a39f132b91
Update versions to 1.19.0-SNAPSHOT and 1.19.0-beta29-SNAPSHOT
2026-07-17 13:42:56 +00:00
66ad5ee6d5
Release versions 1.18.0 and 1.18.0-beta28
2026-07-17 12:34:45 +00:00
7d7c3349d7
Update versions to 1.18.0-SNAPSHOT and 1.18.0-beta28-SNAPSHOT
2026-06-26 14:49:40 +00:00
207407aec9
Release versions 1.17.0 and 1.17.0-beta27
2026-06-26 13:13:06 +00:00
de77530200
fix: infinite loop in OnnxBertBiEncoder.partition for oversized subword runs ( #5454 )
...
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Existing open issue #589 describes this symptom; human sets the ID
(use #589 , or a fresh bug issue draft is provided). -->
Closes #5453
## Change
`OnnxBertBiEncoder.partition(tokens, partitionSize)` could loop forever
or emit empty partitions when a single word's subword run exceeds
`partitionSize`: the `##`-back-off loop had no lower bound, so `to`
descended to `from`, giving an empty `subList(from, to)` while `from =
to` never advanced.
The fix bounds the back-off (keeps ≥1 token of progress) and forces a
full-window split for an oversized single-word run:
```java
while (to > from && tokens.get(to).startsWith("##")) {
to--;
}
if (to == from) {
to = from + partitionSize;
}
```
Normal inputs are unchanged: both new conditions are inert when the
back-off stops above `from`. Added a regression test (partitionSize=1,
long `##` run, `@Timeout`) asserting termination, no empty partition,
and full ordered token coverage.
PR #4406's `isEmpty()` guard in `embed()` masked the symptom; this fixes
the root cause.
<!-- The one-line reformat of the unrelated loadModel string concat is
forced by the spotless ratchet (ratchetFrom origin/main checks the whole
touched file), not a gratuitous change. -->
## General checklist
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core )
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j )
modules, and they are all green <!-- N/A — change is isolated to the
embeddings module; core/main not affected -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs )
<!-- N/A — internal bug fix, no public API/doc change -->
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples ) (only for
"big" features) <!-- N/A — bug fix, not a feature -->
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring ) (if
applicable) <!-- N/A — not applicable -->
<!-- Checklist for adding new maven module: omitted — no new module. -->
<!-- Checklist for adding/changing embedding store integration: omitted
— no embedding store integration touched. -->
## Verification
- Module unit tests (JDK 17): `OnnxBertBiEncoderTest` 7 passed (6
existing + 1 new); module total 9 passed, 0 failures.
- Integration tests (`*IT`): none in this module; not run.
- spotless: `spotless:check -pl embeddings/langchain4j-embeddings`
passes with JDK 17 (workaround applied: ran in main checkout because the
JGit ratchet cannot resolve a linked-worktree `.git` pointer file).
2026-06-17 09:41:04 +02:00
01de41d641
Update versions to 1.17.0-SNAPSHOT and 1.17.0-beta27-SNAPSHOT
2026-06-06 06:46:38 +00:00
cd836845dd
Release versions 1.16.0 and 1.16.0-beta26
2026-06-05 15:46:56 +00:00
6185599e37
Update versions to 1.16.0-SNAPSHOT and 1.16.0-beta26-SNAPSHOT
2026-05-15 16:21:14 +00:00
d0e54aa006
Release versions 1.15.0 and 1.15.0-beta25
2026-05-15 15:55:12 +00:00
3c0d21e7da
fix(deps): update ai.djl.version to v0.36.0 ( #5229 )
...
This PR contains the following updates:
| Package | Change |
[Age](https://docs.renovatebot.com/merge-confidence/ ) |
[Confidence](https://docs.renovatebot.com/merge-confidence/ ) |
|---|---|---|---|
|
[ai.djl.huggingface:tokenizers](http://www.djl.ai/extensions/tokenizers )
([source](https://redirect.github.com/deepjavalibrary/djl )) | `0.31.1` →
`0.36.0` |
|
|
| [ai.djl:api](http://www.djl.ai/api )
([source](https://redirect.github.com/deepjavalibrary/djl )) | `0.31.1` →
`0.36.0` |
|
|
|
[ai.djl.huggingface:tokenizers](http://www.djl.ai/extensions/tokenizers )
([source](https://redirect.github.com/deepjavalibrary/djl )) | `0.33.0` →
`0.36.0` |
|
|
| [ai.djl:api](http://www.djl.ai/api )
([source](https://redirect.github.com/deepjavalibrary/djl )) | `0.33.0` →
`0.36.0` |
|
|
---
> [!WARNING]
> Some dependencies could not be looked up. Check the [Dependency
Dashboard](../issues/2069) for more information.
