Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
docs: 更新文档中的API密钥占位符和示例文本
yifanfeng9724c719dc7527
diff --git a/README.md b/README.mdindex 7b1499f..abda1e3 100644--- a/README.md+++ b/README.md@@ -1,12 +1,13 @@# Hyper-Extract+## 🚀 Smart Knowledge Extraction CLI — Transform documents into structured knowledge with one command.+[📖 English Version](./README.md) · [中文版](./README_ZH.md)> **"Stop reading. Start understanding."**> *"告别文档焦虑,让信息一目了然"*-**Transform documents into knowledge abstracts — with just one command.**[](https://python.org)[](LICENSE)@@ -25,7 +26,7 @@ Hyper-Extract is an intelligent, LLM-powered knowledge extraction and evolution- 📝 **Declarative YAML Templates:** Zero-code extraction definition. Includes 80+ presets across 6 domains.- 🔄 **Incremental Evolution:** Feed new documents on the fly to continuously map out and expand the extracted knowledge.----+***## ⚡ Quick Start@@ -42,17 +43,55 @@ Extract, search, and manage directly from CLI.> By default, the CLI uses `gpt-4o-mini` and `text-embedding-3-small`.```bash-he config init -k YOUR_API_KEY-he parse document.md -o ./output/ -l zh-he search ./output/ "What are the key events?"-he feed ./output/ new_document.md+# Configure OpenAI API Key+he config init -k YOUR_OPENAI_API_KEY++# Extract knowledge (using examples/en/tesla.md as sample input)+he parse examples/en/tesla.md -t general/biography_graph -o ./output/ -l en++# Query the knowledge base+he search ./output/ "What are Tesla's major achievements?"++# Incrementally supplement knowledge+he feed ./output/ another_tesla_document.md```<details>-<summary><b>🛠️ How to define a Knowledge Template (YAML)?</b></summary>+<summary><b> The Python API Way</b></summary><br>-Zero-code approach to define what to extract from incoming texts:+```python+from hyperextract import Template++ka = Template.create("general/biography_graph")+result = ka.parse(text)+```++> 🔗 For complete examples, see [examples/en](./examples/en/)++</details>++## 🧩 Deep Dive: The 8 Auto-Types++Our framework embraces complexity without making you write boilerplate code.++!\[Knowledge Structures Matrix]\(docs/assets/autotypes.png null)++### Example: AutoGraph Visualization++Here is the knowledge graph visualization after `AutoGraph` extraction:++++## 🛠️ Architecture Overview++The system is built on a robust triad: **Auto-Types** (Multi-typed structures), **Methods** (The Execution strategy), and **Templates** (Declarative schema).++++### 📋 Template Structure Example++Here's a complete YAML template example that defines a Knowledge Graph extraction:```yamllanguage: en@@ -103,62 +142,31 @@ display:entity_label: '{name} ({type})'relation_label: '{type}'```-</details>--### 3. The Python API Way--```python-from hyperextract import Template--# Load a preset YAML template-ka = Template.create("finance/event_timeline")--# Extract and auto-parse the document-result = ka.parse(annual_report_text)-```--> 🔗 For complete examples, see [examples/en](./examples/en/)--## 🧩 Deep Dive: The 8 Auto-Types-Our framework embraces complexity without making you write boilerplate code.