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: improve onboarding for multi-provider support (#57)

yifanfeng974dd765cebb36
diff --git a/README.md b/README.md
index a1c3b50..84756fe 100644
--- a/README.md
+++ b/README.md
@@ -155,13 +155,50 @@ Hyper-Extract relies on the LLM's structured output capability (`json_schema` or
## ⚡ 30-Second Quick Start
+**1. Install:**
+
```bash
-# Install
+# Install uv first (if you haven't)
+curl -LsSf https://astral.sh/uv/install.sh | sh
+
+# Install Hyper-Extract CLI
uv tool install hyperextract
+# or: pipx install hyperextract
+```
-# Configure API key
-he config init -k YOUR_OPENAI_API_KEY
+**2. Configure your provider** (pick one):
+
+**OpenAI:**
+```bash
+he config init -p openai -k YOUR_OPENAI_API_KEY
+```
+**Anthropic (Claude):**
+```bash
+he config llm -p anthropic -k YOUR_ANTHROPIC_API_KEY
+he config embedder -p openai -k YOUR_OPENAI_API_KEY
+```
+
+**DeepSeek:**
+```bash
+he config llm -p deepseek -k YOUR_DEEPSEEK_API_KEY
+he config embedder -p openai -k YOUR_OPENAI_API_KEY
+```
+
+**Bailian (Alibaba Cloud):**
+```bash
+he config init -p bailian -k YOUR_BAILIAN_API_KEY
+```
+
+**Local vLLM:**
+```bash
+he config llm -p vllm -u http://localhost:8000/v1 -k dummy -m Qwen/Qwen3.5-9B
+he config embedder -p vllm -u http://localhost:8001/v1 -k dummy -m BAAI/bge-m3
+```
+
+**3. Extract, query & visualize:**
+
+```bash
# Extract knowledge from a document
he parse examples/en/tesla.md -t general/biography_graph -o ./output/ -l en
@@ -175,6 +212,8 @@ he show ./output/
he export obsidian ./output/ -o ./vault/
```
+> **Which provider should I use?** OpenAI and Bailian provide both LLM and embedding models in one API. Anthropic and DeepSeek are LLM-only (pair them with an OpenAI embedder for search/chat). Local vLLM is free but requires a GPU. DeepSeek is the most cost-effective option (~$0.001-0.005/page vs ~$0.01-0.05/page for OpenAI gpt-4o-mini).
+
<details>
<summary><b>🐍 Python API</b> (click to expand)</summary>
<br>
diff --git a/README_ZH.md b/README_ZH.md
index b0796d8..17392bc 100644
--- a/README_ZH.md
+++ b/README_ZH.md
@@ -155,13 +155,50 @@ Hyper-Extract 依赖大语言模型的结构化输出能力(`json_schema` 或
## ⚡ 30 秒快速上手
+**1. 安装:**
+
```bash
-# 安装
+# 先安装 uv(如果还没有)
+curl -LsSf https://astral.sh/uv/install.sh | sh
+
+# 安装 Hyper-Extract CLI
uv tool install hyperextract
+# 或:pipx install hyperextract
+```
-# 配置 API Key
-he config init -k YOUR_OPENAI_API_KEY
+**2. 配置你的 provider**(任选其一):
+
+**OpenAI:**
+```bash
+he config init -p openai -k YOUR_OPENAI_API_KEY
+```
+**Anthropic (Claude):**
+```bash
+he config llm -p anthropic -k YOUR_ANTHROPIC_API_KEY
+he config embedder -p openai -k YOUR_OPENAI_API_KEY
+```
+
+**DeepSeek:**
+```bash
+he config llm -p deepseek -k YOUR_DEEPSEEK_API_KEY
+he config embedder -p openai -k YOUR_OPENAI_API_KEY
+```
+
+**百炼(阿里云):**
+```bash
+he config init -p bailian -k YOUR_BAILIAN_API_KEY
+```
+
+**本地 vLLM:**
+```bash
+he config llm -p vllm -u http://localhost:8000/v1 -k dummy -m Qwen/Qwen3.5-9B
+he config embedder -p vllm -u http://localhost:8001/v1 -k dummy -m BAAI/bge-m3
+```
+
+**3. 提取、查询与可视化:**
+
+```bash
# 从文档提取知识
he parse examples/zh/sushi.md -t general/biography_graph -o ./output/ -l zh
@@ -175,6 +212,8 @@ he show ./output/
he export obsidian ./output/ -o ./vault/
```
+> **该用哪个 provider?** OpenAI 和百炼同时提供 LLM 和 embedding 模型。Anthropic 和 DeepSeek 仅提供 LLM(搜索/聊天功能需搭配 OpenAI 的 embedder)。本地 vLLM 免费但需要 GPU。DeepSeek 最经济(约 $0.001-0.005/页,而 OpenAI gpt-4o-mini 约 $0.01-0.05/页)。
+
<details>
<summary><b>🐍 Python API</b>(点击展开)</summary>
<br>
diff --git a/docs/en/cli/commands/config.md b/docs/en/cli/commands/config.md
index 4266d18..d395839 100644
--- a/docs/en/cli/commands/config.md
+++ b/docs/en/cli/commands/config.md
@@ -28,6 +28,7 @@ Initialize configuration. This is the **lazy one-step setup** — if you pass `-
- **OpenAI preset**: `gpt-4o-mini` + `text-embedding-3-small`
- **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)
```bash
he config init [OPTIONS]
@@ -37,7 +38,7 @@ he config init [OPTIONS]
| Option | Short | Description |
|--------|-------|-------------|
-| `--provider` | `-p` | Provider preset (`openai` / `bailian` / `deepseek` / `vllm`) |
+| `--provider` | `-p` | Provider preset (`openai` / `anthropic` / `deepseek` / `bailian` / `vllm`) |
| `--api-key` | `-k` | API key for both LLM and embedder |
| `--base-url` | `-u` | Custom API base URL (optional) |
@@ -55,6 +56,10 @@ he config init -p bailian -k sk-your-api-key-here
# DeepSeek (LLM only — pair with an OpenAI-compatible embedder)
he config llm -p deepseek -k sk-your-deepseek-key
he config embedder -p openai -k sk-your-openai-key
+
+# Anthropic (LLM only — pair with an OpenAI-compatible embedder)
+he config llm -p anthropic -k sk-your-anthropic-key
+he config embedder -p openai -k sk-your-openai-key
```
This saves the preset's default model and API URL automatically.
