fusion (SIGIR 2009)","https:\u002F\u002Fcormack.uwaterloo.ca\u002Fcormacksigir09-rrf.pdf",{"title":1471,"url":1472},"Malkov and Yashunin, HNSW graphs","https:\u002F\u002Farxiv.org\u002Fabs\u002F1603.09320",{"title":1166,"url":187},{"title":1475,"url":1476},"Elasticsearch: similarity settings","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Findex-settings\u002Fsimilarity",{"title":1478,"url":1479},"PostgreSQL: controlling text search","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Ftextsearch-controls.html",{"title":1481,"url":1482},"Chroma: Evaluating Chunking Strategies for Retrieval","https:\u002F\u002Fwww.trychroma.com\u002Fresearch\u002Fevaluating-chunking",{"title":1423,"url":122},{"title":1485,"url":1486},"Sentence Transformers: Cross-Encoders","https:\u002F\u002Fsbert.net\u002Fexamples\u002Fcross_encoder\u002Fapplications\u002FREADME.html",{"title":1428,"url":1429},{"title":1489,"url":1357},"Claude docs: Citations",{"title":1491,"url":1384},"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":1499,"published":1500,"minutes":90,"category":8,"tags":1501,"tagPages":1503,"keywords":1504,"about":1512,"sources":1519,"cover":1547,"og":1548,"expertise":80,"locales":1549,"lang":83,"title":1550,"description":1551,"coverAlt":1552},"chroma","2026-07-20",[13,10,11,1096,1502],"Metadata filter",[17,16,8,1099],[1505,1506,1507,1508,1509,1510,1511],"chroma vektordatenbank","chroma vs qdrant vergleich","chroma vs pgvector vergleich","hybridsuche reciprocal rank fusion","self-hosted vektordatenbank","chroma cloud preise","metadatenfilter vektorsuche",[1513,1516],{"name":1514,"url":1515},"Chroma","https:\u002F\u002Fgithub.com\u002Fchroma-core\u002Fchroma",{"name":1517,"url":1518},"Apache License 2.0","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FApache_License",[1520,1523,1526,1529,1532,1535,1538,1541,1544],{"title":1521,"url":1522},"Chroma documentation: introduction","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Foverview\u002Fintroduction",{"title":1524,"url":1525},"Chroma architecture overview","https:\u002F\u002Fdocs.trychroma.com\u002Freference\u002Farchitecture\u002Foverview",{"title":1527,"url":1528},"Chroma: getting started with the SDK","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Foverview\u002Fgetting-started",{"title":1530,"url":1531},"Chroma: query and get","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Fquerying-collections\u002Fquery-and-get",{"title":1533,"url":1534},"Chroma: metadata filtering","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Fquerying-collections\u002Fmetadata-filtering",{"title":1536,"url":1537},"Chroma Cloud: Search API overview","https:\u002F\u002Fdocs.trychroma.com\u002Fcloud\u002Fsearch-api\u002Foverview",{"title":1539,"url":1540},"Chroma Cloud: hybrid search with RRF","https:\u002F\u002Fdocs.trychroma.com\u002Fcloud\u002Fsearch-api\u002Fhybrid-search",{"title":1542,"url":1543},"Chroma Cloud: pricing","https:\u002F\u002Fwww.trychroma.com\u002Fpricing",{"title":1545,"url":1546},"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":1554,"published":1555,"updated":1093,"minutes":90,"category":1556,"tags":1557,"tagPages":1561,"keywords":1563,"about":1571,"sources":1576,"cover":1603,"og":1604,"expertise":80,"locales":1605,"lang":83,"title":1606,"description":1607,"coverAlt":1608},"llamaindex","2026-07-14","agents",[1558,11,1559,830,1560],"Agent framework","Python","Workflows",[8,1562],"python",[1554,1564,1565,1566,1567,1568,1569,1570],"llamaindex vs langgraph vergleich","llamaindex workflows anleitung","llama index agenten framework","llamaparse preise","rag-framework python vergleich","dauerhafte workflows python","dokumenten-agent framework",[1572,1575],{"name":1573,"url":1574},"LlamaIndex","https:\u002F\u002Fgithub.com\u002Frun-llama\u002Fllama_index",{"name":111,"url":112},[1577,1579,1582,1585,1588,1591,1594,1597,1600],{"title":1578,"url":1574},"LlamaIndex repository README and focus note",{"title":1580,"url":1581},"Agent Workflows: introduction","https:\u002F\u002Fdevelopers.llamaindex.ai\u002Fpython\u002Fllamaagents\u002Fworkflows\u002F",{"title":1583,"url":1584},"Agent