---
### Release Notes
<details>
<summary>deepjavalibrary/djl (ai.djl.huggingface:tokenizers)</summary>
###
[`v0.36.0`](https://redirect.github.com/deepjavalibrary/djl/releases/tag/v0.36.0 ):
DJL v0.36.0 Release
[Compare
Source](https://redirect.github.com/deepjavalibrary/djl/compare/v0.35.1...v0.36.0 )
##### What's Changed
- Increase build version to 0.36.0 by
[@​access2rohit](https://redirect.github.com/access2rohit ) in
[#​3817](https://redirect.github.com/deepjavalibrary/djl/pull/3817 )
- Update the Documentation (via DocString) to indicate the risks of
using Utils.openUrl() with untrusted inputs by
[@​access2rohit](https://redirect.github.com/access2rohit ) in
[#​3819](https://redirect.github.com/deepjavalibrary/djl/pull/3819 )
- NDManager.create(Number) unsupported type error message improvement by
[@​fracpete](https://redirect.github.com/fracpete ) in
[#​3818](https://redirect.github.com/deepjavalibrary/djl/pull/3818 )
##### New Contributors
- [@​access2rohit](https://redirect.github.com/access2rohit ) made
their first contribution in
[#​3816](https://redirect.github.com/deepjavalibrary/djl/pull/3816 )
- [@​fracpete](https://redirect.github.com/fracpete ) made their
first contribution in
[#​3818](https://redirect.github.com/deepjavalibrary/djl/pull/3818 )
**Full Changelog**:
<https://github.com/deepjavalibrary/djl/compare/v0.35.1...v0.36.0 >
###
[`v0.35.1`](https://redirect.github.com/deepjavalibrary/djl/releases/tag/v0.35.1 ):
DJL v0.35.1 Release
[Compare
Source](https://redirect.github.com/deepjavalibrary/djl/compare/v0.35.0...v0.35.1 )
##### What's Changed
- fix: upgrade jQuery from 2.1.1 to 3.7.1 to address security
vulnerabilities by
[@​Lokiiiiii](https://redirect.github.com/Lokiiiiii ) in
[#​3812](https://redirect.github.com/deepjavalibrary/djl/pull/3812 )
- Fix script injection vulnerabilities in GitHub Actions workflows by
[@​Lokiiiiii](https://redirect.github.com/Lokiiiiii ) in
[#​3813](https://redirect.github.com/deepjavalibrary/djl/pull/3813 )
- Fix security vulnerabilities in QuestionAnsweringTranslator (CVSS 8.2)
by [@​Lokiiiiii](https://redirect.github.com/Lokiiiiii ) in
[#​3814](https://redirect.github.com/deepjavalibrary/djl/pull/3814 )
##### New Contributors
- [@​Lokiiiiii](https://redirect.github.com/Lokiiiiii ) made their
first contribution in
[#​3812](https://redirect.github.com/deepjavalibrary/djl/pull/3812 )
**Full Changelog**:
<https://github.com/deepjavalibrary/djl/compare/v0.35.0...v0.35.1 >
###
[`v0.35.0`](https://redirect.github.com/deepjavalibrary/djl/releases/tag/v0.35.0 ):
DJL v0.35.0 Release
[Compare
Source](https://redirect.github.com/deepjavalibrary/djl/compare/v0.34.0...v0.35.0 )
##### What's Changed
- Engine Updates
- XGBoost 3.0.4
[#​3788](https://redirect.github.com/deepjavalibrary/djl/pull/3788 )
##### Enhancements
- Increase build version to 0.35.0 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3766](https://redirect.github.com/deepjavalibrary/djl/pull/3766 )
- Add default header for openai by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3772](https://redirect.github.com/deepjavalibrary/djl/pull/3772 )
- Update gradle to 9.0.0 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3777](https://redirect.github.com/deepjavalibrary/djl/pull/3777 )
- \[XGBoost] Support json model for XGBoost by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3786](https://redirect.github.com/deepjavalibrary/djl/pull/3786 )
- \[api] Accept json input/output for tensor input by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3787](https://redirect.github.com/deepjavalibrary/djl/pull/3787 )
- Upgrade xgboost to 3.0.4 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3788](https://redirect.github.com/deepjavalibrary/djl/pull/3788 )
- \[pytorch] Add tuple of dict support for IValue by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3797](https://redirect.github.com/deepjavalibrary/djl/pull/3797 )
- \[XGBoost] Add back gpu support for xgboost by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3796](https://redirect.github.com/deepjavalibrary/djl/pull/3796 )
- Update gradle build script to support configuration cache by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3782](https://redirect.github.com/deepjavalibrary/djl/pull/3782 )
- Added percentile implementation for Pytorch engine by
[@​tipame](https://redirect.github.com/tipame ) in
[#​3800](https://redirect.github.com/deepjavalibrary/djl/pull/3800 )
- Implemented CSV translator that handles CSV input/output support for
XGBoost by [@​smouaa](https://redirect.github.com/smouaa ) in
[#​3801](https://redirect.github.com/deepjavalibrary/djl/pull/3801 )
- Correct topK documentation by
[@​alanocallaghan](https://redirect.github.com/alanocallaghan ) in
[#​3808](https://redirect.github.com/deepjavalibrary/djl/pull/3808 )
- \[api] Refactor csvTranslator by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3805](https://redirect.github.com/deepjavalibrary/djl/pull/3805 )
##### Bug Fixes
- Fix pytorch native 2.5.1 aarch64 build by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3767](https://redirect.github.com/deepjavalibrary/djl/pull/3767 )
- \[fix] Fixes load tokenizer gpu shared library issue by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3773](https://redirect.github.com/deepjavalibrary/djl/pull/3773 )
- Fixes