@@ -109,6 +114,7 @@ he config llm [OPTIONS]
| Option | Short | Description |
|--------|-------|-------------|
+| `--provider` | `-p` | Provider preset (e.g. `openai`, `anthropic`, `deepseek`, `bailian`, `vllm`) |
| `--api-key` | `-k` | LLM API key |
| `--model` | `-m` | LLM model name |
| `--base-url` | `-u` | Custom API base URL |
@@ -151,6 +157,7 @@ he config embedder [OPTIONS]
| Option | Short | Description |
|--------|-------|-------------|
+| `--provider` | `-p` | Provider preset (e.g. `openai`, `anthropic`, `deepseek`, `bailian`, `vllm`) |
| `--api-key` | `-k` | Embedder API key |
| `--model` | `-m` | Embedder model name |
| `--base-url` | `-u` | Custom API base URL |
diff --git a/docs/en/cli/configuration.md b/docs/en/cli/configuration.md
index ce98fd0..ba5117c 100644
--- a/docs/en/cli/configuration.md
+++ b/docs/en/cli/configuration.md
@@ -1,6 +1,6 @@
# CLI Configuration Reference
-Configuration guide for Hyper-Extract CLI, supporting **OpenAI**, **DeepSeek**, **Alibaba Cloud Bailian**, and **Local vLLM** deployments.
+Configuration guide for Hyper-Extract CLI, supporting **OpenAI**, **Anthropic**, **DeepSeek**, **Alibaba Cloud Bailian**, and **Local vLLM** deployments.
---
@@ -28,6 +28,32 @@ Choose your deployment method and follow the steps.
- **LLM**: `qwen3.6-plus`
- **Embedder**: `text-embedding-v4`
+=== "Anthropic (Claude)"
+
+ Anthropic provides LLM only — pair with an OpenAI-compatible embedder:
+
+ ```bash
+ he config llm -p anthropic -k YOUR_ANTHROPIC_API_KEY
+ he config embedder -p openai -k YOUR_OPENAI_API_KEY
+ ```
+
+ This creates `~/.he/config.toml` with:
+ - **LLM**: `claude-opus-4-8` (Anthropic)
+ - **Embedder**: `text-embedding-3-small` (OpenAI)
+
+=== "DeepSeek"
+
+ DeepSeek provides LLM only — pair with an OpenAI-compatible embedder:
+
+ ```bash
+ he config llm -p deepseek -k YOUR_DEEPSEEK_API_KEY
+ he config embedder -p openai -k YOUR_OPENAI_API_KEY
+ ```
+
+ This creates `~/.he/config.toml` with:
+ - **LLM**: `deepseek-v4-flash` (DeepSeek, auto-disables thinking mode)
+ - **Embedder**: `text-embedding-3-small` (OpenAI)
+
=== "Local vLLM"
Start the LLM and Embedding services first, then configure separately:
@@ -139,6 +165,22 @@ he config embedder --unset
he config llm -p bailian -k sk-your-key -m qwen-plus
```
+=== "Anthropic (Claude)"
+
+ ```bash
+ # LLM via Anthropic, Embedder via OpenAI
+ he config llm -p anthropic -k sk-ant-your-key
+ he config embedder -p openai -k sk-your-openai-key
+ ```
+
+=== "DeepSeek"
+
+ ```bash
+ # LLM via DeepSeek, Embedder via OpenAI
+ he config llm -p deepseek -k sk-your-key
+ he config embedder -p openai -k sk-your-openai-key
+ ```
+
=== "Local vLLM"
```bash
diff --git a/docs/en/cli/index.md b/docs/en/cli/index.md
index 1b4432f..a3b3d38 100644
--- a/docs/en/cli/index.md
+++ b/docs/en/cli/index.md
@@ -40,7 +40,7 @@ he --version
| `he build-index` | Build/rebuild search index | `-f` force rebuild |
| `he clean` | Remove a KA's index (or the whole KA) | `-a` all, `-y` yes |
| `he list` | List templates and methods | `template` or `method` |
-| `he config` | Manage configuration | `init`, `show`, `set` |
+| `he config` | Manage configuration | `init`, `show`, `llm`, `embedder` |
---
@@ -102,6 +102,15 @@ flowchart TB
he config embedder -p openai -k YOUR_OPENAI_API_KEY
```
+=== "Anthropic (Claude)"
+
+ Anthropic provides LLM only — pair with an OpenAI-compatible embedder:
+
+ ```bash
+ he config llm -p anthropic -k YOUR_ANTHROPIC_API_KEY
+ he config embedder -p openai -k YOUR_OPENAI_API_KEY
+ ```
+
=== "Local vLLM"
First install [vLLM](https://docs.vllm.ai/) and start both services:
diff --git a/docs/en/getting-started/cli-quickstart.md b/docs/en/getting-started/cli-quickstart.md
index 566b836..88d42fb 100644
--- a/docs/en/getting-started/cli-quickstart.md
+++ b/docs/en/getting-started/cli-quickstart.md
@@ -48,8 +48,19 @@ Choose your deployment method and run the corresponding configuration command:
-m BAAI/bge-m3
```
+=== "Anthropic (Claude)"
+
+ Anthropic provides LLM only — pair with an OpenAI-compatible embedder for search/chat:
+
+ ```bash
+ he config llm -p anthropic -k YOUR_ANTHROPIC_API_KEY
+ he config embedder -p openai -k YOUR_OPENAI_API_KEY
+ ```
+
This creates a configuration file at `~/.he/config.toml`. You only need to do this once.
