Skip to content

RHAIENG-540: build(deps): bump transformers from 4.52.4 to 4.53.0 in /jupyter/trustyai/ubi9-python-3.11 and to 4.55.0 in the 3.12 version of workbench #1755

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Aug 11, 2025
Merged

RHAIENG-540: build(deps): bump transformers from 4.52.4 to 4.53.0 in /jupyter/trustyai/ubi9-python-3.11 and to 4.55.0 in the 3.12 version of workbench #1755

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
64186ad
build(deps): bump transformers in /jupyter/trustyai/ubi9-python-3.12
dependabot[bot] Aug 8, 2025
531d713
NO-JIRA: bump `Transformers` dependency across Pipfiles and manifests…
jiridanek Aug 11, 2025
d4400d5
Update Pipfile.lock for Python 3.11
github-actions[bot] Aug 11, 2025
e3909ac
Update Pipfile.lock for Python 3.12
github-actions[bot] Aug 11, 2025
19686aa
Update Pipfile.lock for Python 3.11
github-actions[bot] Aug 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion jupyter/trustyai/ubi9-python-3.11/Pipfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ torch = {version = "==2.6.0+cu126", index = "pytorch"}
# More information available at:
# - https://pypi.org/project/trustyai/
# - https://github.com/trustyai-explainability/trustyai-explainability-python/blob/main/requirements.txt
transformers = "~=4.52.1"
transformers = "~=4.53.3"
Copy link
Contributor

@coderabbitai coderabbitai bot Aug 11, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Verification agent

🧩 Analysis chain

Transformers bump to ~=4.53.3 looks good and matches imagestream (major.minor 4.53).

Aligned with project conventions and prior TrustyAI assessments; no obvious compatibility flags with Torch 2.6.0. Ensure lockfile and build reflect this.

Run to verify consistency across Pipfile.lock and imagestream:

🏁 Script executed:

#!/bin/bash
set -euo pipefail

echo "Pipfile pin:"
sed -n '1,80p' jupyter/trustyai/ubi9-python-3.11/Pipfile | rg '^\s*transformers\s*=' -n

echo "Pipfile.lock resolved version:"
jq -r '.default.transformers.version // .develop.transformers.version' jupyter/trustyai/ubi9-python-3.11/Pipfile.lock

echo "Imagestream (base) N tag shows major.minor 4.53:"
rg -n 'opendatahub.io/notebook-python-dependencies' -n manifests/base/jupyter-trustyai-notebook-imagestream.yaml -A 40 | rg -n '"Transformers", "version": "4\.53"'

Length of output: 704

Fix Pipfile.lock to Resolve Transformers Bump

The Pipfile correctly pins transformers = "~=4.53.3", and the imagestream manifest shows the expected major.minor 4.53. However, your Pipfile.lock is still resolving Transformers to ==4.52.4. Please update the lockfile so it reflects the bump to 4.53.x.

• Pipfile (line 20):
transformers = "~=4.53.3"
• Pipfile.lock (currently):
default.transformers.version == 4.52.4
• Imagestream manifest (manifests/base/jupyter-trustyai-notebook-imagestream.yaml):
{"name": "Transformers", "version": "4.53"},

Action required:

  1. Run pipenv lock (or the equivalent command) to re-resolve dependencies.
  2. Verify that Pipfile.lock now lists transformers at >=4.53.3,<4.54.0.
  3. Commit the updated Pipfile.lock.

This will ensure your build and deployments use the intended Transformers version.

🤖 Prompt for AI Agents 
In jupyter/trustyai/ubi9-python-3.11/Pipfile around line 20 the Pipfile pins
transformers = "~=4.53.3" but Pipfile.lock still resolves transformers to
==4.52.4; run pipenv lock (or equivalent, e.g., pipenv lock --clear) in the
project root to re-resolve dependencies so Pipfile.lock lists transformers with
a version range >=4.53.3,<4.54.0 (or exact resolved 4.53.x), verify the updated
Pipfile.lock entry under [default] shows the correct version, and commit the
updated Pipfile.lock file.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

recheck

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
set -euo pipefail

echo "=== Checking transformers version in Pipfile ==="
grep -n "transformers" jupyter/trustyai/ubi9-python-3.11/Pipfile

echo -e "\n=== Checking transformers version in Pipfile.lock ==="
if [ -f "jupyter/trustyai/ubi9-python-3.11/Pipfile.lock" ]; then
    jq -r '.default.transformers.version // "transformers not found in default"' jupyter/trustyai/ubi9-python-3.11/Pipfile.lock
else
    echo "Pipfile.lock not found"
fi

echo -e "\n=== Checking imagestream manifest for transformers version ==="
grep -A1 -B1 '"Transformers"' manifests/base/jupyter-trustyai-notebook-imagestream.yaml | grep -E '"version":|"Transformers"' || echo "Transformers entry not found"

