Skip to content

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

feat: 添加领域模板示例文件并更新文档

yifanfeng97e86df4c1a783
diff --git a/README.md b/README.md
index 5e32edc..fb5a000 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
# 🔍 Hyper-Extract
> **"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.
@@ -17,71 +17,41 @@ Transform documents into **knowledge abstracts** — with just one command.
```bash
pip install hyper-extract
-he config init
-he parse document.md -o ka -l zh
-he talk ka -i
-```
-
-![CLI Configuration](docs/assets/cli.png)
-
----
-
-## ⚙️ Quick Configuration
-
-**Recommended**: gpt-4o-mini (fast & stable for structured extraction) + text-embedding-3-small
-
-```bash
he config init -k YOUR_API_KEY
-# Or with custom base URL
-he config init -k YOUR_KEY -u https://api.openai.com/v1
+
+he parse document.md -o ./knowledge_abstract/ -l zh
```
-View config: `he config show`
+> 🔗 For detailed usage, see [CLI Guide](./hyperextract/cli/README.md)
---
-## 💡 Usage Example
+## ✨ Key Features
-```bash
-he parse document.md -o ka -l zh
-he show ka
-he search ka "key insights"
-```
+| 🤖 8 Knowledge Types | 🌍 38+ Domain Templates | 💻 Interactive CLI | 🔍 Semantic Search |
+|:---:|:---:|:---:|:---:|
+| From lists to spatio-temporal graphs | Finance, Medical, Legal ready-to-use | One command for full workflow | FAISS vector similarity |
+
+> 🔗 Learn more about [8 Knowledge Types](#knowledge-types) | [Domain Templates](#domain-templates)
---
-## 🧩 Knowledge Abstract Types
+## 📊 Knowledge Types
![8 Types](docs/assets/8-types-v2.jpg)
-8 structures for extracting different types of information:
-
-**Record Types:**
-| Structure | Best For | Example |
-|-----------|----------|---------|
-| AutoModel | Structured reports | Financial statements |
-| AutoList | Key points | Meeting notes |
-| AutoSet | Entity collection | Product catalog |
-
-**Graph Types:**
-| Structure | Best For | Example |
-|-----------|----------|---------|
+| Type | Best For | Example |
+|------|----------|---------|
+| AutoModel | Structured reports | Financial summaries |
+| AutoList | Ordered lists | Meeting notes |
+| AutoSet | Deduplicated collections | Product catalogs |
| AutoGraph | Binary relations | Social networks |
-| AutoHypergraph | Multi-party events | Legal disputes |
-| AutoTemporalGraph | Event sequences | News timeline |
-| AutoSpatialGraph | Locations | Delivery routes |
+| AutoHypergraph | Multi-party events | Contract disputes |
+| AutoTemporalGraph | Temporal relations | News timelines |
+| AutoSpatialGraph | Spatial relations | Delivery routes |
| AutoSpatioTemporalGraph | Events in time & space | Historical battles |
-### Comparison with Other Libraries
-
-| Feature | KG-Gen | ATOM | Graphiti | LightRAG | Hyper-Extract |
-|---------|--------|------|----------|----------|---------------|
-| Knowledge Graph | ✅ | ✅ | ❌ | ✅ | ✅ |
-| Temporal Graph | ❌ | ✅ | ✅ | ❌ | ✅ |
-| Spatial Graph | ❌ | ❌ | ❌ | ❌ | ✅ |
-| Hypergraph | ❌ | ❌ | ❌ | ❌ | ✅ |
-| Templates | ❌ | ❌ | ❌ | ❌ | ✅ |
-| CLI Tool | ❌ | ❌ | ❌ | ❌ | ✅ |
+> 🔗 See [Full Type Documentation](./hyperextract/types/) | [Template Design Guide](./hyperextract/templates/DESIGN_GUIDE.md)
---
@@ -89,10 +59,8 @@ he search ka "key insights"
![Domains](docs/assets/domains-v2.png)
-Pre-built templates for common domains:
-
-| Domain | Templates | Scenarios |
-|--------|-----------|-----------|
+| Domain | Templates | Typical Scenarios |
+|--------|-----------|-------------------|
| General | 13 | Workflow, Biography, Concept maps |
| Finance | 5 | Earnings reports, Risk factors |
| Medicine | 5 | Clinical records, Drug interactions |
@@ -100,48 +68,81 @@ Pre-built templates for common domains:
| Industry | 5 | Equipment topology, Failure analysis |
| Legal | 5 | Contract clauses, Case citations |
-**Total: 6 Domains · 37 Templates**
-
-See [Template Gallery](hyperextract/templates/) for all templates.
+> 🔗 See [Full Template Gallery](./hyperextract/templates/) | [Template Design Guide](./hyperextract/templates/DESIGN_GUIDE.md)
---
-## 💻 CLI Reference
+## 🎯 Python API Examples
-### Parse Command
+```python
+from hyperextract import Template
-```bash
-he parse document.md -o my_ka -l zh
-he parse document.md -o my_ka -t general/knowledge_graph -l zh
+ka = Template.create("finance/earnings_summary")
+result = ka.parse(financial_report_text)
+# result.operating_revenue = "100 billion RMB"
```
-### Build Search Index
+> 🔗 See more [Example Code](./examples/)
+
+---
+
+## 📈 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 | ❌ | ❌ | ❌ | ✅ |
+| Visualization | Partial | ❌ | ❌ | ❌ | ✅ |
+
+---
+
+## 💻 CLI Reference
+
+### Parse Documents
```bash
-he build-index my_ka
+he parse document.md -o ./knowledge_abstract/ -l zh
+he parse earnings.md -o ./finance_report/ -t finance/earnings_summary -l zh
```
-### Search Knowledge Abstract
+### Search & Chat
```bash
-he search my_ka "What are the key findings?"
-he search my_ka "key insights" -n 5
+he search ./finance_report/ "What was the revenue growth?"
+he talk ./finance_report/ -i # Interactive mode
```
### Visualize
```bash
-he show my_ka
-he info my_ka
+he show ./finance_report/ # Graph visualization
+he info ./finance_report/ # Show statistics
```
-For full CLI documentation, see [CLI Guide](hyperextract/cli/README.md).
+> 🔗 For full CLI documentation, see [CLI Guide](./hyperextract/cli/README.md)
+
+---
+
+## 🤝 Contributing
+
+Contributions are welcome! Please submit Issues and PRs.
