Skip to content

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

Merge PR #125: docs catch-up (MCP exports, orcarouter, HE-T008, document type)

yifanfeng977a4db401021c
diff --cc docs/en/cli/commands/config.md
index a4b1911,d0f076c..55f22f7
--- a/docs/en/cli/commands/config.md
+++ b/docs/en/cli/commands/config.md
@@@ -29,7 -29,7 +29,8 @@@ Initialize configuration. This is the *
- **Bailian preset**: `qwen3.6-plus` + `text-embedding-v4`
- **DeepSeek preset**: `deepseek-v4-flash` (LLM only — no embedder preset)
- **Anthropic preset**: `claude-opus-4-8` (LLM only — no embedder preset, pair with an OpenAI-compatible embedder)
+ - **OrcaRouter preset**: `orcarouter/auto` (OpenAI-compatible gateway; key `ORCAROUTER_API_KEY`)
+- **Google Gemini preset**: `gemini-3.8-flash` (LLM only — no embedder preset, pair with an OpenAI-compatible embedder; alias `gemini`)
```bash
he config init [OPTIONS]
@@@ -39,7 -39,7 +40,7 @@@
| Option | Short | Description |
|--------|-------|-------------|
- | `--provider` | `-p` | Provider preset (`openai` / `anthropic` / `google` / `deepseek` / `bailian` / `vllm`) |
-| `--provider` | `-p` | Provider preset (`openai` / `anthropic` / `orcarouter` / `deepseek` / `bailian` / `vllm`) |
++| `--provider` | `-p` | Provider preset (`openai` / `anthropic` / `google` / `orcarouter` / `deepseek` / `bailian` / `vllm`) |
| `--api-key` | `-k` | API key for both LLM and embedder |
| `--base-url` | `-u` | Custom API base URL (optional) |
@@@ -62,9 -62,8 +63,12 @@@ he config embedder -p openai -k sk-your
he config llm -p anthropic -k sk-your-anthropic-key
he config embedder -p openai -k sk-your-openai-key
+ # OrcaRouter (OpenAI-compatible gateway)
+ he config init -p orcarouter -k or-your-orcarouter-key
++
+# Google Gemini (LLM only — pair with an OpenAI-compatible embedder)
+he config llm -p google -k your-google-api-key
+he config embedder -p openai -k sk-your-openai-key
```
This saves the preset's default model and API URL automatically.
@@@ -119,7 -118,7 +123,7 @@@ he config llm [OPTIONS
| Option | Short | Description |
|--------|-------|-------------|
- | `--provider` | `-p` | Provider preset (e.g. `openai`, `anthropic`, `google`, `deepseek`, `bailian`, `vllm`) |
-| `--provider` | `-p` | Provider preset (e.g. `openai`, `anthropic`, `orcarouter`, `deepseek`, `bailian`, `vllm`) |
++| `--provider` | `-p` | Provider preset (e.g. `openai`, `anthropic`, `google`, `orcarouter`, `deepseek`, `bailian`, `vllm`) |
| `--api-key` | `-k` | LLM API key |
| `--model` | `-m` | LLM model name |
| `--base-url` | `-u` | Custom API base URL |
@@@ -162,7 -161,7 +166,7 @@@ he config embedder [OPTIONS
| Option | Short | Description |
|--------|-------|-------------|
- | `--provider` | `-p` | Provider preset (e.g. `openai`, `anthropic`, `google`, `deepseek`, `bailian`, `vllm`) |
