[{"data":1,"prerenderedAt":2331},["ShallowReactive",2],{"blog-category-hu-rag":3},[4,88,149,208,272,340,410,465,521,576,619,669,739,812,883,951,1019,1081,1147,1211,1272,1340,1405,1455,1494,1545,1595,1634,1685,1755,1830,1874,1928,1983,2032,2105,2158,2220,2265],{"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":84,"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],"legjobb embedding modell 2026","hogyan válasszunk embedding modellt","embedding modell összehasonlítás","mteb ranglista magyarázat","rteb benchmark","nyílt forráskódú embedding modell","többnyelvű embedding modell","voyage-4 vagy openai embedding","qwen3-embedding","embeddinggemma","embedding modell rag-hoz","embedding modell csere újraindexelés",[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 választása 2026-ban: ranglisták, költségek és összehasonlító teszt a saját adatokon","Hogyan válassz embedding-modellt RAG-hoz 2026-ban: mit mondanak az MTEB és az RTEB, API vagy nyílt súlyok, árak, dimenziók és egy egyhetes teszt.","Embedding-modell választása: három sütemény hűl a formájából, egy villa épp megkóstol egyet.",{"slug":89,"published":6,"minutes":90,"category":8,"tags":91,"tagPages":95,"keywords":96,"about":108,"sources":118,"cover":143,"og":144,"expertise":80,"locales":145,"lang":84,"title":146,"description":147,"coverAlt":148},"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],"kontextuális visszakeresés","anthropic kontextuális visszakeresés","késleltetett chunkelés","kontextuális chunk beágyazások","kontextuális beágyazások rag","contextual bm25","chunk kontextus rag","voyage-context-3","voyage-context-4","late chunking vs kontextuális visszakeresés","rag chunkelés kontextusvesztés",[109,112,115],{"name":110,"url":111},"Retrieval-augmented generation","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FRetrieval-augmented_generation",{"name":113,"url":114},"Okapi BM25","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOkapi_BM25",{"name":116,"url":117},"Sentence embedding","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FSentence_embedding",[119,122,125,128,131,134,137,140],{"title":120,"url":121},"Anthropic: Introducing Contextual Retrieval (Sep 2024)","https:\u002F\u002Fwww.anthropic.com\u002Fnews\u002Fcontextual-retrieval",{"title":123,"url":124},"Günther et al.: Late Chunking, Contextual Chunk Embeddings Using Long-Context Embedding Models (2024, rev. 2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.04701",{"title":126,"url":127},"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":129,"url":130},"Voyage AI: Introducing voyage-context-3 (Jul 2025)","https:\u002F\u002Fblog.voyageai.com\u002F2025\u002F07\u002F23\u002Fvoyage-context-3\u002F",{"title":132,"url":133},"Voyage AI: voyage-context-4 (Jun 2026)","https:\u002F\u002Fblog.voyageai.com\u002F2026\u002F06\u002F29\u002Fvoyage-context-4\u002F",{"title":135,"url":136},"Voyage AI: Contextualized chunk embeddings documentation","https:\u002F\u002Fdocs.voyageai.com\u002Fdocs\u002Fcontextualized-chunk-embeddings",{"title":138,"url":139},"Anthropic: Claude API pricing","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fabout-claude\u002Fpricing",{"title":141,"url":142},"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],"Kontextuális visszakeresés és késleltetett chunkolás: a RAG-chunkok visszakapják a kontextusukat","A chunkok elveszítik a dokumentumukat. Contextual retrieval, late chunking és kontextusos embedding: mennyibe kerülnek, és mikor hagyhatók ki.","Kontextuális visszakeresés: egy kéz címkés kirakósdarabot tart a helye fölé az asztalon fekvő kirakóban.",{"slug":150,"published":6,"minutes":7,"category":8,"tags":151,"tagPages":155,"keywords":156,"about":169,"sources":177,"cover":202,"og":203,"expertise":80,"locales":204,"lang":84,"title":205,"description":206,"coverAlt":207},"rag-access-control-permissions",[11,152,153,154,13],"Access control","Security","Multi-tenancy",[8,17],[157,158,159,160,161,162,163,164,165,166,167,168],"rag hozzáférés-kezelés","jogosultságtudatos rag","dokumentumszintű biztonság rag","rag multi tenancy","vektoradatbázis hozzáférés-kezelés","pgvector row level security","security trimming azure ai search","openfga rag jogosultságkezelés","qdrant multitenancy","pinecone namespace multitenancy","owasp llm08 vektor és beágyazási gyengeségek","rag adatszivárgás",[170,173,176],{"name":171,"url":172},"Access-control list","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAccess-control_list",{"name":174,"url":175},"Multitenancy","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FMultitenancy",{"name":110,"url":111},[178,181,184,187,190,193,196,199],{"title":179,"url":180},"OWASP GenAI Security Project: LLM08:2025 Vector and Embedding Weaknesses","https:\u002F\u002Fgenai.owasp.org\u002Fllmrisk\u002Fllm082025-vector-and-embedding-weaknesses\u002F",{"title":182,"url":183},"PostgreSQL documentation: Row Security Policies","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Fddl-rowsecurity.html",{"title":185,"url":186},"pgvector README: filtering and iterative index scans","https:\u002F\u002Fgithub.com\u002Fpgvector\u002Fpgvector",{"title":188,"url":189},"Qdrant: Multitenancy and partitions guide","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fguides\u002Fmultiple-partitions\u002F",{"title":191,"url":192},"Pinecone: Implement multitenancy using namespaces","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Fimplement-multitenancy",{"title":194,"url":195},"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":197,"url":198},"OpenFGA: RAG authorization use case","https:\u002F\u002Fopenfga.dev\u002Fdocs\u002Fuse-cases\u002Frag-authorization",{"title":200,"url":201},"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],"Hozzáférés-kezelés RAG-hoz: jogosultságtudatos visszakeresés dokumentumszivárgás nélkül","Hogyan szivárogtatnak dokumentumot a RAG-asszisztensek, és hogyan állítsd meg: ACL minden chunkon, előszűrés, sorszintű biztonság pgvectorban, jogszinkron.","Hozzáférés-kezelés RAG-hoz: belépőkártyás ember könyvet vesz le, mások lezárt üvegajtó mögött maradnak.",{"slug":209,"published":6,"minutes":90,"category":8,"tags":210,"tagPages":215,"keywords":218,"about":230,"sources":238,"cover":265,"og":266,"expertise":267,"locales":268,"lang":84,"title":269,"description":270,"coverAlt":271},"rag-product-catalog-pim-data",[11,211,212,213,214],"PIM","Product data","B2B e-commerce","Metadata filtering",[8,216,217],"pim","b2b-e-commerce",[219,220,221,222,223,224,225,226,227,228,229],"rag termékkatalógus","rag pim adatok","llm termékadatok","termékkatalógus chatbot","akeneo rag","pimcore ai keresés","rag strukturált adatok","metaadat szűrés rag","termékattribútumok beágyazások","b2b termékasszisztens","etim osztályozás ai",[231,234,235],{"name":232,"url":233},"Product information management","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FProduct_information_management",{"name":110,"url":111},{"name":236,"url":237},"ETIM (standard)","https:\u002F\u002Fwww.etim-international.com\u002Fclassification\u002F",[239,242,245,248,250,253,256,259,262],{"title":240,"url":241},"Akeneo API: Products, product values, metric values and product models","https:\u002F\u002Fapi.akeneo.com\u002Fconcepts\u002Fproducts.html",{"title":243,"url":244},"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":246,"url":247},"Pimcore documentation: Classification Store","https:\u002F\u002Fdocs.pimcore.com\u002Fplatform\u002FPimcore\u002FObjects\u002FObject_Classes\u002FData_Types\u002FClassification_Store\u002F",{"title":249,"url":237},"ETIM International: Classification",{"title":251,"url":252},"ETIM International: ETIM releases and the IXF format","https:\u002F\u002Fetim-international.com\u002F?p=754",{"title":254,"url":255},"Reddy et al.: Shopping Queries Dataset, a large-scale ESCI benchmark for improving product search (2022)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.06588",{"title":257,"url":258},"Amazon Science: esci-data repository","https:\u002F\u002Fgithub.com\u002Famazon-science\u002Fesci-data",{"title":260,"url":261},"Qdrant documentation: Filtering","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fconcepts\u002Ffiltering\u002F",{"title":263,"url":264},"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 termékkatalógusra: PIM-adatokból megbízható válaszok","RAG-hoz: a PDF-szerű chunkolás elbukik, mert a termékadat strukturált. Sorosítsd a PIM-attribútumokat, és szűrőkre irányítsd a specifikációs kérdéseket.","RAG termékkatalógusra: nyitott katalógusból termékkártyás szövegbuborék emelkedik fel.",{"slug":273,"published":6,"minutes":274,"category":8,"tags":275,"tagPages":280,"keywords":281,"about":292,"sources":300,"cover":334,"og":335,"expertise":80,"locales":336,"lang":84,"title":337,"description":338,"coverAlt":339},"conversational-search-query-rewriting",12,[276,277,11,278,279],"Conversational search","Query rewriting","HyDE","E-commerce",[8],[282,283,284,285,286,287,288,289,290,291],"beszélgetésalapú keresés lekérdezés-újraírás","korreferencia feloldás keresési lekérdezés","hyde hipotetikus dokumentum beágyazások","többlekérdezéses bővítés rag","llm szűrő kinyerés","b2b termékkereső asszisztens","beszélgetésalapú termékkeresés","lekérdezés-újraírás késleltetés","recall@k kiértékelés","önálló lekérdezés generálás",[293,296,299],{"name":294,"url":295},"Query expansion","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FQuery_expansion",{"name":297,"url":298},"Coreference","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FCoreference",{"name":113,"url":114},[301,304,307,310,313,316,319,322,325,328,331],{"title":302,"url":303},"Gao et al.: Precise Zero-Shot Dense Retrieval without Relevance Labels, ACL 2023","https:\u002F\u002Faclanthology.org\u002F2023.acl-long.99\u002F",{"title":305,"url":306},"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":308,"url":309},"Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion","https:\u002F\u002Faclanthology.org\u002F2025.findings-acl.980.pdf",{"title":311,"url":312},"ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning","https:\u002F\u002Faclanthology.org\u002F2025.emnlp-main.1349\u002F",{"title":314,"url":315},"CFDA and CLIP at TREC iKAT 2025: Query Reformulation and Rank Fusion","https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.15588",{"title":317,"url":318},"MiniELM: A Lightweight and Adaptive Query Rewriting Framework for E-Commerce Search Optimization","https:\u002F\u002Faclanthology.org\u002F2025.findings-acl.363\u002F",{"title":320,"url":321},"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":323,"url":324},"Microsoft Learn: Agentic retrieval overview in Azure AI Search","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fagentic-retrieval-overview",{"title":326,"url":327},"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":329,"url":330},"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":332,"url":333},"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],"Lekérdezés-újraírás beszélgetésalapú kereséshez: kontextus, HyDE és szűrők","Hogyan írjuk át a követő kérdéseket egy B2B webshop-asszisztensben: korreferencia, HyDE, több lekérdezés, szűrők, latencia és kiértékelés.","Lekérdezés-újraírás kereséshez: szövegbuborék egy varrógépen át rendezett cetliként jön ki, rajta nagyító.",{"slug":341,"published":6,"minutes":90,"category":8,"tags":342,"tagPages":347,"keywords":349,"about":362,"sources":368,"cover":404,"og":405,"expertise":80,"locales":406,"lang":84,"title":407,"description":408,"coverAlt":409},"synthetic-test-data-rag-evals",[11,343,344,345,346],"Evaluation","Synthetic