[#​3774](https://redirect.github.com/deepjavalibrary/djl/issues/3774 )
for YoloSegmentationTranslator by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3775](https://redirect.github.com/deepjavalibrary/djl/pull/3775 )
- Fixes issue
[#​3761](https://redirect.github.com/deepjavalibrary/djl/issues/3761 )
by [@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3776](https://redirect.github.com/deepjavalibrary/djl/pull/3776 )
- Fix `BaseNDManager.debugDump` by
[@​petebankhead](https://redirect.github.com/petebankhead ) in
[#​3780](https://redirect.github.com/deepjavalibrary/djl/pull/3780 )
- Fix preference of tokenizer\_config.json and remove doLowerCase from
TokenizerConfig by
[@​Soha-Agarwal](https://redirect.github.com/Soha-Agarwal ) in
[#​3785](https://redirect.github.com/deepjavalibrary/djl/pull/3785 )
- Fixes:
[#​3795](https://redirect.github.com/deepjavalibrary/djl/issues/3795 ),
adds aggregation\_strategy to token classification task by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3798](https://redirect.github.com/deepjavalibrary/djl/pull/3798 )
- Fix pytorch native build for windows by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3802](https://redirect.github.com/deepjavalibrary/djl/pull/3802 )
##### CI/CD
- Build pytorch jni cpu precxx by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3770](https://redirect.github.com/deepjavalibrary/djl/pull/3770 )
- Remove pytorch 2.1.2 and 2.3.1 publish in nightly by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3771](https://redirect.github.com/deepjavalibrary/djl/pull/3771 )
- Fix sentencepiece native workflow by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3768](https://redirect.github.com/deepjavalibrary/djl/pull/3768 )
- Fix fasttext native workflow by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3769](https://redirect.github.com/deepjavalibrary/djl/pull/3769 )
- Fix continuous build by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3804](https://redirect.github.com/deepjavalibrary/djl/pull/3804 )
##### New Contributors
- [@​smouaa](https://redirect.github.com/smouaa ) made their first
contribution in
[#​3801](https://redirect.github.com/deepjavalibrary/djl/pull/3801 )
- [@​alanocallaghan](https://redirect.github.com/alanocallaghan )
made their first contribution in
[#​3808](https://redirect.github.com/deepjavalibrary/djl/pull/3808 )
**Full Changelog**:
<https://github.com/deepjavalibrary/djl/compare/v0.34.0...v0.35.0 >
###
[`v0.34.0`](https://redirect.github.com/deepjavalibrary/djl/releases/tag/v0.34.0 ):
DJL v0.34.0 Release
[Compare
Source](https://redirect.github.com/deepjavalibrary/djl/compare/v0.33.0...v0.34.0 )
##### Key Changes
- Engine Updates
- PyTorch 2.7.1
[#​3733](https://redirect.github.com/deepjavalibrary/djl/pull/3733 )
- Remove TensorRT engine
[#​3765](https://redirect.github.com/deepjavalibrary/djl/pull/3765 )
##### Enhancements
- \[api] Adds FUSE based repository support by
[@​raymondkhliu](https://redirect.github.com/raymondkhliu ) in
[#​3695](https://redirect.github.com/deepjavalibrary/djl/pull/3695 )
- Treat model server as a remote model by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3704](https://redirect.github.com/deepjavalibrary/djl/pull/3704 )
- Align ZeroShotClassificationTranslator with Hugging Face behavior by
[@​raphaeldelio](https://redirect.github.com/raphaeldelio ) in
[#​3712](https://redirect.github.com/deepjavalibrary/djl/pull/3712 )
- Remove usage of UUID.randomUUID() for better performance by
[@​aakashb-kayzen](https://redirect.github.com/aakashb-kayzen ) in
[#​3719](https://redirect.github.com/deepjavalibrary/djl/pull/3719 )
- Replace UUID with NDManager.nextUid() by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3720](https://redirect.github.com/deepjavalibrary/djl/pull/3720 )
- Add NDArray diagonal by
[@​dev-jonghoonpark](https://redirect.github.com/dev-jonghoonpark )
in
[#​3724](https://redirect.github.com/deepjavalibrary/djl/pull/3724 )
- \[api] Implements remote REST API call as a model by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3725](https://redirect.github.com/deepjavalibrary/djl/pull/3725 )
- Adds jsonlines streaming support for RpcEngine by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3727](https://redirect.github.com/deepjavalibrary/djl/pull/3727 )
- Adds genai extension by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3726](https://redirect.github.com/deepjavalibrary/djl/pull/3726 )
- \[genai] tool calls to ChatInput by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3728](https://redirect.github.com/deepjavalibrary/djl/pull/3728 )
- Add utility class for genai function call by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3729](https://redirect.github.com/deepjavalibrary/djl/pull/3729 )
- Improve function call for genai extension by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3731](https://redirect.github.com/deepjavalibrary/djl/pull/3731 )
- Support convert ChatInput to GeminiInput by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3739](https://redirect.github.com/deepjavalibrary/djl/pull/3739 )
- Add partial support for HuggingFace Tokenizer to use parameters from
tokenizer\_config.json by
[@​Soha-Agarwal](https://redirect.github.com/Soha-Agarwal ) in
[#​3738](https://redirect.github.com/deepjavalibrary/djl/pull/3738 )