+> **Note:** Anthropic and DeepSeek provide LLM only. For search (`he search`) and chat (`he talk`) features, pair them with an OpenAI-compatible embedder as shown above.
+
---
## Step 2: Download Sample Document
@@ -224,7 +235,7 @@ he build-index ./output/
## Troubleshooting
**"No API key found"**
-→ Run `he config init -k YOUR_API_KEY`
+→ Run `he config init -p openai -k YOUR_OPENAI_API_KEY` (or use `-p bailian`, `-p deepseek`, etc.)
**"Template not found"**
→ List available templates with `he list template`
diff --git a/docs/en/getting-started/installation.md b/docs/en/getting-started/installation.md
index 3a3cec3..c91a918 100644
--- a/docs/en/getting-started/installation.md
+++ b/docs/en/getting-started/installation.md
@@ -10,6 +10,14 @@ If you want to use the `he` command from anywhere:
=== "uv (recommended)"
+ Install [uv](https://docs.astral.sh/uv/) first (if you haven't):
+
+ ```bash
+ curl -LsSf https://astral.sh/uv/install.sh | sh
+ ```
+
+ Then install Hyper-Extract:
+
```bash
uv tool install hyperextract
```
@@ -20,6 +28,8 @@ If you want to use the `he` command from anywhere:
pipx install hyperextract
```
+ > Don't have pipx? Install it with `pip install pipx`.
+
---
## Install as Python Library
@@ -51,7 +61,7 @@ If you want to use Hyper-Extract in your Python code:
You should see something like:
```
- Hyper-Extract CLI version 0.1.3.dev0
+ Hyper-Extract CLI version 0.4.0
```
=== "Python"
@@ -68,11 +78,13 @@ If you want to use Hyper-Extract in your Python code:
If you want to contribute or modify the source code:
```bash
-# Clone the repository
git clone https://github.com/yifanfeng97/hyper-extract.git
cd hyper-extract
-# Install in editable mode with dev dependencies
+# Install with uv (recommended)
+uv sync --extra dev
+
+# Or with pip
pip install -e ".[dev]"
```
diff --git a/docs/en/getting-started/python-quickstart.md b/docs/en/getting-started/python-quickstart.md
index 70089e6..d9c1446 100644
--- a/docs/en/getting-started/python-quickstart.md
+++ b/docs/en/getting-started/python-quickstart.md
@@ -38,9 +38,35 @@ Create a `.env` file:
echo "OPENAI_API_KEY=your-api-key" > .env
```
-**Option B — Bailian, DeepSeek, or vLLM**
+**Option B — Other providers (Anthropic, DeepSeek, Bailian, vLLM)**
-See the [Provider Configuration Guide](../python/guides/provider-configuration.md) for platform-specific setup.
+Set the appropriate environment variables in `.env`:
+
+```bash
+# Anthropic
+ANTHROPIC_API_KEY=sk-ant-xxx
+OPENAI_API_KEY=sk-xxx # for embeddings
+
+# DeepSeek
+DEEPSEEK_API_KEY=sk-xxx
+OPENAI_API_KEY=sk-xxx # for embeddings
+
+# Bailian (Alibaba Cloud)
+OPENAI_API_KEY=sk-xxx
+OPENAI_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
+```
+
+Then configure the client in your script:
+
+```python
+from hyperextract import create_client, Template
+
+# Example: DeepSeek LLM + OpenAI embedder
+llm, emb = create_client(llm="deepseek", embedder="openai:text-embedding-3-small")
+ka = Template.create("general/biography_graph", language="en", llm_client=llm, embedder=emb)
+```
+
+See the [Provider Configuration Guide](../python/guides/provider-configuration.md) for full details.
---
@@ -241,15 +267,13 @@ def main():
result.show()
print("\nDone!")
-```
-
-![Interactive Knowledge Graph Visualization](../../assets/en_show.jpg)
-
if __name__ == "__main__":
main()
```
+![Interactive Knowledge Graph Visualization](../../assets/en_show.jpg)
+
---
## What's Next?
diff --git a/docs/en/python/guides/provider-configuration.md b/docs/en/python/guides/provider-configuration.md
index faa7717..b838045 100644
--- a/docs/en/python/guides/provider-configuration.md
+++ b/docs/en/python/guides/provider-configuration.md
@@ -25,6 +25,19 @@ llm, emb = create_client("bailian", api_key="sk-xxx")
# Or override model: create_client("bailian:qwen3.6-plus", api_key="sk-xxx")
```
+### Anthropic (Claude)
+
+```python
+from hyperextract import create_client, AutoGraph
+
+# Anthropic is LLM only — pair it with an OpenAI-compatible embedder.