data","Retrieval","Testing",[8,348],"evaluation",[350,351,352,353,354,355,356,357,358,359,360,361],"szintetikus tesztadat rag","rag kiértékelő adathalmaz","kérdésgenerálás chunkekből","hard negatívok visszakeresés kiértékelés","válaszolhatósági szűrő","rag tesztkészlet generálás","szintetikus kérdés-válasz párok","rag eval adat kontamináció","többnyelvű rag kiértékelés német magyar","visszakeresési mutatók recall ndcg","llm bíró emberi ellenőrzés","megválaszolhatatlan kérdések rag",[363,365,367],{"name":110,"url":364},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FRetrieval_augmented_generation",{"name":344,"url":366},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FSynthetic_data",{"name":36,"url":37},[369,372,375,378,381,384,387,390,393,396,399,401],{"title":370,"url":371},"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":373,"url":374},"Ragas docs: Testset Generation for RAG","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fgetstarted\u002Frag_testset_generation\u002F",{"title":376,"url":377},"Ragas docs: Testset generation concepts (query types, scenarios)","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fconcepts\u002Ftest_data_generation\u002Frag\u002F",{"title":379,"url":380},"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":382,"url":383},"DeepEval docs: Datasets and the Synthesizer","https:\u002F\u002Fdeepeval.com\u002Fdocs\u002Fevaluation-datasets",{"title":385,"url":386},"Rajpurkar, Jia, Liang: Know What You Don't Know: Unanswerable Questions for SQuAD (ACL 2018)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1806.03822",{"title":388,"url":389},"Rahmani et al.: Towards Understanding Bias in Synthetic Data for Evaluation (CIKM 2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.10301",{"title":391,"url":392},"Cheng et al.: A Survey on Data Contamination for Large Language Models","https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.14425",{"title":394,"url":395},"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":397,"url":398},"Panickssery, Bowman, Feng: LLM Evaluators Recognize and Favor Their Own Generations","https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.13076",{"title":400,"url":44},"Enevoldsen et al.: MMTEB, Massive Multilingual Text Embedding Benchmark (ICLR 2025)",{"title":402,"url":403},"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],"Szintetikus tesztadatok generálása a RAG-értékeléshez","Kérdésgenerálás blokkokból, hard negatívok, válaszolhatósági címkék, német és magyar lefedettség, kontamináció és emberi ellenőrzések.","Szintetikus tesztadatok RAG-értékeléshez: robot olyan gépet kezel, amely egy könyvből kérdéskártyákat készít.",{"slug":411,"published":412,"minutes":7,"category":8,"tags":413,"tagPages":418,"keywords":420,"about":431,"sources":439,"cover":459,"og":460,"expertise":80,"locales":461,"lang":84,"title":462,"description":463,"coverAlt":464},"pdf-document-parsing-for-rag","2026-10-16",[11,414,415,416,417],"PDF parsing","OCR","Docling","Document AI",[8,419],"document-ai",[421,422,423,424,425,426,427,428,429,430],"pdf feldolgozás rag-hez","legjobb pdf parser rag-hez","docling vs marker","marker vs mineru","pdf markdown llm-hez","táblázatok kinyerése pdf-ből rag-hez","ocr rag pipeline","olmocr bench","szkennelt pdf rag","dokumentum feldolgozás llm",[432,435,438],{"name":433,"url":434},"PDF","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FPDF",{"name":436,"url":437},"Optical character recognition","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOptical_character_recognition",{"name":110,"url":111},[440,443,446,449,452,455,458],{"title":441,"url":442},"Docling: README, features and license (GitHub)","https:\u002F\u002Fgithub.com\u002Fdocling-project\u002Fdocling",{"title":444,"url":445},"Auer et al.: Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion (2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.17887",{"title":447,"url":448},"Datalab: Marker README, olmOCR-bench results and license (GitHub)","https:\u002F\u002Fgithub.com\u002Fdatalab-to\u002Fmarker",{"title":450,"url":451},"OpenDataLab: MinerU README and license (GitHub)","https:\u002F\u002Fgithub.com\u002Fopendatalab\u002FMinerU",{"title":453,"url":454},"Poznanski et al.: olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models (2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.18443",{"title":456,"url":457},"Claude Platform Docs: PDF support","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fbuild-with-claude\u002Fpdf-support",{"title":120,"url":121},"\u002Fimages\u002Fblog\u002Fpdf-document-parsing-for-rag\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fpdf-document-parsing-for-rag\u002Fog.jpg",[82,83,84],"PDF-feldolgozás RAG-hoz: layout-pipeline-ok, OCR és vizuális modellek összevetve","Miért a PDF-feldolgozáson múlik a RAG minősége, miben más a Docling, a Marker, a MinerU és a VLM-OCR, és hogyan teszteld a parsert saját dokumentumokon.","PDF-feldolgozás RAG-hoz: dokumentum hengeres gépen halad át, és külön táblázat-, kép- és szövegkártyákként jön ki.",{"slug":466,"published":412,"minutes":467,"category":8,"tags":468,"tagPages":472,"keywords":473,"about":484,"sources":494,"cover":515,"og":516,"expertise":80,"locales":517,"lang":84,"title":518,"description":519,"coverAlt":520},"multilingual-rag-german-hungarian",7,[11,469,10,470,471],"Multilingual","German","Hungarian",[8,16],[474,475,476,477,478,479,480,481,482,483],"többnyelvű rag","német rag beágyazások","magyar nlp keresés","nyelvek közötti visszakeresés","többnyelvű beágyazó modell","bge-m3 német","német összetett szavak keresése","magyar szótövezés postgres","multilingual-e5-large-instruct","qwen3 embedding többnyelvű",[485,488,491],{"name":486,"url":487},"Cross-language information retrieval","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FCross-language_information_retrieval",{"name":489,"url":490},"Agglutinative language","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAgglutinative_language",{"name":492,"url":493},"Compound (linguistics)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FCompound_(linguistics)",[495,497,500,503,506,509,512],{"title":496,"url":44},"Enevoldsen et al.: MMTEB: Massive Multilingual Text Embedding Benchmark (2025)",{"title":498,"url":499},"Chen et al.: M3-Embedding (BGE-M3): Multi-Linguality, Multi-Functionality, Multi-Granularity (2024)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.03216",{"title":501,"url":502},"Zhang et al.: Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models (2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.05176",{"title":504,"url":505},"Hugging Face: intfloat\u002Fmultilingual-e5-large-instruct model card","https:\u002F\u002Fhuggingface.co\u002Fintfloat\u002Fmultilingual-e5-large-instruct",{"title":507,"url":508},"Elasticsearch Reference: Hyphenation decompounder token filter","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Ftext-analysis\u002Fanalysis-hyp-decomp-tokenfilter",{"title":510,"url":511},"PostgreSQL 18 Documentation: Text search dictionaries","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Ftextsearch-dictionaries.html",{"title":513,"url":514},"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],"Többnyelvű RAG német és magyar tartalomra: embeddingek, összetett szavak és nyelvek közötti keresés","RAG német és magyar tartalom fölött: többnyelvű embeddingek, összetett szavak, szótövezés, ékezetek és nyelvenkénti értékelés.","Többnyelvű RAG német és magyar tartalomra: egy ember könyvet visz át egy kis hídon két könyvespolc között.",{"slug":522,"published":412,"minutes":523,"category":8,"tags":524,"tagPages":530,"keywords":532,"about":543,"sources":552,"cover":570,"og":571,"expertise":80,"locales":572,"lang":84,"title":573,"description":574,"coverAlt":575},"text-to-sql-llm-guardrails",8,[525,526,527,528,529],"Text-to-SQL","LLM security","PostgreSQL","Agents","Analytics",[531],"llm-security",[533,534,535,536,537,538,539,540,541,542],"text-to-sql llm","text-to-sql guardrailek","llm sql ügynök biztonság","természetes nyelvből sql éles rendszerben","csak olvasható adatbázis szerepkör llm","bird benchmark text-to-sql","spider 2.0 benchmark","sqlglot sql validálás","row level security llm","beszélgetés az adatbázisoddal",[544,547,550],{"name":545,"url":546},"SQL","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FSQL",{"name":548,"url":549},"Natural language interface to databases","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FNatural-language_user_interface",{"name":527,"url":551},"https:\u002F\u002Fwww.postgresql.org\u002F",[553,556,559,561,564,567],{"title":554,"url":555},"BIRD-bench: leaderboard and dataset description","https:\u002F\u002Fbird-bench.github.io\u002F",{"title":557,"url":558},"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":560,"url":183},"PostgreSQL 18 Documentation: Row Security Policies",{"title":562,"url":563},"PostgreSQL 18 Documentation: Client Connection Defaults (read-only and timeouts)","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Fruntime-config-client.html",{"title":565,"url":566},"SQLGlot: SQL parser, transpiler and optimizer (GitHub)","https:\u002F\u002Fgithub.com\u002Ftobymao\u002Fsqlglot",{"title":568,"url":569},"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 LLM-mel: sémakontextus, csak olvasható szerepkörök és működő validálás","Mennyire pontos valójában a text-to-SQL, hogyan kapjon sémakontextust a modell, és milyen adatbázis- és kódszintű korlátok teszik biztonságossá az SQL-t.","Text-to-SQL LLM-mel: szövegbuborék rácsos ablakon át jut egy adatbázis-hengerbe, ajtaján lakat.",{"slug":577,"published":412,"minutes":578,"category":8,"tags":579,"tagPages":582,"keywords":583,"about":594,"sources":604,"cover":613,"og":614,"expertise":80,"locales":615,"lang":84,"title":616,"description":617,"coverAlt":618},"embedding-quantization-binary-matryoshka",5,[10,13,580,581,11],"Quantization","pgvector",[16,17,8],[584,585,586,587,588,589,590,591,592,593],"embedding kvantálás","bináris kvantálás beágyazások","int8 embedding","matryoshka embedding","vektoradatbázis memória csökkentése","pgvector halfvec","pgvector binary_quantize","embedding dimenziók csökkentése","bináris beágyazások újrapontozása","vektorindex memóriaköltség",[595,598,601],{"name":596,"url":597},"Quantization (signal processing)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FQuantization_(signal_processing)",{"name":599,"url":600},"Nearest neighbor search","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FNearest_neighbor_search",{"name":602,"url":603},"Hamming distance","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FHamming_distance",[605,608,611],{"title":606,"url":607},"Hugging Face: Binary and Scalar Embedding Quantization for Significantly Faster and Cheaper Retrieval (Mar 2024)","https:\u002F\u002Fhuggingface.co\u002Fblog\u002Fembedding-quantization",{"title":609,"url":610},"Kusupati et al.: Matryoshka Representation Learning (2022)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.13147",{"title":612,"url":186},"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-kvantálás: bináris, int8 és Matryoshka vektorok a visszakeresés minőségének elvesztése nélkül","Hogyan zsugorítja 4–32-szeresére a vektorindexet a bináris és int8 kvantálás és a Matryoshka-vágás, mennyibe kerül ez, és hogyan hozza vissza a rescoring.","Embedding-kvantálás: matrjoska babák sorban nagytól kicsiig, a legkisebb egy mérlegen áll.",{"slug":620,"published":621,"minutes":622,"category":8,"tags":623,"tagPages":628,"keywords":630,"about":640,"sources":644,"cover":663,"og":664,"expertise":80,"locales":665,"lang":84,"title":666,"description":667,"coverAlt":668},"zep","2026-10-06",11,[624,625,626,627,11],"Agent