[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-sparrow":3},{"tool":4,"categoryPool":36},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":13,"repo":18,"company":-1,"articles":34,"createdAt":35},"entity_01ky09vs75fanafxa25a64yv63","Sparrow","sparrow","Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM","https:\u002F\u002Fsparrow.katanaml.io","https:\u002F\u002Fgithub.com\u002Fkatanaml\u002Fsparrow","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fapple-touch-icon-62eaa574.png",true,[14],{"id":-1,"name":15,"slug":16,"count":17},"Extraction","extraction",0,{"fullName":19,"url":10,"stars":20,"forks":21,"openIssues":17,"language":22,"license":23,"topics":24,"pushedAt":32,"archived":33},"katanaml\u002Fsparrow",5194,520,"Python","GPL-3.0",[25,26,27,28,29,30,31],"agentic-ai","computer-vision","documentai","huggingface-transformers","llm","machinelearning","vllm","2026-08-08T14:22:39Z",false,[],1784569259,[37,69,111,128],{"id":38,"name":39,"slug":40,"description":41,"url":42,"githubUrl":43,"logoUrl":44,"openSource":12,"categories":45,"repo":47,"company":-1,"articles":67,"createdAt":68},"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",[46],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":48,"url":43,"stars":49,"forks":50,"openIssues":51,"language":22,"license":52,"topics":53,"pushedAt":66,"archived":33},"ucbepic\u002Fdocetl",3964,423,43,"MIT",[54,55,56,57,58,59,60,29,61,62,63,64,65],"agents","data","data-pipelines","document-analysis","document-processing","elt","etl","python","semantic-data","unstructured-data","unstructured-data-analysis","workflow","2026-08-10T15:00:22Z",[],1784585384,{"id":70,"name":71,"slug":72,"description":73,"url":74,"githubUrl":75,"logoUrl":76,"openSource":12,"categories":77,"repo":82,"company":-1,"articles":97,"createdAt":110},"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",[78,81],{"id":-1,"name":79,"slug":80,"count":17},"Evals","evals",{"id":-1,"name":15,"slug":16,"count":17},{"fullName":83,"url":75,"stars":84,"forks":85,"openIssues":17,"language":22,"license":86,"topics":87,"pushedAt":96,"archived":33},"run-llama\u002FExtractBench",39,4,"Apache-2.0",[88,89,90,91,92,93,94,29,95],"benchmark","coding-agent","document-ai","evaluation","extract","extract-data","llamaindex","vision-language-model","2026-08-08T18:34:23Z",[98],{"id":99,"name":100,"slug":101,"summary":102,"url":103,"kind":104,"platform":105,"author":-1,"authorHandle":-1,"publisher":106,"publishedAt":107,"about":108,"writtenBy":109,"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":112,"name":113,"slug":114,"description":115,"url":116,"githubUrl":116,"logoUrl":-1,"openSource":12,"categories":117,"repo":119,"company":-1,"articles":126,"createdAt":127},"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",[118],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":120,"url":116,"stars":121,"forks":122,"openIssues":123,"language":22,"license":52,"topics":124,"pushedAt":125,"archived":33},"FabioYanezRomero\u002FKnowledge-Graph-Builder",98,12,2,[],"2026-07-04T18:27:20Z",[],1786219226,{"id":129,"name":130,"slug":131,"description":132,"url":133,"githubUrl":134,"logoUrl":135,"openSource":12,"categories":136,"repo":138,"company":-1,"articles":154,"createdAt":155},"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",[137],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":139,"url":134,"stars":140,"forks":141,"openIssues":142,"language":22,"license":86,"topics":143,"pushedAt":153,"archived":33},"google\u002Flangextract",38325,2685,120,[144,145,146,147,148,149,150,29,151,61,152],"gemini","gemini-ai","gemini-api","gemini-flash","gemini-pro","information-extration","large-language-models","nlp","structured-data","2026-08-11T15:31:39Z",[],1784568973]