+# Keys: ANTHROPIC_API_KEY (or CLAUDE_API_KEY) for the LLM, OPENAI_API_KEY for embeddings.
+llm, emb = create_client(
+ llm="anthropic", # default model: claude-opus-4-8 (override with "anthropic:<model>")
+ embedder="openai:text-embedding-3-small",
+)
+```
+
### DeepSeek
```python
@@ -76,6 +89,7 @@ print(f"Nodes: {len(graph.nodes)}, Edges: {len(graph.edges)}")
|----------|---------|
| **OpenAI** | `he config init -p openai -k sk-xxx` |
| **Bailian** | `he config init -p bailian -k sk-xxx` |
+| **Anthropic** | `he config llm -p anthropic -k sk-ant-xxx` + `he config embedder -p openai -k sk-xxx` |
| **DeepSeek** | `he config llm -p deepseek -k sk-xxx` + `he config embedder -p openai -k sk-xxx` |
| **vLLM** | `he config init` → select "local vLLM" |
| **Mixed** (LLM=Bailian, Embedder=vLLM) | `he config llm -p bailian -k sk-xxx` + `he config embedder -p vllm -u http://localhost:8001/v1 -k dummy` |
diff --git a/docs/en/resources/faq.md b/docs/en/resources/faq.md
index b7a60c3..dba125a 100644
--- a/docs/en/resources/faq.md
+++ b/docs/en/resources/faq.md
@@ -20,7 +20,7 @@ Hyper-Extract is an LLM-powered knowledge extraction framework that transforms u
### Is it free?
-The software is open-source (Apache-2.0). You need to provide your own OpenAI API key for LLM calls.
+The software is open-source (Apache-2.0). You need an API key from a supported LLM provider (OpenAI, Anthropic, DeepSeek, Alibaba Bailian, or local vLLM).
---
@@ -29,7 +29,7 @@ The software is open-source (Apache-2.0). You need to provide your own OpenAI AP
### What are the requirements?
- Python 3.11+
-- OpenAI API key
+- An API key from any supported provider (OpenAI, Anthropic, DeepSeek, Bailian, or local vLLM)
### How do I install it?
@@ -58,31 +58,59 @@ pip install hyperextract
### Where do I set my API key?
**Option 1**: CLI
+
```bash
-he config init -k YOUR_API_KEY
+# OpenAI / Bailian (one-step)
+he config init -p openai -k YOUR_API_KEY
+he config init -p bailian -k YOUR_API_KEY
+
+# Anthropic / DeepSeek (LLM + separate embedder)
+he config llm -p deepseek -k YOUR_DEEPSEEK_API_KEY
+he config embedder -p openai -k YOUR_OPENAI_API_KEY
```
**Option 2**: Environment variable
+
```bash
-export OPENAI_API_KEY=your-api-key
+export OPENAI_API_KEY=your-api-key # OpenAI/Bailian
+export ANTHROPIC_API_KEY=your-api-key # Anthropic
+export DEEPSEEK_API_KEY=your-api-key # DeepSeek
```
-**Option 3**: .env file
+**Option 3**: `.env` file
```
OPENAI_API_KEY=your-api-key
```
### Can I use a different LLM provider?
-Yes, set the base URL:
+Yes! Hyper-Extract supports OpenAI, Anthropic, DeepSeek, Alibaba Bailian, and local vLLM out of the box:
+
+```bash
+# OpenAI / Bailian
+he config init -p openai -k YOUR_API_KEY
+
+# DeepSeek / Anthropic (LLM only, pair with OpenAI embedder)
+he config llm -p deepseek -k YOUR_DEEPSEEK_API_KEY
+he config embedder -p openai -k YOUR_OPENAI_API_KEY
+```
+
+For custom OpenAI-compatible endpoints:
```bash
-he config set llm.base_url https://your-provider.com/v1
+he config llm --base-url https://your-provider.com/v1 -k YOUR_API_KEY
```
+See [Provider System](../concepts/provider-system.md) for the full compatibility list.
+
### Which models are supported?
-- OpenAI models (gpt-4o, gpt-4o-mini, etc.)
-- Any OpenAI-compatible API
+- **OpenAI**: gpt-4o, gpt-4o-mini, gpt-5
+- **Anthropic**: claude-opus-4-8, claude-sonnet-4-6, claude-haiku-4-5
+- **DeepSeek**: deepseek-v4-flash, deepseek-v4-pro
+- **Alibaba Bailian**: qwen-plus, qwen-turbo, qwen3.6-plus
+- **Local vLLM**: Any model served via vLLM (e.g. Qwen/Qwen3.5-9B)
+
+See [Provider System](../concepts/provider-system.md) for the full compatibility table.
---
@@ -196,9 +224,10 @@ data_dict = result.data.model_dump()
### "API key not found"
-Run:
```bash
-he config init -k YOUR_API_KEY
+# Specify your provider
+he config init -p openai -k YOUR_API_KEY
+# or: -p bailian, -p deepseek, etc.
```
### "Template not found"
diff --git a/docs/en/resources/troubleshooting.md b/docs/en/resources/troubleshooting.md
index 6e6c37a..5659938 100644
--- a/docs/en/resources/troubleshooting.md
+++ b/docs/en/resources/troubleshooting.md
@@ -44,12 +44,19 @@ Solutions to common issues.