----### Example: AutoGraph Visualization--Here is the knowledge graph visualization after `AutoGraph` extraction:----## 🛠️ Architecture Overview--The system is built on a robust triad: **Auto-Types** (Multi-typed structures), **Methods** (The Execution strategy), and **Templates** (Declarative schema).--+### 📚 Related Documentation-* **Design Guide**: [Template Design Guide](./hyperextract/templates/DESIGN_GUIDE.md)-* **Preset Templates**: [presets directory](./hyperextract/templates/presets/)+- **Preset Templates**: Browse [80+ ready-to-use templates](./hyperextract/templates/presets/) across 6 domains+- **Design Guide**: Learn how to [create custom templates](./hyperextract/templates/DESIGN_GUIDE.md)## 📈 Comparison with Other Libraries-| Feature | GraphRAG | LightRAG | KG-Gen | ATOM | **Hyper-Extract** |-|---------|:---:|:---:|:---:|:---:|:---:|-| Knowledge Graph | ✅ | ✅ | ✅ | ✅ | ✅ |-| Temporal Graph | ✅ | ❌ | ❌ | ✅ | ✅ |-| Spatial Graph | ❌ | ❌ | ❌ | ❌ | ✅ |-| Hypergraph | ❌ | ❌ | ❌ | ❌ | ✅ |-| Domain Templates | ❌ | ❌ | ❌ | ❌ | ✅ |-| CLI Tool | ❌ | ❌ | ❌ | ❌ | ✅ |-| Multi-language | Partial | ❌ | ❌ | ❌ | ✅ |+| Feature | GraphRAG | LightRAG | KG-Gen | ATOM | **Hyper-Extract** |+| ---------------- | :------: | :------: | :----: | :--: | :---------------: |+| Knowledge Graph | ✅ | ✅ | ✅ | ✅ | ✅ |+| Temporal Graph | ✅ | ❌ | ❌ | ✅ | ✅ |+| Spatial Graph | ❌ | ❌ | ❌ | ❌ | ✅ |+| Hypergraph | ❌ | ❌ | ❌ | ❌ | ✅ |+| Domain Templates | ❌ | ❌ | ❌ | ❌ | ✅ |+| CLI Tool | ❌ | ❌ | ❌ | ❌ | ✅ |+| Multi-language | Partial | ❌ | ❌ | ❌ | ✅ |## 📚 Related Documentation-* [Full Documentation](https://hyper-extract.github.io/en/) - Complete documentation site-* [中文文档](https://hyper-extract.github.io/zh/) - 中文文档-* [CLI Guide](https://hyper-extract.github.io/en/guides/cli/) - Command-line interface-* [Template Gallery](https://hyper-extract.github.io/en/reference/template-gallery/) - Available templates-* [Example Code](./examples/) - Working examples+- [Full Documentation](https://hyper-extract.github.io/en/) - Complete documentation site+- [中文文档](https://hyper-extract.github.io/zh/) - 中文文档+- [CLI Guide](https://hyper-extract.github.io/en/guides/cli/) - Command-line interface+- [Template Gallery](https://hyper-extract.github.io/en/reference/template-gallery/) - Available templates+- [Example Code](./examples/) - Working examples## 🤝 Contributing & Licensediff --git a/README_ZH.md b/README_ZH.mdindex 4cd30cb..d8a245b 100644--- a/README_ZH.md+++ b/README_ZH.md@@ -1,30 +1,31 @@# Hyper-Extract+## 🚀 智能知识提取 CLI —— 一行命令,将文档转化为结构化知识+[📖 English Version](./README.md) · [中文版](./README_ZH.md)> **"Stop reading. Start understanding."**> *"告别文档焦虑,让信息一目了然"*-**将文档转化为知识摘要 —— 一行命令即可。**-[](https://python.org)[](LICENSE)[]()## 🚀 什么是 Hyper-Extract-Hyper-Extract 是一个智能的、由大语言模型(LLM)驱动的知识提取与演进框架。它极大地简化了将杂乱不堪的文本转化为持久化、强类型的知识摘要的过程。无论从基础的**集合(Collection/List)**和**结构化模型(Model)**,还是到高阶复杂的**知识图谱(Knowledge Graph)**、**超图(Hypergraph)**,甚至是**时空图谱(Spatio-Temporal Graph)**,它都能轻松拿捏。++Hyper-Extract 是一个智能的、由大语言模型(LLM)驱动的知识提取与演进框架。它极大地简化了将杂乱不堪的文本转化为持久化、强类型的知识摘要的过程。无论从基础的**集合(Collection/List)和**结构化模型(Model),还是到高阶复杂的**知识图谱(Knowledge Graph)**、**超图(Hypergraph)**,甚至是**时空图谱(Spatio-Temporal Graph)**,它都能轻松拿捏。