0.7.12

• change the default model to yolox, as table output appears to be better and speed is similar to yolox_quantized

0.7.11

0.7.11

• chore: remove logger info for chipper since its private
• fix: update broken slack invite link in chipper logger info
• enhancement: Improve error message when # images extracted doesn't match # page layouts.
• fix: use automatic mixed precision on GPU for Chipper
• fix: chipper Table elements now match other layout models' Table element format: html representation is stored in text_as_html attribute and text attribute stores text without html tags

0.7.10

0.7.10

• Handle kwargs explicitly when needed, suppress otherwise
• fix: Reduce Chipper memory consumption on x86_64 cpus
• fix: Skips ordering elements coming from Chipper
• fix: After refactoring to introduce Chipper, annotate() weren't able to show text with extra info from elements, this is fixed now.
• feat: add table cell and dataframe output formats to table transformer's run_prediction call
• breaking change: function unstructured_inference.models.tables.recognize no longer takes out_html parameter and it now only returns table cell data format (lists of dictionaries)

0.7.9

0.7.9

• Allow table model to accept optional OCR tokens

0.7.8

0.7.8

• Fix: include onnx as base dependency.

0.7.7

0.7.7

• Fix a memory leak in DonutProcessor when using large images in numpy format
• Set the right settings for beam search size > 1
• Fix a bug that in very rare cases made the last element predicted by Chipper to have a bbox = None

0.7.6

0.7.6

• fix a bug where invalid zoom factor lead to exceptions; now invalid zoom factors results in no scaling of the image

0.7.5

0.7.5

• Improved packaging

0.7.4

0.7.4

• Dynamic beam search size has been implemented for Chipper, the decoding process starts with a size = 1 and changes to size = 3 if repetitions appear.
• Fixed bug when PDFMiner predicts that an image text occupies the full page and removes annotations by Chipper.
• Added random seed to Chipper text generation to avoid differences between calls to Chipper.
• Allows user to use super-gradients model if they have a callback predict function, a yaml file with names field corresponding to classes and a path to the model weights

0.7.3

0.7.3

• Integration of Chipperv2 and additional Chipper functionality, which includes automatic detection of GPU,
  bounding box prediction and hierarchical representation.
• Remove control characters from the text of all layout elements