feature: add external pdf extract operator by using mineru (#36)

* feature: add UnstructuredFormatter

* feature: add UnstructuredFormatter in db

* feature: add unstructured[docx]==0.18.15

* feature: support doc

* feature: add mineru

* feature: add external pdf extract operator by using mineru

* feature: mineru docker install bugfix

---------

Co-authored-by: Startalker <438747480@qq.com>

scripts/images/mineru/Dockerfile

@@ -0,0 +1,22 @@
+FROM python:3.11-slim
+
+COPY runtime/mineru /opt/runtime/datamate/mineru
+
+RUN sed -i 's/deb.debian.org/mirrors.huaweicloud.com/g' /etc/apt/sources.list.d/debian.sources \
+    && apt-get update \
+    && apt-get install -y curl vim libgl1 libglx0 libopengl0 libglib2.0-0 procps \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN pip config --user set global.index-url https://mirrors.huaweicloud.com/repository/pypi/simple && \
+    pip config --user set global.trusted-host mirrors.huaweicloud.com && \
+    pip install --upgrade setuptools && \
+    pip install -U 'mineru[core]==2.5.4' --break-system-packages && \
+    pip cache purge
+
+ENV CURL_CA_BUNDLE=""
+ENV TORCH_DEVICE_BACKEND_AUTOLOAD=0
+
+RUN /bin/bash -c "mineru-models-download -s modelscope -m all"
+
+ENV MINERU_MODEL_SOURCE=local