yujunjun/unstructured
1
0
Fork 0
mirror of https://github.com/Unstructured-IO/unstructured.git synced 2025-11-02 11:03:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

build(image): bump Dockerfile to python3.10 (#1214)

Browse Source
This commit is contained in:
cragwolfe 2023-08-27 18:30:17 -07:00 committed by GitHub
parent 4c13d12dc3
commit ba70828f4a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 17 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
CHANGELOG.md
View File

@ -1,3 +1,13 @@
## 0.10.8
### Enhancements
* Release docker image that installs Python 3.10 rather than 3.8
### Features
### Fixes
## 0.10.7
### Enhancements
@ -19,7 +29,7 @@
* Add functionality to sort elements using `xy-cut` sorting approach in `partition_pdf` for `hi_res` and `fast` strategies
* Bump unstructured-inference
* Set OMP_THREAD_LIMIT to 1 if not set for better tesseract perf (0.5.17)
### Features
* Extract coordinates from PDFs and images when using OCR only strategy and add to metadata

10
Dockerfile
View File

@ -1,5 +1,5 @@
# syntax=docker/dockerfile:experimental
FROM quay.io/unstructured-io/base-images:rocky8.7-3 as base
FROM quay.io/unstructured-io/base-images:rocky8.7-5 as base
ARG PIP_VERSION
@ -15,7 +15,7 @@ FROM base as deps
# Copy and install Unstructured
COPY requirements requirements
RUN python3.8 -m pip install pip==${PIP_VERSION} && \
RUN python3.10 -m pip install pip==${PIP_VERSION} && \
dnf -y groupinstall "Development Tools" && \
pip install --no-cache -r requirements/base.txt && \
pip install --no-cache -r requirements/test.txt && \
@ -50,14 +50,14 @@ RUN python3.8 -m pip install pip==${PIP_VERSION} && \
dnf -y groupremove "Development Tools" && \
dnf clean all
RUN python3.8 -c "import nltk; nltk.download('punkt')" && \
python3.8 -c "import nltk; nltk.download('averaged_perceptron_tagger')"
RUN python3.10 -c "import nltk; nltk.download('punkt')" && \
python3.10 -c "import nltk; nltk.download('averaged_perceptron_tagger')"
FROM deps as code
COPY example-docs example-docs
COPY unstructured unstructured
RUN python3.8 -c "from unstructured.ingest.doc_processor.generalized import initialize; initialize()"
RUN python3.10 -c "from unstructured.ingest.doc_processor.generalized import initialize; initialize()"
CMD ["/bin/bash"]

2
unstructured/__version__.py
View File

@ -1 +1 @@
__version__ = "0.10.7" # pragma: no cover
__version__ = "0.10.8" # pragma: no cover