0.15.2

0.15.2

Enhancements

• Improve directory handling when extracting image blocks. The figures directory is no longer created when the extract_image_block_to_payload parameter is set to True.

Features

• Added per-class Object Detection metrics in the evaluation. The metrics include average precision, precision, recall, and f1-score for each class in the dataset.

Fixes

• Updates NLTK data file for compatibility with nltk>=3.8.2. The NLTK data file now container punkt_tab, making it possible to upgrade to nltk>=3.8.2. The nltk==3.8.2 patches CVE-2024-39705.
• Renames Astra to Astra DB Conforms with DataStax internal naming conventions.
• Accommodate single-column CSV files. Resolves a limitation of partition_csv() where delimiter detection would fail on a single-column CSV file (which naturally has no delimeters).
• Accommodate image/jpg in PPTX as alias for image/jpeg. Resolves problem partitioning PPTX files having an invalid image/jpg (should be image/jpeg) MIME-type in the [Content_Types].xml member of the PPTX Zip archive.
• Fixes an issue in Object Detection metrics The issue was in preprocessing/validating the ground truth and predicted data for object detection metrics.
• Removes dependency on unstructured.pytesseract Unstructured forked pytesseract while waiting for code to be upstreamed. Now that the new version has been released, this fork can be removed.