+
+## 📄 License
+
+Apache-2.0
---
-## 📚 Documentation
+## 📚 Related Documentation
-- [📖 Full Documentation](docs/)
-- [💻 Examples](examples/)
-- [🏷️ Template Gallery](hyperextract/templates/)
-- [🖥️ CLI Guide](hyperextract/cli/README.md)
+| Documentation | Description |
+|---------------|-------------|
+| [CLI Guide](./hyperextract/cli/README.md) | Complete CLI reference |
+| [Template Gallery](./hyperextract/templates/) | 38+ domain templates |
+| [Example Code](./examples/) | Python API examples |
+| [Full Documentation](./docs/) | Architecture & implementation |
diff --git a/README_ZH.md b/README_ZH.md
index 20ded1b..f4cd1ee 100644
--- a/README_ZH.md
+++ b/README_ZH.md
@@ -1,14 +1,14 @@
# 🔍 Hyper-Extract
> **"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。
![Hero](docs/assets/hero-v2.jpg)
-[📖 English Version](./README.md) · [中文版](#)
+[📖 English Version](./README.md) · [中文版](./README_ZH.md)
---
@@ -17,71 +17,41 @@
```bash
pip install hyper-extract
-he config init
-he parse document.md -o ka -l zh
-he talk ka -i
-```
-
-![CLI 配置指南](docs/assets/cli.png)
-
----
-
-## ⚙️ 快速配置
-
-**推荐配置**:gpt-4o-mini(快速稳定,适合结构化提取)+ text-embedding-3-small
-
-```bash
he config init -k YOUR_API_KEY
-# 或指定自定义接口
-he config init -k YOUR_KEY -u https://api.openai.com/v1
+
+he parse document.md -o ./knowledge_abstract/ -l zh
```
-查看配置:`he config show`
+> 🔗 详细使用说明请查看 [CLI 指南](./hyperextract/cli/README.md)
---
-## 💡 使用示例
+## ✨ 核心特性
-```bash
-he parse document.md -o ka -l zh
-he show ka
-he search ka "关键信息"
-```
+| 🤖 8种知识类型 | 🌍 38+领域模板 | 💻 交互式CLI | 🔍 语义检索 |
+|:---:|:---:|:---:|:---:|
+| 从列表到时空图谱 | 金融医疗法律开箱即用 | 一行命令完成全流程 | FAISS向量相似度 |
----
+> 🔗 了解 [8种知识类型](#知识类型) | [领域模板](#领域模板)
-## 🧩 知识摘要类型
-
-![8 种类型](docs/assets/8-types-v2.jpg)
+---
-8 种知识结构,满足不同文档类型:
+## 📊 知识类型
-**记录型(Record Types):**
-| 结构 | 适用场景 | 示例 |
-|------|----------|------|
-| AutoModel | 结构化报告 | 财务报表 |
-| AutoList | 要点列表 | 会议记录 |
-| AutoSet | 实体集合 | 产品目录 |
+![8种类型](docs/assets/8-types-v2.jpg)
-**图型(Graph Types):**
-| 结构 | 适用场景 | 示例 |
+| 类型 | 适用场景 | 示例 |
|------|----------|------|
+| AutoModel | 结构化报告 | 财报摘要 |
+| AutoList | 有序列表 | 会议要点 |
+| AutoSet | 去重集合 | 产品目录 |
| AutoGraph | 二元关系 | 社交网络 |
-| AutoHypergraph | 多方事件 | 法律纠纷 |
-| AutoTemporalGraph | 事件序列 | 新闻时间线 |
-| AutoSpatialGraph | 地理位置 | 配送路线 |
+| AutoHypergraph | 多元事件 | 合同纠纷 |
+| AutoTemporalGraph | 时序关系 | 新闻时间线 |
+| AutoSpatialGraph | 空间关系 | 配送路线 |
| AutoSpatioTemporalGraph | 时空事件 | 历史战役 |
-### 与其他库的对比
-
-| 功能 | KG-Gen | ATOM | Graphiti | LightRAG | Hyper-Extract |
-|------|--------|------|----------|----------|---------------|
-| 知识图谱 | ✅ | ✅ | ❌ | ✅ | ✅ |
-| 时序图谱 | ❌ | ✅ | ✅ | ❌ | ✅ |
-| 空间图谱 | ❌ | ❌ | ❌ | ❌ | ✅ |
-| 超图 | ❌ | ❌ | ❌ | ❌ | ✅ |
-| 模板 | ❌ | ❌ | ❌ | ❌ | ✅ |
-| CLI 工具 | ❌ | ❌ | ❌ | ❌ | ✅ |
+> 🔗 查看 [完整类型文档](./hyperextract/types/) | [模板设计指南](./hyperextract/templates/DESIGN_GUIDE.md)
---
@@ -89,8 +59,6 @@ he search ka "关键信息"
![领域概览](docs/assets/domains-v2.png)
-开箱即用的领域模板:
-
| 领域 | 模板数 | 典型场景 |
|------|--------|----------|
| General | 13 | 工作流、传记、概念图 |
@@ -100,9 +68,36 @@ he search ka "关键信息"
| Industry | 5 | 设备拓扑、事故分析 |
| Legal | 5 | 合同条款、判例引用 |
-**总计:6 大领域 · 37 个模板**
+> 🔗 查看 [完整模板库](./hyperextract/templates/) | [模板设计指南](./hyperextract/templates/DESIGN_GUIDE.md)
-查看 [模板库](hyperextract/templates/) 获取所有模板。
+---
+
+## 🎯 Python API 示例
+
+```python
+from hyperextract import Template
+
+ka = Template.create("finance/earnings_summary")
+result = ka.parse(financial_report_text)
+# result.operating_revenue = "1000亿元"
+```
+
+> 🔗 查看更多 [示例代码](./examples/)
+
+---
+
+## 📈 与同类项目对比
+
+| 特性 | GraphRAG | LightRAG | KG-Gen | ATOM | **Hyper-Extract** |
+|------|:---:|:---:|:---:|:---:|:---:|
+| 知识图谱 | ✅ | ✅ | ✅ | ✅ | ✅ |
+| 时序图谱 | ✅ | ❌ | ❌ | ✅ | ✅ |
+| 空间图谱 | ❌ | ❌ | ❌ | ❌ | ✅ |
+| 超图 | ❌ | ❌ | ❌ | ❌ | ✅ |
+| 领域模板 | ❌ | ❌ | ❌ | ❌ | ✅ |
+| CLI工具 | ❌ | ❌ | ❌ | ❌ | ✅ |
+| 多语言 | 部分 | ❌ | ❌ | ❌ | ✅ |
+| 可视化 | 部分 | ❌ | ❌ | ❌ | ✅ |
---
@@ -111,37 +106,43 @@ he search ka "关键信息"
### 解析文档
```bash
-he parse document.md -o my_ka -l zh
-he parse document.md -o my_ka -t general/knowledge_graph -l zh
+he parse document.md -o ./knowledge_abstract/ -l zh
+he parse earnings.md -o ./finance_report/ -t finance/earnings_summary -l zh
```
-### 构建搜索索引
+### 搜索与问答
```bash
-he build-index my_ka
+he search ./finance_report/ "营收增长了多少?"
+he talk ./finance_report/ -i # 交互式问答
```
-### 搜索知识摘要
+### 可视化
```bash
-he search my_ka "关键发现是什么?"
-he search my_ka "关键信息" -n 5
+he show ./finance_report/ # 图形化展示
+he info ./finance_report/ # 显示统计信息
```
-### 可视化
+> 🔗 完整的 CLI 文档请查看 [CLI 指南](./hyperextract/cli/README.md)
-```bash
-he show my_ka
-he info my_ka
-```
+---
+
+## 🤝 贡献
+
+欢迎提交 Issue 和 PR!