Workflows: writing durable workflows","https:\u002F\u002Fdevelopers.llamaindex.ai\u002Fpython\u002Fllamaagents\u002Fworkflows\u002Fdurable_workflows\u002F",{"title":1586,"url":1587},"Agent Workflows: observability","https:\u002F\u002Fdevelopers.llamaindex.ai\u002Fpython\u002Fllamaagents\u002Fworkflows\u002Fobservability\u002F",{"title":1589,"url":1590},"LlamaAgents overview","https:\u002F\u002Fdevelopers.llamaindex.ai\u002Fpython\u002Fllamaagents\u002Foverview\u002F",{"title":1592,"url":1593},"llama-index-core on PyPI","https:\u002F\u002Fpypi.org\u002Fproject\u002Fllama-index-core\u002F",{"title":1595,"url":1596},"LlamaIndex and LlamaParse pricing","https:\u002F\u002Fwww.llamaindex.ai\u002Fpricing",{"title":1598,"url":1599},"LiteParse documentation","https:\u002F\u002Fdevelopers.llamaindex.ai\u002Fliteparse\u002F",{"title":1601,"url":1602},"LangGraph on GitHub","https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flanggraph","\u002Fimages\u002Fblog\u002Fllamaindex\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fllamaindex\u002Fog.jpg",[82,83,84],"LlamaIndex im Test: das breiteste Daten-Toolkit, dessen Schwerpunkt schon gewandert ist","LlamaIndex 2026: MIT-lizenziertes Python-Framework für Daten und Agenten mit über 300 Integrationen, Event-Workflows und einem Fokus auf LlamaParse.","LlamaIndex: Ein Lama neben einem großen offenen Werkzeugkasten blickt zu einer kleinen Wolke.",{"slug":1610,"published":1611,"minutes":568,"category":8,"tags":1612,"tagPages":1614,"keywords":1615,"about":1624,"sources":1628,"cover":1653,"og":1654,"expertise":80,"locales":1655,"lang":83,"title":1656,"description":1657,"coverAlt":1658},"pinecone","2026-07-09",[13,10,11,1613,1096],"Namespaces",[17,16,8,1099],[1616,1617,1618,1619,1620,1621,1622,1623],"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",[1625,1626,1627],{"name":1110,"url":1111},{"name":545,"url":546},{"name":114,"url":115},[1629,1632,1635,1638,1641,1644,1647,1650],{"title":1630,"url":1631},"Pinecone docs: Index data overview, indexes, namespaces and metadata","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Findexing-overview",{"title":1633,"url":1634},"Pinecone docs: Adopt the Documents API, API version 2026-07","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Fadopt-the-documents-api",{"title":1636,"url":1637},"Pinecone docs: Create an index, schemas, regions and metrics","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Fcreate-an-index",{"title":1639,"url":1640},"Pinecone docs: Understanding Pinecone cost, read units, write units and egress","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Forganizations\u002Fmanage-cost\u002Funderstanding-cost",{"title":1642,"url":1643},"Pinecone pricing: plans, limits and rates","https:\u002F\u002Fwww.pinecone.io\u002Fpricing\u002F",{"title":1645,"url":1646},"Pinecone docs: Semantic search","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Fsearch\u002Fsemantic-search",{"title":1648,"url":1649},"Pinecone docs: Local development with Pinecone Local","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Foperations\u002Flocal-development",{"title":1651,"url":1652},"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":1660,"published":1661,"updated":686,"minutes":617,"category":8,"tags":1662,"tagPages":1664,"keywords":1665,"about":1675,"sources":1679,"cover":1727,"og":1728,"expertise":80,"locales":1729,"lang":83,"title":1730,"description":1731,"coverAlt":1732},"pgvector-vs-vector-databases","2026-06-15",[527,1030,11,1096,1663],"EU hosting",[8,1099],[1666,1667,1668,1669,1670,535,1671,1672,1673,1674],"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",[1676,1677,1678],{"name":1110,"url":1111},{"name":1029,"url":1163},{"name":111,"url":112},[1680,1683,1685,1688,1689,1692,1695,1698,1701,1704,1707,1710,1712,1715,1718,1721,1724],{"title":1681,"url":1682},"pgvector README (index limits, HNSW defaults, iterative scans, filtering, halfvec)","https:\u002F\u002Fgithub.com\u002Fpgvector\u002Fpgvector\u002Fblob\u002Fmaster\u002FREADME.md",{"title":1684,"url":1169},"pgvector CHANGELOG (0.4.0 to 0.8.7)",{"title":1686,"url":1687},"pgvectorscale: StreamingDiskANN, statistical binary quantization, filtered search","https:\u002F\u002Fgithub.com\u002Ftimescale\u002Fpgvectorscale",{"title":261,"url":262},{"title":1690,"url":1691},"Qdrant documentation: Hybrid queries","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fconcepts\u002Fhybrid-queries\u002F",{"title":1693,"url":1694},"Qdrant documentation: Create a cluster (providers, free tier, Hybrid Cloud)","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fcloud\u002Fcreate-cluster\u002F",{"title":1696,"url":1697},"Weaviate documentation: Hybrid search","https:\u002F\u002Fdocs.weaviate.io\u002Fweaviate\u002Fconcepts\u002Fsearch\u002Fhybrid-search",{"title":1699,"url":1700},"Weaviate documentation: Vector index types","https:\u002F\u002Fdocs.weaviate.io\u002Fweaviate\u002Fconcepts\u002Fvector-index",{"title":1702,"url":1703},"Weaviate Cloud pricing and deployment options","https:\u002F\u002Fweaviate.io\u002Fpricing",{"title":1705,"url":1706},"Milvus documentation: Overview","https:\u002F\u002Fmilvus.io\u002Fdocs\u002Foverview.md",{"title":1708,"url":1709},"Pinecone documentation: Database architecture","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Fget-started\u002Fdatabase-architecture",{"title":1711,"url":1637},"Pinecone documentation: Create an index (clouds, regions, sparse and hybrid)",{"title":1713,"url":1714},"OpenSearch documentation: Methods and engines","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fmappings\u002Fsupported-field-types\u002Fknn-methods-engines\u002F",{"title":1716,"url":1717},"OpenSearch documentation: Efficient k-NN filtering","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fvector-search\u002Ffilter-search-knn\u002Fefficient-knn-filtering\u002F",{"title":1719,"url":1720},"Elasticsearch documentation: Dense vector search","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Fvector\u002Fdense-vector",{"title":1722,"url":1723},"Elasticsearch documentation: kNN query (filter as pre-filter)","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Fquery-languages\u002Fquery-dsl\u002Fquery-dsl-knn-query",{"title":1725,"url":1726},"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":1734,"published":1735,"updated":616,"minutes":275,"category":1736,"tags":1737,"tagPages":1740,"keywords":1741,"about":1752,"sources":1759,"cover":1826,"og":1827,"expertise":80,"locales":1828,"lang":83,"title":1829,"description":1830,"coverAlt":1831},"fine-tuning-vs-rag-vs-prompting","2026-05-12","llmops",[897,11,1738,1739],"Prompting","Distillation",[8],[1742,1743,1744,1745,1746,1747,1748,1749,1750,1751],"fine-tuning oder rag","prompting vs rag vs fine-tuning vergleich","wann llm feintunen","rag oder feintuning","sft vs dpo vs rft","reinforcement fine-tuning anbieter","llm-destillation","openai fine-tuning abschaltung","fine-tuning entscheidungsbaum","fine-tuning für wissen",[1753,1755,1756],{"name":914,"url":1754},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FFine-tuning_(deep_learning)",{"name":111,"url":112},{"name":1757,"url":1758},"Knowledge distillation","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FKnowledge_distillation",[1760,1763,1766,1769,1772,1775,1778,1781,1784,1787,1790,1793,1796,1799,1802,1805,1808,1811,1814,1817,1820,1823],{"title":1761,"url":1762},"OpenAI community: OpenAI self-serve fine-tuning availability (wind-down announcement)","https:\u002F\u002Fcommunity.openai.com\u002Ft\u002Fopenai-s-self-serve-fine-tuning-availability\u002F1380481",{"title":1764,"url":1765},"Tessl: OpenAI is shutting down self-serve fine-tuning","https:\u002F\u002Ftessl.io\u002Fblog\u002Fopenai-shutting-fine-tuning-signals-for-enterprise-ai",{"title":1767,"url":1768},"OpenAI API docs: Model optimization","https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fguides\u002Fmodel-optimization",{"title":1770,"url":1771},"OpenAI API docs: Supervised fine-tuning","https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fguides\u002Fsupervised-fine-tuning",{"title":1773,"url":1774},"OpenAI API docs: Direct preference