[{"data":1,"prerenderedAt":336},["ShallowReactive",2],{"blog-tag-en-document-ai":3},[4,70,144,199,270],{"slug":5,"published":6,"minutes":7,"category":8,"tags":9,"tagPages":15,"keywords":17,"about":28,"sources":38,"cover":60,"og":61,"expertise":62,"locales":63,"lang":64,"title":67,"description":68,"coverAlt":69},"pdf-document-parsing-for-rag","2026-10-16",9,"rag",[10,11,12,13,14],"RAG","PDF parsing","OCR","Docling","Document AI",[8,16],"document-ai",[18,19,20,21,22,23,24,25,26,27],"pdf parsing for rag","best pdf parser for rag","docling vs marker","marker vs mineru","pdf to markdown for llm","extract tables from pdf for rag","ocr for rag pipeline","olmocr bench","scanned pdf rag","document parsing llm",[29,32,35],{"name":30,"url":31},"PDF","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FPDF",{"name":33,"url":34},"Optical character recognition","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FOptical_character_recognition",{"name":36,"url":37},"Retrieval-augmented generation","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FRetrieval-augmented_generation",[39,42,45,48,51,54,57],{"title":40,"url":41},"Docling: README, features and license (GitHub)","https:\u002F\u002Fgithub.com\u002Fdocling-project\u002Fdocling",{"title":43,"url":44},"Auer et al.: Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion (2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.17887",{"title":46,"url":47},"Datalab: Marker README, olmOCR-bench results and license (GitHub)","https:\u002F\u002Fgithub.com\u002Fdatalab-to\u002Fmarker",{"title":49,"url":50},"OpenDataLab: MinerU README and license (GitHub)","https:\u002F\u002Fgithub.com\u002Fopendatalab\u002FMinerU",{"title":52,"url":53},"Poznanski et al.: olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models (2025)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.18443",{"title":55,"url":56},"Claude Platform Docs: PDF support","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fbuild-with-claude\u002Fpdf-support",{"title":58,"url":59},"Anthropic: Introducing Contextual Retrieval (Sep 2024)","https:\u002F\u002Fwww.anthropic.com\u002Fnews\u002Fcontextual-retrieval","\u002Fimages\u002Fblog\u002Fpdf-document-parsing-for-rag\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fpdf-document-parsing-for-rag\u002Fog.jpg","ai-engineer",[64,65,66],"en","de","hu","PDF parsing for RAG: layout pipelines, OCR and vision models compared","Why PDF parsing decides RAG quality, how Docling, Marker, MinerU and VLM OCR differ, and how to test a parser on your own documents.","PDF parsing for RAG: a document goes through a roller machine and comes out as separate table, picture and text cards.",{"slug":71,"published":72,"updated":6,"minutes":73,"category":74,"tags":75,"tagPages":80,"keywords":81,"about":92,"sources":100,"cover":137,"og":138,"expertise":139,"locales":140,"lang":64,"title":141,"description":142,"coverAlt":143},"llm-rfq-quote-automation","2026-10-14",8,"web",[76,77,14,78,79],"RFQ","Quote automation","Product matching","Human review",[16],[82,83,84,85,86,87,88,89,90,91],"RFQ automation","automated quote generation","quote automation LLM","request for quote parsing","part number matching","B2B quote automation software","AI quote generation distribution","human in the loop document review","PDF RFQ extraction","semantic product matching",[93,96,97],{"name":94,"url":95},"Request for quotation","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FRequest_for_quotation",{"name":33,"url":34},{"name":98,"url":99},"Large language model","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FLarge_language_model",[101,104,107,110,113,116,119,122,125,128,131,134],{"title":102,"url":103},"Harvard Business Review: The Short Life of Online Sales Leads (March 2011)","https:\u002F\u002Fhbr.org\u002F2011\u002F03\u002Fthe-short-life-of-online-sales-leads",{"title":105,"url":106},"Mistral AI: OCR 4.1 model card","https:\u002F\u002Fdocs.mistral.ai\u002Fmodels\u002Focr-4-1",{"title":108,"url":109},"Mistral AI: models overview and deprecations","https:\u002F\u002Fdocs.mistral.ai\u002Fgetting-started\u002Fmodels\u002Fmodels_overview\u002F",{"title":111,"url":112},"Google Cloud: Document AI pricing","https:\u002F\u002Fcloud.google.com\u002Fdocument-ai\u002Fpricing",{"title":114,"url":115},"Google Cloud: Document AI deprecations","https:\u002F\u002Fcloud.google.com\u002Fdocument-ai\u002Fdocs\u002Fdeprecation",{"title":117,"url":118},"Amazon Textract pricing","https:\u002F\u002Faws.amazon.com\u002Ftextract\u002Fpricing\u002F",{"title":120,"url":121},"Microsoft Learn: Azure OpenAI structured outputs","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fai-foundry\u002Fopenai\u002Fhow-to\u002Fstructured-outputs",{"title":123,"url":124},"Tian et al.: Just Ask for Calibration (EMNLP 2023)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.14975",{"title":126,"url":127},"Peppol BIS Upgrade 3: ordering profiles and code lists","https:\u002F\u002Fdocs.peppol.eu\u002Fpoacc\u002Fupgrade-3\u002F",{"title":129,"url":130},"ETIM International: model releases","https:\u002F\u002Fwww.etim-international.com\u002Fdownloads\u002F?_sft_downloadcategory=model-releases",{"title":132,"url":133},"ECLASS: classification standard","https:\u002F\u002Fwww.eclass.eu\u002F",{"title":135,"url":136},"O*NET OnLine: Order Clerks (43-4151.00)","https:\u002F\u002Fwww.onetonline.org\u002Flink\u002Fsummary\u002F43-4151.00","\u002Fimages\u002Fblog\u002Fllm-rfq-quote-automation\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fllm-rfq-quote-automation\u002Fog.jpg","b2b-ecommerce-developer",[64,65,66],"RFQ automation with LLMs: parsing, part matching and human review","How to automate RFQ handling with LLMs: document intake, line extraction, part-number matching, contract pricing and a review queue that stays fast.","RFQ automation with LLMs: a sheet leaves an envelope and becomes a sealed document via a small gear.",{"slug":145,"published":72,"minutes":7,"category":74,"tags":146,"tagPages":151,"keywords":153,"about":164,"sources":174,"cover":193,"og":194,"expertise":139,"locales":195,"lang":64,"title":196,"description":197,"coverAlt":198},"b2b-email-order-entry-llm",[147,148,14,149,150],"Order entry","ERP","Idempotency","GDPR",[16,152],"gdpr",[154,155,156,157,158,159,160,161,162,163],"email order entry automation","sales order automation","automate order entry from email","AI order processing ERP","order desk automation","PDF order to ERP","sales order automation ROI","order entry error rate","touchless order processing","order validation rules ERP",[165,168,171],{"name":166,"url":167},"Sales order","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FSales_order",{"name":169,"url":170},"Enterprise resource planning","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FEnterprise_resource_planning",{"name":172,"url":173},"General Data Protection Regulation","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FGeneral_Data_Protection_Regulation",[175,178,179,182,185,186,187,188,189,190],{"title":176,"url":177},"Microsoft Learn: Receive change notifications through webhooks (Microsoft Graph)","https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fgraph\u002Fchange-notifications-delivery-webhooks",{"title":120,"url":121},{"title":180,"url":181},"Stripe API reference: Idempotent requests","https:\u002F\u002Fdocs.stripe.com\u002Fapi\u002Fidempotent_requests",{"title":183,"url":184},"Regulation (EU) 2016\u002F679 (GDPR), EUR-Lex","https:\u002F\u002Feur-lex.europa.eu\u002Flegal-content\u002FEN\u002FTXT\u002F?uri=CELEX%3A32016R0679",{"title":126,"url":127},{"title":135,"url":136},{"title":117,"url":118},{"title":111,"url":112},{"title":105,"url":106},{"title":191,"url":192},"Conexiom: sales order automation (vendor)","https:\u002F\u002Fconexiom.com\u002F","\u002Fimages\u002Fblog\u002Fb2b-email-order-entry-llm\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fb2b-email-order-entry-llm\u002Fog.jpg",[64,65,66],"Email order entry automation: turning emailed orders into ERP orders","How to automate B2B order entry from email with LLMs: reliable mailbox intake, line extraction, validation rules as code, idempotency and GDPR.","Email order entry automation: envelopes unfold into tidy rows on a clipboard that point to a box.",{"slug":200,"published":201,"updated":202,"minutes":7,"category":74,"tags":203,"tagPages":208,"keywords":210,"about":221,"sources":230,"cover":264,"og":265,"expertise":139,"locales":266,"lang":64,"title":267,"description":268,"coverAlt":269},"supplier-data-onboarding-llm","2026-10-12","2026-10-17",[204,205,206,14,207],"Supplier onboarding","PIM","BMEcat","GTIN",[209,16],"pim",[211,212,213,214,215,216,217,218,219,220],"supplier data onboarding","LLM price list extraction","supplier catalog import PIM","BMEcat import","GTIN validation","supplier product data automation","PDF price list extraction","supplier data quality scorecard","cost per row LLM extraction","supplier onboarding automation B2B",[222,225,228],{"name":223,"url":224},"Product information management","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FProduct_information_management",{"name":226,"url":227},"Global Trade Item Number","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FGlobal_Trade_Item_Number",{"name":206,"url":229},"https:\u002F\u002Fwww.bme.de\u002Fservices\u002Fbmecat\u002Fdownloads_BMEcat",[231,234,236,239,242,245,248,251,252,255,258,261],{"title":232,"url":233},"GS1: Everyone needs better product data (Global Data Model)","https:\u002F\u002Fwww.gs1.org\u002Fstandards\u002Fgs1-global-data-model\u002Feveryone-needs-better-product-data",{"title":235,"url":229},"BME: BMEcat downloads (version 2005.2)",{"title":237,"url":238},"ETIM International: exchange format (ETIM xChange)","https:\u002F\u002Fwww.etim-international.com\u002Fclassification\u002Fexchange-format\u002F",{"title":240,"url":241},"ETIM International: model information","https:\u002F\u002Fwww.etim-international.com\u002Fclassification\u002Fmodel-information\u002F",{"title":243,"url":244},"GS1: check digit calculator","https:\u002F\u002Fwww.gs1.org\u002Fservices\u002Fcheck-digit-calculator",{"title":246,"url":247},"Pimcore: Data Importer","https:\u002F\u002Fdocs.pimcore.com\u002Fplatform\u002FData_Importer\u002F",{"title":249,"url":250},"Akeneo: Supplier Data Manager","https:\u002F\u002Fhelp.akeneo.com\u002Fen_US\u002Fsupplier-data-manager",{"title":117,"url":118},{"title":253,"url":254},"Anthropic: Claude pricing","https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fabout-claude\u002Fpricing",{"title":256,"url":257},"GS1 US: data quality","https:\u002F\u002Fwww.gs1us.org\u002Fservices\u002Fdata-quality",{"title":259,"url":260},"GS1 US: National Data Quality Program","https:\u002F\u002Fwww.gs1us.org\u002Fservices\u002Fdata-quality\u002Fnational-data-quality-program",{"title":262,"url":263},"Unite: catalogue format BMEcat 1.2","https:\u002F\u002Funite.eu\u002Fen-gb\u002Fsupport\u002Fcatalogue-format-bmecat-1-2-xml","\u002Fimages\u002Fblog\u002Fsupplier-data-onboarding-llm\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fsupplier-data-onboarding-llm\u002Fog.jpg",[64,65,66],"Supplier