+
+## 📄 许可证
-完整的 CLI 文档请查看 [CLI 指南](hyperextract/cli/README.md)。
+Apache-2.0
---
-## 📚 文档
+## 📚 相关文档
-- [📖 完整文档](docs/)
-- [💻 示例代码](examples/)
-- [🏷️ 模板库](hyperextract/templates/)
-- [🖥️ CLI 指南](hyperextract/cli/README.md)
+| 文档 | 说明 |
+|------|------|
+| [CLI 指南](./hyperextract/cli/README.md) | 命令行工具完整参考 |
+| [模板库](./hyperextract/templates/) | 38+ 领域模板 |
+| [示例代码](./examples/) | Python API 使用示例 |
+| [完整文档](./docs/) | 架构设计与实现细节 |
diff --git a/examples/templates/README.md b/examples/templates/README.md
index c425251..7b0ef46 100644
--- a/examples/templates/README.md
+++ b/examples/templates/README.md
@@ -1,14 +1,18 @@
# Templates 目录
-本目录包含 Hyper-Extract 预设模板的测试工具。
+本目录包含 Hyper-Extract 各领域预设模板的测试工具。
## 文件说明
| 文件 | 说明 |
|------|------|
-| `templates_mapping.yaml` | 模板与测试数据的映射配置 |
| `list_templates.py` | 列出所有可用的预设模板 |
-| `run_template.py` | 执行指定模板的测试 |
+| `finance_template.py` | 金融领域模板测试 |
+| `general_template.py` | 通用领域模板测试 |
+| `industry_template.py` | 工业领域模板测试 |
+| `legal_template.py` | 法律领域模板测试 |
+| `medicine_template.py` | 医学领域模板测试 |
+| `tcm_template.py` | 中医领域模板测试 |
## 使用方法
@@ -18,59 +22,127 @@
python examples/templates/list_templates.py
```
-输出示例:
-```
-【FINANCE 领域】 (5 templates)
- • earnings_summary
- Type: model
- Description: 财报电话会议摘要
- Template: finance/earnings_summary.yaml
- Test Data: tests/test_data/zh/finance/earnings_call_transcript_sample.md
-```
+### 运行领域模板测试
-### 运行模板测试
+每个领域对应一个独立的测试文件,直接运行即可:
```bash
-python examples/templates/run_template.py -d <domain> -t <template>
-```
+# 金融领域
+python examples/templates/finance_template.py
-参数说明:
-- `-d, --domain`: 领域名称 (finance, general, industry, legal, medicine, tcm)
-- `-t, --template`: 模板名称
+# 通用领域
+python examples/templates/general_template.py
-示例:
-```bash
-python examples/templates/run_template.py -d finance -t earnings_summary
-python examples/templates/run_template.py -d general -t base_graph
-python examples/templates/run_template.py -d tcm -t formula_composition
+# 工业领域
+python examples/templates/industry_template.py
+
+# 法律领域
+python examples/templates/legal_template.py
+
+# 医学领域
+python examples/templates/medicine_template.py
+
+# 中医领域
+python examples/templates/tcm_template.py
```
-### 文件内配置
+### 切换测试用例
+
+每个模板文件包含多个测试用例,通过注释的方式切换:
-编辑 `run_template.py` 顶部的 `CONFIG` 字典设置默认的 domain 和 template:
+1. 打开对应的模板文件
+2. 找到"测试用例"部分
+3. 取消注释要测试的用例,注释其他用例
+4. 修改 `main()` 函数中的 `text` 和 `template_name`
```python
-CONFIG = {
- "domain": "general",
- "template": "base_graph",
-}
-```
+# // test for 财报电话会议摘要
+# text = """星河智能科技股份有限公司..."""
+# template_name = "finance/earnings_summary"
-然后直接运行:
-```bash
-python examples/templates/run_template.py
+# // test for 股权结构图(取消注释此行)
+text = """IPO招股说明书"""
+template_name = "finance/ownership_graph"
```
## 支持的领域
-| 领域 | 模板数量 | 描述 |
-|------|---------|------|
-| finance | 5 | 金融领域:财报摘要、股权结构、风险因子等 |
-| general | 11 | 通用领域:基础图谱、传记、工作流程等 |
-| industry | 5 | 工业领域:设备拓扑、应急响应、故障分析等 |
-| legal | 5 | 法律领域:案例引用、合规清单、合同义务等 |
-| medicine | 5 | 医学领域:解剖图谱、药物相互作用、治疗方案等 |
-| tcm | 5 | 中医领域:方剂组成、经络图、证候推理等 |
+| 领域 | 文件 | 模板数量 | 描述 |
+|------|------|---------|------|
+| finance | finance_template.py | 5 | 金融领域:财报摘要、股权结构、风险因子等 |
+| general | general_template.py | 11 | 通用领域:基础图谱、传记、概念图等 |
+| industry | industry_template.py | 5 | 工业领域:设备拓扑、应急响应、故障分析等 |
+| legal | legal_template.py | 5 | 法律领域:案例引用、合规清单、合同义务等 |
+| medicine | medicine_template.py | 5 | 医学领域:解剖图谱、药物相互作用、治疗方案等 |
+| tcm | tcm_template.py | 5 | 中医领域:方剂组成、经络图、证候推理等 |
+
+## 各领域模板列表
+
+### Finance (金融)
+
+| 模板名称 | 类型 | 说明 |
+|---------|------|------|
+| earnings_summary | model | 财报电话会议摘要 |
+| event_timeline | temporal_graph | 重大事件时间线 |
+| ownership_graph | graph | 股权结构图 |
+| risk_factor_set | set | 风险因子集合 |
+| sentiment_model | model | 市场情绪模型 |
+
+### General (通用)
+
+| 模板名称 | 类型 | 说明 |
+|---------|------|------|
+| base_graph | graph | 基础知识图谱 |
+| base_hypergraph | hypergraph | 基础超图 |
+| base_list | list | 基础列表 |
+| biography_graph | graph | 传记图谱 |
+| concept_graph | graph | 概念图谱 |
+| doc_structure | list | 文档结构 |
+| workflow_graph | graph | 工作流程图 |
+| base_model | model | 基础模型 |
+| base_set | set | 基础集合 |
+| base_temporal_graph | temporal_graph | 基础时序图 |
+| base_spatial_graph | spatial_graph | 基础空间图 |
+
+### Industry (工业)
+
+| 模板名称 | 类型 | 说明 |
+|---------|------|------|
+| equipment_topology | graph | 设备拓扑图 |
+| operation_flow | list | 操作流程 |
+| safety_control | set | 安全控制 |
+| emergency_response | temporal_graph | 应急响应时间线 |
+| failure_case | hypergraph | 故障案例 |
+
+### Legal (法律)
+
+| 模板名称 | 类型 | 说明 |
+|---------|------|------|
+| case_citation | graph | 案例引用图 |
+| case_fact_timeline | temporal_graph | 案件事实时间线 |
+| compliance_list | list | 合规清单 |
+| contract_obligation | set | 合同义务 |
+| defined_term_set | set | 术语定义 |
+
+### Medicine (医学)
+
+| 模板名称 | 类型 | 说明 |
+|---------|------|------|
+| anatomy_graph | graph | 解剖结构图 |
+| discharge_instruction | list | 出院指导 |
+| drug_interaction | graph | 药物相互作用图 |
+| hospital_timeline | temporal_graph | 医院事件时间线 |
+| treatment_map | hypergraph | 治疗方案图 |
+
+### TCM (中医)
+
+| 模板名称 | 类型 | 说明 |
+|---------|------|------|
+| formula_composition | graph | 方剂组成图 |
+| herb_property | model | 药材属性 |
+| herb_relation | graph | 药材关系图 |
+| meridian_graph | graph | 经络图 |
+| syndrome_reasoning | hypergraph | 证候推理 |
## 模板类型
diff --git a/examples/templates/finance_template.py b/examples/templates/finance_template.py
new file mode 100644
index 0000000..d567401
--- /dev/null
+++ b/examples/templates/finance_template.py
@@ -0,0 +1,75 @@
+"""
+金融领域模板示例
+
+Usage:
+ python examples/templates/finance_template.py
+"""
+
+import sys
+from pathlib import Path
+
+project_root = Path(__file__).resolve().parent.parent.parent
+sys.path.append(str(project_root))
+
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from hyperextract import Template
+
+import dotenv
+
+dotenv.load_dotenv()
+
+# ==================== 测试用例(取消注释选择要测试的用例) ====================
+
+# // test for 重大事件时间线
+test_data_file = "annual_report_sample.md"
+template_name = "finance/event_timeline"
+
+# // test for 股权结构图
+# test_data_file = "ipo_prospectus_sample.md"
+# template_name = "finance/ownership_graph"
+
+# // test for 风险因子集合
+# test_data_file = "annual_report_sample.md"
+# template_name = "finance/risk_factor_set"
+
+# // test for 市场情绪模型
+# test_data_file = "financial_news_sample.md"
+# template_name = "finance/sentiment_model"
+
+# // test for 财报电话会议摘要
+# test_data_file = "earnings_call_transcript_sample.md"
+# template_name = "finance/earnings_summary"
+
+# ==================== 主函数 ====================
+
+def main():
+ test_data_dir = project_root / "tests" / "test_data" / "zh" / "finance"
+ input_file = test_data_dir / test_data_file
+
+ with open(input_file, "r", encoding="utf-8") as f:
+ text = f.read()
+
+ print("=" * 80)
+ print(f"🧪 测试模板: {template_name}")
+ print(f"📂 测试数据: {input_file}")
+ print("=" * 80)
+
+ llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+ embedder = OpenAIEmbeddings()
+
+ extractor = Template.create(
+ template_name,
+ language="zh",
+ llm_client=llm,
+ embedder=embedder,
+ )
+
+ print("\n📥 正在提取知识摘要...")