1. **CLI Configuration** (recommended):
```bash
- he config init -k YOUR_API_KEY
+ # OpenAI / Bailian (one-step)
+ he config init -p openai -k YOUR_API_KEY
+
+ # Anthropic / DeepSeek (LLM + separate embedder)
+ he config llm -p deepseek -k YOUR_DEEPSEEK_API_KEY
+ he config embedder -p openai -k YOUR_OPENAI_API_KEY
```
2. **Environment Variable**:
```bash
export OPENAI_API_KEY=your-api-key
+ export ANTHROPIC_API_KEY=your-api-key # for Anthropic
+ export DEEPSEEK_API_KEY=your-api-key # for DeepSeek
```
3. **Verify Configuration**:
@@ -65,8 +72,9 @@ Solutions to common issues.
1. Verify key is correct
2. Check for extra spaces
-3. Try regenerating key in OpenAI dashboard
-4. Check if key has available credits
+3. For Anthropic: ensure `ANTHROPIC_API_KEY` (not `OPENAI_API_KEY`)
+4. For DeepSeek: ensure `DEEPSEEK_API_KEY` (not `OPENAI_API_KEY`)
+5. Check if key has available credits/quota
---
diff --git a/docs/en/tutorials/knowledge-base/step1-setup.md b/docs/en/tutorials/knowledge-base/step1-setup.md
index 3b23b96..eec455c 100644
--- a/docs/en/tutorials/knowledge-base/step1-setup.md
+++ b/docs/en/tutorials/knowledge-base/step1-setup.md
@@ -76,6 +76,16 @@ backup_dir: "./backups"
## Management Script
+### Prerequisites
+
+Install the required packages:
+
+```bash
+pip install pyyaml hyperextract python-dotenv
+```
+
+> **Note:** The management script uses `pyyaml` for config files and `python-dotenv` for loading API keys. These are not included in Hyper-Extract's default dependencies.
+
### kb_manager.py (Starter)
```python
@@ -175,6 +185,8 @@ EOF
### 2. Run Setup
+Ensure `pyyaml` and `python-dotenv` are installed (see [Prerequisites](#prerequisites) above):
+
```bash
python kb_manager.py
```
diff --git a/docs/zh/cli/commands/config.md b/docs/zh/cli/commands/config.md
index 7c6b23e..992047b 100644
--- a/docs/zh/cli/commands/config.md
+++ b/docs/zh/cli/commands/config.md
@@ -28,6 +28,7 @@ he config [COMMAND] [OPTIONS]
- **OpenAI preset**: `gpt-4o-mini` + `text-embedding-3-small`
- **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)
```bash
he config init [OPTIONS]
@@ -37,7 +38,7 @@ he config init [OPTIONS]
| 选项 | 简写 | 描述 |
|--------|-------|-------------|
-| `--provider` | `-p` | 提供商 preset (`openai` / `bailian` / `deepseek` / `vllm`) |
+| `--provider` | `-p` | 提供商 preset (`openai` / `anthropic` / `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) |
@@ -55,6 +56,10 @@ he config init -p bailian -k sk-your-api-key-here
# DeepSeek(仅 LLM —— 请搭配 OpenAI 兼容嵌入器)
he config llm -p deepseek -k sk-your-deepseek-key
he config embedder -p openai -k sk-your-openai-key
+
+# Anthropic(仅 LLM —— 请搭配 OpenAI 兼容嵌入器)
+he config llm -p anthropic -k sk-your-anthropic-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。
@@ -109,6 +114,7 @@ he config llm [OPTIONS]
| 选项 | 简写 | 描述 |
|--------|-------|-------------|
+| `--provider` | `-p` | 提供商 preset(如 `openai`、`anthropic`、`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 |
@@ -151,6 +157,7 @@ he config embedder [OPTIONS]
| 选项 | 简写 | 描述 |
|--------|-------|-------------|
+| `--provider` | `-p` | 提供商 preset(如 `openai`、`anthropic`、`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 --git a/docs/zh/cli/configuration.md b/docs/zh/cli/configuration.md
index 6013f9c..1128f56 100644
--- a/docs/zh/cli/configuration.md
+++ b/docs/zh/cli/configuration.md
@@ -1,6 +1,6 @@
# CLI 配置参考
-Hyper-Extract CLI 的配置指南,支持 **OpenAI**、**DeepSeek**、**阿里云百炼** 和 **本地 vLLM** 部署方式。
+Hyper-Extract CLI 的配置指南,支持 **OpenAI**、**Anthropic**、**DeepSeek**、**阿里云百炼** 和 **本地 vLLM** 部署方式。
---
@@ -28,6 +28,32 @@ Hyper-Extract CLI 的配置指南,支持 **OpenAI**、**DeepSeek**、**阿里
- **LLM**: `qwen3.6-plus`