- Add Anthropic support from genai by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3759](https://redirect.github.com/deepjavalibrary/djl/pull/3759 )
##### Bug Fixes
- Correct CaptchaDataset options count to prevent torch.gather
IndexError by [@​xinhuagu](https://redirect.github.com/xinhuagu )
in
[#​3694](https://redirect.github.com/deepjavalibrary/djl/pull/3694 )
- Fix dimension check when reshaping offsets in SeqBatcher by
[@​xinhuagu](https://redirect.github.com/xinhuagu ) in
[#​3702](https://redirect.github.com/deepjavalibrary/djl/pull/3702 )
- Fix the incorrect function name and minor typo in doc by
[@​xinhuagu](https://redirect.github.com/xinhuagu ) in
[#​3703](https://redirect.github.com/deepjavalibrary/djl/pull/3703 )
- Fix incorrect return value in getImageHeight method by
[@​xinhuagu](https://redirect.github.com/xinhuagu ) in
[#​3706](https://redirect.github.com/deepjavalibrary/djl/pull/3706 )
- \[djl\_converter]: Fixes djl\_converter bug by
[@​raymondkhliu](https://redirect.github.com/raymondkhliu ) in
[#​3705](https://redirect.github.com/deepjavalibrary/djl/pull/3705 )
- Fix the out of bounds exception when using an init image by
[@​luke-zhou](https://redirect.github.com/luke-zhou ) in
[#​3717](https://redirect.github.com/deepjavalibrary/djl/pull/3717 )
- Fix earlystopping metric issue
[#​3722](https://redirect.github.com/deepjavalibrary/djl/issues/3722 )
by [@​SamBSalgado](https://redirect.github.com/SamBSalgado ) in
[#​3736](https://redirect.github.com/deepjavalibrary/djl/pull/3736 )
- \[tokenizers] Fix tokenizer cpu and cuda build by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3756](https://redirect.github.com/deepjavalibrary/djl/pull/3756 )
- \[examples] Update tfhub urls by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3752](https://redirect.github.com/deepjavalibrary/djl/pull/3752 )
- Update tfhub repository url by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3755](https://redirect.github.com/deepjavalibrary/djl/pull/3755 )
##### Documentation
- \[docs] Update model zoo document by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3690](https://redirect.github.com/deepjavalibrary/djl/pull/3690 )
##### CI/CD
- increase build version to 0.34.0 by
[@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3689](https://redirect.github.com/deepjavalibrary/djl/pull/3689 )
- Uses new recommended way to build pip wheel by
[@​raymondkhliu](https://redirect.github.com/raymondkhliu ) in
[#​3709](https://redirect.github.com/deepjavalibrary/djl/pull/3709 )
- Bump protobuf from 3.20.2 to 4.25.8 in
/extensions/tokenizers/src/main/python by
[@​dependabot](https://redirect.github.com/dependabot )\[bot] in
[#​3716](https://redirect.github.com/deepjavalibrary/djl/pull/3716 )
- \[android] Upgrade DJL version to 0.34.0 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3721](https://redirect.github.com/deepjavalibrary/djl/pull/3721 )
- \[ci] simplify nightly publish workflow by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3732](https://redirect.github.com/deepjavalibrary/djl/pull/3732 )
- \[ci] Update maven central publish url and credential by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3748](https://redirect.github.com/deepjavalibrary/djl/pull/3748 )
- \[djl-converter] Update license in pyproject.toml by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3749](https://redirect.github.com/deepjavalibrary/djl/pull/3749 )
- \[pytorch] Updates PyTorch to 2.7.1 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3733](https://redirect.github.com/deepjavalibrary/djl/pull/3733 )
- \[ci] Remove serving-publish workflow by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3750](https://redirect.github.com/deepjavalibrary/djl/pull/3750 )
- Update oss sonatype snapshot repository url by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3754](https://redirect.github.com/deepjavalibrary/djl/pull/3754 )
- Upgrade dependency versions by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3762](https://redirect.github.com/deepjavalibrary/djl/pull/3762 )
- \[android] Upgrade pytorch version to 2.7.1 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3763](https://redirect.github.com/deepjavalibrary/djl/pull/3763 )
- \[ci] Add post-publish task by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3764](https://redirect.github.com/deepjavalibrary/djl/pull/3764 )
- Increase DJL version to 0.34.0 by
[@​Soha-Agarwal](https://redirect.github.com/Soha-Agarwal ) in
[#​3758](https://redirect.github.com/deepjavalibrary/djl/pull/3758 )
##### New Contributors
- [@​raymondkhliu](https://redirect.github.com/raymondkhliu ) made
their first contribution in
[#​3695](https://redirect.github.com/deepjavalibrary/djl/pull/3695 )
- [@​raphaeldelio](https://redirect.github.com/raphaeldelio ) made
their first contribution in
[#​3712](https://redirect.github.com/deepjavalibrary/djl/pull/3712 )
- [@​luke-zhou](https://redirect.github.com/luke-zhou ) made their
first contribution in
[#​3717](https://redirect.github.com/deepjavalibrary/djl/pull/3717 )
- [@​aakashb-kayzen](https://redirect.github.com/aakashb-kayzen )
made their first contribution in
[#​3719](https://redirect.github.com/deepjavalibrary/djl/pull/3719 )
-
[@​dev-jonghoonpark](https://redirect.github.com/dev-jonghoonpark )
made their first contribution in
