Skip to content

Commit 2eb9fc6

Browse files
committed
reduce image size
1 parent 187baf5 commit 2eb9fc6

5 files changed

Lines changed: 18 additions & 24 deletions

File tree

Dockerfile

Lines changed: 3 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,17 +1,14 @@
1-
ARG REPOSITORY="docker.io"
2-
FROM dedocproject/dedoc_jammy_p3.10_base:version_2025_09_11
3-
ARG LANGUAGES=""
1+
FROM dedocproject/dedoc_p3.10_base:version_2026_07_29
2+
ARG LANGUAGES="rus"
43
RUN for lang in $LANGUAGES; do apt install -y tesseract-ocr-$(echo $lang | tr "_" "-"); done
54

65
ENV PYTHONPATH "${PYTHONPATH}:/dedoc_root"
76
ENV RESOURCES_PATH "/dedoc_root/resources"
87

98
COPY requirements.txt .
109
RUN pip3 install --no-cache-dir -r requirements.txt
10+
RUN pip3 install --no-cache-dir torch~=2.6.0 torchvision~=0.21.0 --index-url https://download.pytorch.org/whl/cpu
1111
RUN pip3 install --no-cache-dir transformers~=4.49.0
12-
RUN apt-get update && apt-get install -y --fix-missing --no-install-recommends fontforge
13-
RUN apt install -y libutf8proc-dev
14-
RUN ln -s /usr/lib/x86_64-linux-gnu/libutf8proc.so /usr/lib/libutf8proc.so.1
1512

1613
RUN mkdir /dedoc_root
1714
RUN mkdir /dedoc_root/dedoc

docker_gpu/Dockerfile

Lines changed: 9 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -1,25 +1,23 @@
1-
ARG REPOSITORY="docker.io"
2-
FROM dedocproject/dedoc_jammy_p3.10_base:version_2025_09_11
1+
FROM dedocproject/dedoc_p3.10_base:version_2026_07_29
2+
ARG LANGUAGES="rus"
3+
RUN for lang in $LANGUAGES; do apt install -y tesseract-ocr-$(echo $lang | tr "_" "-"); done
34

45
ENV PYTHONPATH "${PYTHONPATH}:/dedoc_root"
56
ENV RESOURCES_PATH "/dedoc_root/resources"
67

7-
ADD requirements.txt .
8+
COPY requirements.txt .
89
RUN pip3 install --no-cache-dir -r requirements.txt
910
RUN pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 -f https://download.pytorch.org/whl/torch_stable.html
1011
RUN pip3 install --no-cache-dir transformers~=4.49.0
1112

1213
RUN mkdir /dedoc_root
1314
RUN mkdir /dedoc_root/dedoc
14-
ADD dedoc/config.py /dedoc_root/dedoc/config.py
15-
ADD dedoc/download_models.py /dedoc_root/dedoc/download_models.py
15+
COPY dedoc/config.py /dedoc_root/dedoc/config.py
16+
COPY dedoc/download_models.py /dedoc_root/dedoc/download_models.py
1617
RUN python3 /dedoc_root/dedoc/download_models.py
1718

18-
ADD dedoc /dedoc_root/dedoc
19-
ADD VERSION /dedoc_root
19+
COPY dedoc /dedoc_root/dedoc
20+
COPY VERSION /dedoc_root
2021
RUN echo "__version__ = \"$(cat /dedoc_root/VERSION)\"" > /dedoc_root/dedoc/version.py
2122

22-
ADD tests /dedoc_root/tests
23-
ADD resources /dedoc_root/resources
24-
25-
CMD ["python3", "/dedoc_root/dedoc/main.py"]
23+
CMD ["python3", "/dedoc_root/dedoc/main.py"]

labeling/Dockerfile

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,12 @@
1-
ARG REPOSITORY="docker.io"
2-
FROM dedocproject/dedoc_jammy_p3.10_base:version_2025_09_11
1+
FROM dedocproject/dedoc_p3.10_base:version_2026_07_29
2+
RUN apt-get install -y tesseract-ocr-rus
33

44
ENV PYTHONPATH "${PYTHONPATH}:/labeling_root:/labeling_root/labeling"
55
ENV RESOURCES_PATH "/labeling_root/resources"
66

77
ADD requirements.txt .
88
RUN pip3 install --no-cache-dir -r requirements.txt
9+
RUN pip3 install --no-cache-dir torch~=2.6.0 torchvision~=0.21.0 --index-url https://download.pytorch.org/whl/cpu
910
RUN pip3 install Jinja2==3.1.2
1011

1112
RUN mkdir /labeling_root

requirements.txt

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,6 @@ huggingface-hub>=0.14.1,<1.0
88
imutils==0.5.4
99
itsdangerous>=2.1.0,<=2.1.2
1010
levenshtein>=0.12.2,<1
11-
numpy>=1.22.0,<2.0
1211
olefile~=0.46
1312
opencv-python>=4.5.5.64,<4.6.0
1413
orjson>=3.8.11,<4.0
@@ -22,7 +21,6 @@ py7zr~=1.0
2221
pypdf>=4.0,<6.0
2322
pytesseract==0.3.10
2423
python-docx==0.8.11
25-
python-logstash-async>=2.5.0,<=2.7.0
2624
python-magic<1.0
2725
python-multipart==0.0.6
2826
rarfile==4.0

tests/Dockerfile

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,13 +1,13 @@
1-
ARG REPOSITORY="docker.io"
2-
FROM dedocproject/dedoc_jammy_p3.10_base:version_2025_09_11
1+
FROM dedocproject/dedoc_p3.10_base:version_2026_07_29
2+
RUN apt-get install -y tesseract-ocr-rus
33

44
ENV PYTHONPATH "${PYTHONPATH}:/dedoc_root:/dedoc_root/tests:/dedoc_root/langchain"
55

66
COPY requirements.txt .
77
RUN pip3 install --no-cache-dir "langchain-community<1.0"
88
RUN pip3 install --no-cache-dir -r requirements.txt
9+
RUN pip3 install --no-cache-dir torch~=2.6.0 torchvision~=0.21.0 --index-url https://download.pytorch.org/whl/cpu
910
RUN pip3 install --no-cache-dir transformers~=4.49.0
10-
RUN apt-get update && apt-get install -y --fix-missing --no-install-recommends fontforge
1111

1212
RUN mkdir /dedoc_root
1313
COPY docs/source/_static/code_examples/langchain /dedoc_root/langchain

0 commit comments

Comments
 (0)