- **嵌入模型**: `text-embedding-v4`
+=== "Anthropic (Claude)"
+
+ Anthropic 仅提供 LLM —— 请搭配 OpenAI 兼容嵌入器:
+
+ ```bash
+ he config llm -p anthropic -k YOUR_ANTHROPIC_API_KEY
+ he config embedder -p openai -k YOUR_OPENAI_API_KEY
+ ```
+
+ 这会创建 `~/.he/config.toml`:
+ - **LLM**: `claude-opus-4-8` (Anthropic)
+ - **嵌入模型**: `text-embedding-3-small` (OpenAI)
+
+=== "DeepSeek"
+
+ DeepSeek 仅提供 LLM —— 请搭配 OpenAI 兼容嵌入器:
+
+ ```bash
+ he config llm -p deepseek -k YOUR_DEEPSEEK_API_KEY
+ he config embedder -p openai -k YOUR_OPENAI_API_KEY
+ ```
+
+ 这会创建 `~/.he/config.toml`:
+ - **LLM**: `deepseek-v4-flash` (DeepSeek,自动关闭思考模式)
+ - **嵌入模型**: `text-embedding-3-small` (OpenAI)
+
=== "本地 vLLM"
需先启动 LLM 和 Embedding 两个服务,然后分别配置:
@@ -139,6 +165,22 @@ he config embedder --unset
he config llm -p bailian -k sk-your-key -m qwen-plus
```
+=== "Anthropic (Claude)"
+
+ ```bash
+ # LLM 用 Anthropic,Embedding 用 OpenAI
+ he config llm -p anthropic -k sk-ant-your-key
+ he config embedder -p openai -k sk-your-openai-key
+ ```
+
+=== "DeepSeek"
+
+ ```bash
+ # LLM 用 DeepSeek,Embedding 用 OpenAI
+ he config llm -p deepseek -k sk-your-key
+ he config embedder -p openai -k sk-your-openai-key
+ ```
+
=== "本地 vLLM"
```bash
diff --git a/docs/zh/cli/index.md b/docs/zh/cli/index.md
index c249bd6..d2d93af 100644
--- a/docs/zh/cli/index.md
+++ b/docs/zh/cli/index.md
@@ -40,7 +40,7 @@ he --version
| `he build-index` | 构建/重建搜索索引 | `-f` 强制重建 |
| `he clean` | 删除 KA 的索引(或整个 KA) | `-a` all, `-y` yes |
| `he list` | 列出模板和方法 | `template` 或 `method` |
-| `he config` | 管理配置 | `init`, `show`, `set` |
+| `he config` | 管理配置 | `init`, `show`, `llm`, `embedder` |
---
@@ -102,6 +102,15 @@ flowchart TB
he config embedder -p openai -k YOUR_OPENAI_API_KEY
```
+=== "Anthropic (Claude)"
+
+ Anthropic 仅提供 LLM —— 请搭配 OpenAI 兼容嵌入器:
+
+ ```bash
+ he config llm -p anthropic -k YOUR_ANTHROPIC_API_KEY
+ he config embedder -p openai -k YOUR_OPENAI_API_KEY
+ ```
+
=== "本地 vLLM"
需先安装 [vLLM](https://docs.vllm.ai/) 并分别启动 LLM 和 Embedding 服务:
@@ -206,7 +215,7 @@ he parse doc.md -m light_rag
```bash
# 英文
-he parse doc.md -t general/biography_graph -l zh
+he parse doc.md -t general/biography_graph -l en
# 中文
he parse doc.md -t general/biography_graph -l zh
diff --git a/docs/zh/getting-started/cli-quickstart.md b/docs/zh/getting-started/cli-quickstart.md
index be985b9..79af322 100644
--- a/docs/zh/getting-started/cli-quickstart.md
+++ b/docs/zh/getting-started/cli-quickstart.md
@@ -48,8 +48,19 @@
-m BAAI/bge-m3
```
+=== "Anthropic (Claude)"
+
+ Anthropic 仅提供 LLM —— 搜索/对话功能需搭配 OpenAI 兼容的 embedder:
+
+ ```bash
+ he config llm -p anthropic -k YOUR_ANTHROPIC_API_KEY
+ he config embedder -p openai -k YOUR_OPENAI_API_KEY
+ ```
+
这会在 `~/.he/config.toml` 创建配置文件,只需配置一次。
+> **注意:** Anthropic 和 DeepSeek 仅提供 LLM。如需使用搜索(`he search`)和对话(`he talk`)功能,请按上文所示搭配 OpenAI 兼容的 embedder。
+
---
## 第 2 步:下载示例文档
@@ -219,7 +230,7 @@ he build-index ./output/
## 故障排除
**"No API key found"**
-→ 运行 `he config init -k YOUR_API_KEY`
+→ 运行 `he config init -p openai -k YOUR_OPENAI_API_KEY`(或使用 `-p bailian`、`-p deepseek` 等)
**"Template not found"**
→ 使用 `he list template` 查看可用模板
diff --git a/docs/zh/getting-started/installation.md b/docs/zh/getting-started/installation.md
index 021a3d3..e580c58 100644
--- a/docs/zh/getting-started/installation.md
+++ b/docs/zh/getting-started/installation.md
@@ -10,6 +10,14 @@ Hyper-Extract 需要 **Python 3.11+**。
=== "uv (推荐)"
+ 首先安装 [uv](https://docs.astral.sh/uv/)(如果尚未安装):
+
+ ```bash
+ curl -LsSf https://astral.sh/uv/install.sh | sh
+ ```
+
+ 然后安装 Hyper-Extract:
+
```bash
uv tool install hyperextract
```
@@ -20,6 +28,8 @@ Hyper-Extract 需要 **Python 3.11+**。