data onboarding with LLMs: price lists, PDFs and certificates","How to onboard supplier product data with LLMs: deterministic BMEcat and Excel imports, PDF price list extraction, GTIN validation and supplier scorecards.","Supplier data onboarding with LLMs: mixed sheets pass through a funnel and come out as identical cards.",{"slug":271,"published":272,"updated":202,"minutes":7,"category":74,"tags":273,"tagPages":277,"keywords":278,"about":289,"sources":299,"cover":330,"og":331,"expertise":139,"locales":332,"lang":64,"title":333,"description":334,"coverAlt":335},"digital-product-passport-llm","2026-10-09",[274,275,276,14,205],"Digital Product Passport","ESPR","Compliance data",[16,209],[279,280,281,282,283,284,285,286,287,288],"digital product passport data extraction","digital product passport","ESPR delegated act 2026","battery passport 18 February 2027","DPP registry","GS1 Digital Link QR code","product compliance data LLM","supplier declaration extraction","recycled content declaration","DPP service provider",[290,293,296],{"name":291,"url":292},"Digital product passport","https:\u002F\u002Fsingle-market-economy.ec.europa.eu\u002Fsingle-market\u002Fdigital-product-passport_en",{"name":294,"url":295},"Ecodesign for Sustainable Products Regulation","https:\u002F\u002Feur-lex.europa.eu\u002Flegal-content\u002FEN\u002FTXT\u002FHTML\u002F?uri=CELEX:32024R1781",{"name":297,"url":298},"GS1 Digital Link","https:\u002F\u002Fwww.gs1.org\u002Fstandards\u002Fgs1-digital-link",[300,302,304,307,310,313,316,319,321,324,327],{"title":301,"url":295},"Regulation (EU) 2024\u002F1781 (ESPR), EUR-Lex",{"title":303,"url":292},"European Commission: Digital Product Passport",{"title":305,"url":306},"Commission Implementing Decision (EU) 2026\u002F1736 on harmonised DPP standards","https:\u002F\u002Feur-lex.europa.eu\u002Flegal-content\u002FEN\u002FTXT\u002FHTML\u002F?uri=CELEX:32026D1736",{"title":308,"url":309},"Commission Implementing Regulation (EU) 2026\u002F1778 on the DPP registry","https:\u002F\u002Feur-lex.europa.eu\u002Flegal-content\u002FEN\u002FTXT\u002FHTML\u002F?uri=CELEX:32026R1778",{"title":311,"url":312},"Regulation (EU) 2023\u002F1542 (Batteries), EUR-Lex","https:\u002F\u002Feur-lex.europa.eu\u002Flegal-content\u002FEN\u002FTXT\u002FHTML\u002F?uri=CELEX:32023R1542",{"title":314,"url":315},"Commission working plan COM(2025) 187 under ESPR","https:\u002F\u002Feur-lex.europa.eu\u002Flegal-content\u002FEN\u002FTXT\u002FHTML\u002F?uri=CELEX:52025DC0187",{"title":317,"url":318},"European Commission: CBAM certificate price","https:\u002F\u002Ftaxation-customs.ec.europa.eu\u002Fcarbon-border-adjustment-mechanism\u002Fprice-cbam-certificates_en",{"title":320,"url":298},"GS1: Digital Link standard",{"title":322,"url":323},"Publications Office: SCIP database information requirements","https:\u002F\u002Fop.europa.eu\u002Fen\u002Fpublication-detail\u002F-\u002Fpublication\u002F887091cb-0938-11ec-b5d3-01aa75ed71a1\u002Flanguage-en",{"title":325,"url":326},"CIRPASS-2 project","https:\u002F\u002Fcirpass2.eu\u002F",{"title":328,"url":329},"Vectara hallucination leaderboard","https:\u002F\u002Fgithub.com\u002Fvectara\u002Fhallucination-leaderboard\u002F","\u002Fimages\u002Fblog\u002Fdigital-product-passport-llm\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fdigital-product-passport-llm\u002Fog.jpg",[64,65,66],"Digital Product Passports with LLMs: extracting and assembling ESPR data","Where the Digital Product Passport stands in October 2026, which data a DPP record needs, and how LLMs extract supplier evidence without inventing values.","Digital Product Passports with LLMs: a product box with a code tag next to an open passport booklet.",1793451238365]