Matt Robinson db8617872b
build: image and dependency updates; fix tesseract files locations (#3310)
### Summary

Updates to the latest version of the `wolfi-base` image. Changes
include:
- Version bumps to address CVEs
- `libreoffice` is now included in the `arm64`. `.doc` files are now
supported for `arm64`. `.ppt` do not work with the `libreoffice` package
currently available on `wolfi-os`. We have follow on work to look into
that.
- Updates the location of the `tesseract` `tessdata` files on the
`arm64` build. Closes #3290.
- Closes #3319 and addes `psutil` to the base dependencies.

### Testing

- `test_dockerfile` should continue to pass with the updates.
2024-07-01 19:39:32 +00:00

24 lines
327 B
Plaintext

-c ./deps/constraints.txt
chardet
filetype
python-magic
lxml
nltk
tabulate
requests
beautifulsoup4
emoji
dataclasses-json
python-iso639
langdetect
# NOTE(robinson) - numpy pin is because ONNX model weights are only compatible
# with numpy 1.x.x
numpy<2
rapidfuzz
backoff
typing-extensions
unstructured-client
wrapt
tqdm
psutil