opensource/MinerU
3
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-09-21 12:42:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #5147 from myhloli/dev

Browse Source 
Update mineru package version and documentation for 3.4 release
This commit is contained in:
Xiaomeng Zhao
2026-06-18 14:53:37 +08:00
committed by GitHub
parent 3a4fcc78a8 c5cc50e81e
commit 71ee160093
15 changed files with 50 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+17 -1
View File
@@ -80,6 +80,22 @@ Domestic AI chips: Ascend · Cambricon · Enflame · MetaX · Moore Threads · K
# Changelog
- 2026/06/18 3.4 Released
This release focuses on **OCR capability upgrades for the pipeline backend**, **OCR processing pipeline optimization**, and **model download experience improvements**. The main updates include:
- OCR model upgrade and processing acceleration
- The OCR model for the `pipeline` backend has been upgraded to `PP-OCRv6`, improving OCR accuracy by about `11%` on OmniDocBench v1.6.
- Removed Japanese, Traditional Chinese, English, and Latin options from OCR language selection. These scenarios are now routed to the `ch` OCR model, simplifying model configuration and language selection.
- Optimized the OCR inference and processing pipeline, increasing OCR processing speed by about `100%` and significantly improving parsing efficiency for batch documents and OCR-intensive documents.
- Model download logic optimization
- Added automatic model source selection, allowing first-time installations to choose a better model source based on the current network environment.
- Before downloading models, MinerU now prioritizes checking locally downloaded model cache files. Cache hits can be reused directly, reducing repeated downloads and unnecessary remote requests.
- For more details about model source configuration, automatic source selection, and local model usage, see the [Model Source Documentation](https://opendatalab.github.io/MinerU/en/usage/model_source/).
With the 3.4 release, MinerU further improves the parsing accuracy and processing efficiency of the `pipeline` backend in OCR scenarios. It also optimizes model downloads, cache reuse, and local configuration write-back, making first-time installation, model updates, and multi-environment deployment more stable and automated.
- 2026/06/11 3.3 Released
This release focuses on **Hybrid parsing performance optimization** and **VLM model capability upgrades**. The main updates include:
@@ -223,7 +239,7 @@ A WebUI developed based on Gradio, with a simple interface and only core parsing
</tr>
<tr>
<th>Accuracy<sup>1</sup></th>
<td style="text-align:center;">85.75</td>
<td style="text-align:center;">86.47</td>
<td style="text-align:center;">95.39 (high)<br>95.26 (medium)</td>
<td style="text-align:center;">95.30</td>
<td style="text-align:center;">95.39 (high)<br>95.26 (medium)</td>
README_zh-CN.md
+17 -1
View File
@@ -79,6 +79,22 @@ MCP Server · LangChain / Dify / FastGPT 原生集成 · 10+ 国产算力适配
# 更新记录
- 2026/06/18 3.4 发布
本次版本更新聚焦于 **pipeline 后端 OCR 能力升级**、**OCR 处理链路优化** 与 **模型下载体验改进**。主要更新内容包括：
- OCR 模型升级与处理加速
- `pipeline` 后端 OCR 模型更新至 `PP-OCRv6`，在 OmniDocBench v1.6 评测中，OCR 相关指标提升约 `11%`。
- 移除 OCR 语言选择中的日语、繁体中文、英语、拉丁文选项，相关场景统一路由到 `ch` OCR 模型，简化模型配置与语言选择逻辑。
- 优化 OCR 推理与处理链路，OCR 处理速度提升约 `100%`，显著改善批量文档和 OCR 密集型文档的解析效率。
- 模型下载逻辑优化
- 新增模型源自动选择能力，首次安装时可根据当前网络环境自动选择更合适的模型源。