+ extractor.feed_text(text)
+ print("✅ 提取完成!\n")
+
+ extractor.show()
+
+
+if __name__ == "__main__":
+ main()
diff --git a/examples/templates/general_template.py b/examples/templates/general_template.py
new file mode 100644
index 0000000..36c2d44
--- /dev/null
+++ b/examples/templates/general_template.py
@@ -0,0 +1,75 @@
+"""
+通用领域模板示例
+
+Usage:
+ python examples/templates/general_template.py
+"""
+
+import sys
+from pathlib import Path
+
+project_root = Path(__file__).resolve().parent.parent.parent
+sys.path.append(str(project_root))
+
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from hyperextract import Template
+
+import dotenv
+
+dotenv.load_dotenv()
+
+# ==================== 测试用例(取消注释选择要测试的用例) ====================
+
+# // test for 基础知识图谱
+test_data_file = "arbitrary_tech_news.md"
+template_name = "general/base_graph"
+
+# // test for 基础超图
+# test_data_file = "encyclopedia_machine_learning.md"
+# template_name = "general/base_hypergraph"
+
+# // test for 基础列表
+# test_data_file = "regulation_company_policy.md"
+# template_name = "general/base_list"
+
+# // test for 传记图谱
+# test_data_file = "biography_scientist.md"
+# template_name = "general/biography_graph"
+
+# // test for 概念图谱
+# test_data_file = "encyclopedia_machine_learning.md"
+# template_name = "general/concept_graph"
+
+# ==================== 主函数 ====================
+
+def main():
+ test_data_dir = project_root / "tests" / "test_data" / "zh" / "general"
+ input_file = test_data_dir / test_data_file
+
+ with open(input_file, "r", encoding="utf-8") as f:
+ text = f.read()
+
+ print("=" * 80)
+ print(f"🧪 测试模板: {template_name}")
+ print(f"📂 测试数据: {input_file}")
+ print("=" * 80)
+
+ llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+ embedder = OpenAIEmbeddings()
+
+ extractor = Template.create(
+ template_name,
+ language="zh",
+ llm_client=llm,
+ embedder=embedder,
+ )
+
+ print("\n📥 正在提取知识摘要...")
+ extractor.feed_text(text)
+ print("✅ 提取完成!\n")
+
+ extractor.show()
+
+
+if __name__ == "__main__":
+ main()
diff --git a/examples/templates/industry_template.py b/examples/templates/industry_template.py
new file mode 100644
index 0000000..e545e54
--- /dev/null
+++ b/examples/templates/industry_template.py
@@ -0,0 +1,75 @@
+"""
+工业领域模板示例
+
+Usage:
+ python examples/templates/industry_template.py
+"""
+
+import sys
+from pathlib import Path
+
+project_root = Path(__file__).resolve().parent.parent.parent
+sys.path.append(str(project_root))
+
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from hyperextract import Template
+
+import dotenv
+
+dotenv.load_dotenv()
+
+# ==================== 测试用例(取消注释选择要测试的用例) ====================
+
+# // test for 设备拓扑图
+test_data_file = "equipment_technical_manual.md"
+template_name = "industry/equipment_topology"
+
+# // test for 操作流程
+# test_data_file = "operation_maintenance_manual.md"
+# template_name = "industry/operation_flow"
+
+# // test for 安全控制
+# test_data_file = "safety_management_handbook.md"
+# template_name = "industry/safety_control"
+
+# // test for 应急响应时间线
+# test_data_file = "safety_management_handbook.md"
+# template_name = "industry/emergency_response"
+
+# // test for 故障案例
+# test_data_file = "failure_analysis_report.md"
+# template_name = "industry/failure_case"
+
+# ==================== 主函数 ====================
+
+def main():
+ test_data_dir = project_root / "tests" / "test_data" / "zh" / "industry"
+ input_file = test_data_dir / test_data_file
+
+ with open(input_file, "r", encoding="utf-8") as f:
+ text = f.read()
+
+ print("=" * 80)
+ print(f"🧪 测试模板: {template_name}")
+ print(f"📂 测试数据: {input_file}")
+ print("=" * 80)
+
+ llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+ embedder = OpenAIEmbeddings()
+
+ extractor = Template.create(
+ template_name,
+ language="zh",
+ llm_client=llm,
+ embedder=embedder,
+ )
+
+ print("\n📥 正在提取知识摘要...")
+ extractor.feed_text(text)
+ print("✅ 提取完成!\n")
+
+ extractor.show()
+
+
+if __name__ == "__main__":
+ main()
diff --git a/examples/templates/legal_template.py b/examples/templates/legal_template.py
new file mode 100644
index 0000000..f0b8df0
--- /dev/null
+++ b/examples/templates/legal_template.py
@@ -0,0 +1,75 @@
+"""
+法律领域模板示例
+
+Usage:
+ python examples/templates/legal_template.py
+"""
+
+import sys
+from pathlib import Path
+
+project_root = Path(__file__).resolve().parent.parent.parent
+sys.path.append(str(project_root))
+
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from hyperextract import Template
+
+import dotenv
+
+dotenv.load_dotenv()
+
+# ==================== 测试用例(取消注释选择要测试的用例) ====================
+
+# // test for 案例引用图
+# test_data_file = "legal_treatise_sample.md"
+# template_name = "legal/case_citation"
+
+# // test for 案件事实时间线
+# test_data_file = "court_judgment_sample.md"
+# template_name = "legal/case_fact_timeline"
+
+# // test for 合规清单
+# test_data_file = "compliance_filing_sample.md"
+# template_name = "legal/compliance_list"
+
+# // test for 合同义务
+test_data_file = "msa_contract_sample.md"
+template_name = "legal/contract_obligation"
+
+# // test for 术语定义
+# test_data_file = "msa_contract_sample.md"
+# template_name = "legal/defined_term_set"
+
+# ==================== 主函数 ====================
+
+def main():
+ test_data_dir = project_root / "tests" / "test_data" / "zh" / "legal"
+ input_file = test_data_dir / test_data_file
+
+ with open(input_file, "r", encoding="utf-8") as f:
+ text = f.read()
+
+ print("=" * 80)
+ print(f"🧪 测试模板: {template_name}")
+ print(f"📂 测试数据: {input_file}")
+ print("=" * 80)
+
+ llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+ embedder = OpenAIEmbeddings()
+
+ extractor = Template.create(
+ template_name,
+ language="zh",
+ llm_client=llm,
+ embedder=embedder,
+ )
+
+ print("\n📥 正在提取知识摘要...")
