Skip to content

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Docs: non-NVIDIA devices need self-installed accelerated torch plus vllm/lmdeploy; link output-formats page from READMEs and doc indexes (zh/en)

myhlolidc44b4afc1df
diff --git a/README.md b/README.md
index 7817547f..53b50689 100644
--- a/README.md
+++ b/README.md
@@ -52,7 +52,7 @@ MinerU 4.0 brings document parsing, a local document library, and service tools
- **Document library and agent reading**: discover files, cache results, search content, continue by page or block, and preserve stable citation locators.
- **Independent model configuration**: ONNX or Torch for small models; llama.cpp, vLLM, or LMDeploy for the VLM.
- **Unified tools**: Python SDK, V1 API, stateless batch conversion, multi-service Router, and a Gradio-based WebUI.
-- **Structured results and rendering**: one document model supports nine rendering targets: Markdown, HTML, LaTeX, DOCX, EPUB, PDF, Structured Content, and Content List V1/V2. Each CLI/API exposes its own subset of exports.
+- **Structured results and rendering**: one document model supports nine rendering targets: Markdown, HTML, LaTeX, DOCX, EPUB, PDF, Structured Content, and Content List V1/V2. Each CLI/API exposes its own subset of exports; see [Output Formats and Result Contract](https://opendatalab.github.io/MinerU/reference/output_files/).
PDF and images support all four tiers. Office, OpenDocument, EPUB, OFD, HTML, and CSV/TSV use local Flash native parsing. Plain text is read directly rather than parsed. Documents are not automatically uploaded to the official service; remote parsing requires explicit configuration.
diff --git a/README_zh-CN.md b/README_zh-CN.md
index bf72cc6e..0e256dbd 100644
--- a/README_zh-CN.md
+++ b/README_zh-CN.md
@@ -47,7 +47,7 @@ MinerU 4.0 将多格式文档解析、文档库和服务工具整合到统一工
- **文档库与 Agent 阅读**:发现文件、缓存结果、搜索内容,按页或块继续阅读,并保留稳定引用位置。
- **独立模型配置**:小模型选择 ONNX 或 Torch;VLM 独立选择 llama.cpp、vLLM、LMDeploy。
- **统一工具入口**:Python SDK、V1 API、无状态批处理、多服务 Router 和基于 Gradio 的 WebUI。
-- **结构化结果与渲染**:统一文档模型支持 Markdown、HTML、LaTeX、DOCX、EPUB、PDF、Structured Content、Content List V1/V2 九种渲染目标;各 CLI/API 的导出范围见输出说明。
+- **结构化结果与渲染**:统一文档模型支持 Markdown、HTML、LaTeX、DOCX、EPUB、PDF、Structured Content、Content List V1/V2 九种渲染目标;各 CLI/API 的导出范围见[输出格式与结果协议](https://opendatalab.github.io/MinerU/zh/reference/output_files/)。
PDF 和图片支持四档解析;Office、OpenDocument、EPUB、OFD、HTML、CSV/TSV 使用本地 Flash 原生解析。纯文本直接读取,不进入解析流程。默认不会自动将文档上传到官网服务,远程解析需要显式配置。
diff --git a/docs/en/index.md b/docs/en/index.md
index 9d801780..b3f0cbd4 100644
--- a/docs/en/index.md
+++ b/docs/en/index.md
@@ -9,7 +9,7 @@ MinerU 4.0 brings document parsing, a local document library, and service tools
- **Document library and agent reading**: discover files, cache results, search content, continue by page or block, and preserve stable citation locators.
- **Independent model configuration**: ONNX or Torch for small models; llama.cpp, vLLM, or LMDeploy for the VLM.
- **Unified tools**: Python SDK, V1 API, stateless batch conversion, multi-service Router, and a Gradio-based WebUI.
-- **Structured results and rendering**: one document model supports nine rendering targets: Markdown, HTML, LaTeX, DOCX, EPUB, PDF, Structured Content, and Content List V1/V2. Each CLI/API exposes its own subset of exports.
+- **Structured results and rendering**: one document model supports nine rendering targets: Markdown, HTML, LaTeX, DOCX, EPUB, PDF, Structured Content, and Content List V1/V2. Each CLI/API exposes its own subset of exports; see [Output Formats and Result Contract](reference/output_files.md).
PDF and images support all four tiers. Office, OpenDocument, EPUB, OFD, HTML, and CSV/TSV use local Flash native parsing. Plain text is read directly rather than parsed. Documents are not automatically uploaded to the official service; remote parsing requires explicit configuration.
diff --git a/docs/zh/index.md b/docs/zh/index.md
index 5087d4b0..0b3bb285 100644
--- a/docs/zh/index.md
+++ b/docs/zh/index.md
@@ -9,7 +9,7 @@ MinerU 4.0 将多格式文档解析、文档库和服务工具整合到统一工
- **文档库与 Agent 阅读**:发现文件、缓存结果、搜索内容,按页或块继续阅读,并保留稳定引用位置。
- **独立模型配置**:小模型选择 ONNX 或 Torch;VLM 独立选择 llama.cpp、vLLM、LMDeploy。
- **统一工具入口**:Python SDK、V1 API、无状态批处理、多服务 Router 和基于 Gradio 的 WebUI。
-- **结构化结果与渲染**:统一文档模型支持 Markdown、HTML、LaTeX、DOCX、EPUB、PDF、Structured Content、Content List V1/V2 九种渲染目标;各 CLI/API 的导出范围见输出说明。
+- **结构化结果与渲染**:统一文档模型支持 Markdown、HTML、LaTeX、DOCX、EPUB、PDF、Structured Content、Content List V1/V2 九种渲染目标;各 CLI/API 的导出范围见[输出格式与结果协议](reference/output_files.md)。
PDF 和图片支持四档解析;Office、OpenDocument、EPUB、OFD、HTML、CSV/TSV 使用本地 Flash 原生解析。纯文本直接读取,不进入解析流程。默认不会自动将文档上传到官网服务,远程解析需要显式配置。