- 下载模型前会优先检查本地已下载的模型缓存文件，命中缓存时可直接复用，减少重复下载和不必要的远端请求。
- 更多模型源配置、自动选择策略与本地模型使用说明，请参考 [模型源说明](https://opendatalab.github.io/MinerU/zh/usage/model_source/)。
在 3.4 版本，MinerU 进一步提升了 `pipeline` 后端在 OCR 场景下的解析精度与处理效率，同时优化了模型下载、缓存复用和本地配置写入流程，让首次安装、模型更新和多环境部署更加稳定、自动化。
- 2026/06/11 3.3 发布
本次版本更新聚焦于 **Hybrid 解析性能优化** 与 **VLM 模型能力升级**。主要更新内容包括：
@@ -221,7 +237,7 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
</tr>
<tr>
<th>精度指标<sup>1</sup></th>
<td style="text-align:center;">85.75</td>
<td style="text-align:center;">86.47</td>
<td style="text-align:center;">95.39（high）<br>95.26（medium）</td>
<td style="text-align:center;">95.30</td>
<td style="text-align:center;">95.39（high）<br>95.26（medium）</td>
docker/china/Dockerfile
+1 -1
View File
@@ -17,7 +17,7 @@ RUN apt-get update && \
rm -rf /var/lib/apt/lists/*
# Install mineru latest
RUN python3 -m pip install -U 'mineru[core]>=3.2.1' -i https://mirrors.aliyun.com/pypi/simple --break-system-packages && \
RUN python3 -m pip install -U 'mineru[core]>=3.4.0' -i https://mirrors.aliyun.com/pypi/simple --break-system-packages && \
python3 -m pip cache purge
# Download models and update the configuration file
docker/china/corex.Dockerfile
+1 -1
View File
@@ -14,7 +14,7 @@ RUN apt-get update && \
# Install mineru latest
RUN python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \
python3 -m pip install 'mineru[core]>=3.0.0' \
python3 -m pip install 'mineru[core]>=3.4.0' \
numpy==1.26.4 \
opencv-python==4.11.0.86 \
-i https://mirrors.aliyun.com/pypi/simple && \
docker/china/dcu.Dockerfile
+1 -1
View File
@@ -14,7 +14,7 @@ RUN apt-get update && \
# Install mineru latest
RUN python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \
python3 -m pip install "mineru[gradio]>=3.0.0" \
python3 -m pip install "mineru[gradio]>=3.4.0" \
"ftfy>=6.3.1,<7" \
"shapely>=2.0.7,<3" \
"pyclipper>=1.3.0,<2" \
docker/china/gcu.Dockerfile
+2 -2
View File
@@ -17,7 +17,7 @@ deb http://mirrors.aliyun.com/ubuntu/ noble-security main restricted universe mu
rm -rf /var/lib/apt/lists/* /tmp/aliyun-sources.list
# Install mineru latest
RUN python3 -m pip install "mineru[core]>=3.0.0" \
RUN python3 -m pip install "mineru[core]>=3.4.0" \
numpy==1.26.4 \
opencv-python==4.11.0.86 \
-i https://mirrors.aliyun.com/pypi/simple && \
@@ -27,4 +27,4 @@ RUN python3 -m pip install "mineru[core]>=3.0.0" \
RUN /bin/bash -c "mineru-models-download -s modelscope -m all"
# Set the entry point to activate the virtual environment and run the command line tool
ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"]
ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"]
docker/china/kxpu.Dockerfile
+2 -2
View File
@@ -14,7 +14,7 @@ RUN apt-get update && \
# Install mineru latest
RUN python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \
python3 -m pip install "mineru[gradio]>=3.0.0" \
python3 -m pip install "mineru[gradio]>=3.4.0" \
"ftfy>=6.3.1,<7" \
"shapely>=2.0.7,<3" \
"pyclipper>=1.3.0,<2" \
@@ -27,4 +27,4 @@ RUN python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \
RUN /bin/bash -c "mineru-models-download -s modelscope -m all"
# Set the entry point to activate the virtual environment and run the command line tool
ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"]
ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"]
docker/china/maca.Dockerfile
+1 -1
View File
@@ -22,7 +22,7 @@ RUN sed -i '3s/^Version: 0.15.1+metax3\.1\.0\.4$/Version: 0.21.0+metax3.1.0.4/'