memory","Knowledge graph","Temporal graph","Context engineering",[629,8],"context-engineering",[631,632,633,634,635,636,637,638,639],"zep ai","zep teszt","zep ügynök memória","graphiti tudásgráf","zep árak","zep vagy mem0","ügynök memória hosszú távon","időbeli tudásgráf","zep cloud",[641],{"name":642,"url":643},"Zep","https:\u002F\u002Fwww.getzep.com\u002F",[645,648,651,654,657,660],{"title":646,"url":647},"Zep pricing: plans, credits and limits","https:\u002F\u002Fwww.getzep.com\u002Fpricing",{"title":649,"url":650},"Zep documentation","https:\u002F\u002Fhelp.getzep.com\u002F",{"title":652,"url":653},"Graphiti on GitHub","https:\u002F\u002Fgithub.com\u002Fgetzep\u002Fgraphiti",{"title":655,"url":656},"Graphiti product page","https:\u002F\u002Fwww.getzep.com\u002Fplatform\u002Fgraphiti\u002F",{"title":658,"url":659},"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":661,"url":662},"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 ismertető: ügynök-memory temporális gráfon","A Zep hostolt memória-API temporális tudásgráffal: kreditek íráskor, lekérdezés ingyen, Flex 125 dollártól havonta, a Graphiti pedig önhosztolható.","Zep ismertető: robot egy falon lévő, összekötött kártyákból álló ábrát néz, mindegyiken kis óra.",{"slug":670,"published":671,"minutes":672,"category":8,"tags":673,"tagPages":677,"keywords":678,"about":689,"sources":696,"cover":733,"og":734,"expertise":80,"locales":735,"lang":84,"title":736,"description":737,"coverAlt":738},"graphrag-knowledge-graph-rag","2026-10-02",13,[674,675,676,11],"GraphRAG","Knowledge graphs","LightRAG",[8],[679,680,681,682,683,684,685,686,687,688],"graphrag magyarázat","tudásgráf rag","graphrag vs vektoros rag","microsoft graphrag magyarázat","lightrag vs graphrag","graphrag globális vs lokális keresés","graphrag indexelés ára","mikor használjunk graphrag-et","többlépéses rag","lazygraphrag",[690,692,693],{"name":625,"url":691},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FKnowledge_graph",{"name":110,"url":111},{"name":694,"url":695},"Leiden algorithm","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FLeiden_algorithm",[697,700,703,706,709,712,715,718,721,724,727,730],{"title":698,"url":699},"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":701,"url":702},"Microsoft GraphRAG documentation: overview","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002F",{"title":704,"url":705},"Microsoft GraphRAG documentation: default dataflow","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Findex\u002Fdefault_dataflow\u002F",{"title":707,"url":708},"Microsoft GraphRAG documentation: global search","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Fquery\u002Fglobal_search\u002F",{"title":710,"url":711},"Microsoft GraphRAG documentation: local search","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Fquery\u002Flocal_search\u002F",{"title":713,"url":714},"Microsoft GraphRAG documentation: DRIFT search","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Fquery\u002Fdrift_search\u002F",{"title":716,"url":717},"Microsoft GraphRAG documentation: getting started","https:\u002F\u002Fmicrosoft.github.io\u002Fgraphrag\u002Fget_started\u002F",{"title":719,"url":720},"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":722,"url":723},"Guo et al.: LightRAG: Simple and Fast Retrieval-Augmented Generation (arXiv:2410.05779)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.05779",{"title":725,"url":726},"HKUDS\u002FLightRAG on GitHub","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FLightRAG",{"title":728,"url":729},"Gutiérrez et al.: HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models (arXiv:2405.14831)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.14831",{"title":731,"url":732},"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 és knowledge-graph RAG: mikor veri a gráf a vektoros keresést","Mit tud a Microsoft GraphRAG és a LightRAG, mibe kerül az indexelés, és mikor veri a tudásgráf a vektoros RAG-et többlépéses és globális kérdéseknél?","GraphRAG és tudásgráf-RAG: nagyító egy kereszteződés fölött egy várostérképen, mellette laza papírkupac.",{"slug":740,"published":741,"updated":412,"minutes":90,"category":8,"tags":742,"tagPages":748,"keywords":749,"about":761,"sources":769,"cover":806,"og":807,"expertise":80,"locales":808,"lang":84,"title":809,"description":810,"coverAlt":811},"multimodal-rag-colpali","2026-10-01",[743,744,745,746,747],"ColPali","Multimodal RAG","Late interaction","Multi-vector embeddings","Visual document retrieval",[],[750,751,752,753,754,755,756,757,758,759,760],"multimodális rag colpali","multimodális rag","colpali","vizuális dokumentum visszakeresés","colqwen2","colqwen3","late interaction maxsim","többvektoros beágyazások","vidore benchmark","oldalkép beágyazások","többvektoros vektoradatbázis",[762,763,766],{"name":110,"url":111},{"name":764,"url":765},"Vector database","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FVector_database",{"name":767,"url":768},"Vision-language model","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FVision-language_model",[770,773,776,779,782,785,788,791,794,797,800,803],{"title":771,"url":772},"ColPali: Efficient Document Retrieval with Vision Language Models (arXiv:2407.01449)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.01449",{"title":774,"url":775},"ViDoRe V2 benchmark (arXiv:2505.17166)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.17166",{"title":777,"url":778},"ViDoRe V3 benchmark (arXiv:2601.08620)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.08620",{"title":780,"url":781},"EVIE: storage and benchmark analysis for ColQwen-family models (arXiv:2610.11553)","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2610.11553v1",{"title":783,"url":784},"Vespa: scaling ColPali to billions","https:\u002F\u002Fblog.vespa.ai\u002Fscaling-colpali-to-billions\u002F",{"title":786,"url":787},"Qdrant documentation: vectors, multivectors and the max_sim comparator","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fconcepts\u002Fvectors\u002F",{"title":789,"url":790},"Qdrant: ColPali optimization with pooling and two-stage retrieval (2024)","https:\u002F\u002Fqdrant.tech\u002Fblog\u002Fcolpali-qdrant-optimization",{"title":792,"url":793},"Qdrant: turbo4 multivector search tutorial","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Ftutorials-search-engineering\u002Fturbo4-multivector-search\u002F",{"title":795,"url":796},"Sentence Transformers v6.0.0 release notes","https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fsentence-transformers\u002Freleases\u002Ftag\u002Fv6.0.0",{"title":798,"url":799},"illuin-tech\u002Fcolpali repository and model table","https:\u002F\u002Fgithub.com\u002Filluin-tech\u002Fcolpali",{"title":801,"url":802},"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":804,"url":805},"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],"Multimodális RAG ColPalival: oldalképek, többvektoros költségek és mikor nyernek","Multimodális RAG ColPalival: oldalkép-beágyazások, MaxSim-pontozás, többvektoros tárhelyköltségek, tömörítés és mikor múlják felül a feldolgozott szöveget.","Multimodális RAG ColPalival: kis mezőkre osztott oldal, néhány mező nagyítóhoz kapcsolódik.",{"slug":813,"published":741,"updated":6,"minutes":523,"category":8,"tags":814,"tagPages":818,"keywords":820,"about":831,"sources":841,"cover":877,"og":878,"expertise":80,"locales":879,"lang":84,"title":880,"description":881,"coverAlt":882},"code-rag-repository-indexing",[11,815,816,10,817],"Code search","Tree-sitter","Coding agents",[8,16,819],"coding-agents",[821,822,823,824,825,826,827,828,829,830],"rag kódon","ast darabolás","tree-sitter kód darabolás","repótérkép","kód beágyazások","szemantikus kódkeresés","kódbázis indexelés","repo map tokenek","inkrementális kódindex","coir benchmark",[832,833,836,838],{"name":110,"url":111},{"name":834,"url":835},"Abstract syntax tree","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAbstract_syntax_tree",{"name":816,"url":837},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FTree-sitter_%28parser_generator%29",{"name":839,"url":840},"Merkle tree","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FMerkle_tree",[842,845,848,851,854,857,860,863,866,868,871,874],{"title":843,"url":844},"cAST: AST-based chunking for code RAG (arXiv 2506.15655)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.15655",{"title":846,"url":847},"Aider docs: repository map","https:\u002F\u002Faider.chat\u002Fdocs\u002Frepomap.html",{"title":849,"url":850},"Aider blog: building a better repository map with tree-sitter (2023)","https:\u002F\u002Faider.chat\u002F2023\u002F10\u002F22\u002Frepomap.html",{"title":852,"url":853},"Anthropic Engineering: effective context engineering for AI agents (Sep 2025)","https:\u002F\u002Fwww.anthropic.com\u002Fengineering\u002Feffective-context-engineering-for-ai-agents",{"title":855,"url":856},"Cursor blog: securely indexing large codebases (Jan 2026)","https:\u002F\u002Fcursor.com\u002Fblog\u002Fsecure-codebase-indexing",{"title":858,"url":859},"turbopuffer: Cursor customer story","https:\u002F\u002Fturbopuffer.com\u002Fcustomers\u002Fcursor",{"title":861,"url":862},"Kilo Code docs: codebase indexing","https:\u002F\u002Fkilo.ai\u002Fdocs\u002Fcustomize\u002Fcontext\u002Fcodebase-indexing",{"title":864,"url":865},"Serena on GitHub","https:\u002F\u002Fgithub.com\u002Foraios\u002Fserena",{"title":867,"url":62},"Voyage AI docs: pricing",{"title":869,"url":870},"Qwen blog: Qwen3-Embedding (Jun 2025)","https:\u002F\u002Fqwenlm.github.io\u002Fblog\u002Fqwen3-embedding\u002F",{"title":872,"url":873},"CoIR: a benchmark for code information retrieval (arXiv 2407.02883)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.02883",{"title":875,"url":876},"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 kódon: AST-darabolás, repótérképek és kódbeágyazások ügynökökhöz","Hogyan találják meg a kódot a kódoló ügynökök: AST-darabolás tree-sitterrel, repótérképek, Merkle-fás szinkron, kódbeágyazók 2026-ban és mikor jobb a grep.","RAG kódon (AST-darabolás): elágazó kódfa táplál egy sor kartotékkártyát.",{"slug":884,"published":885,"updated":741,"minutes":523,"category":8,"tags":886,"tagPages":890,"keywords":891,"about":902,"sources":910,"cover":945,"og":946,"expertise":80,"locales":947,"lang":84,"title":948,"description":949,"coverAlt":950},"reranking-models-compared","2026-09-30",[887,11,888,889,343],"Reranking","Search","Cross-encoders",[8,348],[892,893,894,895,896,897,898,899,900,901],"cross-encoder rerankerek összehasonlítása","cohere rerank 4 árak","bge-reranker-v2-m3","voyage rerank-3","jina reranker v3.5","colbert late interaction vs reranker","llm mint reranker","reciprocal rank fusion vs reranker","újrarangsorolás top-k kiértékelés","saját szerveres reranker onnx cpu",[903,906,909],{"name":904,"url":905},"Learning to rank","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FLearning_to_rank",{"name":907,"url":908},"BERT (language model)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FBERT_%28language_model%29",{"name":36,"url":37},[911,914,917,920,923,926,929,930,933,936,939,942],{"title":912,"url":913},"Sentence-BERT (arXiv 1908.10084)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.10084",{"title":915,"url":916},"Sentence Transformers: retrieve and re-rank","https:\u002F\u002Fsbert.net\u002Fexamples\u002Fsentence_transformer\u002Fapplications\u002Fretrieve_rerank\u002FREADME.html",{"title":918,"url":919},"BAAI\u002Fbge-reranker-v2-m3 