[#​3724](https://redirect.github.com/deepjavalibrary/djl/pull/3724 )
- [@​Soha-Agarwal](https://redirect.github.com/Soha-Agarwal ) made
their first contribution in
[#​3738](https://redirect.github.com/deepjavalibrary/djl/pull/3738 )
- [@​SamBSalgado](https://redirect.github.com/SamBSalgado ) made
their first contribution in
[#​3736](https://redirect.github.com/deepjavalibrary/djl/pull/3736 )
**Full Changelog**:
<https://github.com/deepjavalibrary/djl/compare/v0.33.0...v0.34.0 >
###
[`v0.33.0`](https://redirect.github.com/deepjavalibrary/djl/releases/tag/v0.33.0 ):
DJL v0.33.0 Release
[Compare
Source](https://redirect.github.com/deepjavalibrary/djl/compare/v0.32.0...v0.33.0 )
##### Key Changes
- Engine Updates
- OnnxRuntime Updated to 1.21.0
##### Enhancements
- \[tokenizers] Add lasttoken pooling by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3607](https://redirect.github.com/deepjavalibrary/djl/pull/3607 )
- \[api] Provide concrete implementation of TranslatorContext by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3622](https://redirect.github.com/deepjavalibrary/djl/pull/3622 )
- \[api] Add zero shot object detection support by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3626](https://redirect.github.com/deepjavalibrary/djl/pull/3626 )
- \[api] Adds zero short image classification support by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3628](https://redirect.github.com/deepjavalibrary/djl/pull/3628 )
- Adds yolov8s-world2 model support by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3637](https://redirect.github.com/deepjavalibrary/djl/pull/3637 )
- \[tensorflow] Allow retrieving available signatures for TensorFlow
models by [@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3638](https://redirect.github.com/deepjavalibrary/djl/pull/3638 )
- \[api] Improve listModel performance by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3641](https://redirect.github.com/deepjavalibrary/djl/pull/3641 )
- \[tokenizers] Adds SparseRetrievalTranslator by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3642](https://redirect.github.com/deepjavalibrary/djl/pull/3642 )
- \[tokenizers] Fix tokenizer name in tests by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3652](https://redirect.github.com/deepjavalibrary/djl/pull/3652 )
- \[tokenizer] Updates tokenizers to 0.21.1 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3654](https://redirect.github.com/deepjavalibrary/djl/pull/3654 )
- \[onnxruntime] Updates OnnxRuntime to 1.21.0 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3678](https://redirect.github.com/deepjavalibrary/djl/pull/3678 )
- \[examples] Add WhisperJet model demo by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3681](https://redirect.github.com/deepjavalibrary/djl/pull/3681 )
- \[pytorch] Add diff support by
[@​saedmanaf](https://redirect.github.com/saedmanaf ) in
[#​3663](https://redirect.github.com/deepjavalibrary/djl/pull/3663 )
##### Bug Fixes
- \[examples] fixing some dependencies and test requirements by
[@​sindhuvahinis](https://redirect.github.com/sindhuvahinis ) in
[#​3605](https://redirect.github.com/deepjavalibrary/djl/pull/3605 )
- \[onnxruntime] Fixes intraOpNumThreads bug by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3630](https://redirect.github.com/deepjavalibrary/djl/pull/3630 )
- \[ci] Fixes build.gradle for integration by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3635](https://redirect.github.com/deepjavalibrary/djl/pull/3635 )
- \[ci] Fixes system properties in gradle build script by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3636](https://redirect.github.com/deepjavalibrary/djl/pull/3636 )
- Fix: Corrected 16-bit PCM normalization to avoid overflow issue by
[@​leleZeng](https://redirect.github.com/leleZeng ) in
[#​3646](https://redirect.github.com/deepjavalibrary/djl/pull/3646 )
- Fix rust build with update candle-core the 0.8.4 version by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3645](https://redirect.github.com/deepjavalibrary/djl/pull/3645 )
- Fixed rust build with update candle-core the 0.8.4 version by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3649](https://redirect.github.com/deepjavalibrary/djl/pull/3649 )
- \[fix] LRUReplayBuffer "stepToReplace" index fix by
[@​dwctic](https://redirect.github.com/dwctic ) in
[#​3660](https://redirect.github.com/deepjavalibrary/djl/pull/3660 )
##### Documentation
- docs: added a link to the continuous badge by
[@​operagxoksana](https://redirect.github.com/operagxoksana ) in
[#​3668](https://redirect.github.com/deepjavalibrary/djl/pull/3668 )
- \[doc] Update onnxruntime readme by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3669](https://redirect.github.com/deepjavalibrary/djl/pull/3669 )
- chore: edited badges by
[@​operagxoksana](https://redirect.github.com/operagxoksana ) in
[#​3670](https://redirect.github.com/deepjavalibrary/djl/pull/3670 )
- chore: added an icon to the release by
[@​operagxoksana](https://redirect.github.com/operagxoksana ) in
[#​3671](https://redirect.github.com/deepjavalibrary/djl/pull/3671 )
- Correct 'Load Model' documentation: method
ImageClassificationTranslator.builder().setSynsetArtifactName() does not
exist by [@​xinhuagu](https://redirect.github.com/xinhuagu ) in
[#​3677](https://redirect.github.com/deepjavalibrary/djl/pull/3677 )