+ extractor.feed_text(text)
+ print("✅ 提取完成!\n")
+
+ extractor.show()
+
+
+if __name__ == "__main__":
+ main()
diff --git a/examples/templates/medicine_template.py b/examples/templates/medicine_template.py
new file mode 100644
index 0000000..9e18183
--- /dev/null
+++ b/examples/templates/medicine_template.py
@@ -0,0 +1,75 @@
+"""
+医学领域模板示例
+
+Usage:
+ python examples/templates/medicine_template.py
+"""
+
+import sys
+from pathlib import Path
+
+project_root = Path(__file__).resolve().parent.parent.parent
+sys.path.append(str(project_root))
+
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from hyperextract import Template
+
+import dotenv
+
+dotenv.load_dotenv()
+
+# ==================== 测试用例(取消注释选择要测试的用例) ====================
+
+# // test for 解剖结构图
+# test_data_file = "textbook_sample.md"
+# template_name = "medicine/anatomy_graph"
+
+# // test for 出院指导
+test_data_file = "discharge_summary_sample.md"
+template_name = "medicine/discharge_instruction"
+
+# // test for 药物相互作用图
+# test_data_file = "package_insert_sample.md"
+# template_name = "medicine/drug_interaction"
+
+# // test for 医院事件时间线
+# test_data_file = "pathology_report_sample.md"
+# template_name = "medicine/hospital_timeline"
+
+# // test for 治疗方案图
+# test_data_file = "clinical_guideline_sample.md"
+# template_name = "medicine/treatment_map"
+
+# ==================== 主函数 ====================
+
+def main():
+ test_data_dir = project_root / "tests" / "test_data" / "zh" / "medicine"
+ input_file = test_data_dir / test_data_file
+
+ with open(input_file, "r", encoding="utf-8") as f:
+ text = f.read()
+
+ print("=" * 80)
+ print(f"🧪 测试模板: {template_name}")
+ print(f"📂 测试数据: {input_file}")
+ print("=" * 80)
+
+ llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+ embedder = OpenAIEmbeddings()
+
+ extractor = Template.create(
+ template_name,
+ language="zh",
+ llm_client=llm,
+ embedder=embedder,
+ )
+
+ print("\n📥 正在提取知识摘要...")
+ extractor.feed_text(text)
+ print("✅ 提取完成!\n")
+
+ extractor.show()
+
+
+if __name__ == "__main__":
+ main()
diff --git a/examples/templates/run_template.py b/examples/templates/run_template.py
deleted file mode 100644
index 477b534..0000000
--- a/examples/templates/run_template.py
+++ /dev/null
@@ -1,130 +0,0 @@
-"""
-Run Template - 执行预设模板测试
-
-Usage:
- python examples/templates/run_template.py -d <domain> -t <template_name>
-
- or edit CONFIG below to set default domain and template
-
-Examples:
- python examples/templates/run_template.py -d finance -t earnings_summary
- python examples/templates/run_template.py -d general -t base_graph
- python examples/templates/run_template.py -d tcm -t formula_composition
-"""
-
-import argparse
-import sys
-import yaml
-from pathlib import Path
-
-project_root = Path(__file__).resolve().parent.parent.parent
-sys.path.append(str(project_root))
-
-CONFIG = {
- "domain": "general",
- "template": "base_graph",
-}
-
-
-def load_mappings():
- mapping_file = Path(__file__).parent / "templates_mapping.yaml"
- with open(mapping_file, "r", encoding="utf-8") as f:
- return yaml.safe_load(f)
-
-
-def run_template(domain: str, template_name: str):
- mappings = load_mappings()
-
- if domain not in mappings:
- print(f"Error: Domain '{domain}' not found.")
- print(f"Available domains: {', '.join(mappings.keys())}")
- return False
-
- domain_mappings = mappings[domain]
-
- if template_name not in domain_mappings:
- print(f"Error: Template '{template_name}' not found in domain '{domain}'.")
- print("Available templates:")
- for name in domain_mappings.keys():
- print(f" - {name}")
- return False
-
- template_info = domain_mappings[template_name]
- template_path = project_root / "hyperextract" / "templates" / "presets" / f"{template_info['template']}.yaml"
- input_path = project_root / "tests" / "test_data" / "zh" / template_info["input"]
-
- print("\n" + "=" * 80)
- print(f"🧪 Template Test: {domain}/{template_name}")
- print("=" * 80)
-
- print(f"\n📄 Template: {template_path}")
- print(f"📥 Input: {input_path}")
-
- if not template_path.exists():
- print(f"\n❌ Error: Template file not found: {template_path}")
- return False
-
- if not input_path.exists():
- print(f"\n❌ Error: Input file not found: {input_path}")
- return False
-
- with open(template_path, "r", encoding="utf-8") as f:
- template_content = f.read()
-
- with open(input_path, "r", encoding="utf-8") as f:
- input_content = f.read()
-
- print("\n" + "-" * 80)
- print("📋 Template Content:")
- print("-" * 80)
- print(template_content[:500] + "..." if len(template_content) > 500 else template_content)
-
- print("\n" + "-" * 80)
- print(f"📖 Input Content ({len(input_content)} chars):")
- print("-" * 80)
- print(input_content[:500] + "..." if len(input_content) > 500 else input_content)
-
- print("\n" + "-" * 80)
- print("⚙️ Running extraction...")
- print("-" * 80)
-
- print("\n✅ Template and input loaded successfully!")
- print("\n To implement full extraction, integrate with:")
- print(" - AutoGraph for graph extraction")
- print(" - AutoHypergraph for hypergraph extraction")
- print(" - AutoList for list extraction")
- print(" - AutoModel for model extraction")
- print(" - AutoSet for set extraction")
- print(" - AutoTemporalGraph for temporal graph extraction")
- print(" - AutoSpatialGraph for spatial graph extraction")
- print(" - AutoSpatioTemporalGraph for spatio-temporal graph extraction")
-
- print("\n" + "=" * 80 + "\n")
-
- return True
-
-
-def main():
- parser = argparse.ArgumentParser(description="Run Hyper-Extract preset template test")
- parser.add_argument("-d", "--domain", help="Domain name (e.g., finance, general, tcm)")
- parser.add_argument("-t", "--template", help="Template name (e.g., earnings_summary, base_graph)")
-
- args = parser.parse_args()
-
- domain = args.domain if args.domain else CONFIG["domain"]
- template = args.template if args.template else CONFIG["template"]
-
- if not args.domain and not args.template:
- print("\n📝 Using default config from file:")
- print(f" Domain: {domain}")
- print(f" Template: {template}")
- print(" (Use -d and -t to override)\n")
-
- success = run_template(domain, template)
-
- if not success:
- sys.exit(1)
-
-
-if __name__ == "__main__":
- main()
diff --git a/examples/templates/tcm_template.py b/examples/templates/tcm_template.py
new file mode 100644
index 0000000..ab3e0ff
--- /dev/null
+++ b/examples/templates/tcm_template.py
@@ -0,0 +1,75 @@
+"""
+中医领域模板示例
+
+Usage:
+ python examples/templates/tcm_template.py
+"""
+
+import sys
+from pathlib import Path
+
+project_root = Path(__file__).resolve().parent.parent.parent
+sys.path.append(str(project_root))
+
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from hyperextract import Template
+
+import dotenv
+
+dotenv.load_dotenv()
+
+# ==================== 测试用例(取消注释选择要测试的用例) ====================
+
+# // test for 方剂组成图
+# test_data_file = "prescription_formulary_sample.md"
+# template_name = "tcm/formula_composition"
+
+# // test for 药材属性
+# test_data_file = "herb_property_single.md"
+# template_name = "tcm/herb_property"
+
+# // test for 药材关系图
+# test_data_file = "herbal_compendium_sample.md"
+# template_name = "tcm/herb_relation"
+
+# // test for 经络图
+# test_data_file = "meridian_treatise_sample.md"
+# template_name = "tcm/meridian_graph"
+
+# // test for 证候推理
+test_data_file = "medical_case_record_sample.md"
+template_name = "tcm/syndrome_reasoning"
+
+# ==================== 主函数 ====================
+
+def main():
+ test_data_dir = project_root / "tests" / "test_data" / "zh" / "tcm"
+ input_file = test_data_dir / test_data_file
+
+ with open(input_file, "r", encoding="utf-8") as f:
+ text = f.read()
+
+ print("=" * 80)
+ print(f"🧪 测试模板: {template_name}")
+ print(f"📂 测试数据: {input_file}")
+ print("=" * 80)
+
+ llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+ embedder = OpenAIEmbeddings()
+
+ extractor = Template.create(
+ template_name,
+ language="zh",
+ llm_client=llm,
+ embedder=embedder,
+ )
+
+ print("\n📥 正在提取知识摘要...")
