Bump sentence-transformers from 5.1.0 to 5.1.1 in /backend-agent

[dependabot]

Bumps sentence-transformers from 5.1.0 to 5.1.1.

Release notes

Sourced from sentence-transformers's releases.

v5.1.1 - Explicit incorrect arguments, fixes for multi-GPU, evaluator, and hard negative

This patch makes Sentence Transformers more explicit with incorrect arguments and introduces some fixes for multi-GPU processing, evaluators, and hard negatives mining.

Install this version with

# Training + Inference
pip install sentence-transformers[train]==5.1.1
Inference only, use one of:
pip install sentence-transformers==5.1.1
pip install sentence-transformers[onnx-gpu]==5.1.1
pip install sentence-transformers[onnx]==5.1.1
pip install sentence-transformers[openvino]==5.1.1

Error if unused kwargs is passed & get_model_kwargs (#3500)

Some SentenceTransformer or SparseEncoder models support custom model-specific keyword arguments, such as jinaai/jina-embeddings-v4. As of this release, calling model.encode with keyword arguments that aren't used by the model will result in an error.

>>> from sentence_transformers import SentenceTransformer
>>> model = SentenceTransformer("all-MiniLM-L6-v2")
>>> model.encode("Who is Amelia Earhart?", normalize=True)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "[sic]/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "[sic]/SentenceTransformer.py", line 983, in encode
    raise ValueError(
ValueError: SentenceTransformer.encode() has been called with additional keyword arguments that this model does not use: ['normalize']. As per SentenceTransformer.get_model_kwargs(), this model does not accept any additional keyword arguments.

Quite useful when you, for example, accidentally forget that the parameter to get normalized embeddings is normalize_embeddings. Prior to this version, this parameter would simply quietly be ignored.

To check which custom extra keyword arguments may be used for your model, you can call the new get_model_kwargs method:

>>> from sentence_transformers import SentenceTransformer, SparseEncoder
>>> SentenceTransformer("all-MiniLM-L6-v2").get_model_kwargs()
[]
>>> SentenceTransformer("jinaai/jina-embeddings-v4", trust_remote_code=True).get_model_kwargs()
['task', 'truncate_dim']
>>> SparseEncoder("opensearch-project/opensearch-neural-sparse-encoding-doc-v3-distill").get_model_kwargs()
['task']

Note: You can always pass the task parameter, it's the only model-specific parameter that will be quietly ignored. This means that you can always use model.encode(..., task="query") and model.encode(..., task="document").

Minor Features

... (truncated)

Commits

• 22ff509 Release v5.1.1
• 5ad8a44 Merge branch 'master' into v5.1-release
• 1def8d3 Fix the number of missing negatives in mine_hard_negatives (#3504)
• 2e077fb fix: add makedirs to informationretrievalevaluator (#3516)
• 20c4820 Fix:Import SentenceTransformer class explicitly in losses module (#3521)
• 7240b33 [feat] add get_model_kwargs method; throw error if unused kwarg is passed (...
• 560cc33 always pass input_ids, attention_mask, token_type_ids, inputs_embeds ...
• bd91098 Update rasyosef/splade-mini MSMARCO and BEIR-13 benchmark scores in pretraine...
• ad8d27d Add Support for Knowledgeable Passage Retriever (KPR) (#3495)
• 5b18f36 [feat] Use encode_document and encode_query in mine_hard_negatives (#3502)
• 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]

This change updates the version of the sentence-transformers package from 5.1.0 to 5.1.1 in the pyproject.toml configuration file. This adjustment likely includes bug fixes or minor improvements provided in the newer version.

Walkthrough

• Bug Fix: Updated sentence-transformers to version 5.1.1 to utilize the latest improvements and corrections, enhancing the stability and performance of text embedding functionalities.

_{Model: gpt-4o | Prompt Tokens: 300 | Completion Tokens: 95}

[github-actions]

Here's a collaborative code review enhanced by AI insights. These suggestions are possibilities rather than certainties, so please choose what resonates with your goals. You remain the expert making the final decisions—AI simply offers additional perspective to support your work.

---

Always critique what AI says. Do not let AI replace YOUR I.
_{Model: anthropic--claude-4-sonnet | Prompt Tokens: 856 | Completion Tokens: 211}

[github-actions]

Consider using version ranges instead of pinning exact versions for patch updates. This allows for automatic security patches and bug fixes while maintaining compatibility:

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

Alternatively, if you must pin exact versions, consider adding a comment explaining why this specific version is required (e.g., compatibility issues, specific bug fixes).

[marcorosa]

@dependabot rebase

[dependabot]

OK, I won't notify you again about this release, but will get in touch when a new version is available. If you'd rather skip all updates until the next major or minor version, let me know by commenting @dependabot ignore this major version or @dependabot ignore this minor version. You can also ignore all major, minor, or patch releases for a dependency by adding an ignore condition with the desired update_types to your config file.

If you change your mind, just re-open this PR and I'll resolve any conflicts on it.

[github-actions]

The changes primarily focus on updating a dependency within the pyproject.toml file, incrementing the version of the sentence-transformers library from 5.1.0 to 5.1.1. This enhancement suggests improvements or bug fixes in the third-party library, aiming for better performance, stability, or features provided by the external dependency.

Walkthrough

• Chore: Updated the version of the sentence-transformers library from 5.1.0 to 5.1.1, ensuring that the project utilizes the latest minor improvements or fixes implemented in the library. This update could result in performance enhancements or bug fixes that positively impact functionalities relying on this library.

_{Model: gpt-4o | Prompt Tokens: 300 | Completion Tokens: 146}

[github-actions]

Here's a supportive code review enhanced with AI assistance. These observations offer helpful suggestions and insights, though some are AI-generated predictions rather than definitive conclusions. Please consider what feels most valuable for your project. You remain the expert on your code—AI simply provides additional perspective to support your development process.

---

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]

Consider adding a comment explaining the reason for this version bump from 5.1.0 to 5.1.1. This helps with maintenance and understanding why specific versions are pinned. For example:

# Updated to 5.1.1 to fix compatibility issue with transformers library
'sentence-transformers==5.1.1',

Also, consider whether you need to pin to exact versions (==) or if you could use compatible release specifiers (~=) to allow patch updates automatically while maintaining compatibility.