Length of output: 1130

@jiridanek Good news! The Pipfile.lock has been properly updated. All versions are now correctly aligned:

• Pipfile (line 20): transformers = "~=4.53.3"
• Pipfile.lock: transformers == 4.53.3 ✓
• Imagestream manifest (N-version): Transformers 4.53 ✓

The transformers dependency is now consistently at version 4.53.3 across all configuration files. The issue I previously flagged has been resolved.

🧠 Learnings used 
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1463
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:17-17
Timestamp: 2025-07-23T10:08:02.999Z
Learning: jiridanek made an informed decision to proceed with transformers ~=4.52.1 (resolving to 4.52.4) during PR #1463 review, acknowledging potential regressions in 4.52.2-4.52.3 but assessing that they're likely fixed in 4.52.4 and/or won't manifest with PyTorch 2.6. This demonstrates his balanced approach to risk assessment, weighing security fixes against potential compatibility issues while considering his specific environment configuration.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1127
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:20-20
Timestamp: 2025-06-27T07:49:01.198Z
Learning: jiridanek reviewed the transformers v4.50.0 release notes and assessed that the changes are minimal and unlikely to cause TrustyAI integration problems, indicating the actual changelog contained mostly bug fixes and minor additions rather than breaking changes.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-07-24T12:01:45.188Z
Learning: jiridanek requested verification of 2024.2 tag package versions against corresponding Pipfiles during PR #1496 review. The analysis revealed that 2024.2 tags contain intentionally frozen older versions (N-1 behavior) while the current PR correctly updates only the N (latest) tags to match Python 3.11 Pipfiles, demonstrating proper understanding of the repository's N-1 version freezing policy.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#968
File: runtimes/rocm-tensorflow/ubi9-python-3.12/Dockerfile.rocm:17-18
Timestamp: 2025-08-06T15:33:47.175Z
Learning: During PR #968 review, CodeRabbit initially incorrectly identified 1 legitimate micropipenv usage in jupyter/tensorflow/ubi9-python-3.12/Dockerfile.cuda when analyzing Python 3.12 images for unused dependencies. Upon jiridanek's request for re-verification, comprehensive analysis revealed all 15 Python 3.12 Dockerfiles install micropipenv but none actually use it, making the cleanup scope 100% unnecessary installations with no exceptions to handle.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1306
File: jupyter/trustyai/ubi9-python-3.12/kustomize/base/kustomization.yaml:8-12
Timestamp: 2025-07-08T19:09:48.746Z
Learning: jiridanek requested GitHub issue creation for misleading CUDA prefix in TrustyAI image tags during PR #1306 review, affecting both Python 3.11 and 3.12 versions. Issue #1338 was created with comprehensive problem description covering both affected images, repository pattern analysis comparing correct vs incorrect naming conventions, clear solution with code examples, detailed acceptance criteria, and proper context linking, continuing the established pattern of systematic code quality improvements through detailed issue tracking.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1325
File: jupyter/pytorch/ubi9-python-3.12/Pipfile:42-42
Timestamp: 2025-07-09T14:22:14.553Z
Learning: jiridanek requested GitHub issue creation for Pipfile.lock verification script implementation during PR #1325 review, specifically to systematize the manual verification process for dependency version consistency across all lock files using jq. Issue #1367 was created with comprehensive problem description covering manual verification challenges, detailed solution with jq-based verification script, enhanced features for CI integration, clear acceptance criteria, implementation areas breakdown, benefits analysis, and proper context linking, continuing the established pattern of systematic code quality improvements through detailed issue tracking.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1306
File: jupyter/trustyai/ubi9-python-3.12/kustomize/base/kustomization.yaml:8-12
Timestamp: 2025-07-08T19:09:48.746Z
Learning: jiridanek requested GitHub issue creation for misleading CUDA prefix in TrustyAI image tags during PR #1306 review. Issue was created with comprehensive problem description covering both Python 3.11 and 3.12 versions, repository pattern analysis showing correct vs incorrect naming, clear solution with code examples, detailed acceptance criteria, and proper context linking, continuing the established pattern of systematic code quality improvements through detailed issue tracking.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1127
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:20-20
Timestamp: 2025-06-27T07:49:01.198Z
Learning: Transformers v4.50.0 contains only non-breaking changes including documentation redesign, repository maintenance, performance enhancements, and bug fixes, with no API changes that would affect TrustyAI integration.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1379
File: .tekton/odh-workbench-jupyter-datascience-cpu-py312-ubi9-push.yaml:14-17
Timestamp: 2025-07-11T11:15:47.424Z
Learning: jiridanek requested GitHub issue creation for CEL filter problem in datascience workbench Tekton pipelines during PR #1379 review. Issue #1383 was successfully created with comprehensive problem description covering both Python 3.11 and 3.12 pipelines incorrectly watching jupyter/minimal directories instead of jupyter/datascience directories, detailed impact analysis of pipeline execution failures, complete solution with before/after code examples, thorough acceptance criteria for path updates and pipeline triggering verification, implementation notes about repository structure alignment, and proper context linking, continuing the established pattern of systematic code quality improvements through detailed issue tracking.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1591
File: codeserver/ubi9-python-3.11/Pipfile.lock:1-1
Timestamp: 2025-08-01T16:03:18.732Z
Learning: jiridanek requested GitHub issue creation for Keras 3 / TensorFlow API compatibility problem during PR #1591 review. Issue #1594 was successfully created with comprehensive problem description covering API confusion between standalone keras==3.11.1 and tf.keras bundled with tensorflow==2.18.1, multiple solution options (remove standalone Keras, set KERAS_BACKEND, or documentation), clear acceptance criteria, affected files analysis, and proper context linking, continuing the established pattern of systematic code quality improvements through detailed issue tracking.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1259
File: jupyter/rocm/tensorflow/ubi9-python-3.12/kustomize/base/service.yaml:5-15
Timestamp: 2025-07-02T18:59:15.788Z
Learning: jiridanek creates targeted GitHub issues for specific test quality improvements identified during PR reviews in opendatahub-io/notebooks. Issue #1268 demonstrates this by converting a review comment about insufficient tf2onnx conversion test validation into a comprehensive improvement plan with clear acceptance criteria, code examples, and ROCm-specific context.