# Install mineru latest
RUN /opt/conda/bin/python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \
/opt/conda/bin/python3 -m pip install 'mineru[core]>=3.0.0' \
/opt/conda/bin/python3 -m pip install 'mineru[core]>=3.4.0' \
numpy==1.26.4 \
opencv-python==4.11.0.86 \
-i https://mirrors.aliyun.com/pypi/simple && \
docker/china/mlu.Dockerfile
+1 -1
View File
@@ -22,7 +22,7 @@ RUN /bin/bash -c '\
source /torch/venv3/pytorch_infer/bin/activate; \
fi && \
python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \
python3 -m pip install "mineru[core]>=3.0.0" \
python3 -m pip install "mineru[core]>=3.4.0" \
numpy==1.26.4 \
opencv-python==4.11.0.86 \
-i https://mirrors.aliyun.com/pypi/simple && \
docker/china/musa.Dockerfile
+2 -2
View File
@@ -18,7 +18,7 @@ RUN python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \
git clone https://gitcode.com/gh_mirrors/vi/vision.git -b v0.20.0 --depth 1 && \
cd vision && \
python3 setup.py install && \
python3 -m pip install "mineru[gradio]>=3.0.0" \
python3 -m pip install "mineru[gradio]>=3.4.0" \
"ftfy>=6.3.1,<7" \
"shapely>=2.0.7,<3" \
"pyclipper>=1.3.0,<2" \
@@ -32,4 +32,4 @@ RUN python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \
RUN /bin/bash -c "mineru-models-download -s modelscope -m all"
# Set the entry point to activate the virtual environment and run the command line tool
ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"]
ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"]
docker/china/npu.Dockerfile
+1 -1
View File
@@ -19,7 +19,7 @@ RUN apt-get update && \
# Install mineru latest
RUN python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \
python3 -m pip install 'mineru[core]>=3.0.0' \
python3 -m pip install 'mineru[core]>=3.4.0' \
numpy==1.26.4 \
opencv-python==4.11.0.86 \
-i https://mirrors.aliyun.com/pypi/simple && \
docker/china/ppu.Dockerfile
+1 -1
View File
@@ -18,7 +18,7 @@ RUN apt-get update && \
# Install mineru latest
RUN python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \
python3 -m pip install 'mineru[core]>=3.0.0' \
python3 -m pip install 'mineru[core]>=3.4.0' \
numpy==1.26.4 \
opencv-python==4.11.0.86 \
-i https://mirrors.aliyun.com/pypi/simple && \
docker/global/Dockerfile
+1 -1
View File
@@ -17,7 +17,7 @@ RUN apt-get update && \
rm -rf /var/lib/apt/lists/*
# Install mineru latest
RUN python3 -m pip install -U 'mineru[core]>=3.2.1' --break-system-packages && \
RUN python3 -m pip install -U 'mineru[core]>=3.4.0' --break-system-packages && \
python3 -m pip cache purge
# Download models and update the configuration file
docs/en/quick_start/index.md
+1 -1
View File
@@ -52,7 +52,7 @@ A WebUI developed based on Gradio, with a simple interface and only core parsing
</tr>
<tr>
<th>Accuracy<sup>1</sup></th>
<td style="text-align:center;">85.75</td>
<td style="text-align:center;">86.47</td>
<td style="text-align:center;">95.39 (high)<br>95.26 (medium)</td>
<td style="text-align:center;">95.30</td>
<td style="text-align:center;">95.39 (high)<br>95.26 (medium)</td>
docs/zh/quick_start/index.md
+1 -1
View File
@@ -52,7 +52,7 @@
</tr>
<tr>
<th>精度指标<sup>1</sup></th>
<td style="text-align:center;">85.75</td>
<td style="text-align:center;">86.47</td>
<td style="text-align:center;">95.39（high）<br>95.26（medium）</td>
<td style="text-align:center;">95.30</td>
<td style="text-align:center;">95.39（high）<br>95.26（medium）</td>