Commit Graph

178 Commits

Author SHA1 Message Date
Anthony R
90836db90a
fix: Dockerfile example copy command (#234)
Signed-off-by: Anthony R <anthonyringoet@gmail.com>
2024-11-05 12:48:27 +01:00
Panos Vagenas
5ce02c5c59
docs: add coming-soon section (#235)
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-11-05 08:53:02 +01:00
Panos Vagenas
d5e65aedac
docs: add artifacts-path param to CLI (#233)
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-11-05 08:51:21 +01:00
github-actions[bot]
e30a9c25a2 chore: bump version to 2.4.0 [skip ci] 2024-11-04 15:11:09 +00:00
Panos Vagenas
862d78d271
chore: update pyproject.toml metadata (#229)
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-11-04 15:48:00 +01:00
Panos Vagenas
eeee3b4371
docs: add explicit artifacts path example (#224)
* docs: add explicit artifacts path example

[skip ci]

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* minor docs fix

[skip ci]

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* touch to trigger needed checks

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

---------

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-11-04 14:27:56 +01:00
Michele Dolfi
5f5fea90a9
docs: update custom convert and dockerfile (#226)
* docs: remove old code from custom_convert.py

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* docs: update example Dockerfile

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2024-11-04 14:27:40 +01:00
Vicky Sekhon
41acaa9e2e
docs: correct spelling of 'individual' (#219)
Signed-off-by: Vicky Sekhon <114193273+VickySekhon@users.noreply.github.com>
2024-11-04 14:27:02 +01:00
Michele Dolfi
40ad987303
feat: pdf backend, table mode as options and artifacts path (#203)
* feat: add more options in the CLI

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update CLI docs

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* expose artifacts-path as argument

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2024-11-04 14:26:05 +01:00
Johnny Salazar
af323c04ef
fit: Specify encoding when writing output file (#214)
Specify encoding when writing output file to avoid errors when default target encoding doesn't have all characters. utf8 seems like the most universal and supported encoding. Otherwise, the cli fails with encoding errors when input file contains unicode text (basically most files nowadays) and the target system has default encoding set to some one-byte charset like cp1252

Signed-off-by: Johnny Salazar <cepera.ang@gmail.com>
2024-11-04 14:24:13 +01:00
Panos Vagenas
8fb445f46c
chore: make tests lighter (#228)
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-11-04 14:02:28 +01:00
Panos Vagenas
244ca69cfd
docs: update LlamaIndex docs (#196)
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-11-01 20:55:28 +01:00
github-actions[bot]
9d8865856d chore: bump version to 2.3.1 [skip ci] 2024-10-30 18:23:53 +00:00
Michele Dolfi
eb679ccbb4
fix: simplify torch dependencies and update pinned docling deps (#190)
* fix: simplify torch dependencies and update pinned docling deps

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update docling-ibm-models

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2024-10-30 18:44:08 +01:00
Michele Dolfi
904d24d600
fix: allow to explicitly initialize the pipeline (#189)
* feat: allow to explicitly initialize the pipeline

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* clean examples

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2024-10-30 17:54:53 +01:00
github-actions[bot]
43349865d0 chore: bump version to 2.3.0 [skip ci] 2024-10-30 14:47:37 +00:00
Christoph Auer
2a2c65bf4f
feat: Add pipeline timings and toggle visualization, establish debug settings (#183)
* Add settings to turn visualization on or off

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Add profiling code to all models

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Refactor and fix profiling codes

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Visualization codes output PNG to debug dir

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fixes for time logging

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Optimize imports

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update lockfile

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Add start_timestamps to ProfilingItem

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
2024-10-30 15:04:19 +01:00
Peter W. J. Staar
94a5290789
chore: update the with input formats and DoclingDocument (#188)
---------

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
2024-10-30 15:02:28 +01:00
Peter W. J. Staar
f542460af3
fix: fix duplicate title and heading + add e2e tests for html and docx (#186)
* add real e2e tests for html and docx

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* updated the output of itxt

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* reformatted the text

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the tests

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the tests (2)

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the examples (1)

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the output of the test

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* updated the tests, moved the ground-truth

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* moved the ground-truth data

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the html tests

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* restructure title fix (#187)

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

---------

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-10-30 13:14:56 +01:00
github-actions[bot]
dda2645d4c chore: bump version to 2.2.1 [skip ci] 2024-10-28 17:18:41 +00:00
Panos Vagenas
b9f5c74a7d
fix: fix header levels for DOCX & HTML (#184)
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-10-28 17:02:52 +01:00
Maxim Lysak
94d0729c50
fix: handling of long sequence of unescaped underscore chars in markdown (#173)
* Fix for md hanging when encountering long sequence of unescaped underscore chars

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Added comment explaining reason for fix

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Fixed trailing inline text handling (at the end of a file), and corrected underscore sequence shortening

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* making fix more rare

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
2024-10-28 16:34:48 +01:00
Panos Vagenas
2cece27208
docs: update LlamaIndex docs for Docling v2 (#182)
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-10-28 14:28:26 +01:00
Michele Dolfi
189d3c2d44
docs: fix batch convert (#177)
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2024-10-26 05:50:34 +02:00
Maxim Lysak
7d19418b77
fix: HTML backend, fixes for Lists and nested texts (#180)
* Fixes for HTML backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* removed prints

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* cleaning up

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
2024-10-25 20:14:04 +02:00
Maxim Lysak
88c1673057
fix: MD Backend, fixes to properly handle trailing inline text and emphasis in headers (#178)
* Small fix to properly handle trailing inline text in the md backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Added proper handling of headers with bold, italic or emphasis

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* removed print

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Made smarter processing of headers, with arbitrary styling