model card","https:\u002F\u002Fhuggingface.co\u002FBAAI\u002Fbge-reranker-v2-m3",{"title":921,"url":922},"Cohere docs: reranking best practices","https:\u002F\u002Fdocs.cohere.com\u002Fdocs\u002Freranking-best-practices",{"title":924,"url":925},"Cohere pricing","https:\u002F\u002Fcohere.com\u002Fpricing",{"title":927,"url":928},"Voyage AI blog: rerank-3 (30 Sep 2026)","https:\u002F\u002Fblog.voyageai.com\u002F2026\u002F09\u002F30\u002Frerank-3\u002F",{"title":867,"url":62},{"title":931,"url":932},"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":934,"url":935},"ColBERTv2 (arXiv 2112.01488)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.01488",{"title":937,"url":938},"Elasticsearch docs: reciprocal rank fusion","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Frest-apis\u002Freciprocal-rank-fusion",{"title":940,"url":941},"Azure AI Search: semantic ranking overview","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fsemantic-search-overview",{"title":943,"url":944},"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 rerankerek: Cohere, bge, Voyage, Jina és késői interakció (2026)","Rerankerek 2026 októberében: pointwise, listwise és késői interakció, Cohere, Voyage, bge, Qwen3, Jina és mxbai, árak, saját üzemeltetés és a k választása.","Cross-encoder rerankerek: egy tölcsér sok kártyát ötre szűkít, egy kártya előre emelkedik.",{"slug":952,"published":885,"updated":741,"minutes":523,"category":8,"tags":953,"tagPages":958,"keywords":960,"about":971,"sources":977,"cover":1013,"og":1014,"expertise":80,"locales":1015,"lang":84,"title":1016,"description":1017,"coverAlt":1018},"elasticsearch-opensearch-vector-search",[954,955,13,956,957],"Elasticsearch","OpenSearch","Hybrid search","Licensing",[17,959],"hybrid-search",[961,962,963,964,965,966,967,968,969,970],"vektorkeresés elasticsearchben és opensearchben","elasticsearch knn vektorkeresés","opensearch neural search","hibrid keresés rrf","elasticsearch bbq bináris kvantálás","opensearch diskann jvector","elasticsearch agpl licenc","szűrt knn keresés","elasticsearch vs opensearch vektoradatbázis","keresőmotor vektortárként",[972,974,976],{"name":954,"url":973},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FElasticsearch",{"name":955,"url":975},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOpenSearch_%28software%29",{"name":599,"url":600},[978,981,984,987,990,992,995,998,1001,1004,1007,1010],{"title":979,"url":980},"Elastic docs: kNN search","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Fvector\u002Fknn",{"title":982,"url":983},"Elastic docs: filtered kNN search","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Fvector\u002Fknn\u002Ffiltered-knn-search",{"title":985,"url":986},"Elastic docs: dense_vector field type","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Fmapping-reference\u002Fdense-vector",{"title":988,"url":989},"Elastic docs: BBQ","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Fmapping-reference\u002Fbbq",{"title":991,"url":938},"Elastic docs: reciprocal rank fusion",{"title":993,"url":994},"Elastic docs: GPU vector indexing","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Fvector\u002Fgpu-vector-indexing",{"title":996,"url":997},"Elastic blog: Elasticsearch is open source again (Aug 2024)","https:\u002F\u002Fwww.elastic.co\u002Fblog\u002Felasticsearch-is-open-source-again",{"title":999,"url":1000},"OpenSearch docs: methods and engines","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fmappings\u002Fsupported-field-types\u002Fknn-methods-engines\u002F",{"title":1002,"url":1003},"OpenSearch docs: memory-optimized vectors","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fmappings\u002Fsupported-field-types\u002Fknn-memory-optimized\u002F",{"title":1005,"url":1006},"OpenSearch docs: reciprocal rank fusion","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fvector-search\u002Fai-search\u002Fhybrid-search\u002Frrf\u002F",{"title":1008,"url":1009},"OpenSearch docs: version history","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fversion-history\u002F",{"title":1011,"url":1012},"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],"Vektoros keresés Elasticsearchben és OpenSearchben: kNN, hibrid keresés és a licencek","Elasticsearch és OpenSearch vektortárként: kNN és szűrők, BBQ és bináris kvantálás, hibrid keresés RRF-fel, GPU-s indexépítés és a licenckérdés.","Elasticsearch és OpenSearch vektorkeresés: szekrény szöveges és vektoros fiókkal, egyetlen nagyító keres bennük.",{"slug":1020,"published":1021,"updated":741,"minutes":523,"category":8,"tags":1022,"tagPages":1025,"keywords":1026,"about":1036,"sources":1041,"cover":1075,"og":1076,"expertise":80,"locales":1077,"lang":84,"title":1078,"description":1079,"coverAlt":1080},"turbopuffer","2026-09-29",[1020,764,1023,1024,956],"Object storage","Pricing",[959],[1020,1027,1028,1029,1030,1031,1032,1033,1034,1035],"turbopuffer árak","vektorkeresés objektumtáron","serverless vektoradatbázis","turbopuffer vagy pinecone","turbopuffer namespace","spfresh vektorindex","turbopuffer hibrid keresés","lekérdezésalapú vektoradatbázis árazás","objektumtár vektoradatbázis",[1037,1038,1040],{"name":764,"url":765},{"name":1023,"url":1039},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FObject_storage",{"name":599,"url":600},[1042,1045,1048,1051,1054,1057,1060,1063,1066,1069,1072],{"title":1043,"url":1044},"turbopuffer blog: turbopuffer (updated Mar 2026)","https:\u002F\u002Fturbopuffer.com\u002Fblog\u002Fturbopuffer",{"title":1046,"url":1047},"turbopuffer blog: ANN v3 (Jan 2026)","https:\u002F\u002Fturbopuffer.com\u002Fblog\u002Fann-v3",{"title":1049,"url":1050},"SPFresh (SOSP 2023)","https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3600006.3613166",{"title":1052,"url":1053},"turbopuffer blog: native filtering","https:\u002F\u002Fturbopuffer.com\u002Fblog\u002Fnative-filtering",{"title":1055,"url":1056},"turbopuffer docs: hybrid search","https:\u002F\u002Fturbopuffer.com\u002Fdocs\u002Fhybrid",{"title":1058,"url":1059},"turbopuffer blog: native embedding (Sep 2026)","https:\u002F\u002Fturbopuffer.com\u002Fblog\u002Fnative-embedding",{"title":1061,"url":1062},"turbopuffer docs: architecture","https:\u002F\u002Fturbopuffer.com\u002Fdocs\u002Farchitecture",{"title":1064,"url":1065},"turbopuffer pricing","https:\u002F\u002Fturbopuffer.com\u002Fpricing",{"title":1067,"url":1068},"turbopuffer docs: limits","https:\u002F\u002Fturbopuffer.com\u002Fdocs\u002Flimits",{"title":1070,"url":1071},"turbopuffer v3 benchmarks","https:\u002F\u002Fturbopuffer.com\u002Fv3",{"title":1073,"url":1074},"Pinecone pricing","https:\u002F\u002Fwww.pinecone.io\u002Fpricing\u002F","\u002Fimages\u002Fblog\u002Fturbopuffer\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fturbopuffer\u002Fog.jpg",[82,83,84],"turbopuffer-ismertető: vektoros keresés objektumtáron, és egy lekérdezés ára","A turbopuffer bemutatása: objektumtár mint hiteles forrás, SPFresh és RaBitQ, hibrid keresés, GB-alapú árazás a Pinecone-nal szemben, és mikor éri meg.","turbopuffer-ismertető: lent egy nagy tárolóvödör, fölötte kis gyorsítótár-tálca, amely néhány kártyát felhúz.",{"slug":1082,"published":1021,"updated":412,"minutes":523,"category":8,"tags":1083,"tagPages":1086,"keywords":1087,"about":1098,"sources":1104,"cover":1141,"og":1142,"expertise":80,"locales":1143,"lang":84,"title":1144,"description":1145,"coverAlt":1146},"table-extraction-rag",[11,1084,1085,343,525],"Tables","Document parsing",[8,348],[1088,1089,1090,1091,1092,1093,1094,1095,1096,1097],"táblázatkinyerés rag-hez","táblázatok rag pipeline-okban","pdfplumber vs camelot","table transformer pubtables-1m","docling table mode tableformer","azure document intelligence táblázatok","teds metrika korlátai","markdown vs html táblázat llm-nek","text-to-sql táblázatkérdésekhez","llamaparse táblázatkinyerés",[1099,1100,1103],{"name":110,"url":111},{"name":1101,"url":1102},"Table (information)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FTable_%28information%29",{"name":433,"url":434},[1105,1108,1111,1114,1117,1120,1123,1126,1129,1132,1135,1138],{"title":1106,"url":1107},"Factorial study of parsers, chunkers and retrievers (arXiv 2609.31660)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.31660",{"title":1109,"url":1110},"pdfplumber on GitHub","https:\u002F\u002Fgithub.com\u002Fjsvine\u002Fpdfplumber",{"title":1112,"url":1113},"Camelot documentation","https:\u002F\u002Fcamelot-py.readthedocs.io\u002Fen\u002Flatest\u002F",{"title":1115,"url":1116},"Microsoft Table Transformer (archived)","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftable-transformer",{"title":1118,"url":1119},"PubTabNet and TEDS (arXiv 1911.10683)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.10683",{"title":1121,"url":1122},"Semantic evaluation of table extraction (arXiv 2603.18652)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.18652",{"title":1124,"url":1125},"TableFormer (arXiv 2203.01017)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.01017",{"title":1127,"url":1128},"Docling docs: advanced options","https:\u002F\u002Fdocling-project.github.io\u002Fdocling\u002Fusage\u002Fadvanced_options\u002F",{"title":1130,"url":1131},"Azure Document Intelligence: layout model","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fai-services\u002Fdocument-intelligence\u002Fprebuilt\u002Flayout",{"title":1133,"url":1134},"Table Meets LLM (WSDM 2024)","https:\u002F\u002Fzmy.io\u002Ffiles\u002Fwsdm24-SUC.pdf",{"title":1136,"url":1137},"TableRAG (arXiv 2410.04739)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.04739",{"title":1139,"url":1140},"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],"Táblázatkinyerés RAG-hoz: kinyerési rétegek, szerializálás és megbízható lekérdezések","Táblázatok RAG-ban: miért töri szét őket a darabolás, pdfplumber, Camelot, Docling és felhős kinyerők, mit nem lát a TEDS, szerializálás és SQL-irányítás.","Táblázatkinyerés RAG-hoz: egy oldalon lévő táblázatból különálló sorcsíkok lesznek, mindegyiken fejlécfüllel.",{"slug":1148,"published":1149,"updated":6,"minutes":523,"category":8,"tags":1150,"tagPages":1153,"keywords":1154,"about":1165,"sources":1171,"cover":1205,"og":1206,"expertise":80,"locales":1207,"lang":84,"title":1208,"description":1209,"coverAlt":1210},"embedding-fine-tuning-domain","2026-09-28",[10,1151,11,343,1152],"Fine-tuning","Sentence Transformers",[16,8,348],[1155,1156,1157,1158,1159,1160,1161,1162,1163,1164],"beágyazó modellek finomhangolása","domain adaptation beágyazások","hard negative mining visszakeresés","multiplenegativesrankingloss","gistembed vs mnrl","matryoshka beágyazás dimenziók","qwen3-embedding finomhangolás","bge-m3 vs embeddinggemma","beágyazás kiértékelés recall@k","katasztrofális felejtés dense retrieval",[1166,1167,1170],{"name":33,"url":34},{"name":1168,"url":1169},"Fine-tuning (deep learning)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FFine-tuning_%28deep_learning%29",{"name":36,"url":37},[1172,1175,1178,1181,1184,1187,1190,1191,1194,1197,1200,1202],{"title":1173,"url":1174},"Sentence Transformers: training overview","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fsentence_transformer\u002Ftraining_overview.html",{"title":1176,"url":1177},"Sentence Transformers: loss overview","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fsentence_transformer\u002Floss_overview.html",{"title":1179,"url":1180},"Sentence Transformers: hard negative mining","https:\u002F\u002Fsbert.net\u002Fdocs\u002Fpackage_reference\u002Futil\u002Fhard_negatives.html",{"title":1182,"url":1183},"RocketQA (arXiv 