[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-docetl":3},{"tool":4,"categoryPool":43},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":13,"repo":18,"company":-1,"articles":41,"createdAt":42},"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",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":39,"archived":40},"ucbepic\u002Fdocetl",3964,423,43,"Python","MIT",[26,27,28,29,30,31,32,33,34,35,36,37,38],"agents","data","data-pipelines","document-analysis","document-processing","elt","etl","llm","python","semantic-data","unstructured-data","unstructured-data-analysis","workflow","2026-08-10T15:00:22Z",false,[],1784585384,[44,50,92,109],{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":45,"repo":47,"company":-1,"articles":49,"createdAt":42},[46],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":19,"url":10,"stars":20,"forks":21,"openIssues":22,"language":23,"license":24,"topics":48,"pushedAt":39,"archived":40},[26,27,28,29,30,31,32,33,34,35,36,37,38],[],{"id":51,"name":52,"slug":53,"description":54,"url":55,"githubUrl":56,"logoUrl":57,"openSource":12,"categories":58,"repo":63,"company":-1,"articles":78,"createdAt":91},"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",[59,62],{"id":-1,"name":60,"slug":61,"count":17},"Evals","evals",{"id":-1,"name":15,"slug":16,"count":17},{"fullName":64,"url":56,"stars":65,"forks":66,"openIssues":17,"language":23,"license":67,"topics":68,"pushedAt":77,"archived":40},"run-llama\u002FExtractBench",39,4,"Apache-2.0",[69,70,71,72,73,74,75,33,76],"benchmark","coding-agent","document-ai","evaluation","extract","extract-data","llamaindex","vision-language-model","2026-08-08T18:34:23Z",[79],{"id":80,"name":81,"slug":82,"summary":83,"url":84,"kind":85,"platform":86,"author":-1,"authorHandle":-1,"publisher":87,"publishedAt":88,"about":89,"writtenBy":90,"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":93,"name":94,"slug":95,"description":96,"url":97,"githubUrl":97,"logoUrl":-1,"openSource":12,"categories":98,"repo":100,"company":-1,"articles":107,"createdAt":108},"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",[99],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":101,"url":97,"stars":102,"forks":103,"openIssues":104,"language":23,"license":24,"topics":105,"pushedAt":106,"archived":40},"FabioYanezRomero\u002FKnowledge-Graph-Builder",98,12,2,[],"2026-07-04T18:27:20Z",[],1786219226,{"id":110,"name":111,"slug":112,"description":113,"url":114,"githubUrl":115,"logoUrl":116,"openSource":12,"categories":117,"repo":119,"company":-1,"articles":135,"createdAt":136},"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",[118],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":120,"url":115,"stars":121,"forks":122,"openIssues":123,"language":23,"license":67,"topics":124,"pushedAt":134,"archived":40},"google\u002Flangextract",38325,2685,120,[125,126,127,128,129,130,131,33,132,34,133],"gemini","gemini-ai","gemini-api","gemini-flash","gemini-pro","information-extration","large-language-models","nlp","structured-data","2026-08-11T15:31:39Z",[],1784568973]