Skip to content

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

chore: bump version to 0.10.0; docs news for 0.10.0/0.9.1

yifanfeng97eadd1e35d59f
diff --git a/README.md b/README.md
index 2bc2894..bcf7cb5 100644
--- a/README.md
+++ b/README.md
@@ -342,7 +342,7 @@ identifiers:
## 📰 What's New
-**v0.9.0** — 📄 Rich document ingestion: `he parse` / `he feed` now take PDF, Word, PowerPoint, Excel, HTML, EPUB and more (`pip install "hyperextract[ingest]"`) · 🧱 New `chunk_rag` method: zero-extraction chunk baseline with full provenance · 🐛 `he tag` and method-KA command fixes.
+**v0.10.0** — 📤 New exports: JSON-LD & Cypher (Neo4j) alongside GraphML/CSV/Obsidian — all four also available via MCP · 📄 `he feed` now accepts directories · 🧠 Native Gemini support (`pip install "hyperextract[google]"`) · 🛡️ Windows config hardening & scoped-search fixes across every KA type.
📰 **[Full release notes](https://yifanfeng97.github.io/Hyper-Extract/latest/news/)** · [All releases](https://github.com/yifanfeng97/hyper-extract/releases)
@@ -366,7 +366,7 @@ pip install 'hyperextract[mcp]'
he-mcp # stdio MCP server
```
-Tools: `list_templates`, `info`, `search`, `ask` (RAG), `export_obsidian`. Full guide: [MCP Server docs](https://yifanfeng97.github.io/Hyper-Extract/latest/mcp/).
+Tools: `list_templates`, `info`, `search`, `ask` (RAG), `export_obsidian`, `export_graphml`, `export_csv`, `export_jsonld`, `export_cypher`. Full guide: [MCP Server docs](https://yifanfeng97.github.io/Hyper-Extract/latest/mcp/).
## 🤝 Contributing & License
diff --git a/README_ZH.md b/README_ZH.md
index 973491a..b8bd877 100644
--- a/README_ZH.md
+++ b/README_ZH.md
@@ -342,7 +342,7 @@ identifiers:
## 📰 最新动态
-**v0.9.0** — 📄 丰富的文档输入:`he parse` / `he feed` 现在支持 PDF、Word、PowerPoint、Excel、HTML、EPUB 等格式(`pip install "hyperextract[ingest]"`)· 🧱 新增 `chunk_rag` 方法:零提取成本的块检索基线,具备完整溯源 · 🐛 修复 `he tag` 与方法型知识库的命令崩溃问题。
+**v0.10.0** — 📤 新增导出:JSON-LD 与 Cypher(Neo4j),连同 GraphML/CSV/Obsidian——四种格式均可经 MCP 调用 · 📄 `he feed` 现在支持目录 · 🧠 原生 Gemini 支持(`pip install "hyperextract[google]"`)· 🛡️ Windows 配置加固与全部知识库类型的范围检索修复。
📰 **[完整版本说明](https://yifanfeng97.github.io/Hyper-Extract/latest/zh/news/)** · [全部 Releases](https://github.com/yifanfeng97/hyper-extract/releases)
@@ -366,7 +366,7 @@ pip install 'hyperextract[mcp]'
he-mcp # stdio MCP 服务器
```
-工具:`list_templates`、`info`、`search`、`ask`(RAG)、`export_obsidian`。完整指南:[MCP 服务器文档](https://yifanfeng97.github.io/Hyper-Extract/latest/zh/mcp/)。
+工具:`list_templates`、`info`、`search`、`ask`(RAG)、`export_obsidian`、`export_graphml`、`export_csv`、`export_jsonld`、`export_cypher`。完整指南:[MCP 服务器文档](https://yifanfeng97.github.io/Hyper-Extract/latest/zh/mcp/)。
## 🤝 参与贡献与协议
diff --git a/docs/en/news.md b/docs/en/news.md
index e0527b7..b4ba50f 100644
--- a/docs/en/news.md
+++ b/docs/en/news.md
@@ -4,6 +4,24 @@ Release notes and highlights. For a complete changelog, see the [GitHub releases
---
+## v0.10.0 — More Export Formats, Gemini, and Quality Hardening
+
+- **📤 JSON-LD & Cypher exports** — `he export jsonld` (pairwise edges + GraphML-style hyperedges) and `he export cypher` (Neo4j-compatible MERGE script; N-ary edges become Hyperedge nodes, not lossy cliques). *(#139, #141)*
+- **🔌 MCP export parity** — `export_graphml`, `export_csv`, `export_jsonld`, `export_cypher` tools on `he-mcp`; MCP `list_templates` now includes methods and `info` shows chunks/timestamps/sources like the CLI. *(#106, #131, #133, #144)*
+- **📄 `he feed` accepts directories** — parity with `he parse`: per-file source attribution, same skip/warning behavior. *(#135)*
+- **🧠 Native Gemini support** — the previously unused `[google]` extra is now wired to `create_llm`: `pip install "hyperextract[google]"`. *(#137)*
