From e0e58fc0d8531f2d9d57b4fc7451d5653c4e5dd0 Mon Sep 17 00:00:00 2001 From: myhloli Date: Thu, 18 Jun 2026 11:14:06 +0800 Subject: [PATCH 1/3] feat: update mineru package version to 3.4.0 in Dockerfiles --- docker/china/Dockerfile | 2 +- docker/china/corex.Dockerfile | 2 +- docker/china/dcu.Dockerfile | 2 +- docker/china/gcu.Dockerfile | 4 ++-- docker/china/kxpu.Dockerfile | 4 ++-- docker/china/maca.Dockerfile | 2 +- docker/china/mlu.Dockerfile | 2 +- docker/china/musa.Dockerfile | 4 ++-- docker/china/npu.Dockerfile | 2 +- docker/china/ppu.Dockerfile | 2 +- docker/global/Dockerfile | 2 +- 11 files changed, 14 insertions(+), 14 deletions(-) diff --git a/docker/china/Dockerfile b/docker/china/Dockerfile index 00c95c0e..b079d5f4 100644 --- a/docker/china/Dockerfile +++ b/docker/china/Dockerfile @@ -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 diff --git a/docker/china/corex.Dockerfile b/docker/china/corex.Dockerfile index 8e1ba13b..a1bf6723 100644 --- a/docker/china/corex.Dockerfile +++ b/docker/china/corex.Dockerfile @@ -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 && \ diff --git a/docker/china/dcu.Dockerfile b/docker/china/dcu.Dockerfile index 8eb33408..83d25f20 100644 --- a/docker/china/dcu.Dockerfile +++ b/docker/china/dcu.Dockerfile @@ -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" \ diff --git a/docker/china/gcu.Dockerfile b/docker/china/gcu.Dockerfile index bcfc74b6..cbc0b20e 100644 --- a/docker/china/gcu.Dockerfile +++ b/docker/china/gcu.Dockerfile @@ -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 \"$@\"", "--"] \ No newline at end of file +ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"] diff --git a/docker/china/kxpu.Dockerfile b/docker/china/kxpu.Dockerfile index 3559445e..e76920cb 100644 --- a/docker/china/kxpu.Dockerfile +++ b/docker/china/kxpu.Dockerfile @@ -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 \"$@\"", "--"] \ No newline at end of file +ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"] diff --git a/docker/china/maca.Dockerfile b/docker/china/maca.Dockerfile index 938896cf..ab5bd4b6 100644 --- a/docker/china/maca.Dockerfile +++ b/docker/china/maca.Dockerfile @@ -22,7 +22,7 @@ RUN sed -i '3s/^Version: 0.15.1+metax3\.1\.0\.4$/Version: 0.21.0+metax3.1.0.4/' # Install mineru latest RUN /opt/conda/bin/python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \ - /opt/conda/bin/python3 -m pip install 'mineru[core]>=3.0.0' \ + /opt/conda/bin/python3 -m pip install 'mineru[core]>=3.4.0' \ numpy==1.26.4 \ opencv-python==4.11.0.86 \ -i https://mirrors.aliyun.com/pypi/simple && \ diff --git a/docker/china/mlu.Dockerfile b/docker/china/mlu.Dockerfile index 09174e1c..048ef74c 100644 --- a/docker/china/mlu.Dockerfile +++ b/docker/china/mlu.Dockerfile @@ -22,7 +22,7 @@ RUN /bin/bash -c '\ source /torch/venv3/pytorch_infer/bin/activate; \ fi && \ python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \ - python3 -m pip install "mineru[core]>=3.0.0" \ + python3 -m pip install "mineru[core]>=3.4.0" \ numpy==1.26.4 \ opencv-python==4.11.0.86 \ -i https://mirrors.aliyun.com/pypi/simple && \ diff --git a/docker/china/musa.Dockerfile b/docker/china/musa.Dockerfile index 3bfb63a8..a26a23b4 100644 --- a/docker/china/musa.Dockerfile +++ b/docker/china/musa.Dockerfile @@ -18,7 +18,7 @@ RUN python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \ git clone https://gitcode.com/gh_mirrors/vi/vision.git -b v0.20.0 --depth 1 && \ cd vision && \ python3 setup.py install && \ - python3 -m pip install "mineru[gradio]>=3.0.0" \ + python3 -m pip install "mineru[gradio]>=3.4.0" \ "ftfy>=6.3.1,<7" \ "shapely>=2.0.7,<3" \ "pyclipper>=1.3.0,<2" \ @@ -32,4 +32,4 @@ RUN python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \ RUN /bin/bash -c "mineru-models-download -s modelscope -m all" # Set the entry point to activate the virtual environment and run the command line tool -ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"] \ No newline at end of file +ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"] diff --git a/docker/china/npu.Dockerfile b/docker/china/npu.Dockerfile index 0ad43ce1..52047f26 100644 --- a/docker/china/npu.Dockerfile +++ b/docker/china/npu.Dockerfile @@ -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 && \ diff --git a/docker/china/ppu.Dockerfile b/docker/china/ppu.Dockerfile index 8af39394..839078ef 100644 --- a/docker/china/ppu.Dockerfile +++ b/docker/china/ppu.Dockerfile @@ -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 && \ diff --git a/docker/global/Dockerfile b/docker/global/Dockerfile index f09313ac..3d05cd90 100644 --- a/docker/global/Dockerfile +++ b/docker/global/Dockerfile @@ -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 From f6ffdd0a4a870d74d25cb558ee2b5d48e1f59886 Mon Sep 17 00:00:00 2001 From: myhloli Date: Thu, 18 Jun 2026 14:42:49 +0800 Subject: [PATCH 2/3] feat: update accuracy metrics in documentation --- README.md | 2 +- README_zh-CN.md | 2 +- docs/en/quick_start/index.md | 2 +- docs/zh/quick_start/index.md | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 8edb9bf7..85077068 100644 --- a/README.md +++ b/README.md @@ -223,7 +223,7 @@ A WebUI developed based on Gradio, with a simple interface and only core parsing Accuracy1 - 85.75 + 86.47 95.39 (high)
95.26 (medium) 95.30 95.39 (high)
95.26 (medium) diff --git a/README_zh-CN.md b/README_zh-CN.md index fdc4bbb9..60657043 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -221,7 +221,7 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c 精度指标1 - 85.75 + 86.47 95.39（high）
95.26（medium） 95.30 95.39（high）
95.26（medium） diff --git a/docs/en/quick_start/index.md b/docs/en/quick_start/index.md index f49a7c08..fdc5dbd6 100644 --- a/docs/en/quick_start/index.md +++ b/docs/en/quick_start/index.md @@ -52,7 +52,7 @@ A WebUI developed based on Gradio, with a simple interface and only core parsing Accuracy1 - 85.75 + 86.47 95.39 (high)
95.26 (medium) 95.30 95.39 (high)
95.26 (medium) diff --git a/docs/zh/quick_start/index.md b/docs/zh/quick_start/index.md index e3512caf..358b17d6 100644 --- a/docs/zh/quick_start/index.md +++ b/docs/zh/quick_start/index.md @@ -52,7 +52,7 @@ 精度指标1 - 85.75 + 86.47 95.39（high）
95.26（medium） 95.30 95.39（high）
95.26（medium） From c5cc50e81ee08a2fa0221e45f651f66bcd9da5d4 Mon Sep 17 00:00:00 2001 From: myhloli Date: Thu, 18 Jun 2026 14:51:23 +0800 Subject: [PATCH 3/3] feat: update changelog for version 3.4 release with OCR upgrades and model download optimizations --- README.md | 16 ++++++++++++++++ README_zh-CN.md | 16 ++++++++++++++++ 2 files changed, 32 insertions(+) diff --git a/README.md b/README.md index 85077068..8975ba79 100644 --- a/README.md +++ b/README.md @@ -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: diff --git a/README_zh-CN.md b/README_zh-CN.md index 60657043..87283249 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -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：