mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-12-27 15:13:35 +00:00
d99b39923d
This PR aims to remove "unstructured.paddlepaddle" fork. Previously, we
used `unstructured.paddlepaddle` fork to support
`unstructured.paddleocr` on arm64 architecture. But currently,
`unstructured.paddleocr` with `unstructured.paddlepaddle` fails to work
on `arm64` architecture. Also, `unstructured.paddleocr` with the latest
version of the original `paddlepaddle` works on both `amd64` and `arm64`
architectures.
### Testing
```
os.environ["OCR_AGENT"] = "unstructured.partition.utils.ocr_models.paddle_ocr.OCRAgentPaddle"
elements = partition_pdf(
filename=<file_path>,
strategy="hi_res",
infer_table_structure=True,
)
```
28 lines
1.1 KiB
Docker
28 lines
1.1 KiB
Docker
FROM quay.io/unstructured-io/base-images:wolfi-base-e48da6b@sha256:8ad3479e5dc87a86e4794350cca6385c01c6d110902c5b292d1a62e231be711b as base
|
|
|
|
USER root
|
|
|
|
WORKDIR /app
|
|
|
|
COPY ./requirements requirements/
|
|
COPY unstructured unstructured
|
|
COPY test_unstructured test_unstructured
|
|
COPY example-docs example-docs
|
|
|
|
RUN chown -R notebook-user:notebook-user /app && \
|
|
apk add font-ubuntu git && \
|
|
fc-cache -fv && \
|
|
ln -s /usr/bin/python3.11 /usr/bin/python3
|
|
|
|
USER notebook-user
|
|
|
|
RUN find requirements/ -type f -name "*.txt" -exec pip3.11 install --no-cache-dir --user -r '{}' ';' && \
|
|
python3.11 -c "from unstructured.nlp.tokenize import download_nltk_packages; download_nltk_packages()" && \
|
|
python3.11 -c "from unstructured.partition.model_init import initialize; initialize()" && \
|
|
python3.11 -c "from unstructured_inference.models.tables import UnstructuredTableTransformerModel; model = UnstructuredTableTransformerModel(); model.initialize('microsoft/table-transformer-structure-recognition')"
|
|
|
|
ENV PATH="${PATH}:/home/notebook-user/.local/bin"
|
|
ENV TESSDATA_PREFIX=/usr/local/share/tessdata
|
|
|
|
CMD ["/bin/bash"]
|