-| `--provider` | `-p` | Provider preset (e.g. `openai`, `anthropic`, `orcarouter`, `deepseek`, `bailian`, `vllm`) |
++| `--provider` | `-p` | Provider preset (e.g. `openai`, `anthropic`, `google`, `orcarouter`, `deepseek`, `bailian`, `vllm`) |
| `--api-key` | `-k` | Embedder API key |
| `--model` | `-m` | Embedder model name |
| `--base-url` | `-u` | Custom API base URL |
diff --cc docs/en/cli/index.md
index eb959f0,7b44d52..f0bfd71
--- a/docs/en/cli/index.md
+++ b/docs/en/cli/index.md
@@@ -33,11 -33,7 +33,9 @@@ he --versio
| `he parse` | Extract knowledge from documents | `-t` template, `-o` output, `-l` language, `--source` attribution |
| `he show` | Visualize knowledge graph | — |
| `he export obsidian` | Export to an Obsidian vault | `-o` output, `--name`, `-f` force |
-| `he export graphml` | Export a pairwise graph to GraphML | `-o` output file |
+| `he export graphml` | Export pairwise `<edge>` and N-ary `<hyperedge>` GraphML | `-o` output file, `-f` force |
+| `he export jsonld` | Export pairwise edges and N-ary hyperedges to JSON-LD | `-o` output file, `-f` force |
- =======
+| `he export cypher` | Export Neo4j-compatible MERGE (N-ary as Hyperedge nodes) | `-o` output file, `-f` force |
- >>>>>>> pr-141-src
| `he export csv` | Export nodes/edges as CSV tables | `-o` directory, `-f` force |
| `he search` | Semantic search in knowledge abstract | `-n` top-k results, `--source`, `--tag` |
| `he talk` | Chat with knowledge abstract | `-i` interactive, `-q` query |
@@@ -176,11 -172,7 +174,9 @@@ he show ./output
- **[`he talk`](commands/talk.md)** — Chat with knowledge abstract
- **[`he info`](commands/info.md)** — View knowledge abstract statistics
- **[`he export obsidian`](commands/export.md)** — Export to an Obsidian vault
-- **[`he export graphml`](commands/export.md#he-export-graphml)** — Export a pairwise graph to GraphML
+- **[`he export graphml`](commands/export.md#he-export-graphml)** — Export pairwise `<edge>` and N-ary `<hyperedge>` GraphML
+- **[`he export jsonld`](commands/export.md#he-export-jsonld)** — Export pairwise edges and N-ary hyperedges to JSON-LD
- =======
+- **[`he export cypher`](commands/export.md#he-export-cypher)** — Export a Neo4j-compatible Cypher MERGE script
- >>>>>>> pr-141-src
- **[`he export csv`](commands/export.md#he-export-csv)** — Export nodes/edges as CSV tables
### Management
diff --cc docs/zh/cli/commands/config.md
index 341223d,81e4af0..f1ce8e2
--- a/docs/zh/cli/commands/config.md
+++ b/docs/zh/cli/commands/config.md
@@@ -29,7 -29,7 +29,8 @@@ he config [COMMAND] [OPTIONS
- **百炼 preset**: `qwen3.6-plus` + `text-embedding-v4`
- **DeepSeek preset**: `deepseek-v4-flash`(仅 LLM —— 无嵌入预设)
- **Anthropic preset**: `claude-opus-4-8`(仅 LLM —— 无嵌入预设,请搭配 OpenAI 兼容嵌入器)
+ - **OrcaRouter preset**: `orcarouter/auto`(OpenAI 兼容网关;密钥 `ORCAROUTER_API_KEY`)