+- **🏗️ Internal** — `GraphIndexMixin` extracts the shared merge/index/search surface of graph & hypergraph (−168 lines); contract tests for every registered method; test matrix now includes Windows. *(#112, #108, #145)*
+- **🛡️ Hardening** — chunk options validated at parse time (`chunk_overlap < chunk_size`); `relation_members` requires `source`/`target` roles; Windows `config.toml` ACL restricted to the current user; FAISS deserialization warning. *(#91, #92, #110, #94)*
+- **🐛 Fixes** — scoped search forwarded on hypergraph; `he search` prints nodes/edges instead of raw tuples; MCP `search` no longer crashes on 3-tuples; GraphML export respects `--force`. *(#90, #144)*
+
+---
+
+## v0.9.1 — Scoped Search Completeness & Validator Hardening
+
+- **🐛 Fixes** — scoped search forwarded on hypergraph (`AutoHypergraph.search` dropped `source_ids`/`tags`); AutoSet provenance wired end-to-end (recording, tags, rollback, persistence); `Graph_RAG`/`Cog_RAG` scope forwarding; friendly error for scope on non-tracked types.
+
+---
+
## v0.9.0 — Rich Document Ingestion & chunk_rag Baseline
- **📄 Rich Document Ingestion** — `he parse` / `he feed` now accept PDF, Word, PowerPoint, Excel, HTML, CSV/JSON/XML, EPUB and more via the optional ingest extra (`pip install "hyperextract[ingest]"`, powered by [MarkItDown](https://github.com/microsoft/markitdown)). Non-UTF-8 text (GBK, etc.) is auto-detected; text-less (scanned) PDFs fail with a clear OCR hint instead of silently ingesting garbage.
diff --git a/docs/zh/news.md b/docs/zh/news.md
index 46c4dff..96df3ef 100644
--- a/docs/zh/news.md
+++ b/docs/zh/news.md
@@ -4,6 +4,24 @@
---
+## v0.10.0 — 更多导出格式、Gemini 与质量加固
+
+- **📤 JSON-LD 与 Cypher 导出** — `he export jsonld`(二元边 + GraphML 风格超边)与 `he export cypher`(Neo4j 兼容 MERGE 脚本;N 元边编码为 Hyperedge 节点,不做有损团 expansion)。*(#139, #141)*
+- **🔌 MCP 导出对齐** — `he-mcp` 新增 `export_graphml`、`export_csv`、`export_jsonld`、`export_cypher` 工具;MCP `list_templates` 包含方法模板、`info` 与 CLI 一样展示 chunks/时间戳/来源。*(#106, #131, #133, #144)*
+- **📄 `he feed` 支持目录** — 与 `he parse` 对齐:逐文件来源标注、相同的跳过/警告行为。*(#135)*
+- **🧠 原生 Gemini 支持** — 此前未接线的 `[google]` extra 已接入 `create_llm`:`pip install "hyperextract[google]"`。*(#137)*
+- **🏗️ 内部改进** — `GraphIndexMixin` 抽取 graph/hypergraph 共享的合并/索引/检索面(净删 168 行);全部注册方法的契约测试;测试矩阵加入 Windows。*(#112, #108, #145)*
+- **🛡️ 加固** — chunk 参数解析期校验(`chunk_overlap < chunk_size`);`relation_members` 必须含 `source`/`target` 角色;Windows `config.toml` ACL 收紧到当前用户;FAISS 反序列化警告。*(#91, #92, #110, #94)*
+- **🐛 修复** — 超图范围检索透传;`he search` 打印节点/边而非原始元组;MCP `search` 不再因三元组崩溃;GraphML 导出尊重 `--force`。*(#90, #144)*
+
+---
+
+## v0.9.1 — 范围检索补全与校验器加固
+
+- **🐛 修复** — 超图 `search` 透传 scope(此前丢弃 `source_ids`/`tags`);AutoSet 溯源端到端接通(记录/标签/回滚/持久化);`Graph_RAG`/`Cog_RAG` scope 转发;无账本类型上范围检索给出明确报错。
+
+---
+
## v0.9.0 — 丰富的文档输入与 chunk_rag 基线
- **📄 丰富的文档输入** — `he parse` / `he feed` 现在支持 PDF、Word、PowerPoint、Excel、HTML、CSV/JSON/XML、EPUB 等格式,安装可选依赖即可启用(`pip install "hyperextract[ingest]"`,由 [MarkItDown](https://github.com/microsoft/markitdown) 驱动)。非 UTF-8 文本(GBK 等)自动识别编码;无文字层的扫描版 PDF 会给出明确的 OCR 提示,而不是静默摄入乱码。
diff --git a/pyproject.toml b/pyproject.toml
index 83d4108..20390fd 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
[project]
name = "hyperextract"
-version = "0.9.1"
+version = "0.10.0"
description = "An intelligent, LLM-powered knowledge extraction and evolution framework with semantic search capabilities"
readme = "README.md"
requires-python = ">=3.11"
diff --git a/uv.lock b/uv.lock
index 5540df0..716a9f5 100644
--- a/uv.lock
+++ b/uv.lock
@@ -977,7 +977,7 @@ wheels = [
[[package]]
name = "hyperextract"
-version = "0.9.1"
+version = "0.10.0"
source = { editable = "." }
dependencies = [
{ name = "faiss-cpu" },