pipx install hyperextract
```
+ > 没有安装 pipx?运行 `pip install pipx` 安装。
+
---
## 安装为 Python 库
@@ -51,7 +61,7 @@ Hyper-Extract 需要 **Python 3.11+**。
您应该看到类似输出:
```
- Hyper-Extract CLI version 0.1.3.dev0
+ Hyper-Extract CLI version 0.4.0
```
=== "Python"
@@ -68,11 +78,13 @@ Hyper-Extract 需要 **Python 3.11+**。
如果您想贡献或修改源代码:
```bash
-# 克隆仓库
git clone https://github.com/yifanfeng97/hyper-extract.git
cd hyper-extract
-# 以可编辑模式安装开发依赖
+# 使用 uv 安装(推荐)
+uv sync --extra dev
+
+# 或使用 pip
pip install -e ".[dev]"
```
diff --git a/docs/zh/getting-started/python-quickstart.md b/docs/zh/getting-started/python-quickstart.md
index 3e8ebfd..c3bbb18 100644
--- a/docs/zh/getting-started/python-quickstart.md
+++ b/docs/zh/getting-started/python-quickstart.md
@@ -38,9 +38,35 @@ pip install hyperextract
echo "OPENAI_API_KEY=your-api-key" > .env
```
-**方式 B — 百炼、DeepSeek 或 vLLM**
+**方式 B — 其他 Provider(Anthropic、DeepSeek、百炼、vLLM)**
-平台特定配置见 [Provider 配置指南](../python/guides/provider-configuration.md)。
+在 `.env` 中设置相应的环境变量:
+
+```bash
+# Anthropic
+ANTHROPIC_API_KEY=sk-ant-xxx
+OPENAI_API_KEY=sk-xxx # 用于 embeddings
+
+# DeepSeek
+DEEPSEEK_API_KEY=sk-xxx
+OPENAI_API_KEY=sk-xxx # 用于 embeddings
+
+# 百炼(阿里云)
+OPENAI_API_KEY=sk-xxx
+OPENAI_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
+```
+
+然后在脚本中配置客户端:
+
+```python
+from hyperextract import create_client, Template
+
+# 示例:DeepSeek LLM + OpenAI embedder
+llm, emb = create_client(llm="deepseek", embedder="openai:text-embedding-3-small")
+ka = Template.create("general/biography_graph", language="zh", llm_client=llm, embedder=emb)
+```
+
+详见 [Provider 配置指南](../python/guides/provider-configuration.md)。
---
@@ -241,7 +267,6 @@ if __name__ == "__main__":
```
![交互式知识图谱可视化](../../assets/zh_show.jpg)
-```
---
diff --git a/docs/zh/python/guides/provider-configuration.md b/docs/zh/python/guides/provider-configuration.md
index 03c7fbe..692f49e 100644
--- a/docs/zh/python/guides/provider-configuration.md
+++ b/docs/zh/python/guides/provider-configuration.md
@@ -25,6 +25,19 @@ llm, emb = create_client("bailian", api_key="sk-xxx")
# 或换模型: create_client("bailian:qwen3.6-plus", api_key="sk-xxx")
```
+### Anthropic (Claude)
+
+```python
+from hyperextract import create_client, AutoGraph
+
+# Anthropic 仅提供 LLM——请搭配 OpenAI 兼容嵌入器。
+# 密钥:LLM 使用 ANTHROPIC_API_KEY(或 CLAUDE_API_KEY),嵌入使用 OPENAI_API_KEY。
+llm, emb = create_client(
+ llm="anthropic", # 默认模型:claude-opus-4-8(用 "anthropic:<model>" 覆盖)
+ embedder="openai:text-embedding-3-small",
+)
+```
+
### DeepSeek
```python
@@ -75,6 +88,7 @@ print(f"节点: {len(graph.nodes)}, 关系: {len(graph.edges)}")
|------|------|
| **OpenAI** | `he config init -p openai -k sk-xxx` |
| **百炼** | `he config init -p bailian -k sk-xxx` |
+| **Anthropic** | `he config llm -p anthropic -k sk-ant-xxx` + `he config embedder -p openai -k sk-xxx` |
| **DeepSeek** | `he config llm -p deepseek -k sk-xxx` + `he config embedder -p openai -k sk-xxx` |
| **vLLM** | `he config init` → 选择「本地 vLLM」 |
| **混合部署**(LLM=百炼 + Embedding=本地) | `he config llm -p bailian -k sk-xxx` + `he config embedder -p vllm -u http://localhost:8001/v1 -k dummy` |
diff --git a/docs/zh/resources/faq.md b/docs/zh/resources/faq.md
index fcb1ef2..edb9a19 100644
--- a/docs/zh/resources/faq.md
+++ b/docs/zh/resources/faq.md
@@ -20,7 +20,7 @@ Hyper-Extract 是一个基于大语言模型的知识提取框架,可以将非
### 它是免费的吗?
-本软件是开源的(Apache-2.0 协议)。您需要提供自己的 OpenAI API 密钥来进行大语言模型调用。
+本软件是开源的(Apache-2.0 协议)。您需要从支持的 LLM 提供商获取 API 密钥(OpenAI、Anthropic、DeepSeek、阿里云百炼或本地 vLLM)。
---
@@ -29,7 +29,7 @@ Hyper-Extract 是一个基于大语言模型的知识提取框架,可以将非
### 系统要求是什么?
- Python 3.11+
-- OpenAI API 密钥
+- 任意支持的提供商的 API 密钥(OpenAI、Anthropic、DeepSeek、百炼或本地 vLLM)