+ extractor.feed_text(text)
+ print("✅ 提取完成!\n")
+
+ extractor.show()
+
+
+if __name__ == "__main__":
+ main()
diff --git a/examples/templates/templates_mapping.yaml b/examples/templates/templates_mapping.yaml
deleted file mode 100644
index 3ff1079..0000000
--- a/examples/templates/templates_mapping.yaml
+++ /dev/null
@@ -1,243 +0,0 @@
-# Hyper-Extract Examples: Templates Mapping
-# 模板与测试数据映射表
-# 格式: 模板路径 -> 测试数据路径
-
-# 测试数据根目录
-test_data_root: "tests/test_data/zh"
-
-# 模板根目录
-template_root: "hyperextract/templates/presets"
-
-# Finance 领域 (5个模板)
-finance:
- earnings_summary:
- template: "finance/earnings_summary"
- input: "finance/earnings_call_transcript_sample.md"
- type: "model"
- description: "财报电话会议摘要"
-
- event_timeline:
- template: "finance/event_timeline"
- input: "finance/annual_report_sample.md"
- type: "temporal_graph"
- description: "重大事件时间线"
-
- ownership_graph:
- template: "finance/ownership_graph"
- input: "finance/ipo_prospectus_sample.md"
- type: "graph"
- description: "股权结构图"
-
- risk_factor_set:
- template: "finance/risk_factor_set"
- input: "finance/annual_report_sample.md"
- type: "set"
- description: "风险因子集合"
-
- sentiment_model:
- template: "finance/sentiment_model"
- input: "finance/financial_news_sample.md"
- type: "model"
- description: "市场情绪模型"
-
-# General 领域 (11个模板)
-general:
- base_graph:
- template: "general/base_graph"
- input: "general/arbitrary_tech_news.md"
- type: "graph"
- description: "基础知识图谱"
-
- base_hypergraph:
- template: "general/base_hypergraph"
- input: "general/encyclopedia_machine_learning.md"
- type: "hypergraph"
- description: "基础超图"
-
- base_list:
- template: "general/base_list"
- input: "general/regulation_company_policy.md"
- type: "list"
- description: "基础列表"
-
- base_model:
- template: "general/base_model"
- input: "general/arbitrary_tech_news.md"
- type: "model"
- description: "基础模型"
-
- base_set:
- template: "general/base_set"
- input: "general/arbitrary_tech_news.md"
- type: "set"
- description: "基础集合"
-
- base_temporal_graph:
- template: "general/base_temporal_graph"
- input: "general/biography_scientist.md"
- type: "temporal_graph"
- description: "基础时序图"
-
- base_spatial_graph:
- template: "general/base_spatial_graph"
- input: "general/spatio_temporal_event_report.md"
- type: "spatial_graph"
- description: "基础空间图"
-
- base_spatio_temporal_graph:
- template: "general/base_spatio_temporal_graph"
- input: "general/spatio_temporal_event_report.md"
- type: "spatio_temporal_graph"
- description: "基础时空图"
-
- biography_graph:
- template: "general/biography_graph"
- input: "general/biography_scientist.md"
- type: "graph"
- description: "传记图谱"
-
- concept_graph:
- template: "general/concept_graph"
- input: "general/encyclopedia_machine_learning.md"
- type: "graph"
- description: "概念图谱"
-
- doc_structure:
- template: "general/doc_structure"
- input: "general/regulation_company_policy.md"
- type: "list"
- description: "文档结构"
-
- workflow_graph:
- template: "general/workflow_graph"
- input: "general/social_network_entrepreneur_story.md"
- type: "graph"
- description: "工作流程图"
-
-# Industry 领域 (5个模板)
-industry:
- emergency_response:
- template: "industry/emergency_response"
- input: "industry/safety_management_handbook.md"
- type: "temporal_graph"
- description: "应急响应时间线"
-
- equipment_topology:
- template: "industry/equipment_topology"
- input: "industry/equipment_technical_manual.md"
- type: "graph"
- description: "设备拓扑图"
-
- failure_case:
- template: "industry/failure_case"
- input: "industry/failure_analysis_report.md"
- type: "hypergraph"
- description: "故障案例"
-
- operation_flow:
- template: "industry/operation_flow"
- input: "industry/operation_maintenance_manual.md"
- type: "list"
- description: "操作流程"
-
- safety_control:
- template: "industry/safety_control"
- input: "industry/safety_management_handbook.md"
- type: "set"
- description: "安全控制"
-
-# Legal 领域 (5个模板)
-legal:
- case_citation:
- template: "legal/case_citation"
- input: "legal/legal_treatise_sample.md"
- type: "graph"
- description: "案例引用图"
-
- case_fact_timeline:
- template: "legal/case_fact_timeline"
- input: "legal/court_judgment_sample.md"
- type: "temporal_graph"
- description: "案件事实时间线"
-
- compliance_list:
- template: "legal/compliance_list"
- input: "legal/compliance_filing_sample.md"
- type: "list"
- description: "合规清单"
-
- contract_obligation:
- template: "legal/contract_obligation"
- input: "legal/msa_contract_sample.md"
- type: "set"
- description: "合同义务"
-
- defined_term_set:
- template: "legal/defined_term_set"
- input: "legal/msa_contract_sample.md"
- type: "set"
- description: "术语定义"
-
-# Medicine 领域 (5个模板)
-medicine:
- anatomy_graph:
- template: "medicine/anatomy_graph"
- input: "medicine/textbook_sample.md"
- type: "graph"
- description: "解剖结构图"
-
- discharge_instruction:
- template: "medicine/discharge_instruction"
- input: "medicine/discharge_summary_sample.md"
- type: "list"
- description: "出院指导"
-
- drug_interaction:
- template: "medicine/drug_interaction"
- input: "medicine/package_insert_sample.md"
- type: "graph"
- description: "药物相互作用图"
-
- hospital_timeline:
- template: "medicine/hospital_timeline"
- input: "medicine/pathology_report_sample.md"
- type: "temporal_graph"
- description: "医院事件时间线"
-
- treatment_map:
- template: "medicine/treatment_map"
- input: "medicine/clinical_guideline_sample.md"
- type: "hypergraph"
- description: "治疗方案图"
-
-# TCM 领域 (5个模板)
-tcm:
- formula_composition:
- template: "tcm/formula_composition"
- input: "tcm/prescription_formulary_sample.md"
- type: "graph"
- description: "方剂组成图"
-
- herb_property:
- template: "tcm/herb_property"
- input: "tcm/herb_property_single.md"
- type: "model"
- description: "药材属性"
-
- herb_relation:
- template: "tcm/herb_relation"
- input: "tcm/herbal_compendium_sample.md"
- type: "graph"
- description: "药材关系图"
-
- meridian_graph:
- template: "tcm/meridian_graph"
- input: "tcm/meridian_treatise_sample.md"
- type: "graph"
- description: "经络图"
-
- syndrome_reasoning:
- template: "tcm/syndrome_reasoning"
- input: "tcm/medical_case_record_sample.md"
- type: "hypergraph"
- description: "证候推理"
diff --git a/hyperextract/templates/presets/finance/event_timeline.yaml b/hyperextract/templates/presets/finance/event_timeline.yaml
index 4ec0336..a0d2315 100644
--- a/hyperextract/templates/presets/finance/event_timeline.yaml
+++ b/hyperextract/templates/presets/finance/event_timeline.yaml
@@ -49,7 +49,7 @@ output:
- name: type
type: str
description:
- zh: '关系类型:precedes/causes/triggers'
+ zh: '关系类型:先于/导致/触发'
en: 'Relation type: precedes/causes/triggers'
required: true
- name: time
@@ -80,9 +80,9 @@ guideline:
- 'Event type should reflect the nature of the event (announcement/rating adjustment/earnings release, etc.)'
