Christoph Auer
|
c5873f2496
|
chore: clean up code and comments
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
|
2025-02-26 12:47:10 +01:00 |
|
Christoph Auer
|
f994654918
|
Make drawing code resilient against bad bboxes
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
|
2025-02-26 11:01:11 +01:00 |
|
Christoph Auer
|
d269c8596c
|
Add back device_map and accelerate
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
|
2025-02-25 19:19:23 +01:00 |
|
Christoph Auer
|
a6d406764a
|
Fix VLM example exclusion in CI
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
|
2025-02-25 16:00:39 +01:00 |
|
Christoph Auer
|
10f64a948c
|
Expose control over using flash_attention_2
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
|
2025-02-25 15:31:32 +01:00 |
|
Christoph Auer
|
84c77c9fcb
|
Move imports
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
|
2025-02-25 14:03:28 +01:00 |
|
Christoph Auer
|
341806e54b
|
Rename example
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
|
2025-02-25 13:43:05 +01:00 |
|
Christoph Auer
|
1cba96ecfd
|
Generalize and refactor VLM pipeline and models
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
|
2025-02-25 13:38:44 +01:00 |
|
Maksym Lysak
|
1c75b52f85
|
re-built poetry.lock
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 17:37:35 +01:00 |
|
Maksym Lysak
|
9ecec1d330
|
Updated poetry.lock
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 17:27:50 +01:00 |
|
Maksym Lysak
|
923f766ada
|
Replaced remaining strings to appropriate enums
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 16:54:59 +01:00 |
|
Maksym Lysak
|
a095a7c5b7
|
removing changes from base_pipeline
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 15:13:59 +01:00 |
|
Maksym Lysak
|
a7a1f32b10
|
Added example on how to get original predicted doctags in minimal_smol_docling
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 14:39:18 +01:00 |
|
Maksym Lysak
|
1dbedcbb4e
|
removed pipeline_options.generate_table_images from vlm_pipeline (deprecated in the pipelines)
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 14:17:06 +01:00 |
|
Maksym Lysak
|
0c60ef199a
|
Moved keep_backend = True to vlm pipeline
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:50:40 +01:00 |
|
Maksym Lysak
|
853544ba11
|
Addressing PR comments, added enabled property to SmolDocling, and related VLM pipeline option, few other minor things
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:46:47 +01:00 |
|
Maksym Lysak
|
b0935daec4
|
Removed special html code wrapping when exporting to docling document, cleaned up comments
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:22:50 +01:00 |
|
Maksym Lysak
|
b12f5ba80f
|
removed minimal_smol_docling example from CI checks
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:20:10 +01:00 |
|
Maksym Lysak
|
66532eadb6
|
More elegant solution in removing the input prompt
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:20:10 +01:00 |
|
Maksym Lysak
|
e486eb1720
|
Cleaned up unnecessary logging
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:20:10 +01:00 |
|
Christoph Auer
|
55fa4eb4e3
|
Fix repo id
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
|
2025-02-24 13:20:05 +01:00 |
|
Christoph Auer
|
6f9f4f4aee
|
Update minimal smoldocling example
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
|
2025-02-24 13:18:25 +01:00 |
|
Maksym Lysak
|
b1df461ca8
|
Added captions for the images for SmolDocling assembly code, improved provenance definition for all elements
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:15:19 +01:00 |
|
Maksym Lysak
|
d7abe1b1cd
|
Updated example of Smol Docling usage
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:15:19 +01:00 |
|
Maksym Lysak
|
479ee239aa
|
New assembly code for latest model revision, updated prompt and parsing of doctags, updated logging
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:15:19 +01:00 |
|
Maksym Lysak
|
7c4ab5c716
|
Moved artifacts_path for SmolDocling into vlm_options instead of global pipeline option
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:15:19 +01:00 |
|
Maksym Lysak
|
f2751e11f9
|
Introduced SmolDoclingOptions to configure model parameters (such as query and artifacts path) via client code, see example in minimal_smol_docling. Provisioning for other potential vlm all-in-one models.