##### CI/CD
- \[release] Release DJL 0.32.0 by
[@​sindhuvahinis](https://redirect.github.com/sindhuvahinis ) in
[#​3603](https://redirect.github.com/deepjavalibrary/djl/pull/3603 )
- bump build version to 0.33.0 by
[@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3627](https://redirect.github.com/deepjavalibrary/djl/pull/3627 )
- \[ci] Upgrade gradle to 8.13 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3650](https://redirect.github.com/deepjavalibrary/djl/pull/3650 )
- \[ci] Fixes CI build for cmake 4.0.0 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3659](https://redirect.github.com/deepjavalibrary/djl/pull/3659 )
- Bump openssl from 0.10.71 to 0.10.72 in /extensions/tokenizers/rust by
[@​dependabot](https://redirect.github.com/dependabot ) in
[#​3661](https://redirect.github.com/deepjavalibrary/djl/pull/3661 )
- update some dependency versions by
[@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3665](https://redirect.github.com/deepjavalibrary/djl/pull/3665 )
- remove status from log4j configuration of status logger by
[@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3667](https://redirect.github.com/deepjavalibrary/djl/pull/3667 )
- Remove unnecessary exclusion for testng by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3687](https://redirect.github.com/deepjavalibrary/djl/pull/3687 )
- Updates dependencies version by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3688](https://redirect.github.com/deepjavalibrary/djl/pull/3688 )
- \[onnx] use zulu jdk to fix windows issues by
[@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3683](https://redirect.github.com/deepjavalibrary/djl/pull/3683 )
- \[onnx] fix one more usage of java distribution to zulu for windows by
[@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3684](https://redirect.github.com/deepjavalibrary/djl/pull/3684 )
##### New Contributors
- [@​leleZeng](https://redirect.github.com/leleZeng ) made their
first contribution in
[#​3646](https://redirect.github.com/deepjavalibrary/djl/pull/3646 )
- [@​dwctic](https://redirect.github.com/dwctic ) made their first
contribution in
[#​3660](https://redirect.github.com/deepjavalibrary/djl/pull/3660 )
- [@​saedmanaf](https://redirect.github.com/saedmanaf ) made their
first contribution in
[#​3663](https://redirect.github.com/deepjavalibrary/djl/pull/3663 )
- [@​xinhuagu](https://redirect.github.com/xinhuagu ) made their
first contribution in
[#​3677](https://redirect.github.com/deepjavalibrary/djl/pull/3677 )
**Full Changelog**:
<https://github.com/deepjavalibrary/djl/compare/v0.32.0...v0.33.0 >
###
[`v0.32.0`](https://redirect.github.com/deepjavalibrary/djl/releases/tag/v0.32.0 ):
DJL v0.32.0 Release
[Compare
Source](https://redirect.github.com/deepjavalibrary/djl/compare/v0.31.1...v0.32.0 )
##### Key Changes
- Engine Updates
- Tokenizers updated to 0.21.0
- OnnxRuntime updated to 1.20.0
##### Enhancements
- \[pytorch] support pytorch 2.1.2 for Neuron by
[@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3542](https://redirect.github.com/deepjavalibrary/djl/pull/3542 )
- \[onnxruntime] Updates OnnxRuntime engine to 1.20.0 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3549](https://redirect.github.com/deepjavalibrary/djl/pull/3549 )
- \[tokenizers] Return detail for QA inference by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3555](https://redirect.github.com/deepjavalibrary/djl/pull/3555 )
- \[api] Allows to configure custom batchifer by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3559](https://redirect.github.com/deepjavalibrary/djl/pull/3559 )
- \[tokenizer] Updates huggingface tokenizer to 0.21.0 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3572](https://redirect.github.com/deepjavalibrary/djl/pull/3572 )
- \[tokenizers] Add int32 option to encoding by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3571](https://redirect.github.com/deepjavalibrary/djl/pull/3571 )
- \[api] Adds ZeroShotClassification support by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3579](https://redirect.github.com/deepjavalibrary/djl/pull/3579 )
- \[tokenizers] Support import zero-shot-classification to model zoo by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3580](https://redirect.github.com/deepjavalibrary/djl/pull/3580 )
- \[FASTTEXT] Adds linux-aarch64 support by
[@​iamshubhambhola](https://redirect.github.com/iamshubhambhola )
in
[#​3584](https://redirect.github.com/deepjavalibrary/djl/pull/3584 )
- Expose OnnxRuntime's getMetadata() in DJL API by
[@​VanjaRadulovic](https://redirect.github.com/VanjaRadulovic ) in
[#​3596](https://redirect.github.com/deepjavalibrary/djl/pull/3596 )
- \[api] Refactor image processing by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3588](https://redirect.github.com/deepjavalibrary/djl/pull/3588 )
- Adds zero-shot-classification to model zoo by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3589](https://redirect.github.com/deepjavalibrary/djl/pull/3589 )
- \[api] Adds Pad image transform for CV by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3593](https://redirect.github.com/deepjavalibrary/djl/pull/3593 )
##### Bug Fixes
- \[api] fix issue in Tar/Zip Utils that resulted in incorrect artifact
… by [@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3544](https://redirect.github.com/deepjavalibrary/djl/pull/3544 )
