Bump sentence-transformers from 5.1.1 to 5.1.2 in /backend-agent

[dependabot]

Bumps sentence-transformers from 5.1.1 to 5.1.2.

Release notes

Sourced from sentence-transformers's releases.

v5.1.2 - Sentence Transformers joins Hugging Face; model saving/loading improvements and loss compatibility

This patch celebrates the transition of Sentence Transformers to Hugging Face, and improves model saving, loading defaults, and loss compatibilities.

Install this version with

# Training + Inference
pip install sentence-transformers[train]==5.1.2
Inference only, use one of:
pip install sentence-transformers==5.1.2
pip install sentence-transformers[onnx-gpu]==5.1.2
pip install sentence-transformers[onnx]==5.1.2
pip install sentence-transformers[openvino]==5.1.2

Sentence Transformers is joining Hugging Face!

Today, Sentence Transformers is moving from the Ubiquitous Knowledge Processing (UKP) Lab at Technische Universität Darmstadt to Hugging Face. This formalizes the existing maintenance structure, as Tom Aarsen (that's me!) from Hugging Face has been maintaining the project for the past two years. The project's development roadmap, license, support, and commitment to the community remain unchanged. Read the full announcement for more details!

Minor changes re. saving and loading

• Improve saving models with StaticEmbedding (#3524) and Dense (#3528) modules.
• Fix training with CPU when "stronger" devices (CUDA, MPS) are available (#3525)
• Default to 'xpu' device over 'cpu' if the former is available (#3537)

Minor changes re. losses

• Change errors/warnings for MatryoshkaLoss to prevent easy-to-make mistakes, e.g. forgetting to use the original dimension (#3530)
• Introduce compatibility between MSELoss and MatryoshkaLoss (#3538)
• Also use mini-batches for positives with MegaBatchMarginLoss (#3550)

All Changes

• fix: static model saving fails because weights are not contiguous by @​stephantul in UKPLab/sentence-transformers#3524
• bug: fix state bug in trainer by @​stephantul in UKPLab/sentence-transformers#3525
• [fix] Patch Router training with Cached losses by @​tomaarsen in UKPLab/sentence-transformers#3527
• [fix] Allow loading Dense modules not saved in fp32 by @​tomaarsen in UKPLab/sentence-transformers#3528
• [tests] Patch Regex expected output for Python 3.9 by @​tomaarsen in UKPLab/sentence-transformers#3529
• Future-proof tests for upcoming transformers version by @​tomaarsen in UKPLab/sentence-transformers#3533
• feat: matryoshka dims bounds checks and warning by @​stephantul in UKPLab/sentence-transformers#3530
• Performance table format and Few markdownlint error correction by @​kaushikacharya in UKPLab/sentence-transformers#3534
• fix typos: inaccuracte -> inaccurate by @​whybe-choi in UKPLab/sentence-transformers#3542
• [fix] correct dataset link in training scripts by @​thomasht86 in UKPLab/sentence-transformers#3543
• [fix] Allow MatryoshkaLoss with MSELoss by @​tomaarsen in UKPLab/sentence-transformers#3538
• [docs] Format all markdown using mdformat by @​tomaarsen in UKPLab/sentence-transformers#3539
• feat: provide support for python 3.13 by @​lordoffreaks in UKPLab/sentence-transformers#3551
• Update MTEB docs to v2 by @​KennethEnevoldsen in UKPLab/sentence-transformers#3548
• Add support for Intel 'xpu' device in environment.py by @​domschl in UKPLab/sentence-transformers#3537
• docs: Update project metadata by @​tomaarsen in huggingface/sentence-transformers#3553
• MegaBatchMarginLoss use mini batches for positives too by @​benHeid in huggingface/sentence-transformers#3550

... (truncated)

Commits

• dfcbbd9 Release v5.1.2
• 9cfa9ad Merge branch 'master' into v5.1-release
• 85ec645 MegaBatchMarginLoss use mini batches for positives too (#3550)
• 8e4c85b docs: Update project metadata (#3553)
• 2220062 Add support for Intel 'xpu' device in environment.py (#3537)
• 315a67d Update MTEB docs to v2 (#3548)
• 471387e chore: add python 3.13 to CI and classifiers (#3551)
• 77ae248 docs: Format all markdown using mdformat (#3539)
• b84cc32 [fix] Allow MatryoshkaLoss with MSELoss (#3538)
• 051ce1a Correct link in example training scripts (#3543)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[github-actions]

The change in the pyproject.toml file involves updating the version of the sentence-transformers package from version 5.1.1 to 5.1.2. This is a minor version update, likely to include bug fixes, minor improvements, or optimizations while maintaining backward compatibility.

Walkthrough

• Chore: Updated sentence-transformers from version 5.1.1 to 5.1.2, which might include minor bug fixes or improvements aimed at enhancing the user experience or performance without introducing breaking changes. Users can benefit from a potentially more stable and efficient library.

_{Model: gpt-4o | Prompt Tokens: 300 | Completion Tokens: 128}

[github-actions]

Here's a thoughtful code review enhanced with AI assistance. These suggestions offer potential improvements and insights to consider, though they're recommendations rather than requirements. You have full control over which feedback to incorporate into your work. The AI tools simply provide additional perspective to support your decision-making process and help identify opportunities for enhancement.

---

Always critique what AI says. Do not let AI replace YOUR I.
_{Model: anthropic--claude-4-sonnet | Prompt Tokens: 856 | Completion Tokens: 254}

[github-actions]

Good practice updating the sentence-transformers dependency to the latest patch version. However, consider documenting the reason for this version bump in your commit message or changelog. You may also want to verify that this version update doesn't introduce any breaking changes by running your test suite.

For better dependency management, consider using version ranges instead of pinning exact versions for patch updates:

'sentence-transformers>=5.1.1,<5.2.0',

This allows automatic patch updates while preventing potentially breaking minor version changes.