2010.08191)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.08191",{"title":1185,"url":1186},"InPars (arXiv 2202.05144)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.05144",{"title":1188,"url":1189},"Promptagator (arXiv 2209.11755)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.11755",{"title":869,"url":870},{"title":1192,"url":1193},"BAAI\u002Fbge-m3 model card","https:\u002F\u002Fhuggingface.co\u002FBAAI\u002Fbge-m3",{"title":1195,"url":1196},"Google: EmbeddingGemma docs (Oct 2026)","https:\u002F\u002Fai.google.dev\u002Fgemma\u002Fdocs\u002Fembeddinggemma",{"title":1198,"url":1199},"Sentence Transformers: Matryoshka embeddings","https:\u002F\u002Fsbert.net\u002Fexamples\u002Fsentence_transformer\u002Ftraining\u002Fmatryoshka\u002FREADME.html",{"title":1201,"url":44},"MMTEB (arXiv 2502.13595)",{"title":1203,"url":1204},"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],"Beágyazó modellek finomhangolása: nehéz negatívok, veszteségek és kiértékelés","Beágyazások finomhangolása: mikor jobb a rerankernél, tanítópárok, nehéz negatívok, veszteségek a sentence-transformers v6-ban, Matryoshka és költség.","Beágyazó modellek finomhangolása: a bal oldali laza pontokból tanítás után szoros csoportok lesznek jobbra.",{"slug":1212,"published":1149,"updated":741,"minutes":523,"category":8,"tags":1213,"tagPages":1217,"keywords":1218,"about":1229,"sources":1235,"cover":1266,"og":1267,"expertise":80,"locales":1268,"lang":84,"title":1269,"description":1270,"coverAlt":1271},"splade-learned-sparse-retrieval",[1214,1215,1216,956,954],"SPLADE","Sparse retrieval","BM25",[959],[1219,1220,1221,1222,1223,1224,1225,1226,1227,1228],"tanult ritka visszakeresés","splade","splade++ vs bm25","neurális ritka keresés","elasticsearch sparse_vector","elser","rank_features","opensearch neural sparse","tanult ritka visszakeresés indexméret","sentence-transformers sparse encoder",[1230,1231,1234],{"name":113,"url":114},{"name":1232,"url":1233},"Inverted index","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FInverted_index",{"name":907,"url":908},[1236,1239,1242,1245,1248,1251,1254,1257,1260,1263],{"title":1237,"url":1238},"naver\u002Fsplade on GitHub","https:\u002F\u002Fgithub.com\u002Fnaver\u002Fsplade",{"title":1240,"url":1241},"SPLADE++ (arXiv 2205.04733)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.04733",{"title":1243,"url":1244},"naver\u002Fsplade-v3 model card","https:\u002F\u002Fhuggingface.co\u002Fnaver\u002Fsplade-v3",{"title":1246,"url":1247},"Static pruning for learned sparse indexes (arXiv 2304.12702)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.12702",{"title":1249,"url":1250},"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":1252,"url":1253},"OpenSearch docs: sparse encoding processor","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fingest-pipelines\u002Fprocessors\u002Fsparse-encoding\u002F",{"title":1255,"url":1256},"Elastic docs: sparse_vector field type","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Fmapping-reference\u002Fsparse-vector",{"title":1258,"url":1259},"Elastic docs: ELSER","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fexplore-analyze\u002Fmachine-learning\u002Fnlp\u002Fml-nlp-elser",{"title":1261,"url":1262},"Elastic Search Labs: ELSER v2, part 2","https:\u002F\u002Fwww.elastic.co\u002Fsearch-labs\u002Fblog\u002Fintroducing-elser-v2-part-2",{"title":1264,"url":1265},"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 és tanult ritka visszakeresés a gyakorlatban: BM25, indexméret, késleltetés","Tanult ritka visszakeresés: hogyan bővít a SPLADE, a modellcsalád és licencei, indexméret és késleltetés, motortámogatás, és mikor jobb a BM25-nél.","SPLADE visszakeresés: szócsík sok vékony oszlopra bomlik, a kevés magas egy kartotékdobozt táplál.",{"slug":1273,"published":1274,"updated":1275,"minutes":523,"category":8,"tags":1276,"tagPages":1279,"keywords":1280,"about":1291,"sources":1299,"cover":1334,"og":1335,"expertise":80,"locales":1336,"lang":84,"title":1337,"description":1338,"coverAlt":1339},"knowledge-graph-extraction-llm","2026-09-25","2026-10-12",[675,674,1277,11,1278],"Entity resolution","Neo4j",[8],[1281,1282,1283,1284,1285,1286,1287,1288,1289,1290],"tudásgráf kinyerése llm-ekkel","graphrag indexelés","entitásfeloldás tudásgráf","hármas kinyerő prompt","ontológia tervezés llm kinyeréshez","entitás duplikáció szűrés beágyazásokkal","tudásgráf eredetkövetés","növekményes tudásgráf frissítés","graphrag költség","neo4j simplekgpipeline",[1292,1293,1296],{"name":625,"url":691},{"name":1294,"url":1295},"Record linkage","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FRecord_linkage",{"name":1297,"url":1298},"Ontology (information science)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOntology_%28information_science%29",[1300,1303,1306,1308,1311,1314,1317,1320,1323,1326,1329,1331],{"title":1301,"url":1302},"Microsoft GraphRAG: default dataflow","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fgraphrag\u002Fblob\u002Fmain\u002Fdocs\u002Findex\u002Fdefault_dataflow.md",{"title":1304,"url":1305},"Microsoft GraphRAG on GitHub","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fgraphrag",{"title":1307,"url":720},"Microsoft Research: LazyGraphRAG (Nov 2024)",{"title":1309,"url":1310},"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":1312,"url":1313},"neo4j-graphrag-python on GitHub","https:\u002F\u002Fgithub.com\u002Fneo4j\u002Fneo4j-graphrag-python",{"title":1315,"url":1316},"Neo4j GraphRAG: knowledge graph builder guide","https:\u002F\u002Fneo4j.com\u002Fdocs\u002Fneo4j-graphrag-python\u002Fcurrent\u002Fuser_guide_kg_builder.html",{"title":1318,"url":1319},"Splink on GitHub","https:\u002F\u002Fgithub.com\u002Fmoj-analytical-services\u002Fsplink",{"title":1321,"url":1322},"Google LangExtract on GitHub","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Flangextract",{"title":1324,"url":1325},"KGGen (arXiv 2502.09956)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.09956",{"title":1327,"url":1328},"GraphEval (arXiv 2407.10793)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.10793",{"title":1330,"url":662},"Zep temporal knowledge graph (arXiv 2501.13956)",{"title":1332,"url":1333},"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],"Tudásgráf kinyerése LLM-ekkel: ontológia, entitásfeloldás, eredet","Tudásgráf építése LLM-ekkel: minimális ontológia, kinyerő promptok, entitásfeloldás, eredetkövetés, növekményes frissítés, kiértékelés és tárolás.","Tudásgráf kinyerése LLM-ekkel: csomópontok lépnek ki egy lapkötegből, hálót alkotva, ahol két kör eggyé olvad.",{"slug":1341,"published":1274,"updated":6,"minutes":523,"category":8,"tags":1342,"tagPages":1346,"keywords":1347,"about":1358,"sources":1365,"cover":1399,"og":1400,"expertise":80,"locales":1401,"lang":84,"title":1402,"description":1403,"coverAlt":1404},"incremental-indexing-cdc",[11,1343,527,1344,1345],"Change data capture","Vector databases","Data freshness",[8],[1348,1349,1350,1351,1352,1353,1354,1355,1356,1357],"növekményes indexelés rag-hez","change data capture rag","debezium postgres logical decoding","újrabeágyazás költsége","blue\u002Fgreen indexcsere vektoradatbázis","index elavulás monitorozás","törlések vektorindexben","jogosultságváltozások rag indexben","qdrant aliasok","high water mark változásfelismerés",[1359,1361,1362],{"name":1343,"url":1360},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FChange_data_capture",{"name":110,"url":111},{"name":1363,"url":1364},"Blue–green deployment","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FBlue%E2%80%93green_deployment",[1366,1369,1372,1375,1378,1381,1384,1387,1390,1392,1395,1398],{"title":1367,"url":1368},"PostgreSQL docs: logical decoding concepts","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Flogicaldecoding-explanation.html",{"title":1370,"url":1371},"Debezium docs: PostgreSQL connector","https:\u002F\u002Fdebezium.io\u002Fdocumentation\u002Freference\u002Fstable\u002Fconnectors\u002Fpostgresql.html",{"title":1373,"url":1374},"PostgreSQL docs: CREATE PUBLICATION","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Fsql-createpublication.html",{"title":1376,"url":1377},"PostgreSQL docs: pg_replication_slots","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Fview-pg-replication-slots.html",{"title":1379,"url":1380},"Azure AI Search: changed and deleted blobs","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fsearch-howto-index-changed-deleted-blobs",{"title":1382,"url":1383},"Azure AI Search: scheduling indexers","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fsearch\u002Fsearch-howto-schedule-indexers",{"title":1385,"url":1386},"Qdrant docs: collections and aliases","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fconcepts\u002Fcollections\u002F",{"title":1388,"url":1389},"Elastic docs: aliases","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fmanage-data\u002Fdata-store\u002Faliases",{"title":1391,"url":186},"pgvector on GitHub",{"title":1393,"url":1394},"GDPR Article 17","https:\u002F\u002Fgdpr-info.eu\u002Fart-17-gdpr\u002F",{"title":1396,"url":1397},"OpenAI API pricing","https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fpricing",{"title":867,"url":62},"\u002Fimages\u002Fblog\u002Fincremental-indexing-cdc\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fincremental-indexing-cdc\u002Fog.jpg",[82,83,84],"A RAG-index frissen tartása: növekményes indexelés, CDC és blue\u002Fgreen újrabeágyazás","A RAG-index frissen tartása: elavulási keret, változáskövetés, CDC Postgresből Debeziummal, törlések, jogosultságok, blue\u002Fgreen csere és költség.","RAG-index frissen tartása: adatbázis változásokat továbbít egy szekrénybe, mellette egy második szekrény és egy kapcsoló.",{"slug":1406,"published":1407,"updated":1408,"minutes":7,"category":8,"tags":1409,"tagPages":1411,"keywords":1412,"about":1419,"sources":1424,"cover":1449,"og":1450,"expertise":80,"locales":1451,"lang":84,"title":1452,"description":1453,"coverAlt":1454},"lancedb","2026-09-21","2026-10-07",[13,956,1410,11],"Embedded database",[17,959,8],[1406,1413,1414,1415,1416,964,1417,1418],"lancedb teszt","lance vektoradatbázis","beágyazott vektoradatbázis","lancedb vagy qdrant","lancedb indexelés","lance adatformátum",[1420,1421],{"name":764,"url":765},{"name":1422,"url":1423},"Apache Arrow","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FApache_Arrow",[1425,1428,1431,1434,1437,1440,1443,1446],{"title":1426,"url":1427},"LanceDB quickstart","https:\u002F\u002Fdocs.lancedb.com\u002Fquickstart",{"title":1429,"url":1430},"LanceDB vector indexes","https:\u002F\u002Fdocs.lancedb.com\u002Findexing\u002Fvector-index",{"title":1432,"url":1433},"LanceDB indexing guide","https:\u002F\u002Fdocs.lancedb.com\u002Findexing\u002Findex",{"title":1435,"url":1436},"LanceDB hybrid search","https:\u002F\u002Fdocs.lancedb.com\u002Fsearch\u002Fhybrid-search",{"title":1438,"url":1439},"LanceDB Enterprise","https:\u002F\u002Fdocs.lancedb.com\u002Fenterprise",{"title":1441,"url":1442},"LanceDB frequently asked questions","https:\u002F\u002Fdocs.lancedb.com\u002Ffaq\u002Ffaq-oss",{"title":1444,"url":1445},"LanceDB pricing","https:\u002F\u002Flancedb.com\u002Fpricing",{"title":1447,"url":1448},"LanceDB on PyPI","https:\u002F\u002Fpypi.org\u002Fproject\u002Flancedb\u002F","\u002Fimages\u002Fblog\u002Flancedb\u002Fcover.webp","\u002Fimages\u002Fblog\u002Flancedb\u002Fog.jpg",[82,83,84],"LanceDB: vektoros keresés, amely könyvtárként indul","A LanceDB értékelése: beágyazott, Apache-2.0 vektorkönyvtár, IVF és HNSW indexek, hibrid keresés rangsoregyesítéssel, és mit ad az