[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-spacy":3},{"tool":4,"categoryPool":52},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":13,"repo":18,"company":44,"articles":50,"createdAt":51},"entity_01ky1fkymdfzx9bdsf5ghyh075","spaCy","spacy","Industrial-strength Natural Language Processing (NLP) in Python","https:\u002F\u002Fspacy.io\u002F","https:\u002F\u002Fgithub.com\u002Fexplosion\u002FspaCy","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ficon-192x192-88e0d3fa.png",true,[14],{"id":-1,"name":15,"slug":16,"count":17},"Extraction","extraction",0,{"fullName":19,"url":10,"stars":20,"forks":21,"openIssues":22,"language":23,"license":24,"topics":25,"pushedAt":42,"archived":43},"explosion\u002FspaCy",33814,4709,231,"Python","MIT",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,7,40,41],"ai","artificial-intelligence","cython","data-science","deep-learning","entity-linking","machine-learning","named-entity-recognition","natural-language-processing","neural-network","neural-networks","nlp","nlp-library","python","text-classification","tokenization","2026-08-07T11:44:36Z",false,{"id":45,"name":46,"slug":47,"url":48,"bio":49,"githubOrg":47},"entity_01kynhncvseczterbwjjejq09j","Explosion","explosion","https:\u002F\u002Fexplosion.ai\u002F","Explosion is a software company specializing in developer tools and tailored solutions for Artificial Intelligence and Natural Language Processing. We’re the makers of spaCy, one of the leading open-source libraries for advanced NLP.",[],1784608848,[53,84,126,143],{"id":54,"name":55,"slug":56,"description":57,"url":58,"githubUrl":59,"logoUrl":60,"openSource":12,"categories":61,"repo":63,"company":-1,"articles":82,"createdAt":83},"entity_01ky0s7wgrf239sywgdkw7e8gz","DocETL","docetl","Open-source toolkit, built by the EPIC Data Lab at UC Berkeley, for creating LLM-powered pipelines that extract, transform, and link knowledge from unstructured documents.","https:\u002F\u002Fwww.docetl.org\u002F","https:\u002F\u002Fgithub.com\u002Fucbepic\u002Fdocetl","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fdocetl-favicon-color-9d034c86.png",[62],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":64,"url":59,"stars":65,"forks":66,"openIssues":67,"language":23,"license":24,"topics":68,"pushedAt":81,"archived":43},"ucbepic\u002Fdocetl",3964,423,43,[69,70,71,72,73,74,75,76,39,77,78,79,80],"agents","data","data-pipelines","document-analysis","document-processing","elt","etl","llm","semantic-data","unstructured-data","unstructured-data-analysis","workflow","2026-08-10T15:00:22Z",[],1784585384,{"id":85,"name":86,"slug":87,"description":88,"url":89,"githubUrl":90,"logoUrl":91,"openSource":12,"categories":92,"repo":97,"company":-1,"articles":112,"createdAt":125},"entity_01kzs3gy7rfantmwgtrzpzt8yn","ExtractBench","extractbench","A benchmark for schema-guided extraction from real enterprise documents. 370 documents, 4,869 pages, 67 document types, each with its own JSON Schema. Scored on value accuracy, completeness, and evidence.","https:\u002F\u002Fwww.extractbench.ai\u002F","https:\u002F\u002Fgithub.com\u002Frun-llama\u002FExtractBench","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fapple-touch-icon-da922544.png",[93,96],{"id":-1,"name":94,"slug":95,"count":17},"Evals","evals",{"id":-1,"name":15,"slug":16,"count":17},{"fullName":98,"url":90,"stars":99,"forks":100,"openIssues":17,"language":23,"license":101,"topics":102,"pushedAt":111,"archived":43},"run-llama\u002FExtractBench",39,4,"Apache-2.0",[103,104,105,106,107,108,109,76,110],"benchmark","coding-agent","document-ai","evaluation","extract","extract-data","llamaindex","vision-language-model","2026-08-08T18:34:23Z",[113],{"id":114,"name":115,"slug":116,"summary":117,"url":118,"kind":119,"platform":120,"author":-1,"authorHandle":-1,"publisher":121,"publishedAt":122,"about":123,"writtenBy":124,"createdAt":-1},"entity_01kzs3krzxfantmwj9zrcz3hbt","ExtractBench: The Most Comprehensive Extraction Benchmark","introducing-extractbench","The most comprehensive document extraction benchmark: 14 systems scored on accuracy, completeness, grounding, and cost across 370 enterprise documents.","https:\u002F\u002Fwww.llamaindex.ai\u002Fblog\u002Fintroducing-extractbench","announcement","web","LlamaIndex","2026-08-11",[],[],1786475215,{"id":127,"name":128,"slug":129,"description":130,"url":131,"githubUrl":131,"logoUrl":-1,"openSource":12,"categories":132,"repo":134,"company":-1,"articles":141,"createdAt":142},"entity_01kzhfcs4xeh2vtra99mntepyy","Knowledge Graph Builder","knowledge-graph-builder","Repository for building knowledge graphs from specific datasets using generative language model through ollama","https:\u002F\u002Fgithub.com\u002FFabioYanezRomero\u002FKnowledge-Graph-Builder",[133],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":135,"url":131,"stars":136,"forks":137,"openIssues":138,"language":23,"license":24,"topics":139,"pushedAt":140,"archived":43},"FabioYanezRomero\u002FKnowledge-Graph-Builder",98,12,2,[],"2026-07-04T18:27:20Z",[],1786219226,{"id":144,"name":145,"slug":146,"description":147,"url":148,"githubUrl":149,"logoUrl":150,"openSource":12,"categories":151,"repo":153,"company":-1,"articles":168,"createdAt":169},"entity_01ky09k25gfanafx44rj2f9dpf","LangExtract","langextract","A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.","https:\u002F\u002Fpypi.org\u002Fproject\u002Flangextract\u002F","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Flangextract","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ffavicon.35549fe8-6dd120da.ico",[152],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":154,"url":149,"stars":155,"forks":156,"openIssues":157,"language":23,"license":101,"topics":158,"pushedAt":167,"archived":43},"google\u002Flangextract",38325,2685,120,[159,160,161,162,163,164,165,76,37,39,166],"gemini","gemini-ai","gemini-api","gemini-flash","gemini-pro","information-extration","large-language-models","structured-data","2026-08-11T15:31:39Z",[],1784568973]