### 如何安装?
@@ -58,31 +58,59 @@ pip install hyperextract
### 在哪里设置 API 密钥?
**选项 1**:命令行
+
```bash
-he config init -k YOUR_API_KEY
+# OpenAI / 百炼(一步到位)
+he config init -p openai -k YOUR_API_KEY
+he config init -p bailian -k YOUR_API_KEY
+
+# Anthropic / DeepSeek(LLM + 独立嵌入器)
+he config llm -p deepseek -k YOUR_DEEPSEEK_API_KEY
+he config embedder -p openai -k YOUR_OPENAI_API_KEY
```
**选项 2**:环境变量
+
```bash
-export OPENAI_API_KEY=your-api-key
+export OPENAI_API_KEY=your-api-key # OpenAI/百炼
+export ANTHROPIC_API_KEY=your-api-key # Anthropic
+export DEEPSEEK_API_KEY=your-api-key # DeepSeek
```
-**选项 3**:.env 文件
+**选项 3**:`.env` 文件
```
OPENAI_API_KEY=your-api-key
```
### 可以使用其他大语言模型提供商吗?
-可以,设置 base URL:
+可以!Hyper-Extract 开箱即用支持 OpenAI、Anthropic、DeepSeek、阿里云百炼和本地 vLLM:
+
+```bash
+# OpenAI / 百炼
+he config init -p openai -k YOUR_API_KEY
+
+# DeepSeek / Anthropic(仅 LLM,需搭配 OpenAI 嵌入器)
+he config llm -p deepseek -k YOUR_DEEPSEEK_API_KEY
+he config embedder -p openai -k YOUR_OPENAI_API_KEY
+```
+
+对于自定义的 OpenAI 兼容端点:
```bash
-he config set llm.base_url https://your-provider.com/v1
+he config llm --base-url https://your-provider.com/v1 -k YOUR_API_KEY
```
+参见 [Provider 系统](../concepts/provider-system.md) 了解完整兼容性列表。
+
### 支持哪些模型?
-- OpenAI 模型(gpt-4o、gpt-4o-mini 等)
-- 任何兼容 OpenAI API 的接口
+- **OpenAI**:gpt-4o、gpt-4o-mini、gpt-5
+- **Anthropic**:claude-opus-4-8、claude-sonnet-4-6、claude-haiku-4-5
+- **DeepSeek**:deepseek-v4-flash、deepseek-v4-pro
+- **阿里云百炼**:qwen-plus、qwen-turbo、qwen3.6-plus
+- **本地 vLLM**:通过 vLLM 提供的任意模型(如 Qwen/Qwen3.5-9B)
+
+参见 [Provider 系统](../concepts/provider-system.md) 了解完整兼容性表格。
---
@@ -196,9 +224,10 @@ data_dict = result.data.model_dump()
### "API key not found"
-运行:
```bash
-he config init -k YOUR_API_KEY
+# 指定您的提供商
+he config init -p openai -k YOUR_API_KEY
+# 或:-p bailian、-p deepseek 等
```
### "Template not found"
diff --git a/docs/zh/resources/troubleshooting.md b/docs/zh/resources/troubleshooting.md
index 6040e8a..af62c32 100644
--- a/docs/zh/resources/troubleshooting.md
+++ b/docs/zh/resources/troubleshooting.md
@@ -42,12 +42,19 @@
1. **CLI 配置**(推荐):
```bash
- he config init -k YOUR_API_KEY
+ # OpenAI / 百炼(一步到位)
+ he config init -p openai -k YOUR_API_KEY
+
+ # Anthropic / DeepSeek(LLM + 独立嵌入器)
+ he config llm -p deepseek -k YOUR_DEEPSEEK_API_KEY
+ he config embedder -p openai -k YOUR_OPENAI_API_KEY
```
2. **环境变量**:
```bash
export OPENAI_API_KEY=your-api-key
+ export ANTHROPIC_API_KEY=your-api-key # 用于 Anthropic
+ export DEEPSEEK_API_KEY=your-api-key # 用于 DeepSeek
```
3. **验证配置**:
@@ -62,8 +69,9 @@
**解决方案**:
1. 验证密钥是否正确
2. 检查是否有额外的空格
-3. 尝试在 OpenAI 控制台重新生成密钥
-4. 检查密钥是否有可用额度
+3. Anthropic:确保使用 `ANTHROPIC_API_KEY`(而非 `OPENAI_API_KEY`)
+4. DeepSeek:确保使用 `DEEPSEEK_API_KEY`(而非 `OPENAI_API_KEY`)
+5. 检查密钥是否有可用额度/配额
---
diff --git a/docs/zh/tutorials/knowledge-base/step1-setup.md b/docs/zh/tutorials/knowledge-base/step1-setup.md
index 8505f59..f430fc2 100644
--- a/docs/zh/tutorials/knowledge-base/step1-setup.md
+++ b/docs/zh/tutorials/knowledge-base/step1-setup.md
@@ -76,6 +76,16 @@ backup_dir: "./backups"
## 管理脚本
+### 前置依赖
+
+安装所需的包:
+
+```bash
+pip install pyyaml hyperextract python-dotenv
+```
+
+> **注意:** 管理脚本使用 `pyyaml` 处理配置文件,使用 `python-dotenv` 加载 API 密钥。这些不包含在 Hyper-Extract 的默认依赖中。
+
### kb_manager.py(入门版)
```python
@@ -175,6 +185,8 @@ EOF
### 2. 运行设置
+确保已安装 `pyyaml` 和 `python-dotenv`(参见上方的前置依赖部分):
+
```bash
python kb_manager.py
```