Enterprise.","LanceDB: egy nyitott könyvből golyókkal teli, szétválogatott polcok nyílnak ki.",{"slug":581,"published":1407,"updated":741,"minutes":90,"category":8,"tags":1456,"tagPages":1460,"keywords":1461,"about":1469,"sources":1473,"cover":1488,"og":1489,"expertise":80,"locales":1490,"lang":84,"title":1491,"description":1492,"coverAlt":1493},[13,1457,1458,11,1459],"Postgres","HNSW","Quantisation",[17,8],[581,1462,1463,1464,1465,1466,1467,1468],"pgvector teszt","pgvector vagy qdrant","postgres vektorkeresés","hnsw index postgres","iteratív indexszkennelés","bináris kvantálás postgres","vektoradatbázis postgres",[1470,1471],{"name":581,"url":186},{"name":527,"url":1472},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FPostgreSQL",[1474,1476,1479,1482,1485],{"title":1475,"url":186},"pgvector README",{"title":1477,"url":1478},"pgvector changelog","https:\u002F\u002Fgithub.com\u002Fpgvector\u002Fpgvector\u002Fblob\u002Fmaster\u002FCHANGELOG.md",{"title":1480,"url":1481},"PostgreSQL news: pgvector 0.8.2 released","https:\u002F\u002Fwww.postgresql.org\u002Fabout\u002Fnews\u002Fpgvector-082-released-3245\u002F",{"title":1483,"url":1484},"AWS: Scale pgvector with binary quantization","https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fdatabase\u002Fscale-pgvector-with-binary-quantization-on-amazon-aurora-postgresql\u002F",{"title":1486,"url":1487},"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, értékelés: az a vektordatázis, amelyet nem kell üzemeltetned","pgvector 0.8.7: iteratív szűrt keresés, HNSW és IVFFlat, bináris kvantálás 100 millió vektornál, és a CVE, ami javítandóvá tette az indexépítést.","pgvector értékelés: egy elefánt kis fiókos szekrényt visz a hátán, benne szétválogatott golyók.",{"slug":1495,"published":1496,"updated":741,"minutes":90,"category":8,"tags":1497,"tagPages":1499,"keywords":1500,"about":1507,"sources":1511,"cover":1539,"og":1540,"expertise":80,"locales":1541,"lang":84,"title":1542,"description":1543,"coverAlt":1544},"mem0","2026-09-17",[624,1498,11,13],"Long-term memory",[8,17],[1495,1501,1502,1503,1504,1505,1506],"mem0 teszt","ügynök memória réteg","mem0 saját szerveren","mem0 árak","hosszú távú memória ügynökökhöz","mem0 alternatíva",[1508],{"name":1509,"url":1510},"Mem0","https:\u002F\u002Fmem0.ai",[1512,1515,1518,1521,1524,1527,1530,1533,1536],{"title":1513,"url":1514},"Mem0 documentation","https:\u002F\u002Fdocs.mem0.ai\u002Fintroduction",{"title":1516,"url":1517},"Mem0 quickstart","https:\u002F\u002Fdocs.mem0.ai\u002Fquickstart",{"title":1519,"url":1520},"How Mem0 works","https:\u002F\u002Fdocs.mem0.ai\u002Fcore-concepts\u002Fhow-it-works",{"title":1522,"url":1523},"Mem0 pricing","https:\u002F\u002Fmem0.ai\u002Fpricing",{"title":1525,"url":1526},"Mem0 on GitHub","https:\u002F\u002Fgithub.com\u002Fmem0ai\u002Fmem0",{"title":1528,"url":1529},"mem0ai on PyPI","https:\u002F\u002Fpypi.org\u002Fproject\u002Fmem0ai\u002F",{"title":1531,"url":1532},"Mem0 research and benchmarks","https:\u002F\u002Fmem0.ai\u002Fresearch",{"title":1534,"url":1535},"Mem0 MCP server","https:\u002F\u002Fdocs.mem0.ai\u002Fplatform\u002Fmem0-mcp",{"title":1537,"url":1538},"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: mennyibe kerül egy ügynökmemória körönként","A Mem0 elemzése: körönként kinyert tények, a 2026. áprilisi benchmark-tábla platformos fenntartása, négy felhőcsomag és az önhosztolásból kimaradók.","Mem0 költsége körönként: egy robot jegyzetel egy parkolóóra mellett, mögötte cetlik sora.",{"slug":1546,"published":1547,"updated":1548,"minutes":90,"category":8,"tags":1549,"tagPages":1552,"keywords":1553,"about":1562,"sources":1570,"cover":1589,"og":1590,"expertise":80,"locales":1591,"lang":84,"title":1592,"description":1593,"coverAlt":1594},"milvus-zilliz","2026-09-08","2026-09-20",[13,956,1550,1551,11],"BM25 full text","Distributed",[17,959,8],[1554,1555,1556,1557,1558,1559,1560,1561],"milvus","milvus vagy qdrant","zilliz cloud árak","vektoradatbázis összehasonlítás","milvus hibrid keresés","apache milvus saját szerveren","milvus 3.0 teszt","rag vektortár",[1563,1566,1569],{"name":1564,"url":1565},"Milvus","https:\u002F\u002Fmilvus.io",{"name":1567,"url":1568},"Zilliz Cloud","https:\u002F\u002Fzilliz.com",{"name":110,"url":111},[1571,1574,1577,1580,1583,1586],{"title":1572,"url":1573},"Milvus architecture overview","https:\u002F\u002Fmilvus.io\u002Fdocs\u002Farchitecture_overview.md",{"title":1575,"url":1576},"Milvus release notes","https:\u002F\u002Fmilvus.io\u002Fdocs\u002Frelease_notes.md",{"title":1578,"url":1579},"Milvus releases on GitHub","https:\u002F\u002Fgithub.com\u002Fmilvus-io\u002Fmilvus\u002Freleases",{"title":1581,"url":1582},"Milvus README: features and licence","https:\u002F\u002Fgithub.com\u002Fmilvus-io\u002Fmilvus",{"title":1584,"url":1585},"Zilliz Cloud pricing","https:\u002F\u002Fzilliz.com\u002Fpricing",{"title":1587,"url":1588},"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 elemzés: a legteljesebb vektordatbázis üzemeltetve","Milvus 3.0.2: a legteljesebb nyílt forráskódú vektoradatbázis és a legnehezebben üzemeltethető. Architektúra, hibrid keresés, költségek és korlátok.","Milvus és Zilliz: magas polcos raktár targoncával, egy dolgozó csavarkulccsal a vezérlőpultnál.",{"slug":1596,"published":1547,"updated":671,"minutes":90,"category":8,"tags":1597,"tagPages":1601,"keywords":1602,"about":1609,"sources":1613,"cover":1628,"og":1629,"expertise":80,"locales":1630,"lang":84,"title":1631,"description":1632,"coverAlt":1633},"graphrag",[625,11,1598,1599,1600],"Global search","Community summaries","Token cost",[8],[1596,1603,1604,1605,1606,1607,680,1608],"microsoft graphrag","graphrag vagy vektoros rag","graphrag indexelési költség","graphrag lekérdezési módok","graphrag vs lightrag összehasonlítás","graphrag dinamikus közösségválasztás",[1610,1612],{"name":674,"url":1611},"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fgraphrag\u002F",{"name":110,"url":111},[1614,1616,1618,1620,1623,1625],{"title":1615,"url":1305},"GraphRAG on GitHub",{"title":1617,"url":702},"GraphRAG documentation",{"title":1619,"url":699},"From Local to Global: A Graph RAG Approach to Query-Focused Summarization",{"title":1621,"url":1622},"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":1624,"url":720},"LazyGraphRAG: Setting a new standard for quality and cost",{"title":1626,"url":1627},"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: tudásgráfos RAG, előre kifizetve","A Microsoft GraphRAG 3.2.0 tesztje: MIT, karbantartási mód és egy indexelési számla, amely az első lekérdezés előtt eldől.","Microsoft GraphRAG: parafatábla fonalakkal összekötött kártyákkal, a sarkán árcédula.",{"slug":1635,"published":1636,"updated":1637,"minutes":90,"category":8,"tags":1638,"tagPages":1644,"keywords":1646,"about":1653,"sources":1657,"cover":1679,"og":1680,"expertise":80,"locales":1681,"lang":84,"title":1682,"description":1683,"coverAlt":1684},"firecrawl","2026-08-25","2026-09-04",[1639,1640,1641,1642,1643],"Web scraping","RAG ingestion","Crawling","MCP","AGPL",[1645],"mcp",[1635,1647,1648,1649,1650,1651,1652],"firecrawl vs apify összehasonlítás","firecrawl alternatíva","web scraping api llm-hez","firecrawl saját szerveren","markdown scraper api","webkúszó api rag pipeline-okhoz",[1654],{"name":1655,"url":1656},"Firecrawl","https:\u002F\u002Fgithub.com\u002Ffirecrawl\u002Ffirecrawl",[1658,1661,1664,1667,1670,1673,1676],{"title":1659,"url":1660},"Firecrawl pricing","https:\u002F\u002Fwww.firecrawl.dev\u002Fpricing",{"title":1662,"url":1663},"Firecrawl crawl documentation","https:\u002F\u002Fdocs.firecrawl.dev\u002Ffeatures\u002Fcrawl",{"title":1665,"url":1666},"Firecrawl self-hosting guide","https:\u002F\u002Fdocs.firecrawl.dev\u002Fcontributing\u002Fself-host",{"title":1668,"url":1669},"Open source or Firecrawl Cloud","https:\u002F\u002Fdocs.firecrawl.dev\u002Fcontributing\u002Fopen-source-or-cloud",{"title":1671,"url":1672},"Firecrawl benchmarks","https:\u002F\u002Fwww.firecrawl.dev\u002Fbenchmarks",{"title":1674,"url":1675},"Apify pricing","https:\u002F\u002Fapify.com\u002Fpricing",{"title":1677,"url":1678},"Browserbase pricing","https:\u002F\u002Fwww.browserbase.com\u002Fpricing","\u002Fimages\u002Fblog\u002Ffirecrawl\u002Fcover.webp","\u002Fimages\u002Fblog\u002Ffirecrawl\u002Fog.jpg",[82,83,84],"Firecrawl: webkúszó API RAG pipeline-okhoz, értékeléssel","A Firecrawl hosztolt API-val URL-ekből tiszta Markdownt készít. Mennyibe kerül, hol hibázik a crawl-számlázás, és mikor érdemes saját AGPL-magot futtatni.","Firecrawl webkúszó: pók ül egy böngészőablakra szőtt hálón, és rendezett lapokat ejt egy kosárba.",{"slug":1686,"published":1687,"updated":1496,"minutes":672,"category":8,"tags":1688,"tagPages":1692,"keywords":1693,"about":1704,"sources":1710,"cover":1749,"og":1750,"expertise":267,"locales":1751,"lang":84,"title":1752,"description":1753,"coverAlt":1754},"semantic-product-search-b2b","2026-08-21",[1689,956,1690,1691,955],"B2B search","Semantic search","Spryker",[959],[1694,1695,1696,1697,1698,1699,1700,1701,1702,1703],"szemantikus termékkeresés b2b","b2b webshop keresés","bm25 és vektor hibrid keresés","cikkszámos keresés webshop","spryker keresés elasticsearch","opensearch hibrid keresés rrf","többnyelvű termékkeresés német angol magyar","nulla találatos arány oldalkeresés","llm lekérdezés-értelmezés webshop","ai termékkeresés b2b webshopokban",[1705,1707,1708],{"name":1690,"url":1706},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FSemantic_search",{"name":954,"url":973},{"name":955,"url":1709},"https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOpenSearch",[1711,1714,1717,1720,1723,1726,1729,1732,1735,1738,1741,1744,1746],{"title":1712,"url":1713},"Baymard Institute: E-commerce search query types","https:\u002F\u002Fbaymard.com\u002Fblog\u002Fecommerce-search-query-types",{"title":1715,"url":1716},"Elastic Search Labs: Hybrid search in Elasticsearch","https:\u002F\u002Fwww.elastic.co\u002Fsearch-labs\u002Fblog\u002Fhybrid-search-elasticsearch",{"title":1718,"url":1719},"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":1721,"url":1722},"Elasticsearch documentation: Semantic reranking","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Fsolutions\u002Fsearch\u002Franking\u002Fsemantic-reranking",{"title":1724,"url":1725},"Elasticsearch documentation: Word delimiter graph token filter","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Ftext-analysis\u002Fanalysis-word-delimiter-graph-tokenfilter",{"title":1727,"url":1728},"Elasticsearch documentation: Synonym graph token filter","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Ftext-analysis\u002Fanalysis-synonym-graph-tokenfilter",{"title":1730,"url":1731},"OpenSearch documentation: Score ranker processor (RRF)","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fsearch-plugins\u002Fsearch-pipelines\u002Fscore-ranker-processor\u002F",{"title":1733,"url":1734},"OpenSearch documentation: Normalization processor","https:\u002F\u002Fdocs.opensearch.org\u002Flatest\u002Fsearch-plugins\u002Fsearch-pipelines\u002Fnormalization-processor\u002F",{"title":1736,"url":1737},"Spryker documentation: Search feature overview","https:\u002F\u002Fdocs.spryker.com\u002Fdocs\u002Fpbc\u002Fall\u002Fsearch\u002Flatest\u002Fbase-shop\u002Fsearch-feature-overview\u002Fsearch-feature-overview",{"title":1739,"url":1740},"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":1742,"url":1743},"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":1745,"url":499},"arXiv: M3-Embedding, multilingual, multi-functionality, multi-granularity text