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Updated docling-core to 2.2.1

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Updated tests because of the change in Markdown export in docling-core

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
2024-10-25 18:02:20 +02:00
Michele Dolfi
77a89c3334
chore: make auto-release on request (#179)
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2024-10-25 10:47:25 +02:00
Michele Dolfi
8d356aa247
docs: add export with embedded images (#175)
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2024-10-24 20:19:41 +02:00
github-actions[bot]
8208c93e3a chore: bump version to 2.2.0 [skip ci] 2024-10-23 16:04:55 +00:00
Peter W. J. Staar
4116819b51
feat: Update to docling-parse v2 without history (#170)
* updated the pyproject (still need to run poetry lock after docling-parse is accepted)

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* Update imports for docling_parse.pdf_parser_v1

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Lock docling-parse 2.0.0

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Lock docling-parse 2.0.0

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* repin poetry.lock

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
2024-10-23 17:20:11 +02:00
Christoph Auer
3023f18ba0
feat: Support AsciiDoc and Markdown input format (#168)
* updated the base-model and added the asciidoc_backend

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* updated the asciidoc backend

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* Ensure all models work only on valid pages (#158)

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* ci: run ci also on forks (#160)


---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>

* fix: fix legacy doc ref (#162)

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* docs: typo fix (#155)

* Docs: Typo fix

- Corrected spelling of invidual to automatic

Signed-off-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com>

* add synchronize event for forks

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>

* feat: add coverage_threshold to skip OCR for small images (#161)

* feat: add coverage_threshold to skip OCR for small images

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* filter individual boxes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* rename option

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* chore: bump version to 2.1.0 [skip ci]

* adding tests for asciidocs

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* first working asciidoc parser

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* reformatted the code

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the mypy

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* adding test_02.asciidoc

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* Drafting Markdown backend via Marko library

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* work in progress on MD backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* md_backend produces docling document with headers, paragraphs, lists

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Improvements in md parsing

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Detecting and assembling tables in markdown in temporary buffers

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Added initial docling table support to md_backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Cleaned code, improved logging for MD

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Fixes MyPy requirements, and rest of pre-commit

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Fixed example run_md, added origin info to md_backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* working on asciidocs, struggling with ImageRef

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* able to parse the captions and image uri's

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the mypy

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* Update all backends with proper filename in DocumentOrigin

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update to docling-core v2.1.0

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fixes for MD Backend, to avoid duplicated text inserts into docling doc

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Fix styling

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Added support for code blocks and fenced code in MD

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* cleaned prints

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Added proper processing of in-line textual elements for MD backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Fixed issues with duplicated paragraphs and incorrect lists in pptx

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Fixed issue with group ordeering in pptx backend, added gebug log into run with formats

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Signed-off-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com>
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Peter Staar <taa@zurich.ibm.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
2024-10-23 16:14:26 +02:00
Michele Dolfi
3496b4838f
fix: set valid=false for invalid backends (#171)
* fix: set valid=false for invalid backends

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Add test case for InputDocument

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
2024-10-23 15:52:30 +02:00
Panos Vagenas
b8d2286dd1
chore: various minor docs fixes (#169)
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-10-22 15:29:36 +02:00
Mohamed Ali
fa5f94ec10
Fix Typo errors in CONTRIBUTING.md file (#164) 2024-10-22 07:01:48 +02:00
github-actions[bot]
d5460e2d1f chore: bump version to 2.1.0 [skip ci] 2024-10-18 13:21:15 +00:00
Michele Dolfi
b346faf622
feat: add coverage_threshold to skip OCR for small images (#161)
* feat: add coverage_threshold to skip OCR for small images

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* filter individual boxes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* rename option

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2024-10-18 13:58:23 +02:00
ABHISHEK FADAKE
f799e777c1
docs: typo fix (#155)
* Docs: Typo fix

- Corrected spelling of invidual to automatic

Signed-off-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com>

* add synchronize event for forks

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
2024-10-18 13:56:48 +02:00
Panos Vagenas
63bef59d9e
fix: fix legacy doc ref (#162)
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-10-18 13:11:20 +02:00
Michele Dolfi
bb7a58d45d
ci: run ci also on forks (#160)
---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
2024-10-18 12:32:27 +02:00
Christoph Auer
a00c937e19
Ensure all models work only on valid pages (#158)
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
2024-10-18 08:54:06 +02:00
Maxim Lysak
034a411057
docs: add graphical band in readme (#154)
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
2024-10-17 18:15:40 +02:00
Michele Dolfi
61c092f445
docs: add use docling (#150)
---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-10-17 18:14:48 +02:00
Michele Dolfi
24f949ada2
chore: run apt-get update before install (#156)
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2024-10-17 17:27:16 +02:00
github-actions[bot]
a29c256041 chore: bump version to 2.0.0 [skip ci] 2024-10-16 19:48:06 +00:00
Christoph Auer
7d3be0edeb
feat!: Docling v2 (#117)
---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Maxim Lysak <mly@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-10-16 21:02:03 +02:00
Panos Vagenas
d504432c1e
docs: introduce docs site (#141)
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-10-14 14:13:13 +02:00
Michele Dolfi
2b1e72d327
refactor: fix type of tesseractocr options (#140)
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
2024-10-14 08:40:22 +02:00
github-actions[bot]
4672b24c1a chore: bump version to 1.20.0 [skip ci] 2024-10-11 13:48:02 +00:00
Christoph Auer
5e4944f15f
feat: new experimental docling-parse v2 backend (#131)
---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
2024-10-11 15:12:49 +02:00
github-actions[bot]
2ec39636f0 chore: bump version to 1.19.1 [skip ci] 2024-10-11 08:52:09 +00:00