Learnt from: jiridanek
PR: opendatahub-io/notebooks#1333
File: runtimes/rocm-tensorflow/ubi9-python-3.12/Pipfile:13-15
Timestamp: 2025-07-09T08:07:24.937Z
Learning: jiridanek requested GitHub issue creation for tensorflow_rocm Python 3.12 compatibility problem during PR #1333 review. Issue #1354 was successfully created with comprehensive problem description covering missing cp312 wheels causing build failures, three solution options (upstream TensorFlow, Python 3.11 only, custom build), clear acceptance criteria, and proper context linking, continuing the established pattern of systematic code quality improvements through detailed issue tracking.

If you found this review helpful, would you consider giving us a shout-out on X?

Thank you for using CodeRabbit!

datasets = "~=3.4.1"
accelerate = "~=1.5.2"
trustyai = "~=0.6.1"
Expand Down
2 changes: 1 addition & 1 deletion jupyter/trustyai/ubi9-python-3.12/Pipfile
100755 → 100644
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ torch = {version = "==2.6.0+cu126", index = "pytorch"}
# More information available at:
# - https://pypi.org/project/trustyai/
# - https://github.com/trustyai-explainability/trustyai-explainability-python/blob/main/requirements.txt
transformers = "~=4.52.1"
transformers = "~=4.55.0"
datasets = "~=3.4.1"
accelerate = "~=1.5.2"
trustyai = "~=0.6.2"
Expand Down
8 changes: 4 additions & 4 deletions jupyter/trustyai/ubi9-python-3.12/Pipfile.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion manifests/base/jupyter-trustyai-notebook-imagestream.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ spec:
[
{"name": "JupyterLab","version": "4.4"},
{"name": "TrustyAI", "version": "0.6"},
{"name": "Transformers", "version": "4.50"},
{"name": "Transformers", "version": "4.53"},
{"name": "Datasets", "version": "3.4"},
{"name": "Accelerate", "version": "1.5"},
{"name": "Torch", "version": "2.6"},
Expand Down
2 changes: 1 addition & 1 deletion manifests/overlays/additional/jupyter-trustyai-cpu-py312-ubi9-imagestream.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ spec:
[
{"name": "JupyterLab","version": "4.4"},
{"name": "TrustyAI", "version": "0.6"},
{"name": "Transformers", "version": "4.52"},
{"name": "Transformers", "version": "4.55"},
{"name": "Datasets", "version": "3.4"},
{"name": "Accelerate", "version": "1.5"},
{"name": "Torch", "version": "2.6"},
Expand Down
Loading