rules_for_relations:
zh:
- - 'type为precedes表示事件的时间先后顺序'
- - 'type为causes表示因果关联'
- - 'type为triggers表示触发关系'
+ - 'type为"先于"表示事件的时间先后顺序'
+ - 'type为"导致"表示因果关联'
+ - 'type为"触发"表示触发关系'
- '仅提取文本中明确说明的关系'
- 'description中应说明事件是否构成重大事项'
en:
diff --git a/hyperextract/templates/presets/finance/ownership_graph.yaml b/hyperextract/templates/presets/finance/ownership_graph.yaml
index 82514d9..ef5645b 100644
--- a/hyperextract/templates/presets/finance/ownership_graph.yaml
+++ b/hyperextract/templates/presets/finance/ownership_graph.yaml
@@ -55,7 +55,7 @@ output:
- name: type
type: str
description:
- zh: '关系类型:controls/belongs_to/holds_shares'
+ zh: '关系类型:控制/属于/持股'
en: 'Relation type: controls/belongs_to/holds_shares'
required: true
- name: ownership_percentage
diff --git a/hyperextract/templates/presets/general/base_graph.yaml b/hyperextract/templates/presets/general/base_graph.yaml
index 2f3469b..da49c7e 100644
--- a/hyperextract/templates/presets/general/base_graph.yaml
+++ b/hyperextract/templates/presets/general/base_graph.yaml
@@ -41,12 +41,12 @@ output:
- name: source
type: str
description:
- zh: '关系起点实体,必须对应已提取实体的 name。'
+ zh: '关系起点实体,必须对应已提取实体的名称。'
en: 'Source entity of the relation, must correspond to the name of an extracted entity.'
- name: target
type: str
description:
- zh: '关系终点实体,必须对应已提取实体的 name。'
+ zh: '关系终点实体,必须对应已提取实体的名称。'
en: 'Target entity of the relation, must correspond to the name of an extracted entity.'
- name: type
type: str
diff --git a/hyperextract/templates/presets/general/base_spatial_graph.yaml b/hyperextract/templates/presets/general/base_spatial_graph.yaml
index eec008e..99534c8 100644
--- a/hyperextract/templates/presets/general/base_spatial_graph.yaml
+++ b/hyperextract/templates/presets/general/base_spatial_graph.yaml
@@ -41,12 +41,12 @@ output:
- name: source
type: str
description:
- zh: '关系起点实体,必须对应已提取实体的 name。'
+ zh: '关系起点实体,必须对应已提取实体的名称。'
en: 'Source entity of the relation, must correspond to the name of an extracted entity.'
- name: target
type: str
description:
- zh: '关系终点实体,必须对应已提取实体的 name。'
+ zh: '关系终点实体,必须对应已提取实体的名称。'
en: 'Target entity of the relation, must correspond to the name of an extracted entity.'
- name: type
type: str
diff --git a/hyperextract/templates/presets/general/base_spatio_temporal_graph.yaml b/hyperextract/templates/presets/general/base_spatio_temporal_graph.yaml
index 02a72b5..0f87f9d 100644
--- a/hyperextract/templates/presets/general/base_spatio_temporal_graph.yaml
+++ b/hyperextract/templates/presets/general/base_spatio_temporal_graph.yaml
@@ -41,12 +41,12 @@ output:
- name: source
type: str
description:
- zh: '关系起点实体,必须对应已提取实体的 name。'
+ zh: '关系起点实体,必须对应已提取实体的名称。'
en: 'Source entity of the relation, must correspond to the name of an extracted entity.'
- name: target
type: str
description:
- zh: '关系终点实体,必须对应已提取实体的 name。'
+ zh: '关系终点实体,必须对应已提取实体的名称。'
en: 'Target entity of the relation, must correspond to the name of an extracted entity.'
- name: type
type: str
diff --git a/hyperextract/templates/presets/general/base_temporal_graph.yaml b/hyperextract/templates/presets/general/base_temporal_graph.yaml
index fa8ad00..7e97825 100644
--- a/hyperextract/templates/presets/general/base_temporal_graph.yaml
+++ b/hyperextract/templates/presets/general/base_temporal_graph.yaml
@@ -41,12 +41,12 @@ output:
- name: source
type: str
description:
- zh: '关系起点实体,必须对应已提取实体的 name。'
+ zh: '关系起点实体,必须对应已提取实体的名称。'
en: 'Source entity of the relation, must correspond to the name of an extracted entity.'
- name: target
type: str
description:
- zh: '关系终点实体,必须对应已提取实体的 name。'
+ zh: '关系终点实体,必须对应已提取实体的名称。'
en: 'Target entity of the relation, must correspond to the name of an extracted entity.'
- name: type
type: str
diff --git a/hyperextract/templates/presets/industry/emergency_response.yaml b/hyperextract/templates/presets/industry/emergency_response.yaml
index 9a3a417..ea35599 100644
--- a/hyperextract/templates/presets/industry/emergency_response.yaml
+++ b/hyperextract/templates/presets/industry/emergency_response.yaml
@@ -55,7 +55,7 @@ output:
- name: type
type: str
description:
- zh: '关系类型:triggers/executed_by/requires'
+ zh: '关系类型:触发/执行/需要'
en: 'Relation type: triggers/executed_by/requires'
required: true
- name: responsible_role
@@ -80,9 +80,9 @@ guideline:
- 'Extract required resources as entities'
rules_for_relations:
zh:
- - 'type为triggers表示触发响应'
- - 'type为executed_by表示执行责任人'
- - 'type为requires表示所需资源'
+ - 'type为"触发"表示触发响应'
+ - 'type为"执行"表示执行责任人'
+ - 'type为"需要"表示所需资源'
en:
- 'type triggers indicates triggering response'
- 'type executed_by indicates executing responsible person'
diff --git a/hyperextract/templates/presets/industry/equipment_topology.yaml b/hyperextract/templates/presets/industry/equipment_topology.yaml
index f618c1c..2c14d2f 100644
--- a/hyperextract/templates/presets/industry/equipment_topology.yaml
+++ b/hyperextract/templates/presets/industry/equipment_topology.yaml
@@ -61,7 +61,7 @@ output:
- name: type
type: str
description:
- zh: '关系类型:connected_to/located_in/contains'
+ zh: '关系类型:连接/位于/包含'
en: 'Relation type: connected_to/located_in/contains'
required: true
diff --git a/hyperextract/templates/presets/industry/failure_case.yaml b/hyperextract/templates/presets/industry/failure_case.yaml
index 965919d..fb0d0f4 100644
--- a/hyperextract/templates/presets/industry/failure_case.yaml
+++ b/hyperextract/templates/presets/industry/failure_case.yaml
@@ -80,9 +80,9 @@ guideline:
- 'Extract corrective measures as entities'
rules_for_relations:
zh:
- - 'type为caused_by表示由某原因引起'
- - 'type为resolved_by表示通过某措施解决'
- - 'type为prevented_by表示通过某措施预防'
+ - 'type为"原因"表示由某原因引起'
+ - 'type为"解决"表示通过某措施解决'
+ - 'type为"预防"表示通过某措施预防'
- 'lesson字段应总结经验教训'
en:
- 'type caused_by indicates caused by a reason'
diff --git a/hyperextract/templates/presets/industry/operation_flow.yaml b/hyperextract/templates/presets/industry/operation_flow.yaml