## ✨ 核心亮点-- 🔷 **8大自动数据结构(Auto-Types):** 从基础的 `AutoModel`/`AutoList` 到高阶的 `AutoGraph`, `AutoHypergraph`, 以及 `AutoSpatioTemporalGraph`(时空图)。+- 🔷 **8大基础知识结构数据结构(Auto-Types):** 从基础的 `AutoModel`/`AutoList` 到高阶的 `AutoGraph`, `AutoHypergraph`, 以及 `AutoSpatioTemporalGraph`(时空图)。- 🧠 **10+ 前沿提取引擎:** 开箱即用整合了业界顶尖的检索范式,例如 `GraphRAG`、`LightRAG`、`Hyper-RAG` 和 `KG-Gen`。- 📝 **声明式 YAML 模板:** 零代码定义提取策略。内置覆盖 6 大领域的 80+ 预设模板。- 🔄 **知识增量演进:** 支持动态喂入新文档(Feed),让提取的知识图谱自动补全和扩展。----+***## ⚡ 快速上手@@ -36,22 +37,60 @@ uv pip install hyper-extract### 2. CLI 命令行玩法-仅仅几行命令体验最纯粹的知识图谱交互。+仅仅几行命令体验最纯粹的知识交互。-> 默认采用兼顾性价比的组合:`gpt-4o-mini` + `text-embedding-3-small`。+> 默认采用`gpt-4o-mini` 作为大模型基座, `text-embedding-3-small`作为文本嵌入模型。```bash-he config init -k YOUR_API_KEY-he parse document.md -o ./output/ -l zh-he search ./output/ "有哪些关键事件?"-he feed ./output/ new_document.md+# 配置 OpenAI API Key+he config init -k YOUR_OPENAI_API_KEY++# 提取知识(使用 examples/zh/sushi.md 作为示例输入)+he parse examples/zh/sushi.md -t general/biography_graph -o ./output/ -l zh++# 查询知识库+he search ./output/ "苏轼有哪些重要的作品?"++# 增量补充知识+he feed ./output/ another_sushi_document.md```<details>-<summary><b>🛠️ 如何定义知识模板(YAML)?</b></summary>+<summary><b>🐍 Python API 深度集成</b></summary><br>-无需编写长篇代码,只需使用优雅的 YAML 结构直接声明你想要的信息形态:+```python+from hyperextract import Template++ka = Template.create("general/biography_graph")+result = ka.parse(text)+```++> 🔗 完整示例代码,请参阅 [examples/zh](./examples/zh/)++</details>++## 🧩 8 种核心知识结构++拒绝样板代码,纯干货聚焦数据本身。++++### 示例:AutoGraph 知识图谱可视化++以下是 `AutoGraph` 类型提取后的知识图谱可视化效果:++++## 🛠️ 系统架构++系统底座基于坚实的铁三角架构:**Auto-Types** (提取结构)、**Methods** (执行策略)、以及 **Templates** (声明式配置)。++++### 📋 模板结构示例++以下是一个完整的 YAML 模板示例,定义了知识图谱提取:```yamllanguage: zh@@ -102,61 +141,30 @@ display:entity_label: '{name} ({type})'relation_label: '{type}'```-</details>--### 3. Python API 深度集成--```python-from hyperextract import Template--# 一行加载内置的 YAML 模板策略-ka = Template.create("finance/event_timeline")--# 解析提取-result = ka.parse(annual_report_text)-```--> 🔗 完整示例代码,请参阅 [examples/zh](./examples/zh/)--## 🧩 8 种核心知识结构-拒绝样板代码,纯干货聚焦数据本身。----### 示例:AutoGraph 知识图谱可视化--以下是 `AutoGraph` 类型提取后的知识图谱可视化效果:----## 🛠️ 系统架构--系统底座基于坚实的铁三角架构:**Auto-Types** (提取结构)、**Methods** (执行策略)、以及 **Templates** (声明式配置)。--+### 📚 相关文档-* **设计指南**: [模板设计指南](./hyperextract/templates/DESIGN_GUIDE_ZH.md)-* **内置模板**: [预设模板目录](./hyperextract/templates/presets/)+- **预设模板**: 浏览覆盖 6 大领域的 [80+ 即用型模板](./hyperextract/templates/presets/)+- **设计指南**: 学习如何[创建自定义模板](./hyperextract/templates/DESIGN_GUIDE_ZH.md)## 📈 与其他流行库的对比-| 特性 | GraphRAG | LightRAG | KG-Gen | ATOM | **Hyper-Extract** |-|------|:---:|:---:|:---:|:---:|:---:|-| 知识图谱支持 | ✅ | ✅ | ✅ | ✅ | ✅ |-| 时序图谱 | ✅ | ❌ | ❌ | ✅ | ✅ |-| 空间图谱 | ❌ | ❌ | ❌ | ❌ | ✅ |-| 超图提取 | ❌ | ❌ | ❌ | ❌ | ✅ |-| 领域模板驱动 | ❌ | ❌ | ❌ | ❌ | ✅ |-| 交互式 CLI | ❌ | ❌ | ❌ | ❌ | ✅ |-| 多语言支持 | 部分支持 | ❌ | ❌ | ❌ | ✅ |+| 特性 | GraphRAG | LightRAG | KG-Gen | ATOM | **Hyper-Extract** |+| ------- | :------: | :------: | :----: | :--: | :---------------: |+| 知识图谱支持 | ✅ | ✅ | ✅ | ✅ | ✅ |+| 时序图谱 | ✅ | ❌ | ❌ | ✅ | ✅ |+| 空间图谱 | ❌ | ❌ | ❌ | ❌ | ✅ |+| 超图提取 | ❌ | ❌ | ❌ | ❌ | ✅ |+| 领域模板驱动 | ❌ | ❌ | ❌ | ❌ | ✅ |+| 交互式 CLI | ❌ | ❌ | ❌ | ❌ | ✅ |+| 多语言支持 | 部分支持 | ❌ | ❌ | ❌ | ✅ |## 📚 项目参考文档-* [CLI 