CHANGELOG.md

0.3.0-dev8

• Implement staging brick for Argilla. Converts lists of Text elements to argilla dataset classes.
• Removing the local PDF parsing code and any dependencies and tests.
• Reorganizes the staging bricks in the unstructured.partition module
• Allow entities to be passed into the Datasaur staging brick
• Added HTML escapes to the replace_unicode_quotes brick
• Fix bad responses in partition_pdf to raise ValueError
• Adds partition_html for partitioning HTML documents.

0.2.6

• Small change to how _read is placed within the inheritance structure since it doesn't really apply to pdf
• Add partitioning brick for calling the document image analysis API

0.2.5

• Update python requirement to >=3.7

0.2.4

• Add alternative way of importing Final to support google colab

0.2.3

• Add cleaning bricks for removing prefixes and postfixes
• Add cleaning bricks for extracting text before and after a pattern

0.2.2

• Add staging brick for Datasaur

0.2.1

• Added brick to convert an ISD dictionary to a list of elements
• Update PDFDocument to use the from_file method
• Added staging brick for CSV format for ISD (Initial Structured Data) format.
• Added staging brick for separating text into attention window size chunks for transformers.
• Added staging brick for LabelBox.
• Added ability to upload LabelStudio predictions
• Added utility function for JSONL reading and writing
• Added staging brick for CSV format for Prodigy
• Added staging brick for Prodigy
• Added ability to upload LabelStudio annotations
• Added text_field and id_field to stage_for_label_studio signature

0.2.0

• Initial release of unstructured