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:15:15 +01:00 |
|
Maksym Lysak
|
88b9ac6706
|
Fixing doctags starting tag, that broke elements on first line during assembly
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:12:55 +01:00 |
|
Maksym Lysak
|
0fe12d819a
|
Updated vlm pipeline assembly and smol docling model code to support updated doctags
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:12:55 +01:00 |
|
Maksym Lysak
|
f6d123a01c
|
Flipped keep_backend to True for vlm_pipeline assembly to work
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:12:55 +01:00 |
|
Maksym Lysak
|
9901729d8c
|
Exposed "force_backend_text" as pipeline parameter
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 13:12:51 +01:00 |
|
Maksym Lysak
|
0dc3ac43b1
|
Added capability for vlm_pipeline to grab text from preconfigured backend
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 12:56:57 +01:00 |
|
Maksym Lysak
|
e0929781f4
|
Added tokens/sec measurement, improved example
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 12:56:57 +01:00 |
|
Maksym Lysak
|
437053572d
|
Replaced hardcoded otsl tokens with the ones from docling-core tokens.py enum
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 12:56:57 +01:00 |
|
Maksym Lysak
|
2a43c199d5
|
Cleaned up logs, added pages to vlm_pipeline, basic timing per page measurement in smol_docling models
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 12:56:57 +01:00 |
|
Maksym Lysak
|
61bb9dbba2
|
Properly propagating image data per page, together with predicted tags in VLM pipeline. This enables correct figure extraction and page numbers in provenances
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 12:56:56 +01:00 |
|
Maksym Lysak
|
01c46e24b1
|
Fix for table span compute in vlm_pipeline
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 12:56:56 +01:00 |
|
Maksym Lysak
|
ef079e4e78
|
Enabled figure support in vlm_pipeline
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 12:56:56 +01:00 |
|
Maksym Lysak
|
1b968e4984
|
Fixes to preserve page image and demo export to html
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 12:56:56 +01:00 |
|
Maksym Lysak
|
3c4c647615
|
WIP, first working code for inference of SmolDocling, and vlm pipeline assembly code, example included.
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 12:56:56 +01:00 |
|
Maksym Lysak
|
03c8d45790
|
wip smolDocling inference and vlm pipeline
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 12:56:52 +01:00 |
|
Christoph Auer
|
dc3a388aa2
|
Skeleton for SmolDocling model and VLM Pipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
|
2025-02-24 11:46:04 +01:00 |
|
Suehtam
|
1d17e7397a
|
test: avoid testing exact JSON in CSV backend (#1038)
* feat: updated verify_export
Moved verify_export to verify_utils
Reuse verify_export in tests
Signed-off-by: Matheus Abdias <matheusfabdias@gmail.com>
* feat: replace verify_export with verify_document in CSV conversion tests
Signed-off-by: Matheus Abdias <matheusfabdias@gmail.com>
---------
Signed-off-by: Matheus Abdias <matheusfabdias@gmail.com>
|
2025-02-24 08:10:40 +01:00 |
|
github-actions[bot]
|
d8a81c3168
|
chore: bump version to 2.24.0 [skip ci]
v2.24.0
|
2025-02-20 18:31:20 +00:00 |
|
Christoph Auer
|
c93e36988f
|
feat: Implement new reading-order model (#916)
* Implement new reading-order model, replacing DS GLM model (WIP)
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update reading-order model branch
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update lockfile [skip ci]
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add captions, footnotes and merges [skip ci]
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Updates for reading-order implementation
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Updates for reading-order implementation
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update tests and lockfile
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fixes, update tests
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add normalization, update tests again
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update tests with code
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Push final lockfile
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* sanitize text
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* Inlcude furniture, Update tests with furniture
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fix content_layer assignment
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* chore: Delete empty file docling/models/ds_glm_model.py
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Nikos Livathinos <nli@zurich.ibm.com>
|
2025-02-20 17:51:17 +01:00 |
|
github-actions[bot]
|
c031a7ae47
|
chore: bump version to 2.23.1 [skip ci]
v2.23.1
|
2025-02-20 16:26:41 +00:00 |
|
Cesar Berrospi Ramis
|
1ac010354f
|
test: avoid testing exact JSON (#1027)
* test: avoid testing exact JSON
Avoid testing exact JSON output in html and xml backends.
Reuse the JSON verify helper function among backend test files.
Improve type annotations in html backend.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* Update tests/test_backend_patent_uspto.py
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---------
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
|
2025-02-20 16:20:07 +01:00 |
|
fanszoro
|
6796f0a132
|
fix: Runtime error when Pandas Series is not always of string type (#1024)
Signed-off-by: fan <fansluck@qq.com>
|
2025-02-20 15:41:41 +01:00 |
|
Christoph Auer
|
dfcc30dddb
|
chore: Update tests and lockfile (#1021)
Update tests and lockfile
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
|
2025-02-19 16:51:53 +01:00 |
|
Panos Vagenas
|
27c04007bc
|
docs: revamp picture description example (#1015)
* docs: revamp picture description example
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
* Improvements for visualization example (#1017)
* fix colab install, use granite and improve viz of description
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* switch docs to notbook
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* show results with all models
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* show other vlm
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
---------
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
---------
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
|
2025-02-19 11:28:54 +01:00 |
|