- \[tokenizer] fixes token\_classification import issues by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3570](https://redirect.github.com/deepjavalibrary/djl/pull/3570 )
- \[tokenizer] fixes trust\_remote\_code issues for DJL converter by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3569](https://redirect.github.com/deepjavalibrary/djl/pull/3569 )
- \[fix] Fix YoloV8Translator by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3575](https://redirect.github.com/deepjavalibrary/djl/pull/3575 )
- \[tokenizers] Fixes ZeroShotClassificationTranslator bug by
[@​bryanktliu](https://redirect.github.com/bryanktliu ) in
[#​3581](https://redirect.github.com/deepjavalibrary/djl/pull/3581 )
- \[xgb] Fix xgb intern to close replaced array by
[@​ewan0x79](https://redirect.github.com/ewan0x79 ) in
[#​3558](https://redirect.github.com/deepjavalibrary/djl/pull/3558 )
##### Documentation
- \[pytorch] Update supported versions of pytorch for 0.32.0 by
[@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3541](https://redirect.github.com/deepjavalibrary/djl/pull/3541 )
- Update README.md (fix typo) by
[@​paulk-asert](https://redirect.github.com/paulk-asert ) in
[#​3576](https://redirect.github.com/deepjavalibrary/djl/pull/3576 )
- Docs: (Readme) by
[@​Lubov66](https://redirect.github.com/Lubov66 ) in
[#​3577](https://redirect.github.com/deepjavalibrary/djl/pull/3577 )
##### CI/CD
- Increase build version to 0.32.0 by
[@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3540](https://redirect.github.com/deepjavalibrary/djl/pull/3540 )
- \[ci] fix ci to test windows properly by
[@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3543](https://redirect.github.com/deepjavalibrary/djl/pull/3543 )
- \[ci] adding back serving.publish to DJL by
[@​sindhuvahinis](https://redirect.github.com/sindhuvahinis ) in
[#​3551](https://redirect.github.com/deepjavalibrary/djl/pull/3551 )
- \[ci] adding back serving.publish to DJL by
[@​sindhuvahinis](https://redirect.github.com/sindhuvahinis ) in
[#​3551](https://redirect.github.com/deepjavalibrary/djl/pull/3551 )
- \[djl-convert] Remove onnxruntime from djl-convert requirements.txt by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3550](https://redirect.github.com/deepjavalibrary/djl/pull/3550 )
- \[djl-convert] Remove onnxruntime from djl-convert requirements by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3552](https://redirect.github.com/deepjavalibrary/djl/pull/3552 )
- Fixes java23 compile error by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3556](https://redirect.github.com/deepjavalibrary/djl/pull/3556 )
- \[fix]\[ci] don't compile fasttext jni for windows by
[@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3590](https://redirect.github.com/deepjavalibrary/djl/pull/3590 )
- \[ci] Upgrade gradle to 8.12 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3573](https://redirect.github.com/deepjavalibrary/djl/pull/3573 )
- \[ci]\[docs] enable debug logging for s3 commands to troubleshoot
failu… by [@​siddvenk](https://redirect.github.com/siddvenk ) in
[#​3591](https://redirect.github.com/deepjavalibrary/djl/pull/3591 )
- \[ci] Update upload-artifact action to v4 by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3594](https://redirect.github.com/deepjavalibrary/djl/pull/3594 )
- \[fix] Fix the pytorch-native ci failure by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3595](https://redirect.github.com/deepjavalibrary/djl/pull/3595 )
- \[ci] Fix nightly publish upload artifact name by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3597](https://redirect.github.com/deepjavalibrary/djl/pull/3597 )
- Implement NDArray.sub operation by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3598](https://redirect.github.com/deepjavalibrary/djl/pull/3598 )
- \[ci] Fix continuous ci failure by
[@​xyang16](https://redirect.github.com/xyang16 ) in
[#​3599](https://redirect.github.com/deepjavalibrary/djl/pull/3599 )
- \[ci] Fix ClipModelTest assertion failure by
[@​sindhuvahinis](https://redirect.github.com/sindhuvahinis ) in
[#​3602](https://redirect.github.com/deepjavalibrary/djl/pull/3602 )
##### New Contributors
- [@​paulk-asert](https://redirect.github.com/paulk-asert ) made
their first contribution in
[#​3576](https://redirect.github.com/deepjavalibrary/djl/pull/3576 )
- [@​Lubov66](https://redirect.github.com/Lubov66 ) made their
first contribution in
[#​3577](https://redirect.github.com/deepjavalibrary/djl/pull/3577 )
- [@​iamshubhambhola](https://redirect.github.com/iamshubhambhola )
made their first contribution in
[#​3584](https://redirect.github.com/deepjavalibrary/djl/pull/3584 )
- [@​VanjaRadulovic](https://redirect.github.com/VanjaRadulovic )
made their first contribution in
[#​3596](https://redirect.github.com/deepjavalibrary/djl/pull/3596 )
**Full Changelog**:
<https://github.com/deepjavalibrary/djl/compare/v0.31.1...v0.32.0 >
</details>
---
### Configuration
📅 **Schedule**: (UTC)
- Branch creation
- At any time (no schedule defined)
- Automerge
- At any time (no schedule defined)
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about these
updates again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
This PR was generated by [Mend Renovate](https://mend.io/renovate/ ).
