2 Releases published by 1 person

• v2.6.0

  published Nov 19, 2024

• v2.7.0

  published Nov 20, 2024

14 Pull requests merged by 8 people

• fix: force pydantic < 2.10.0

  #407 merged Nov 22, 2024

• chore: update the README

  #409 merged Nov 21, 2024

• docs: add DocETL, Kotaemon, spaCy integrations; minor docs improvements

  #408 merged Nov 21, 2024

• chore: add downloads in README, security policy and update ci actions

  #401 merged Nov 21, 2024

• fix: python3.9 support

  #396 merged Nov 20, 2024

• feat: add support for ocrmac OCR engine on macOS

  #276 merged Nov 20, 2024

• fix: propagate document limits to converter

  #388 merged Nov 20, 2024

• Sample chunking notebook that includes merging, etc.

  #193 merged Nov 19, 2024

• feat: added support for exporting DocItem to an image when page image is available

  #379 merged Nov 19, 2024

• docs: fixed typo in v2 example v2

  #378 merged Nov 19, 2024

• feat: expose ocr-lang in CLI

  #375 merged Nov 19, 2024

• feat: added excel backend

  #334 merged Nov 19, 2024

• chore: update lock of deps

  #371 merged Nov 19, 2024

• feat: Extracting picture data for raster images found in PPTX

  #349 merged Nov 18, 2024

4 Pull requests opened by 3 people

• Advanced chunking example

  #384 opened Nov 19, 2024

• feat(ocr): added support for PaddleOCR engine

  #393 opened Nov 20, 2024

• feat(ocr): added support for RapidOCR engine

  #415 opened Nov 22, 2024

• fix(layout_utils): correct conditional logic in adapt_bbox function

  #416 opened Nov 22, 2024

25 Issues closed by 7 people

• do we have a function to generate a folder which contains images folder and markdown file

  #387 closed Nov 22, 2024

• Graphical user interface for parsed JSON?

  #403 closed Nov 22, 2024

• Is it possible to fine tune with our own datasets?

  #411 closed Nov 22, 2024

• Title differenciation

  #412 closed Nov 22, 2024

• I get an error trying to export figures

  #406 closed Nov 21, 2024

• Can support for widgets in Dify be considered?

  #394 closed Nov 21, 2024

• analyzing the pdf is too slow

  #398 closed Nov 21, 2024

• Python 3.9 Support?

  #385 closed Nov 20, 2024

• Convert pdf to md simplified Chinese character issue

  #225 closed Nov 19, 2024

• Allow extraction of formula images similar to tables and pages

  #299 closed Nov 19, 2024

• Specific language for easyOCR

  #255 closed Nov 19, 2024

• Newcomers who want to start source code, how should I do it？

  #372 closed Nov 19, 2024

• Support Excel files

  #258 closed Nov 19, 2024

• Support for HOCR?

  #366 closed Nov 19, 2024

• Bug

  #370 closed Nov 19, 2024

• How to give HTML code as a string

  #368 closed Nov 19, 2024

• export_to_markdown page separator

  #359 closed Nov 18, 2024

• LXML versions greater or equal than 5.0.0 are not allowed

  #363 closed Nov 18, 2024

• Docling <page_assemble_model> reading order algorithm

  #358 closed Nov 18, 2024

• cannot import name 'TextPipelineOptions' from 'docling.datamodel.pipeline_options'

  #360 closed Nov 18, 2024

• Using Docling with costume layout and table recognition models

  #250 closed Nov 18, 2024

• Streamline the dependence, the dependence is too heavy now

  #252 closed Nov 18, 2024

• Analyzing PDf files is too slow

  #346 closed Nov 18, 2024

• Syntax error while parsing object key (pdf with Chinese characters)

  #351 closed Nov 18, 2024

• OCR Extracted Information

  #244 closed Nov 18, 2024

11 Issues opened by 11 people

• parse docx file error :

  #417 opened Nov 23, 2024

• Using .DOCX format in cloud - suggestion on the below error?

  #410 opened Nov 22, 2024

• Support Image path/url

  #405 opened Nov 21, 2024

• Which type of Markdown is supported?

  #404 opened Nov 21, 2024

• Document normalization: warning on `checkbox-unselected`

  #399 opened Nov 21, 2024

• Docx cannot get pic info

  #391 opened Nov 20, 2024

• Loading a pdf results in a StopIteration error

  #383 opened Nov 19, 2024

• Table representation misaligned between PDF and DOCX

  #382 opened Nov 19, 2024

• Add Parallelization Support to `convert_all()` Function with `num_worker` Parameter

  #369 opened Nov 19, 2024

• Should the second "if" keyword in adapt_bbox from layout_utils.py rather be an "elif" keyword ?

  #362 opened Nov 18, 2024

• docling identified my entire page as a picture

  #357 opened Nov 18, 2024

14 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Add LaTex and mathpix-markdown-it as outputs

  #343 commented on Nov 18, 2024 • 0 new comments

• Standardized Access to Common Email and Calendar Formats

  #327 commented on Nov 18, 2024 • 0 new comments

• Docling crashes when using EasyOCR on Windows 11

  #318 commented on Nov 18, 2024 • 0 new comments

• Deployment of docling using Docker

  #303 commented on Nov 18, 2024 • 0 new comments

• Leverage word bbox from pdf-parser-v2 in the layout- and table-model

  #285 commented on Nov 18, 2024 • 0 new comments

• For long tables, fields are being truncated

  #278 commented on Nov 18, 2024 • 0 new comments

• cli and PDF: wrong table output

  #268 commented on Nov 18, 2024 • 0 new comments

• Support export of DoclingDocument to HTML

  #300 commented on Nov 18, 2024 • 0 new comments

• Add option to export_to_markdown to mark page breaks

  #309 commented on Nov 19, 2024 • 0 new comments

• Python 3.13 support

  #136 commented on Nov 19, 2024 • 0 new comments

• EasyOCR does not extract text properly

  #295 commented on Nov 21, 2024 • 0 new comments

• Result viewer application

  #277 commented on Nov 22, 2024 • 0 new comments

• Dev/update html parser with h1

  #240 commented on Nov 19, 2024 • 0 new comments

• enhancement: Add timeout limit to document parsing job. #270

  #320 commented on Nov 23, 2024 • 0 new comments