+- **Google Gemini preset**: `gemini-3.8-flash`(仅 LLM —— 无嵌入预设,请搭配 OpenAI 兼容嵌入器;别名 `gemini`)
```bash
he config init [OPTIONS]
@@@ -39,7 -39,7 +40,7 @@@
| 选项 | 简写 | 描述 |
|--------|-------|-------------|
- | `--provider` | `-p` | 提供商 preset (`openai` / `anthropic` / `google` / `deepseek` / `bailian` / `vllm`) |
-| `--provider` | `-p` | 提供商 preset (`openai` / `anthropic` / `orcarouter` / `deepseek` / `bailian` / `vllm`) |
++| `--provider` | `-p` | 提供商 preset (`openai` / `anthropic` / `google` / `orcarouter` / `deepseek` / `bailian` / `vllm`) |
| `--api-key` | `-k` | LLM 和嵌入模型的 API 密钥 |
| `--base-url` | `-u` | 自定义 API 基础 URL(可选) |
@@@ -62,9 -62,8 +63,12 @@@ he config embedder -p openai -k sk-your
he config llm -p anthropic -k sk-your-anthropic-key
he config embedder -p openai -k sk-your-openai-key
+ # OrcaRouter(OpenAI 兼容网关)
+ he config init -p orcarouter -k or-your-orcarouter-key
++
+# Google Gemini(仅 LLM —— 请搭配 OpenAI 兼容嵌入器)
+he config llm -p google -k your-google-api-key
+he config embedder -p openai -k sk-your-openai-key
```
执行后会自动保存对应 preset 的默认模型和 API 地址。
@@@ -119,7 -118,7 +123,7 @@@ he config llm [OPTIONS
| 选项 | 简写 | 描述 |
|--------|-------|-------------|
- | `--provider` | `-p` | 提供商 preset(如 `openai`、`anthropic`、`google`、`deepseek`、`bailian`、`vllm`) |
-| `--provider` | `-p` | 提供商 preset(如 `openai`、`anthropic`、`orcarouter`、`deepseek`、`bailian`、`vllm`) |
++| `--provider` | `-p` | 提供商 preset(如 `openai`、`anthropic`、`google`、`orcarouter`、`deepseek`、`bailian`、`vllm`) |
| `--api-key` | `-k` | LLM API 密钥 |
| `--model` | `-m` | LLM 模型名称 |
| `--base-url` | `-u` | 自定义 API 基础 URL |
@@@ -162,7 -161,7 +166,7 @@@ he config embedder [OPTIONS
| 选项 | 简写 | 描述 |
|--------|-------|-------------|
- | `--provider` | `-p` | 提供商 preset(如 `openai`、`anthropic`、`google`、`deepseek`、`bailian`、`vllm`) |
-| `--provider` | `-p` | 提供商 preset(如 `openai`、`anthropic`、`orcarouter`、`deepseek`、`bailian`、`vllm`) |
++| `--provider` | `-p` | 提供商 preset(如 `openai`、`anthropic`、`google`、`orcarouter`、`deepseek`、`bailian`、`vllm`) |
| `--api-key` | `-k` | 嵌入模型 API 密钥 |
| `--model` | `-m` | 嵌入模型名称 |
| `--base-url` | `-u` | 自定义 API 基础 URL |
diff --cc docs/zh/cli/index.md
index 7a9d9e8,e8b2b64..46484e3
--- a/docs/zh/cli/index.md
+++ b/docs/zh/cli/index.md
@@@ -33,11 -33,7 +33,9 @@@ he --versio
| `he parse` | 从文档提取知识 | `-t` 模板, `-o` 输出, `-l` 语言, `--source` 来源标注 |
| `he show` | 可视化知识图谱 | — |
| `he export obsidian` | 导出为 Obsidian 知识库 | `-o` 输出, `--name`, `-f` 强制 |
-| `he export graphml` | 将二元图导出为 GraphML | `-o` 输出文件 |
+| `he export graphml` | 导出二元 `<edge>` 与 N 元 `<hyperedge>` GraphML | `-o` 输出文件, `-f` 强制 |
+| `he export jsonld` | 将二元边与 N 元超边导出为 JSON-LD | `-o` 输出文件, `-f` 强制 |
- =======
+| `he export cypher` | 导出 Neo4j 兼容 MERGE(N 元边为 Hyperedge 节点) | `-o` 输出文件, `-f` 强制 |
- >>>>>>> pr-141-src