View the [repository job
log](https://developer.mend.io/github/langchain4j/langchain4j ).
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0My4xNzMuNiIsInVwZGF0ZWRJblZlciI6IjQzLjE3My42IiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6WyJkZXBlbmRlbmNpZXMiXX0=-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
2026-05-14 12:57:35 +02:00
628ac34c01
Update versions to 1.15.0-SNAPSHOT and 1.15.0-beta25-SNAPSHOT
2026-04-30 18:43:12 +00:00
4917afa297
Release versions 1.14.0 and 1.14.0-beta24
2026-04-30 18:10:30 +00:00
4798a89d66
Update versions to 1.14.0-SNAPSHOT and 1.14.0-beta24-SNAPSHOT
2026-04-09 14:41:27 +00:00
759cd9a236
Release versions 1.13.0 and 1.13.0-beta23
2026-04-09 13:07:30 +00:00
760610c131
Add option to allow skipping embeddings model download ( #4667 )
...
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
During compilation, if the cache is not available, the embeddings model
will be downloaded, which can consume a significant amount of time or
even time out. However, in many scenarios, such as basic AIService and
Agents, they do not rely on embeddings. Therefore, it is necessary to
add an option that can be skipped to speed up compilation (the default
value of the option is to download).
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core )
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j )
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs )
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples ) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring ) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
2026-04-01 14:17:33 +02:00
e10abf04d0
Update versions to 1.13.0-SNAPSHOT and 1.13.0-beta23-SNAPSHOT ( #4710 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2026-03-13 11:39:50 +01:00
c92ea033e4
Update versions to 1.13.0-SNAPSHOT and 1.13.0-beta22-SNAPSHOT ( #4666 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2026-03-05 17:18:22 +01:00
336b2accce
Update versions to 1.12.0-SNAPSHOT and 1.12.0-beta20-SNAPSHOT ( #4537 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2026-02-04 14:27:44 +01:00
1a3ec92008
DX: added clarifying error message when in-process embedding model file is not available during local dev
...
https://github.com/langchain4j/langchain4j/pull/4069#issuecomment-3759833519
2026-01-16 16:05:01 +01:00
86b8aeb325
fix: handle empty embeddings in OnnxBertBiEncoder ( #4406 )
...
## Issue
Closes #923
## Change
Added an empty list check in the `embed()` method of `OnnxBertBiEncoder`
to prevent `IndexOutOfBoundsException` when embedding empty or
whitespace-only text.
**Root cause**: When tokenizing empty/whitespace text, the tokenizer
returns only special tokens `[CLS]` and `[SEP]`. The `partition()`
method skips these, resulting in an empty partitions list. Subsequently,
`weightedAverage()` fails when accessing `embeddings.get(0)` on an empty
list.
**Fix**: Added early validation in `embed()` to throw
`IllegalArgumentException` with a clear message before processing empty
partitions.
## General checklist
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core )
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j )
modules, and they are all green
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs )
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples ) (only for
\"big\" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring ) (if
applicable)
2026-01-12 12:22:58 +01:00
5232be05da
[BUG] Missing interrupt status restoration in InterruptedException handlers ( #4340 )
...
## Issue
Closes #4339
## Change
Restore interrupt status by calling `Thread.currentThread().interrupt()`
when catching `InterruptedException`:
- `AbstractInProcessEmbeddingModel.parallelizeEmbedding()`: Separate
`InterruptedException` from `ExecutionException`
- `JdkHttpClient.execute()`: Separate `InterruptedException` from
`IOException`
## General checklist
- [X] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core )
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j )
modules, and they are all green
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs )
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples ) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring ) (if
applicable)
2026-01-05 09:47:35 +01:00
a06ec71840
CI: retry download of embedding model files
2025-12-25 11:00:33 +01:00
778be1b360
Update versions to 1.11.0-SNAPSHOT and 1.11.0-beta19-SNAPSHOT ( #4285 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-12-24 15:38:05 +01:00
9b7e8b5a37
stabilizing CI
2025-12-15 10:06:29 +01:00
25d3b3ec87
cleaned up test dependencies
2025-12-10 10:18:30 +01:00
c3a491e0b4
Migrate in-process embedding modules into main repo ( #4179 )
...
## Change
Migrated all modules form the
https://github.com/langchain4j/langchain4j-embeddings repository into
main (this) repository.
## General checklist
- [X] There are no breaking changes (API, behaviour)
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core )
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j )
modules, and they are all green
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs )
2025-12-04 16:03:11 +01:00
github-actions[bot]