optimization","https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fguides\u002Fdirect-preference-optimization",{"title":1776,"url":1777},"OpenAI API docs: Reinforcement fine-tuning","https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fguides\u002Freinforcement-fine-tuning",{"title":1779,"url":1780},"OpenAI API docs: Fine-tuning best practices","https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fguides\u002Ffine-tuning-best-practices",{"title":1782,"url":1783},"OpenAI Cookbook: Choosing between SFT, DPO and RFT","https:\u002F\u002Fdevelopers.openai.com\u002Fcookbook\u002Fexamples\u002Ffine_tuning_direct_preference_optimization_guide",{"title":1785,"url":1786},"Google Cloud: Introduction to tuning (Gemini)","https:\u002F\u002Fdocs.cloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fmodels\u002Ftune-models",{"title":1788,"url":1789},"Google Cloud: About supervised fine-tuning for Gemini models","https:\u002F\u002Fdocs.cloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fmodels\u002Fgemini-supervised-tuning",{"title":1791,"url":1792},"Google Cloud: About preference tuning for Gemini models","https:\u002F\u002Fdocs.cloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fmodels\u002Fgemini-preference-tuning",{"title":1794,"url":1795},"Google Cloud: Reward functions for reinforcement learning fine-tuning","https:\u002F\u002Fdocs.cloud.google.com\u002Fgemini-enterprise-agent-platform\u002Fmodels\u002Ftuning\u002Freinforcement-tuning\u002Freinforcement-tuning-job\u002Freward-functions",{"title":1797,"url":1798},"Google Cloud: Supervised and distillation fine-tuning for open models","https:\u002F\u002Fdocs.cloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fmodels\u002Fopen-model-tuning",{"title":1800,"url":1801},"AWS: Fine-tuning for Claude 3 Haiku in Amazon Bedrock is now generally available","https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Faws\u002Ffine-tuning-for-anthropics-claude-3-haiku-model-in-amazon-bedrock-is-now-generally-available\u002F",{"title":1803,"url":1804},"AWS: Amazon Bedrock now supports reinforcement fine-tuning","https:\u002F\u002Faws.amazon.com\u002Fabout-aws\u002Fwhats-new\u002F2025\u002F12\u002Fbedrock-reinforcement-fine-tuning-66-base-models",{"title":1806,"url":1807},"AWS: Amazon Bedrock Model Distillation (preview announcement)","https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Faws\u002Fbuild-faster-more-cost-efficient-highly-accurate-models-with-amazon-bedrock-model-distillation-preview\u002F",{"title":1809,"url":1810},"AWS: Bedrock reinforcement fine-tuning adds open-weight models","https:\u002F\u002Faws.amazon.com\u002Fabout-aws\u002Fwhats-new\u002F2026\u002F02\u002Famazon-bedrock-reinforcement-fine-tuning-openai",{"title":1812,"url":1813},"Microsoft Foundry blog: What is new in Foundry fine-tuning, April 2026","https:\u002F\u002Fdevblogs.microsoft.com\u002Ffoundry\u002Fwhats-new-in-foundry-finetune-april-2026\u002F",{"title":1815,"url":1816},"Microsoft: Announcing new fine-tuning models and techniques in Azure AI Foundry","https:\u002F\u002Fazure.microsoft.com\u002Fen-us\u002Fblog\u002Fannouncing-new-fine-tuning-models-and-techniques-in-azure-ai-foundry\u002F",{"title":1818,"url":1819},"Ovadia et al.: Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.05934",{"title":1821,"url":1822},"Gekhman et al.: Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.05904",{"title":1824,"url":1825},"Hu et al.: LoRA: Low-Rank Adaptation of Large Language Models","https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.09685","\u002Fimages\u002Fblog\u002Ffine-tuning-vs-rag-vs-prompting\u002Fcover.webp","\u002Fimages\u002Fblog\u002Ffine-tuning-vs-rag-vs-prompting\u002Fog.jpg",[82,83,84],"Prompting vs. RAG vs. Fine-Tuning vs. Distillation: Entscheidungshilfe für 2026","Prompting, RAG, Fine-Tuning oder Distillation: was jeder Hebel ändert (Wissen, Verhalten, Format), was er kostet und wer 2026 SFT, DPO und RFT anbietet.","Prompting, RAG, Fine-Tuning: Ein Roboter mit Karte vor vier Türen mit Sprechblase, Büchern, Schraubenschlüssel und Trichter.",1793451237700]