命令行指南](./hyperextract/cli/README.md)-* [模板画廊](./hyperextract/templates/)-* [示例代码示例](./examples/)-* [完整架构文档](./docs/)+- [CLI 命令行指南](./hyperextract/cli/README.md)+- [模板画廊](./hyperextract/templates/)+- [示例代码示例](./examples/)+- [完整架构文档](./docs/)## 🤝 参与贡献与协议diff --git a/docs/assets/cli.png b/docs/assets/cli.pngindex 1b8979f..b67b872 100644Binary files a/docs/assets/cli.png and b/docs/assets/cli.png differdiff --git a/docs/en/getting-started/configuration.md b/docs/en/getting-started/configuration.mdindex 5ca4ae1..23fcc95 100644--- a/docs/en/getting-started/configuration.md+++ b/docs/en/getting-started/configuration.md@@ -6,11 +6,11 @@ Hyper-Extract uses a TOML configuration file. Default location: `~/.he/config.to```bash# Initialize with API key (recommended)-he config init -k YOUR_API_KEY+he config init -k <your-api-key># Or configure LLM and Embedder separately-he config llm --api-key YOUR_API_KEY-he config embedder --api-key YOUR_API_KEY+he config llm --api-key <your-api-key>+he config embedder --api-key <your-api-key>```## Configuration Options@@ -18,7 +18,7 @@ he config embedder --api-key YOUR_API_KEY### LLM Settings```bash-he config llm --api-key YOUR_KEY --model gpt-4o-mini+he config llm --api-key <your-api-key> --model gpt-4o-mini```| Option | Description | Default |@@ -30,7 +30,7 @@ he config llm --api-key YOUR_KEY --model gpt-4o-mini### Embedder Settings```bash-he config embedder --api-key YOUR_KEY --model text-embedding-3-small+he config embedder --api-key <your-api-key> --model text-embedding-3-small```| Option | Description | Default |diff --git a/docs/en/guides/cli.md b/docs/en/guides/cli.mdindex 7de71df..6d3af70 100644--- a/docs/en/guides/cli.md+++ b/docs/en/guides/cli.md@@ -15,13 +15,13 @@ pip install hyper-extract### Initialize Configuration```bash-he config init -k YOUR_API_KEY+he config init -k <your-api-key>```### Parse a Document```bash-he parse document.txt -o output/+he parse sample.txt -o output/```### Search Extracted Knowledge@@ -33,7 +33,7 @@ he search output/ "What are the key events?"### Feed New Documents```bash-he feed output/ new_document.txt+he feed output/ another_sample.txt```## Commands@@ -44,8 +44,8 @@ Manage configuration:```bash# Initialize-he config init -k API_KEY-+he config init -k <your-api-key>+```# Show current confighe config showdiff --git a/docs/en/index.md b/docs/en/index.mdindex 74eb87a..9656352 100644--- a/docs/en/index.md+++ b/docs/en/index.md@@ -32,10 +32,10 @@ uv pip install hyper-extract### The Command Line Way```bash-he config init -k YOUR_API_KEY-he parse document.md -o ./output/ -l zh+he config init -k <your-api-key>+he parse sample.md -t general/biography_graph -o ./output/ -l enhe search ./output/ "What are the key events?"-he feed ./output/ new_document.md+he feed ./output/ another_sample.md```### The Python API Way@@ -43,11 +43,8 @@ he feed ./output/ new_document.md```pythonfrom hyperextract import Template-# Load a preset YAML template-ka = Template.create("finance/event_timeline")--# Extract and auto-parse the document-result = ka.parse(annual_report_text)+ka = Template.create("general/biography_graph")+result = ka.parse(text)```## Documentationdiff --git a/docs/en/resources/contributing.md