index 5170e40..85a27ad 100644
--- a/hyperextract/templates/presets/industry/operation_flow.yaml
+++ b/hyperextract/templates/presets/industry/operation_flow.yaml
@@ -61,7 +61,7 @@ output:
- name: type
type: str
description:
- zh: '关系类型:next/triggers/results_in'
+ zh: '关系类型:后续/触发/导致'
en: 'Relation type: next/triggers/results_in'
required: true
- name: description
@@ -86,9 +86,9 @@ guideline:
- 'Equipment states should indicate key state changes'
rules_for_relations:
zh:
- - 'type为next表示顺序执行'
- - 'type为triggers表示触发条件'
- - 'type为results_in表示导致状态变化'
+ - 'type为"顺序"表示顺序执行'
+ - 'type为"触发"表示触发条件'
+ - 'type为"导致"表示导致状态变化'
- '仅提取文档中明确说明的关系'
en:
- 'type next indicates sequential execution'
diff --git a/hyperextract/templates/presets/industry/safety_control.yaml b/hyperextract/templates/presets/industry/safety_control.yaml
index d29352a..b8cdc1a 100644
--- a/hyperextract/templates/presets/industry/safety_control.yaml
+++ b/hyperextract/templates/presets/industry/safety_control.yaml
@@ -55,7 +55,7 @@ output:
- name: type
type: str
description:
- zh: '关系类型:causes/mitigates/assigned_to'
+ zh: '关系类型:导致/缓解/分配给'
en: 'Relation type: causes/mitigates/assigned_to'
required: true
- name: responsible_role
@@ -80,9 +80,9 @@ guideline:
- 'Extract control measures as entities'
rules_for_relations:
zh:
- - 'type为causes表示导致风险'
- - 'type为mitigates表示减轻风险'
- - 'type为assigned_to表示责任分配'
+ - 'type为"导致"表示导致风险'
+ - 'type为"减轻"表示减轻风险'
+ - 'type为"分配"表示责任分配'
- 'responsible_role应标注具体的责任人或部门'
en:
- 'type causes indicates causing risk'
diff --git a/hyperextract/templates/presets/legal/case_citation.yaml b/hyperextract/templates/presets/legal/case_citation.yaml
index 94f45bc..936f0c4 100644
--- a/hyperextract/templates/presets/legal/case_citation.yaml
+++ b/hyperextract/templates/presets/legal/case_citation.yaml
@@ -55,7 +55,7 @@ output:
- name: type
type: str
description:
- zh: '关系类型:cites/distinguished_from/overruled_by'
+ zh: '关系类型:引用/区分/推翻'
en: 'Relation type: cites/distinguished_from/overruled_by'
required: true
- name: description
@@ -80,9 +80,9 @@ guideline:
- 'Court information should be accurately labeled'
rules_for_relations:
zh:
- - 'type为cites表示引用关系'
- - 'type为distinguished_from表示区分解释'
- - 'type为overruled_by表示被推翻'
+ - 'type为"引用"表示引用关系'
+ - 'type为"区分"表示区分解释'
+ - 'type为"推翻"表示被推翻'
- '仅提取文本中明确提及的引用关系'
en:
- 'type cites indicates citation relationship'
diff --git a/hyperextract/templates/presets/legal/case_fact_timeline.yaml b/hyperextract/templates/presets/legal/case_fact_timeline.yaml
index f495568..e994dfa 100644
--- a/hyperextract/templates/presets/legal/case_fact_timeline.yaml
+++ b/hyperextract/templates/presets/legal/case_fact_timeline.yaml
@@ -55,7 +55,7 @@ output:
- name: type
type: str
description:
- zh: '关系类型:preceded_by/proves/disputes'
+ zh: '关系类型:先于/证明/争议'
en: 'Relation type: preceded_by/proves/disputes'
required: true
- name: time
@@ -86,9 +86,9 @@ guideline:
- 'Entity descriptions should be concise and accurate'
rules_for_relations:
zh:
- - 'type为preceded_by表示时间先后顺序'
- - 'type为proves表示证据支持'
- - 'type为disputes表示对某一事实存在争议'
+ - 'type为"先于"表示时间先后顺序'
+ - 'type为"证明"表示证据支持'
+ - 'type为"争议"表示对某一事实存在争议'
- '仅提取文本中明确陈述的事实关系'
en:
- 'type preceded_by indicates temporal sequence'
diff --git a/hyperextract/templates/presets/medicine/anatomy_graph.yaml b/hyperextract/templates/presets/medicine/anatomy_graph.yaml
index 5c598f6..f881efc 100644
--- a/hyperextract/templates/presets/medicine/anatomy_graph.yaml
+++ b/hyperextract/templates/presets/medicine/anatomy_graph.yaml
@@ -55,7 +55,7 @@ output:
- name: type
type: str
description:
- zh: '关系类型:contains/located_in'
+ zh: '关系类型:包含/位于'
en: 'Relation type: contains/located_in'
required: true
diff --git a/hyperextract/templates/presets/medicine/hospital_timeline.yaml b/hyperextract/templates/presets/medicine/hospital_timeline.yaml
index b4310b4..1257f42 100644
--- a/hyperextract/templates/presets/medicine/hospital_timeline.yaml
+++ b/hyperextract/templates/presets/medicine/hospital_timeline.yaml
@@ -55,7 +55,7 @@ output:
- name: type
type: str
description:
- zh: '关系类型:follows/results_in'
+ zh: '关系类型:后续/导致'
en: 'Relation type: follows/results_in'
required: true
- name: time
@@ -86,8 +86,8 @@ guideline:
- 'Descriptions should concisely summarize event content'
rules_for_relations:
zh:
- - 'type为follows表示事件的时序关系'
- - 'type为results_in表示因果结果关系'
+ - 'type为"后续"表示事件的时序关系'
+ - 'type为"导致"表示因果结果关系'
- 'performer应标注执行人或科室'
en:
- 'type follows indicates temporal sequence of events'
diff --git a/hyperextract/templates/presets/medicine/treatment_map.yaml b/hyperextract/templates/presets/medicine/treatment_map.yaml
index 38d70c3..4ace2af 100644
--- a/hyperextract/templates/presets/medicine/treatment_map.yaml
+++ b/hyperextract/templates/presets/medicine/treatment_map.yaml
@@ -67,7 +67,7 @@ output:
- name: type
type: str
description:
- zh: '关系类型:indicates/contraindicated_with'
+ zh: '关系类型:适用于/禁忌联合'
en: 'Relation type: indicates/contraindicated_with'
required: true
@@ -88,8 +88,8 @@ guideline:
- 'Extract treatment outcomes as entities'
rules_for_relations:
zh:
- - 'type为indicates表示适应症'
- - 'type为contraindicated_with表示禁忌组合'
+ - 'type为"适用"表示适应症'
+ - 'type为"禁忌"表示禁忌组合'
- 'conditions字段应包含所有相关的患者特征/适用条件'
en:
- 'type indicates indicates indication'
diff --git a/hyperextract/templates/presets/tcm/meridian_graph.yaml b/hyperextract/templates/presets/tcm/meridian_graph.yaml
index 8c3d2e6..ebaee42 100644
--- a/hyperextract/templates/presets/tcm/meridian_graph.yaml
+++ b/hyperextract/templates/presets/tcm/meridian_graph.yaml
@@ -74,8 +74,8 @@ guideline:
- 'Location descriptions should accurately indicate anatomical positions'
rules_for_relations:
zh:
- - 'type为located_on表示穴位属于某经脉'
- - 'type为flows_to表示经脉的流注顺序'
+ - 'type为"位于"表示穴位属于某经脉'
+ - 'type为"流注"表示经脉的流注顺序'
en:
- 'type located_on indicates acupoint belongs to a meridian'
- 'type flows_to indicates the flow sequence of meridians'