This is an automated email from the ASF dual-hosted git repository. exceptionfactory pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/nifi.git
commit 6e9da11be9bf80ac1c2e85c92355d1ae4d3d117b Author: Pierre Villard <[email protected]> AuthorDate: Tue Jan 16 23:03:39 2024 +0400 NIFI-12619 Fixed Python dependencies in ParseDocument This closes #8255 Signed-off-by: David Handermann <[email protected]> --- .../nifi-text-embeddings-module/src/main/python/ParseDocument.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/nifi-python-extensions/nifi-text-embeddings-module/src/main/python/ParseDocument.py b/nifi-python-extensions/nifi-text-embeddings-module/src/main/python/ParseDocument.py index a6582cc346..777f80e402 100644 --- a/nifi-python-extensions/nifi-text-embeddings-module/src/main/python/ParseDocument.py +++ b/nifi-python-extensions/nifi-text-embeddings-module/src/main/python/ParseDocument.py @@ -51,8 +51,8 @@ class ParseDocument(FlowFileTransform): Note that use of this Processor may require significant storage space and RAM utilization due to third-party dependencies necessary for processing PDF and image files. Also note that in order to process PDF or Images, Tesseract and Poppler must be installed on the system.""" tags = ["text", "embeddings", "vector", "machine learning", "ML", "artificial intelligence", "ai", "document", "langchain", "pdf", "html", "markdown", "word", "excel", "powerpoint"] - dependencies = ['langchain', 'unstructured', 'unstructured-inference', 'unstructured_pytesseract', 'numpy', - 'opencv-python', 'pdf2image', 'pdfminer.six[image]', 'python-docx', 'openpyxl', 'python-pptx'] + dependencies = ['pikepdf', 'pypdf', 'langchain', 'unstructured', 'unstructured-inference', 'unstructured_pytesseract', 'numpy', + 'opencv-python', 'pdf2image', 'pdfminer.six', 'python-docx', 'openpyxl', 'python-pptx'] INPUT_FORMAT = PropertyDescriptor(
