LLM/docling-serve
1
0
Fork 0
mirror of https://github.com/docling-project/docling-serve.git synced 2026-03-07 22:33:44 +00:00
Code Issues Packages Projects Releases Wiki Activity
234 Commits 4 Branches 46 Tags
be7ac72b334d206074b9fe59aaa14684dcf843f2
Commit Graph

39 Commits

Author SHA1 Message Date
Michele Dolfi
5a814d7797 fix: arm64 image for CUDA 12.8 (#508) 
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
 2026-02-23 10:39:14 +01:00
Michele Dolfi
b4800c50f2 feat: new docling parse, model inference engines and presets (#499) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2026-02-18 15:35:08 +01:00
Michele Dolfi
c590cb42e1 feat: distribute linux arm64 images and update cuda versions (#496) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2026-02-16 15:42:49 +01:00
Paweł Rein
416312a41b feat: OpenTelemetry support for traces and metrics (#456) 
Signed-off-by: Pawel Rein <pawel.rein@prezi.com>
 2026-01-12 13:17:07 +01:00
Michele Dolfi
772fcec4ae chore: avoid installing multiple times dependencies (#429) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-11-21 15:42:42 +01:00
Michele Dolfi
35319b0da7 docs: Expand automatic docs to nested objects. More complete usage docs. (#426) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-10-31 15:02:20 +01:00
Michele Dolfi
56e8535a7a chore: publish release notes on Discord (#409) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-10-20 14:15:58 +02:00
Rui Dias Gomes
fa1c5f04f3 ci: improve caching steps (#371) 
Signed-off-by: rmdg88 <rmdg88@gmail.com>
 2025-09-23 18:15:12 +02:00
Michele Dolfi
4adc0dfa79 ci: fix use simple tag for testing (#354) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-09-08 11:29:55 +02:00
Rui Dias Gomes
fe98338239 ci: fix runner disk space issue (#350) 
Signed-off-by: Rui Dias Gomes <66125272+rmdg88@users.noreply.github.com>
 2025-09-04 09:17:19 +02:00
Michele Dolfi
b844ce737e ci: remove mdlint (#348) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-09-03 15:42:55 +02:00
Rui Dias Gomes
1df62adf01 ci: workflow improvements (#310) 
Signed-off-by: rmdg88 <rmdg88@gmail.com>
Signed-off-by: Rui Dias Gomes <66125272+rmdg88@users.noreply.github.com>
 2025-09-03 10:06:30 +02:00
Michele Dolfi
6e9aa8c759 docs: handling models in docling-serve (#319) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-08-14 09:12:04 +02:00
Michele Dolfi
885f319d3a feat: Add RQ engine (#315) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-08-14 08:48:31 +02:00
Rui Dias Gomes
fd1b987e8d feat: add rocm image build support and fix cuda (#292) 
Signed-off-by: rmdg88 <rmdg88@gmail.com>
Signed-off-by: Rui-Dias-Gomes <rui.dias.gomes@ibm.com>
Co-authored-by: Rui-Dias-Gomes <rui.dias.gomes@ibm.com>
 2025-07-31 14:22:42 +02:00
Michele Dolfi
8222cf8955 ci: add spellchecker with custom vocabulary and fix typos (#268) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-07-15 14:17:35 +02:00
Michele Dolfi
30aca92298 feat: package updates and more cuda images (#229) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-06-24 16:59:05 +02:00
Michele Dolfi
7a682494d6 chore: dco advisor (#224) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-06-17 09:38:56 +02:00
Michele Dolfi
35c2630c61 fix: add flash-attn for cuda images (#161) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-04-29 16:58:33 +02:00
Michele Dolfi
7994b19b9f chore: move to docling-project gh org (#95) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-03-14 14:04:31 +01:00
Eugene
3c9825df30 ci: Speed up python linting (#64) 
Signed-off-by: Eugene <fogaprod@gmail.com>
 2025-03-10 18:05:33 +01:00
Michele Dolfi
d406802f9d chore: update uv.lock with new release version (#89) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-03-10 16:57:48 +01:00
Michele Dolfi
a92ad48b28 fix: submodules in wheels (#85) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-03-10 16:19:34 +01:00
Michele Dolfi
7e6d9cdef3 feat: New container images (#68) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-02-26 12:49:20 +01:00
Anil Vishnoi
63141f1cc7 ci: Use release event to trigger the image publishing job for releases (#63) 
Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>
 2025-02-24 08:21:17 +01:00
Michele Dolfi
ec33a61faa feat: Add new docling-serve cli (#50) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-02-19 20:54:13 +01:00
Michele Dolfi
ae3b4906f1 fix: support python 3.13 and docling updates and switch to uv (#48) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-02-19 09:53:07 +01:00
Michele Dolfi
7a351fcdea fix missing secrets inherit 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-02-13 17:02:01 +00:00
Michele Dolfi
1615f977a2 ci: add semantic release and build/publish python wheel (#41) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-02-13 16:49:43 +01:00
Anil Vishnoi
ee7a237076 Minor fixes - 
- Use port 5001
 - Publish cpu only arm64 image to quay.io as well

Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>
 2025-01-28 16:08:10 +00:00
Michele Dolfi
3f1e8fb4d7 ci: build on tags (#21) 
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
 2025-01-28 08:30:56 +01:00
Anil Vishnoi
dff5cb35a3 Add support for arm64 architecture for cpu only image 
Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>
 2025-01-28 04:32:29 +00:00
Anil Vishnoi
01fc6e10e8 Add github job to build image (and not publish) on PR creation (#20) 
Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>
 2025-01-23 11:24:07 +01:00
Anil Vishnoi
e0c98aa953 Run workflow jobs sequentially to avoid disk space outage (#19) 
Github Action runners are running out of the space while
building both the images in parallel.

This change will build the image sequentially and also
clean up the cpu images before start building gpu image.

Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>
 2025-01-22 18:55:01 +01:00
Anil Vishnoi
ac3518c34c Add python, markdown and github action linter (#5) 
to ensure the code maintenance. Thanks to docling
project- took some good bits around python linting
from the project.

These checks are also added in the markdown, so that
user can run these checks locally to recreate the
errors.

Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>
 2024-09-13 14:26:32 +02:00
Anil Vishnoi
fc11dc2540 Enable concurrent running of the image generation jobs (#4) 
Group GPU image generate for GHCR and QUAY in one job,
and similarly group CPU only image generation for GHCR
and QUAY in another job. These two jobs can now run
concurrently.

By grouping the jobs for the same image type, it can
use the docker layer cache to run the second job faster.
If we separately build these images in four diffent and
concurrent jobs, they won't be able to use the cache.

If this still takes significantly long, we probably
have to generate image in it's own job, so that they can run
concurrently, without leveraging cache of docker layers.

Also added make file target to lint the github workflows.

Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>
 2024-09-13 10:31:06 +02:00
Anil Vishnoi
4dd517c96a Use consistent naming across ghcr.io and quay.io images (#3) 
Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>
 2024-09-13 08:28:52 +02:00
Anil Vishnoi
ae07e12b33 Fix github workflow (#2) 
Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>
 2024-09-12 22:16:00 +02:00
Anil Vishnoi
a91ee83c61 Publish docling-serve images to ghcr and quay container repositories (#1) 
* Publish docling-serve images to ghcr and quay container repositories

This commit:
- Creates container file to build the image for cpu only
and default "with gpu" images
- Adds workflow jobs to publish the images to ghcr.io and quay.io
- Makefile to build these images locally for linux/amd64 platform.

Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>

* make cpu-only version with poetry

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

* Rename cpu/gpu image names and also update the supported platforms

Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>

---------

Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-09-12 22:02:42 +02:00