Skip to content

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

docs: add Knowledge Base Manager use case (source attribution, upsert, rollback, scoped search, audit)

yifanfeng97025e894e80d3
diff --git a/README.md b/README.md
index ebe7545..fd20059 100644
--- a/README.md
+++ b/README.md
@@ -193,6 +193,35 @@ llm, emb = create_client(
</details>
+<details>
+<summary><b>📜 Knowledge Base Manager — Keep your KB in sync with reality</b></summary>
+<br>
+
+Documents change. Hyper-Extract tracks every source so you can update, roll back, or audit without starting over.
+
+```bash
+# Ingest with attribution — every fact is traceable to its source
+he feed ./ka/ contract-v1.md --source contract-v1
+he tag ./ka/ --source contract-v1 --add legal --add acme
+
+# Document updated? Re-feed under the same source — old facts roll back automatically
+he feed ./ka/ contract-v2.md --source contract-v1
+
+# Document is obsolete? Roll back everything it contributed
+he remove ./ka/ --document contract-v1
+
+# Remove a single wrong fact (LLM-assisted, with dry-run preview)
+he remove ./ka/ --edit-node Apple --fact "founded by Steve Jobs" --dry-run
+
+# Search only within legal-tagged documents
+he search ./ka/ "termination clause" --tag legal
+
+# Audit: which documents contributed what?
+he info ./ka/ --sources
+```
+
+</details>
+
## 🚀 Supported Platforms & Models
Hyper-Extract uses LangChain structured output with **function calling**. The model must support tool/function calling.
diff --git a/README_ZH.md b/README_ZH.md
index cfa727c..8f8eaa8 100644
--- a/README_ZH.md
+++ b/README_ZH.md
@@ -193,6 +193,35 @@ llm, emb = create_client(
</details>
+<details>
+<summary><b>📜 知识库管理员 — 让知识库与文档同步演化</b></summary>
+<br>
+
+文档会变。Hyper-Extract 追踪每个来源,让你可以更新、回滚或审计,而不用从头重建。
+
+```bash
+# 带来源标注摄取——每条知识可追溯到来源文档
+he feed ./ka/ contract-v1.md --source contract-v1
+he tag ./ka/ --source contract-v1 --add legal --add acme
+
+# 文档更新了?同 source 重喂——旧事实自动回滚
+he feed ./ka/ contract-v2.md --source contract-v1
+
+# 文档过时了?回滚它贡献的全部知识
+he remove ./ka/ --document contract-v1
+
+# 删除单条错误事实(大模型辅助,支持 dry-run 预览)
+he remove ./ka/ --edit-node Apple --fact "founded by Steve Jobs" --dry-run
+
+# 只搜法律类文档
+he search ./ka/ "termination clause" --tag legal
+
+# 审计:哪些文档贡献了什么?
+he info ./ka/ --sources
+```
+
+</details>
+
## 🚀 支持的平台与模型
Hyper-Extract 通过 LangChain 结构化输出的 **function calling** 方法工作。模型需支持 tool/function calling。