[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:hyper-extract":3},"\u003Cdiv align=\"center\">\u003Ca href=\"https:\u002F\u002Fyifanfeng97.github.io\u002FHyper-Extract\u002Flatest\u002F\" rel=\"nofollow ugc noopener\">\n\u003Cpicture>\n  \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"docs\u002Fassets\u002Flogo\u002Flogo-horizontal-dark.svg\">\u003C\u002Fsource>\n  \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"docs\u002Fassets\u002Flogo\u002Flogo-horizontal.svg\">\u003C\u002Fsource>\n  \u003Cimg alt=\"Hyper-Extract Logo\" src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fyifanfeng97\u002Fhyper-extract\u002FHEAD\u002Fdocs\u002Fassets\u002Flogo\u002Flogo-horizontal.svg\" width=\"600\" \u002F>\n\u003C\u002Fpicture>\n\u003C\u002Fa>\u003Cbr \u002F>\n\u003Cbr \u002F>\u003Cp>\u003Cstrong>Smart Knowledge Extraction CLI\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Transform documents into structured knowledge with one command.\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fyifanfeng97\u002Fhyper-extract\u002Fblob\u002FHEAD\u002FREADME.md\" rel=\"nofollow ugc noopener\">📖 English Version\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fyifanfeng97\u002Fhyper-extract\u002Fblob\u002FHEAD\u002FREADME_ZH.md\" rel=\"nofollow ugc noopener\">中文版\u003C\u002Fa>\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F25420\" rel=\"nofollow ugc noopener\">\n    \u003Cimg src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F25420\" alt=\"Trendshift\" width=\"250\" height=\"55\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fhyperextract\u002F\" rel=\"nofollow ugc noopener\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fhyperextract?style=for-the-badge&logo=pypi&logoColor=white&labelColor=1a1a2e&color=3776ab\" alt=\"PyPI Version\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fpython.org\" rel=\"nofollow ugc noopener\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-3.11%2B-3776ab?style=for-the-badge&logo=python&logoColor=white&labelColor=1a1a2e\" alt=\"Python Version\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fyifanfeng97\u002Fhyper-extract\u002Fblob\u002FHEAD\u002FLICENSE\" rel=\"nofollow ugc noopener\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-Apache%202.0-06b6d4?style=for-the-badge&labelColor=1a1a2e\" alt=\"License\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fyifanfeng97.github.io\u002FHyper-Extract\u002Flatest\u002F\" rel=\"nofollow ugc noopener\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocs-online-3b82f6?style=for-the-badge&logo=readthedocs&logoColor=white&labelColor=1a1a2e\" alt=\"Docs\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fyifanfeng97\u002Fhyper-extract\u002Fstargazers\" rel=\"nofollow ugc noopener\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyifanfeng97\u002Fhyper-extract?style=for-the-badge&logo=github&labelColor=1a1a2e&color=facc15\" alt=\"GitHub Stars\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\u003Cbr \u002F>\u003Cblockquote>\n\u003Cp>\u003Cstrong>\"Stop reading. Start understanding.\"\u003C\u002Fstrong>\u003Cbr \u002F>\u003Cem>\"告别文档焦虑，让信息一目了然\"\u003C\u002Fem>\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Cbr \u002F>\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fyifanfeng97\u002Fhyper-extract\u002FHEAD\u002Fdocs\u002Fassets\u002Fhero.jpg\" alt=\"Hero & Workflow\" width=\"800\" \u002F>\u003Cbr \u002F>\n\u003C\u002Fdiv>\u003Ch2>📰 What's New\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Cstrong>🔌 MCP Server\u003C\u002Fstrong> — Query your knowledge abstracts from Claude Desktop and IDE agents with \u003Ccode>he-mcp\u003C\u002Fcode>. \u003Cem>(PR #40)\u003C\u002Fem>\u003C\u002Fli>\n\u003Cli>\u003Cstrong>🧠 Anthropic Claude Support\u003C\u002Fstrong> — Use \u003Ccode>claude-opus-4-8\u003C\u002Fcode>, \u003Ccode>claude-sonnet-4-6\u003C\u002Fcode>, and \u003Ccode>claude-haiku-4-5\u003C\u002Fcode> directly as your LLM provider. \u003Cem>(PR #38)\u003C\u002Fem>\u003C\u002Fli>\n\u003Cli>\u003Cstrong>📝 Obsidian Export\u003C\u002Fstrong> — Turn any graph into an Obsidian vault with Markdown notes linked by \u003Ccode>[[wikilinks]]\u003C\u002Fcode>. \u003Cem>(PR #37)\u003C\u002Fem>\u003C\u002Fli>\n\u003Cli>\u003Cstrong>🧹 \u003Ccode>he clean\u003C\u002Fcode>\u003C\u002Fstrong> — Remove a KA's index or the whole knowledge abstract in one command. \u003Cem>(PR #39)\u003C\u002Fem>\u003C\u002Fli>\n\u003Cli>\u003Cstrong>🔧 Reliability Fixes\u003C\u002Fstrong> — True mean for multi-chunk embeddings, capped OpenAI-compatible batch sizes, and resolved multi-word \u003Ccode>llm_*\u003C\u002Fcode> merge strategies. \u003Cem>(PRs #35, #36, #41)\u003C\u002Fem>\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>See the full changelog in the \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fyifanfeng97\u002Fhyper-extract\u002Freleases\" rel=\"nofollow ugc noopener\">GitHub releases\u003C\u002Fa>.\u003C\u002Fp>\n\u003Cp>Hyper-Extract is an intelligent, LLM-powered knowledge extraction and evolution framework. It radically simplifies transforming highly unstructured texts into persistent, predictable, and strongly-typed \u003Cstrong>Knowledge Abstracts\u003C\u002Fstrong>. It effortlessly extracts information into a wide spectrum of formats—ranging from simple \u003Cstrong>Collections\u003C\u002Fstrong> (Lists\u002FSets) and \u003Cstrong>Pydantic Models\u003C\u002Fstrong>, to complex \u003Cstrong>Knowledge Graphs\u003C\u002Fstrong>, \u003Cstrong>Hypergraphs\u003C\u002Fstrong>, and even \u003Cstrong>Spatio-Temporal Graphs\u003C\u002Fstrong>.\u003C\u002Fp>\n\u003Ch2>✨ Core Features\u003C\u002Fh2>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth align=\"left\">\u003C\u002Fth>\n\u003Cth align=\"left\">\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd align=\"left\">🔷 \u003Cstrong>8 Knowledge Structures\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd align=\"left\">From simple Lists to advanced Graphs, Hypergraphs, and Spatio-Temporal Graphs\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd align=\"left\">🧠 \u003Cstrong>10+ Extraction Engines\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd align=\"left\">GraphRAG, LightRAG, Hyper-RAG, KG-Gen, and more — ready to use\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd align=\"left\">📝 \u003Cstrong>80+ YAML Templates\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd align=\"left\">Zero-code extraction across Finance, Legal, Medical, TCM, Industry, and General domains\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd align=\"left\">🔄 \u003Cstrong>Incremental Evolution\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd align=\"left\">Feed new documents anytime to expand and refine your knowledge base\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd align=\"left\">📤 \u003Cstrong>Obsidian Export\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd align=\"left\">Turn any extracted graph into an Obsidian vault — Markdown notes linked by \u003Ccode>[[wikilinks]]\u003C\u002Fcode>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Ch2>🎯 What Can You Do With It?\u003C\u002Fh2>\n\u003Cp><detai\u003C\u002Fp>\n",1784240407428]