embeddings",{"title":1747,"url":1748},"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],"Szemantikus termékkeresés B2B webshopokban: cikkszámok, hibrid keresés és amit mérned kell","Szemantikus keresés B2B shopban cikkszámos keresés sérülése nélkül: BM25 és vektorok hibridje, szűrők, DE\u002FEN\u002FHU, LLM-es lekérdezés, reranking, metrikák.","Szemantikus termékkeresés B2B webshopokban: nagyító lebeg egy csavaros rekesz fölött egy vasbolti polcon.",{"slug":1756,"published":1757,"updated":1758,"minutes":672,"category":8,"tags":1759,"tagPages":1764,"keywords":1765,"about":1776,"sources":1784,"cover":1824,"og":1825,"expertise":80,"locales":1826,"lang":84,"title":1827,"description":1828,"coverAlt":1829},"llm-hallucination-grounding-citations","2026-08-20","2026-09-01",[1760,11,1761,1762,1763],"Hallucinations","Citations","Grounding","Faithfulness",[8],[1766,1767,1768,1769,1770,1771,1772,1773,1774,1775],"llm hallucinációk csökkentése éles rendszerben","hogyan csökkentsük a hallucinációt rag-ben","llm citations api","anthropic citations api","rag hűségmetrika","llm tartózkodás nem tudom válasz","állításszintű ellenőrzés llm","llm válaszok megalapozása forrásokban","grounding ellenőrző api","források megjelenítése ai chatbot felületen",[1777,1780,1781],{"name":1778,"url":1779},"Hallucination (artificial intelligence)","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FHallucination_(artificial_intelligence)",{"name":110,"url":111},{"name":1782,"url":1783},"Large language model","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FLarge_language_model",[1785,1788,1791,1794,1797,1800,1803,1806,1809,1812,1815,1818,1821],{"title":1786,"url":1787},"Anthropic: Citations (Claude API documentation)","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fbuild-with-claude\u002Fcitations",{"title":1789,"url":1790},"Anthropic: Search results (Claude API documentation)","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fbuild-with-claude\u002Fsearch-results",{"title":1792,"url":1793},"Anthropic: Reduce hallucinations (Claude API documentation)","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Ftest-and-evaluate\u002Fstrengthen-guardrails\u002Freduce-hallucinations",{"title":1795,"url":1796},"Anthropic: Introducing Citations on the Anthropic API","https:\u002F\u002Fclaude.com\u002Fblog\u002Fintroducing-citations-api",{"title":1798,"url":1799},"Simon Willison: Anthropic's new Citations API (24 January 2025)","https:\u002F\u002Fsimonwillison.net\u002F2025\u002FJan\u002F24\u002Fanthropics-new-citations-api\u002F",{"title":1801,"url":1802},"OpenAI: Web search guide (url_citation annotations and display requirement)","https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fguides\u002Ftools-web-search",{"title":1804,"url":1805},"Cohere: Documents and citations","https:\u002F\u002Fdocs.cohere.com\u002Fdocs\u002Fdocuments-and-citations",{"title":1807,"url":1808},"Google Cloud: Check grounding API","https:\u002F\u002Fdocs.cloud.google.com\u002Fgenerative-ai-app-builder\u002Fdocs\u002Fcheck-grounding",{"title":1810,"url":1811},"AWS: Amazon Bedrock Guardrails contextual grounding check","https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fguardrails-contextual-grounding-check.html",{"title":1813,"url":1814},"Ragas: Faithfulness metric","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fconcepts\u002Fmetrics\u002Favailable_metrics\u002Ffaithfulness\u002F",{"title":1816,"url":1817},"Kalai, Nachum, Vempala, Zhang: Why Language Models Hallucinate (arXiv 2509.04664)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.04664",{"title":1819,"url":1820},"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":1822,"url":1823},"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-hallucinációk csökkentése éles rendszerben: grounding, hivatkozások és a nemet mondás tudománya","Hallucinációk csökkentése éles RAG-ban: hivatkozás-API-k, tartózkodás, állításszintű ellenőrzés, faithfulness-mérés, forrás-UI és ami mégis átcsúszik.","LLM-hallucinációk csökkentése: hőlégballont kötelek rögzítenek egy könyvkupachoz.",{"slug":1831,"published":1832,"updated":1833,"minutes":523,"category":8,"tags":1834,"tagPages":1837,"keywords":1838,"about":1847,"sources":1851,"cover":1868,"og":1869,"expertise":80,"locales":1870,"lang":84,"title":1871,"description":1872,"coverAlt":1873},"rag-2026-hybrid-agentic-long-context","2026-07-30","2026-09-22",[11,1835,1836,956,93],"Long context","Agentic search",[8,959],[1839,1840,1841,1842,1843,1844,1845,1846],"rag 2026-ban","hosszú kontextus vs rag","agentikus rag","hibrid keresés","contextual retrieval rag 2026","meghalt a rag","ügynöki keresés vs vektorkeresés","rag vs 1 millió tokenes kontextablak",[1848,1849,1850],{"name":110,"url":111},{"name":1782,"url":1783},{"name":113,"url":114},[1852,1854,1857,1860,1862,1865],{"title":1853,"url":121},"Anthropic: Introducing Contextual Retrieval",{"title":1855,"url":1856},"Chroma: Context Rot","https:\u002F\u002Fwww.trychroma.com\u002Fresearch\u002Fcontext-rot",{"title":1858,"url":1859},"Liu et al., Lost in the Middle (2023)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03172",{"title":1861,"url":139},"Claude docs: Pricing",{"title":1863,"url":1864},"Claude docs: Models overview","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fabout-claude\u002Fmodels\u002Foverview",{"title":1866,"url":1867},"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 2026-ban: hibrid retrieval, ügynöki keresés vagy egymillió tokenes kontextus?","RAG 2026-ban: mikor nyer a hibrid keresés, mikor illik az ügynöki keresés, és mit ér az egymillió tokenes kontextus kérésenként.","RAG 2026-ban: egy ember három út közül választ: könyvespolc, zseblámpás robot és hosszú tekercs.",{"slug":1875,"published":1876,"updated":1832,"minutes":90,"category":8,"tags":1877,"tagPages":1878,"keywords":1879,"about":1889,"sources":1893,"cover":1922,"og":1923,"expertise":80,"locales":1924,"lang":84,"title":1925,"description":1926,"coverAlt":1927},"rag-pipeline-chunking-hybrid-search-reranking","2026-07-24",[11,956,92,887,581],[8,959],[1880,1881,1882,1883,1884,1885,1886,1887,1888],"rag pipeline","visszakereséssel bővített generálás pipeline","chunkelési stratégia rag-hez","hibrid keresés bm25 vektor","reciprocal rank fusion","cross-encoder újrarangsorolás","pgvector hibrid keresés","rag minőségmérés","hogyan építsünk rag pipeline-t",[1890,1891,1892],{"name":110,"url":111},{"name":113,"url":114},{"name":581,"url":186},[1894,1897,1900,1903,1904,1907,1910,1913,1914,1917,1918,1920],{"title":1895,"url":1896},"Lewis et al., Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11401",{"title":1898,"url":1899},"Cormack, Clarke and Büttcher, Reciprocal Rank Fusion (SIGIR 2009)","https:\u002F\u002Fcormack.uwaterloo.ca\u002Fcormacksigir09-rrf.pdf",{"title":1901,"url":1902},"Malkov and Yashunin, HNSW graphs","https:\u002F\u002Farxiv.org\u002Fabs\u002F1603.09320",{"title":1475,"url":186},{"title":1905,"url":1906},"Elasticsearch: similarity settings","https:\u002F\u002Fwww.elastic.co\u002Fdocs\u002Freference\u002Felasticsearch\u002Findex-settings\u002Fsimilarity",{"title":1908,"url":1909},"PostgreSQL: controlling text search","https:\u002F\u002Fwww.postgresql.org\u002Fdocs\u002Fcurrent\u002Ftextsearch-controls.html",{"title":1911,"url":1912},"Chroma: Evaluating Chunking Strategies for Retrieval","https:\u002F\u002Fwww.trychroma.com\u002Fresearch\u002Fevaluating-chunking",{"title":1853,"url":121},{"title":1915,"url":1916},"Sentence Transformers: Cross-Encoders","https:\u002F\u002Fsbert.net\u002Fexamples\u002Fcross_encoder\u002Fapplications\u002FREADME.html",{"title":1858,"url":1859},{"title":1919,"url":1787},"Claude docs: Citations",{"title":1921,"url":1814},"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],"Termelési RAG pipeline lépésről lépésre: chunkelés, hibrid keresés, újrarangsorolás","Építs RAG pipeline-t lépésről lépésre: parse, chunkelés, pgvector, BM25 plusz vektorok RRF-fel, újrarangsorolás, hivatkozások és retrieval evalek.","Termelési RAG pipeline: egy kenyeret felszeletelnek, a szeletek szitán át rendezett sorban kerülnek a tányérra.",{"slug":1929,"published":1930,"minutes":90,"category":8,"tags":1931,"tagPages":1933,"keywords":1934,"about":1942,"sources":1949,"cover":1977,"og":1978,"expertise":80,"locales":1979,"lang":84,"title":1980,"description":1981,"coverAlt":1982},"chroma","2026-07-20",[13,10,11,956,1932],"Metadata filter",[17,16,8,959],[1935,1936,1937,1938,1939,1940,1941],"chroma vektoradatbázis","chroma vs qdrant összehasonlítás","chroma vagy pgvector","hibrid keresés reciprocal rank fusion","saját szerveren futó vektoradatbázis","chroma cloud árak","metaadat szűrés vektorkeresés",[1943,1946],{"name":1944,"url":1945},"Chroma","https:\u002F\u002Fgithub.com\u002Fchroma-core\u002Fchroma",{"name":1947,"url":1948},"Apache License 2.0","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FApache_License",[1950,1953,1956,1959,1962,1965,1968,1971,1974],{"title":1951,"url":1952},"Chroma documentation: introduction","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Foverview\u002Fintroduction",{"title":1954,"url":1955},"Chroma architecture overview","https:\u002F\u002Fdocs.trychroma.com\u002Freference\u002Farchitecture\u002Foverview",{"title":1957,"url":1958},"Chroma: getting started with the SDK","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Foverview\u002Fgetting-started",{"title":1960,"url":1961},"Chroma: query and get","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Fquerying-collections\u002Fquery-and-get",{"title":1963,"url":1964},"Chroma: metadata filtering","https:\u002F\u002Fdocs.trychroma.com\u002Fdocs\u002Fquerying-collections\u002Fmetadata-filtering",{"title":1966,"url":1967},"Chroma Cloud: Search API overview","https:\u002F\u002Fdocs.trychroma.com\u002Fcloud\u002Fsearch-api\u002Foverview",{"title":1969,"url":1970},"Chroma Cloud: hybrid search with RRF","https:\u002F\u002Fdocs.trychroma.com\u002Fcloud\u002Fsearch-api\u002Fhybrid-search",{"title":1972,"url":1973},"Chroma Cloud: pricing","https:\u002F\u002Fwww.trychroma.com\u002Fpricing",{"title":1975,"url":1976},"Chroma changelog","https:\u002F\u002Fwww.trychroma.com\u002Fchangelog","\u002Fimages\u002Fblog\u002Fchroma\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fchroma\u002Fog.jpg",[82,83,84],"Chroma: egyszerű vektorkeresés egy bökkenővel","A Chroma Apache-2.0 vektoradatbázis, beágyazva, egy csomóponton vagy Chroma Cloudként. Hol kényelmes, és hol érnek véget a jó keresési funkciók a felhőnél?","Chroma vektorkeresés: fiókos szekrény szétválogatott golyókkal, a tetején egy repedt kavics.",{"slug":1984,"published":1985,"minutes":622,"category":8,"tags":1986,"tagPages":1988,"keywords":1989,"about":1998,"sources":2002,"cover":2026,"og":2027,"expertise":80,"locales":2028,"lang":84,"title":2029,"description":2030,"coverAlt":2031},"pinecone","2026-07-09",[13,10,11,1987,956],"Namespaces",[17,16,8,959],[1984,1990,1991,1992,1993,1994,1995,1996,1997],"pinecone vektoradatbázis","pinecone árak","pinecone read unit","pinecone namespace","pinecone vagy qdrant","pinecone vagy pgvector","pinecone documents api","serverless vektoradatbázis költség",[1999,2000,2001],{"name":764,"url":765},{"name":599,"url":600},{"name":113,"url":114},[2003,2006,2009,2012,2015,2017,2020,2023],{"title":2004,"url":2005},"Pinecone docs: Index data overview, indexes, namespaces and metadata","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Findexing-overview",{"title":2007,"url":2008},"Pinecone docs: Adopt the Documents API, API version 2026-07","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Fadopt-the-documents-api",{"title":2010,"url":2011},"Pinecone