b/docs/en/resources/contributing.mdindex 42cc39d..de17703 100644--- a/docs/en/resources/contributing.md+++ b/docs/en/resources/contributing.md@@ -26,7 +26,7 @@ We welcome feature suggestions! Please:1. Fork the repository2. Clone your fork:```bash- git clone https://github.com/YOUR_USERNAME/hyper-extract.git+ git clone https://github.com/yifanfeng97/hyper-extract.gitcd hyper-extract```diff --git a/docs/en/resources/faq.md b/docs/en/resources/faq.mdindex 1ad0f39..afb813d 100644--- a/docs/en/resources/faq.md+++ b/docs/en/resources/faq.md@@ -69,7 +69,7 @@ See the [Template Design Guide](../concepts/templates.md) for creating custom teSolution: Set your API key using:```bash-he config init -k YOUR_API_KEY+he config init -k <your-api-key>```### Extraction Qualitydiff --git a/docs/en/resources/troubleshooting.md b/docs/en/resources/troubleshooting.mdindex 3eea635..10dbfaf 100644--- a/docs/en/resources/troubleshooting.md+++ b/docs/en/resources/troubleshooting.md@@ -138,7 +138,7 @@ pip install hyper-extract**Solution**: Initialize configuration:```bash-he config init -k YOUR_API_KEY+he config init -k <your-api-key>```## Still Having Issues?diff --git a/docs/zh/getting-started/configuration.md b/docs/zh/getting-started/configuration.mdindex bb4bc31..bdcc0d8 100644--- a/docs/zh/getting-started/configuration.md+++ b/docs/zh/getting-started/configuration.md@@ -30,7 +30,7 @@ he config llm --api-key YOUR_KEY --model gpt-4o-mini### Embedder 设置```bash-he config embedder --api-key YOUR_KEY --model text-embedding-3-small+he config embedder --api-key <your-api-key> --model text-embedding-3-small```| 选项 | 说明 | 默认值 |diff --git a/docs/zh/guides/cli.md b/docs/zh/guides/cli.mdindex 7c33477..036361b 100644--- a/docs/zh/guides/cli.md+++ b/docs/zh/guides/cli.md@@ -15,13 +15,13 @@ pip install hyper-extract### 初始化配置```bash-he config init -k YOUR_API_KEY+he config init -k <your-api-key>```### 解析文档```bash-he parse document.txt -o output/+he parse sample.txt -o output/```### 搜索提取的知识@@ -33,7 +33,7 @@ he search output/ "关键事件有哪些?"### 添加新文档```bash-he feed output/ new_document.txt+he feed output/ another_sample.txt```## 命令@@ -44,7 +44,7 @@ he feed output/ new_document.txt```bash# 初始化-he config init -k API_KEY+he config init -k <your-api-key># 显示当前配置he config showdiff --git a/docs/zh/index.md b/docs/zh/index.mdindex 5cdaf52..8cdaaaa 100644--- a/docs/zh/index.md+++ b/docs/zh/index.md@@ -32,10 +32,10 @@ uv pip install hyper-extract### 命令行方式```bash-he config init -k YOUR_API_KEY-he parse document.md -o ./output/ -l zh+he config init -k <your-api-key>+he parse sample.md -t general/biography_graph -o ./output/ -l zhhe search ./output/ "关键事件有哪些?"-he feed ./output/ new_document.md+he feed ./output/ another_sample.md```### Python API 方式@@ -43,11 +43,8 @@ he feed ./output/ new_document.md```pythonfrom hyperextract import Template-# 加载预设 YAML 模板-ka = Template.create("finance/event_timeline")--# 提取并自动解析文档-result = ka.parse(annual_report_text)+ka = Template.create("general/biography_graph")+result = ka.parse(text)```## 文档diff --git a/docs/zh/resources/contributing.md b/docs/zh/resources/contributing.mdindex 09a9870..139e515 100644--- a/docs/zh/resources/contributing.md+++ b/docs/zh/resources/contributing.md@@ -26,7 +26,7 @@1. Fork 仓库2. 