| `he export csv` | 将节点/边导出为 CSV 表 | `-o` 目录, `-f` 强制 |
| `he search` | 知识库语义搜索 | `-n` top-k 结果数, `--source`, `--tag` |
| `he talk` | 与知识库对话 | `-i` 交互模式, `-q` 查询 |
@@@ -176,11 -172,7 +174,9 @@@ he show ./output
- **[`he talk`](commands/talk.md)** — 与知识库对话
- **[`he info`](commands/info.md)** — 查看知识库统计信息
- **[`he export obsidian`](commands/export.md)** — 导出为 Obsidian 知识库
-- **[`he export graphml`](commands/export.md#he-export-graphml)** — 将二元图导出为 GraphML
+- **[`he export graphml`](commands/export.md#he-export-graphml)** — 导出二元 `<edge>` 与 N 元 `<hyperedge>` GraphML
+- **[`he export jsonld`](commands/export.md#he-export-jsonld)** — 将二元边与 N 元超边导出为 JSON-LD
- =======
+- **[`he export cypher`](commands/export.md#he-export-cypher)** — 导出 Neo4j 兼容的 Cypher MERGE 脚本
- >>>>>>> pr-141-src
- **[`he export csv`](commands/export.md#he-export-csv)** — 将节点/边导出为 CSV 表
### 管理
diff --cc docs/zh/concepts/provider-system.md
index 0967dd2,d9e152f..bbcdc44
--- a/docs/zh/concepts/provider-system.md
+++ b/docs/zh/concepts/provider-system.md
@@@ -1,6 -1,6 +1,6 @@@
# Provider 系统
- Hyper-Extract 支持以下接入方式:**OpenAI**、**Anthropic**、**Google Gemini**、**阿里云百炼**、**DeepSeek**、**本地 vLLM**。统一使用 `create_client()` 接口,仅需修改第一行。
-Hyper-Extract 支持以下接入方式:**OpenAI**、**Anthropic**、**阿里云百炼**、**DeepSeek**、**OrcaRouter**、**本地 vLLM**。统一使用 `create_client()` 接口,仅需修改第一行。
++Hyper-Extract 支持以下接入方式:**OpenAI**、**Anthropic**、**Google Gemini**、**阿里云百炼**、**DeepSeek**、**OrcaRouter**、**本地 vLLM**。统一使用 `create_client()` 接口,仅需修改第一行。
---
@@@ -12,8 -12,8 +12,9 @@@
|------|------|:--------:|:------:|------|
| **OpenAI** | gpt-4o / gpt-4o-mini / gpt-5 | ✅ | ✅ | 官方原生支持,推荐 |
| **Anthropic** | claude-opus-4-8 / claude-sonnet-4-6 / claude-haiku-4-5 | ✅(工具调用) | ✅ | 仅 LLM——无嵌入接口(请搭配 OpenAI 兼容嵌入器)。需 `hyperextract[anthropic]` |
+| **Google Gemini** | gemini-3.8-flash / gemini-2.5-flash / gemini-2.5-pro | ✅(工具调用) | ✅ | 仅 LLM——本仓库无成熟嵌入路径(请搭配 OpenAI 兼容嵌入器)。需 `hyperextract[google]`。密钥:`GOOGLE_API_KEY` 或 `GEMINI_API_KEY`。别名:`gemini` |
| **DeepSeek** | deepseek-v4-flash / deepseek-v4-pro | ✅ | ✅ | OpenAI 兼容。V4 模型默认开启"thinking"模式,Hyper-Extract 会自动关闭以保证结构化抽取可用。仅 LLM——无嵌入接口。密钥:`DEEPSEEK_API_KEY` |
+ | **OrcaRouter** | `orcarouter/auto`、`openai/gpt-4o-mini`、`anthropic/claude-haiku-4-5`、`deepseek/...`、`gemini/...` | ✅ | ✅ | OpenAI 兼容网关,用同一端点和密钥路由 OpenAI、Anthropic、Google、DeepSeek、Qwen、MiniMax、xAI 等 150+ 模型。密钥:`ORCAROUTER_API_KEY` |
| **阿里云百炼** | qwen-plus / qwen-turbo / qwen3.6-plus / deepseek-r1 | ✅ | ✅ | 直接使用,无需修改 |
| **阿里云百炼** | qwen-max / deepseek-v3 | ❌ | ❌ | 仅支持 `json_object`,不兼容 function calling 结构化输出 |
diff --cc uv.lock
index 125854c,125854c..5540df0
--- a/uv.lock
+++ b/uv.lock
@@@ -977,7 -977,7 +977,7 @@@ wheels =
[[package]]
name = "hyperextract"
--version = "0.9.0"
++version = "0.9.1"
source = { editable = "." }
dependencies = [
{ name = "faiss-cpu" },