docs: Create an index, schemas, regions and metrics","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Findex-data\u002Fcreate-an-index",{"title":2013,"url":2014},"Pinecone docs: Understanding Pinecone cost, read units, write units and egress","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Forganizations\u002Fmanage-cost\u002Funderstanding-cost",{"title":2016,"url":1074},"Pinecone pricing: plans, limits and rates",{"title":2018,"url":2019},"Pinecone docs: Semantic search","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Fsearch\u002Fsemantic-search",{"title":2021,"url":2022},"Pinecone docs: Local development with Pinecone Local","https:\u002F\u002Fdocs.pinecone.io\u002Fguides\u002Foperations\u002Flocal-development",{"title":2024,"url":2025},"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: értékelés a menedzselt vektordatabázisról","Mennyibe kerül valójában a Pinecone: a read unit a namespace méretével nő, a sémát utólag nem lehet módosítani, és hol éri meg saját vektoradatbázis.","Pinecone értékelés: fenyőtoboz egy felhőn golyókat tart a pikkelyei között, alatta kulcs.",{"slug":2033,"published":2034,"updated":741,"minutes":672,"category":8,"tags":2035,"tagPages":2037,"keywords":2038,"about":2049,"sources":2053,"cover":2099,"og":2100,"expertise":80,"locales":2101,"lang":84,"title":2102,"description":2103,"coverAlt":2104},"pgvector-vs-vector-databases","2026-06-15",[581,1344,11,956,2036],"EU hosting",[8,959],[2039,2040,2041,2042,2043,2044,2045,2046,2047,2048],"pgvector vagy vektoradatbázis","pgvector vs qdrant összehasonlítás","pgvector vagy pinecone","legjobb vektoradatbázis 2026","pgvector hnsw iteratív keresés","pgvector halfvec típus","opensearch vs elasticsearch vektorkeresés","vektoradatbázis eu tárhely","hibrid keresés postgres","weaviate vs milvus",[2050,2051,2052],{"name":764,"url":765},{"name":527,"url":1472},{"name":110,"url":111},[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":1478},"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":260,"url":261},{"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":2011},"Pinecone documentation: Create an index (clouds, regions, sparse and hybrid)",{"title":2087,"url":1000},"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":1719},"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 vagy vektoradatbázis? Így válassz vektortárolót 2026-ban","pgvector, Qdrant, Weaviate, Milvus, Pinecone, OpenSearch vagy Elasticsearch? 2026-os útmutató: szűrés, hibrid keresés, skálázás, költség és EU-s hosztolás.","pgvector vagy vektoradatbázis: egy ember az elágazásnál választ egy fiókos elefánt és egy magas raktár között.",{"slug":2106,"published":2107,"updated":1408,"minutes":90,"category":8,"tags":2108,"tagPages":2109,"keywords":2110,"about":2120,"sources":2129,"cover":2152,"og":2153,"expertise":80,"locales":2154,"lang":84,"title":2155,"description":2156,"coverAlt":2157},"weaviate","2026-06-02",[13,956,1458,580,154],[17,959],[2111,2112,2113,2114,2115,2116,2117,2118,2119],"weaviate vektoradatbázis","weaviate vagy qdrant","weaviate vagy pinecone","weaviate vagy pgvector","hnsw vs hfresh","weaviate cloud árak","vektoradatbázis választás","weaviate hibrid keresés","weaviate teszt",[2121,2124,2126],{"name":2122,"url":2123},"Weaviate","https:\u002F\u002Fgithub.com\u002Fweaviate\u002Fweaviate",{"name":2125,"url":600},"Hierarchical Navigable Small World",{"name":2127,"url":2128},"SPFresh","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2410.14452",[2130,2132,2135,2138,2141,2144,2146,2149],{"title":2131,"url":2074},"Weaviate documentation: Vector indexing",{"title":2133,"url":2134},"Weaviate documentation: ANN benchmark","https:\u002F\u002Fdocs.weaviate.io\u002Fweaviate\u002Fbenchmarks\u002Fann",{"title":2136,"url":2137},"Weaviate 1.39 release notes","https:\u002F\u002Fweaviate.io\u002Fblog\u002Fweaviate-1-39-release",{"title":2139,"url":2140},"Weaviate 1.38 release notes","https:\u002F\u002Fweaviate.io\u002Fblog\u002Fweaviate-1-38-release",{"title":2142,"url":2143},"Weaviate documentation: MCP server","https:\u002F\u002Fdocs.weaviate.io\u002Fweaviate\u002Fconfiguration\u002Fmcp-server",{"title":2145,"url":2077},"Weaviate Cloud pricing",{"title":2147,"url":2148},"weaviate\u002Fweaviate: LICENSE","https:\u002F\u002Fgithub.com\u002Fweaviate\u002Fweaviate\u002Fblob\u002Fmain\u002FLICENSE",{"title":2150,"url":2151},"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: egy vektordatabázis, amelynek a keresésben kell nyernie, nem csak a hasonlóságban","Weaviate-teszt: hibrid BM25- és vektorkeresés egy hívásban, HNSW és lemezes HFresh index, kvantálás, beépített MCP-szerver, és mi kerül licenckulcs mögé.","Weaviate: egy mágnes és egy nagyító keresztezi egymást egy golyókupac fölött.",{"slug":2159,"published":2160,"updated":2161,"minutes":90,"category":8,"tags":2162,"tagPages":2164,"keywords":2165,"about":2173,"sources":2177,"cover":2214,"og":2215,"expertise":80,"locales":2216,"lang":84,"title":2217,"description":2218,"coverAlt":2219},"qdrant","2026-05-26","2026-10-05",[13,1458,1459,956,2163],"Filtering",[17,959],[2159,2166,2167,2168,2169,2170,2171,2172],"qdrant vagy pinecone","vektoradatbázisok összehasonlítása","hnsw index","szűrt vektorkeresés","vektor kvantálás","qdrant hibrid keresés","qdrant teszt",[2174,2175,2176],{"name":764,"url":765},{"name":599,"url":600},{"name":110,"url":111},[2178,2181,2184,2186,2189,2192,2195,2198,2200,2202,2205,2208,2211],{"title":2179,"url":2180},"Qdrant documentation","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002F",{"title":2182,"url":2183},"Qdrant: points","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fmanage-data\u002Fpoints\u002F",{"title":2185,"url":1386},"Qdrant: collections",{"title":2187,"url":2188},"Qdrant: indexing","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F",{"title":2190,"url":2191},"Qdrant: quantisation","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F",{"title":2193,"url":2194},"Qdrant: capacity planning","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fcapacity-planning\u002F",{"title":2196,"url":2197},"Qdrant: optimise performance","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fops-optimization\u002Foptimize\u002F",{"title":2199,"url":2065},"Qdrant: hybrid and multi-stage queries",{"title":2201,"url":261},"Qdrant: filtering",{"title":2203,"url":2204},"Qdrant: security and access control","https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fsecurity\u002F",{"title":2206,"url":2207},"Qdrant pricing","https:\u002F\u002Fqdrant.tech\u002Fpricing\u002F",{"title":2209,"url":2210},"Qdrant on GitHub","https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant",{"title":2212,"url":2213},"Qdrant vector search benchmarks","https:\u002F\u002Fqdrant.tech\u002Fbenchmarks\u002F","\u002Fimages\u002Fblog\u002Fqdrant\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fqdrant\u002Fog.jpg",[82,83,84],"Qdrant: egy szűrés körül felépített vektordatabázis","Qdrant értékelés: szűrhető HNSW, négy kvantálási mód, a memória-szintek az 1.19-ben és az üzemeltetés, amit már senki nem publikál.","Qdrant vektordatabázis: többrétegű szita golyókat válogat egy tálba.",{"slug":2221,"published":2222,"minutes":622,"category":8,"tags":2223,"tagPages":2226,"keywords":2227,"about":2236,"sources":2240,"cover":2259,"og":2260,"expertise":80,"locales":2261,"lang":84,"title":2262,"description":2263,"coverAlt":2264},"unstructured","2026-05-21",[1085,1640,2224,92,2225],"PDF extraction","ETL",[],[2228,2229,2230,2231,2232,2233,2234,2235],"unstructured.io","unstructured python könyvtár","unstructured vagy llamaparse","dokumentum feldolgozás rag-hez","pdf particionálás hi_res","unstructured árak","chunkelés cím szerint","dokumentum betöltési pipeline",[2237],{"name":2238,"url":2239},"Unstructured","https:\u002F\u002Funstructured.io\u002F",[2241,2244,2247,2250,2253,2256],{"title":2242,"url":2243},"Unstructured documentation: pipelines overview","https:\u002F\u002Fdocs.unstructured.io\u002Fwelcome",{"title":2245,"url":2246},"Unstructured documentation: transform quickstart","https:\u002F\u002Fdocs.unstructured.io\u002Fapi-reference\u002Ftransform\u002Fquickstart\u002Foverview",{"title":2248,"url":2249},"Unstructured pricing: free pages, rate per page and plans","https:\u002F\u002Funstructured.io\u002Fpricing",{"title":2251,"url":2252},"Unstructured benchmarks: 1,000+ enterprise pages against other parsers","https:\u002F\u002Funstructured.io\u002Fbenchmarks",{"title":2254,"url":2255},"Unstructured library on GitHub","https:\u002F\u002Fgithub.com\u002FUnstructured-IO\u002Funstructured",{"title":2257,"url":2258},"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 ismertető: dokumentumok feldolgozása RAG-hez","Az Unstructured PDF-ekből, Word-ből és képekből típusos elemeket csinál RAG-hez: Apache-2.0 könyvtár, platform 0,015 $\u002Foldal 10 000 ingyenes oldal után.","Unstructured ismertető: kezek egy rendetlen papír- és fotókupacot három rendezett tálcába válogatnak.",{"slug":2266,"published":2267,"updated":671,"minutes":274,"category":8,"tags":2268,"tagPages":2274,"keywords":2275,"about":2286,"sources":2292,"cover":2325,"og":2326,"expertise":80,"locales":2327,"lang":84,"title":2328,"description":2329,"coverAlt":2330},"rag-evaluation-metrics","2026-05-13",[2269,2270,2271,2272,2273],"RAG evaluation","Retrieval metrics","LLM-as-judge","Golden set","Ragas",[],[2276,2277,2278,2279,2280,2281,2282,2283,2284,2285],"rag kiértékelés","hogyan értékeljük a rag-et","rag kiértékelési metrikák","recall@k mrr ndcg","faithfulness vs válaszrelevancia","golden dataset rag-hez","llm mint bíró kalibrálás","ragas vs deepeval vs trulens","rag evals ci-ban","visszakeresési vs generálási hiba",[2287,2288,2289],{"name":110,"url":111},{"name":39,"url":40},{"name":2290,"url":2291},"Mean reciprocal rank","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FMean_reciprocal_rank",[2293,2296,2299,2301,2303,2306,2309,2312,2315,2318,2320,2322],{"title":2294,"url":2295},"Es et al.: RAGAS, Automated Evaluation of Retrieval Augmented Generation (arXiv 2309.15217)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.15217",{"title":2297,"url":2298},"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":2300,"url":333},"Ragas documentation: available metrics",{"title":2302,"url":1814},"Ragas documentation: faithfulness",{"title":2304,"url":2305},"Ragas documentation: context precision","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fconcepts\u002Fmetrics\u002Favailable_metrics\u002Fcontext_precision\u002F",{"title":2307,"url":2308},"Ragas documentation: context recall","https:\u002F\u002Fdocs.ragas.io\u002Fen\u002Fstable\u002Fconcepts\u002Fmetrics\u002Favailable_metrics\u002Fcontext_recall\u002F",{"title":2310,"url":2311},"DeepEval documentation: metrics introduction","https:\u002F\u002Fdeepeval.com\u002Fdocs\u002Fmetrics-introduction",{"title":2313,"url":2314},"TruLens","https:\u002F\u002Fwww.trulens.org\u002F",{"title":2316,"url":2317},"Arize Phoenix documentation","https:\u002F\u002Farize.com\u002Fdocs\u002Fphoenix",{"title":2319,"url":40},"Wikipedia: Discounted cumulative gain",{"title":2321,"url":2291},"Wikipedia: Mean reciprocal rank",{"title":2323,"url":2324},"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 kiértékelése: retrieval metrikák, faithfulness, és hogyan derül ki, melyik fele hibázott","RAG-kiértékelés: recall at k, MRR, nDCG vs. faithfulness és válaszrelevancia, golden set valódi kérdésekből, kalibrált LLM-bíró és evalok a CI-ban.","RAG kiértékelése: horgászbot emel ki egy könyvet a tóból, egy mérleg szövegbuborékot mér.",1793451238748]