克隆您的 fork:```bash- git clone https://github.com/YOUR_USERNAME/hyper-extract.git+ git clone https://github.com/yifanfeng97/hyper-extract.gitcd hyper-extract```diff --git a/docs/zh/resources/faq.md b/docs/zh/resources/faq.mdindex b9fb2f3..553887e 100644--- a/docs/zh/resources/faq.md+++ b/docs/zh/resources/faq.md@@ -69,7 +69,7 @@ result = ka.parse(document_text)解决方案:使用以下方式设置 API 密钥:```bash-he config init -k YOUR_API_KEY+he config init -k <your-api-key>```### 提取质量问题diff --git a/docs/zh/resources/troubleshooting.md b/docs/zh/resources/troubleshooting.mdindex ba5a0ac..d519272 100644--- a/docs/zh/resources/troubleshooting.md+++ b/docs/zh/resources/troubleshooting.md@@ -138,7 +138,7 @@ pip install hyper-extract**解决方案**: 初始化配置:```bash-he config init -k YOUR_API_KEY+he config init -k <your-api-key>```## 仍然有问题?diff --git a/examples/.env.example b/examples/.env.examplenew file mode 100644index 0000000..2fc8dcd--- /dev/null+++ b/examples/.env.example@@ -0,0 +1,5 @@+# OpenAI API Key (Required)+OPENAI_API_KEY=sk-your-api-key-here++# Base URL (Optional, configure when using proxy)+OPENAI_BASE_URL=https://api.openai.com/v1diff --git a/hyperextract/cli/cli.py b/hyperextract/cli/cli.pyindex 314acc6..4a56129 100644--- a/hyperextract/cli/cli.py+++ b/hyperextract/cli/cli.py@@ -51,7 +51,7 @@ def main(is_eager=True,),):- """Hyper-Extract CLI - Transform unstructured text into structured knowledge."""+ """Hyper-Extract CLI - Transform document into knowledge-abstract."""if version:from . import __version__console.print(f"[bold]Hyper-Extract CLI[/bold] version {__version__}")@@ -65,7 +65,7 @@ def main(title_text = Text("HYPER-EXTRACT", style="bold cyan")version_text = Text(f"v{__version__}", style="dim white")- desc_text = Text("Transform unstructured text into structured knowledge", style="dim")+ desc_text = Text("Transform document into knowledge-abstract", style="dim", no_wrap=True)header = Table(box=None, show_header=False, pad_edge=False)header.add_column(no_wrap=True)@@ -95,7 +95,7 @@ def main(border_style="cyan dim",padding=(0, 1),title_align="center",- width=70,+ width=80,)sections = [@@ -104,16 +104,16 @@ def main(("he list method", "List extraction methods"),("he config --help", "Manage LLM/Embedder config"),]),- make_section("✨ Create KA", [- ("he parse <input> -o <ka_path>", "Extract knowledge to new KA"),- ("he feed <ka_path> <input>", "Add knowledge to existing KA"),+ make_section("✨ Create Knowledge Abstract (KA)", [+ ("he parse <input_document> -o <ka_path>", "Extract KA from document"),+ ("he feed <ka_path> <input_document>", "Add document to existing KA"),("he build-index <ka_path>", "Build semantic search index"),]),- make_section("🔍 Explore KA", [- ("he info <ka_path>", "View Knowledge Abstract info & stats"),- ("he talk <ka_path> [-i]", "Chat with Knowledge Abstract"),+ make_section("🔍 Explore Knowledge Abstract (KA)", [+ ("he info <ka_path>", "View KA info & stats"),+ ("he talk <ka_path> [-i]", "Chat with KA"),("he search <ka_path> <query>", "Semantic search"),- ("he show <ka_path>", "Visualize knowledge graph"),+ ("he show <ka_path>", "Visualize KA"),]),]