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: align structured output wording with function_calling implementation

Frankie-Xub4d4f34ee31b
diff --git a/README.md b/README.md
index 84756fe..62c47cd 100644
--- a/README.md
+++ b/README.md
@@ -126,7 +126,7 @@ llm, emb = create_client(
## 🚀 Supported Platforms & Models
-Hyper-Extract relies on the LLM's structured output capability (`json_schema` or Function Calling).
+Hyper-Extract uses LangChain structured output with **function calling**. The model must support tool/function calling.
| Platform | Verified Models |
|----------|-----------------|
diff --git a/README_ZH.md b/README_ZH.md
index 17392bc..0a4f5f9 100644
--- a/README_ZH.md
+++ b/README_ZH.md
@@ -126,7 +126,7 @@ llm, emb = create_client(
## 🚀 支持的平台与模型
-Hyper-Extract 依赖大语言模型的结构化输出能力(`json_schema` 或 Function Calling)。
+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。
| 平台 | 已验证模型 |
|----------|-----------------|
diff --git a/docs/en/concepts/provider-system.md b/docs/en/concepts/provider-system.md
index 8d8ff9f..6dd5a2e 100644
--- a/docs/en/concepts/provider-system.md
+++ b/docs/en/concepts/provider-system.md
@@ -8,15 +8,15 @@ Hyper-Extract supports these ways to connect to LLMs: **OpenAI**, **Anthropic**,
### Cloud API
-| Platform | Model | `json_schema` Support | Compatible | Notes |
-|----------|-------|:---------------------:|:----------:|-------|
+| Platform | Model | Function calling | Compatible | Notes |
+|----------|-------|:----------------:|:----------:|-------|
| **OpenAI** | gpt-4o / gpt-4o-mini / gpt-5 | ✅ | ✅ | Native support, recommended |
| **Anthropic** | claude-opus-4-8 / claude-sonnet-4-6 / claude-haiku-4-5 | ✅ (tool calling) | ✅ | LLM only — no embeddings API (pair with an OpenAI-compatible embedder). Needs `hyperextract[anthropic]` |
| **DeepSeek** | deepseek-v4-flash / deepseek-v4-pro | ✅ | ✅ | OpenAI-compatible. V4 models default to "thinking" mode, which Hyper-Extract auto-disables (`extra_body`) so structured extraction works. LLM only — no embeddings API. Keys: `DEEPSEEK_API_KEY` |
| **Alibaba Bailian** | qwen-plus / qwen-turbo / qwen3.6-plus / deepseek-r1 | ✅ | ✅ | Works out of the box |
-| **Alibaba Bailian** | qwen-max / deepseek-v3 | ❌ | ❌ | Only `json_object`; `json_schema` not supported |
+| **Alibaba Bailian** | qwen-max / deepseek-v3 | ❌ | ❌ | Only `json_object`; not compatible with function-calling structured output |
-> **Bailian users**: Both qwen-max and deepseek-v3 do not support `json_schema`. If you hit `messages must contain the word 'json'` or get non-JSON output, switch to qwen-plus, qwen-turbo, or deepseek-r1. See [Issue #24](https://github.com/yifanfeng97/Hyper-Extract/issues/24).
+> **Bailian users**: qwen-max and deepseek-v3 only support `json_object` and are not compatible with Hyper-Extract's function-calling structured output. If you hit `messages must contain the word 'json'` or get non-JSON output, switch to qwen-plus, qwen-turbo, or deepseek-r1. See [Issue #24](https://github.com/yifanfeng97/Hyper-Extract/issues/24).
### Local Deployment
diff --git a/docs/zh/concepts/provider-system.md b/docs/zh/concepts/provider-system.md
index bc2a2a0..9dfb9bf 100644
--- a/docs/zh/concepts/provider-system.md
+++ b/docs/zh/concepts/provider-system.md
@@ -8,15 +8,15 @@ Hyper-Extract 支持以下接入方式:**OpenAI**、**Anthropic**、**阿里
### 云端 API
-| 平台 | 模型 | `json_schema` 支持 | 兼容性 | 备注 |
-|------|------|:------------------:|:------:|------|
+| 平台 | 模型 | 函数调用 | 兼容性 | 备注 |
+|------|------|:--------:|:------:|------|
| **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]` |
| **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` |
| **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`,不支持 `json_schema` |
+| **阿里云百炼** | qwen-max / deepseek-v3 | ❌ | ❌ | 仅支持 `json_object`,不兼容 function calling 结构化输出 |
-> **百炼用户注意**:qwen-max 和 deepseek-v3 均不支持 `json_schema`,若遇到 `messages must contain the word 'json'` 错误或不返回 JSON,请切换到 qwen-plus、qwen-turbo 或 deepseek-r1。详见 [Issue #24](https://github.com/yifanfeng97/Hyper-Extract/issues/24)。
+> **百炼用户注意**:qwen-max 和 deepseek-v3 仅支持 `json_object`,无法用于 Hyper-Extract 的 function calling 结构化输出。若遇到 `messages must contain the word 'json'` 错误或不返回 JSON,请切换到 qwen-plus、qwen-turbo 或 deepseek-r1。详见 [Issue #24](https://github.com/yifanfeng97/Hyper-Extract/issues/24)。
### 本地部署