[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-langextract-typescript":3},{"tool":4,"categoryPool":28},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":9,"logoUrl":-1,"openSource":10,"categories":11,"repo":16,"company":-1,"articles":26,"createdAt":27},"entity_01ky09jxktfanafx364xbx9yb8","LangExtract TypeScript","langextract-typescript","Port from Google's LangExtract to Typescript","https:\u002F\u002Fgithub.com\u002Fkmbro\u002Flangextract-typescript",true,[12],{"id":-1,"name":13,"slug":14,"count":15},"Extraction","extraction",0,{"fullName":17,"url":9,"stars":18,"forks":19,"openIssues":20,"language":21,"license":22,"topics":23,"pushedAt":24,"archived":25},"kmbro\u002Flangextract-typescript",63,5,7,"TypeScript","Apache-2.0",[],"2026-01-21T04:02:59Z",false,[],1784568968,[29,63,104,121],{"id":30,"name":31,"slug":32,"description":33,"url":34,"githubUrl":35,"logoUrl":36,"openSource":10,"categories":37,"repo":39,"company":-1,"articles":61,"createdAt":62},"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",[38],{"id":-1,"name":13,"slug":14,"count":15},{"fullName":40,"url":35,"stars":41,"forks":42,"openIssues":43,"language":44,"license":45,"topics":46,"pushedAt":60,"archived":25},"ucbepic\u002Fdocetl",3964,423,43,"Python","MIT",[47,48,49,50,51,52,53,54,55,56,57,58,59],"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",[],1784585384,{"id":64,"name":65,"slug":66,"description":67,"url":68,"githubUrl":69,"logoUrl":70,"openSource":10,"categories":71,"repo":76,"company":-1,"articles":90,"createdAt":103},"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",[72,75],{"id":-1,"name":73,"slug":74,"count":15},"Evals","evals",{"id":-1,"name":13,"slug":14,"count":15},{"fullName":77,"url":69,"stars":78,"forks":79,"openIssues":15,"language":44,"license":22,"topics":80,"pushedAt":89,"archived":25},"run-llama\u002FExtractBench",39,4,[81,82,83,84,85,86,87,54,88],"benchmark","coding-agent","document-ai","evaluation","extract","extract-data","llamaindex","vision-language-model","2026-08-08T18:34:23Z",[91],{"id":92,"name":93,"slug":94,"summary":95,"url":96,"kind":97,"platform":98,"author":-1,"authorHandle":-1,"publisher":99,"publishedAt":100,"about":101,"writtenBy":102,"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":105,"name":106,"slug":107,"description":108,"url":109,"githubUrl":109,"logoUrl":-1,"openSource":10,"categories":110,"repo":112,"company":-1,"articles":119,"createdAt":120},"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",[111],{"id":-1,"name":13,"slug":14,"count":15},{"fullName":113,"url":109,"stars":114,"forks":115,"openIssues":116,"language":44,"license":45,"topics":117,"pushedAt":118,"archived":25},"FabioYanezRomero\u002FKnowledge-Graph-Builder",98,12,2,[],"2026-07-04T18:27:20Z",[],1786219226,{"id":122,"name":123,"slug":124,"description":125,"url":126,"githubUrl":127,"logoUrl":128,"openSource":10,"categories":129,"repo":131,"company":-1,"articles":147,"createdAt":148},"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",[130],{"id":-1,"name":13,"slug":14,"count":15},{"fullName":132,"url":127,"stars":133,"forks":134,"openIssues":135,"language":44,"license":22,"topics":136,"pushedAt":146,"archived":25},"google\u002Flangextract",38325,2685,120,[137,138,139,140,141,142,143,54,144,55,145],"gemini","gemini-ai","gemini-api","gemini-flash","gemini-pro","information-extration","large-language-models","nlp","structured-data","2026-08-11T15:31:39Z",[],1784568973]