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

coderabbitai · 2025-08-11T08:08:40Z

💡 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:

Run pipenv lock (or the equivalent command) to re-resolve dependencies.

Verify that Pipfile.lock now lists transformers at >=4.53.3,<4.54.0.

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.

🧩 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!

coderabbitai · 2025-08-11T11:34:26Z

💡 Verification agent

🧩 Analysis chain

Verify hashes and dependency constraints from PyPI (optional).

Run this to confirm the two sha256 hashes exist for 4.53.3 and to inspect requires_dist matches your pinned deps:

🏁 Script executed:

#!/bin/bash set -euo pipefail VER=4.53.3 # 1) Show all available SHA256 digests for the release echo "===> Available SHA256 digests for transformers ${VER}" curl -sS https://pypi.org/pypi/transformers/${VER}/json | jq -r '.releases["'${VER}'"][] | "\(.filename) \(.digests.sha256)"' # 2) Check that the pinned hashes are present PINNED_HASHES=( "5aba81c92095806b6baf12df35d756cf23b66c356975fb2a7fa9e536138d7c75" "b2eda1a261de79b78b97f7888fe2005fc0c3fabf5dad33d52cc02983f9f675d8" ) echo "===> Verifying pinned hashes" for h in "${PINNED_HASHES[@]}"; do if curl -sS https://pypi.org/pypi/transformers/${VER}/json | jq -e --arg H "$h" '.releases["'${VER}'"][] | select(.digests.sha256==$H)' >/dev/null; then echo "OK: hash $h found" else echo "MISSING: hash $h not found"; exit 1 fi done # 3) Inspect runtime requirements for compatibility echo "===> requires_dist for transformers ${VER}" curl -sS https://pypi.org/pypi/transformers/${VER}/json | jq -r '.info.requires_dist[]' || true

Length of output: 334

Action Required: Verify transformers==4.53.3 on PyPI

The PyPI metadata query returned null for .releases["4.53.3"], which means version 4.53.3 of transformers isn’t published under that name on the default index. Please confirm whether:

You intended to pin a different released version (e.g. 4.53.2 or 4.54.0), or

The package is hosted on a custom index and needs an --extra-index-url entry.

Locations to update:

jupyter/trustyai/ubi9-python-3.11/requirements.txt lines 3002–3004

Current snippet:

-transformers==4.53.3; python_full_version >= '3.9.0' \ - --hash=sha256:5aba81c92095806b6baf12df35d756cf23b66c356975fb2a7fa9e536138d7c75 \ - --hash=sha256:b2eda1a261de79b78b97f7888fe2005fc0c3fabf5dad33d52cc02983f9f675d8

Suggested fix:

Update to an existing version on PyPI, or

Add the appropriate index URL for your private registry.

Committable suggestion skipped: line range outside the PR's diff.

🤖 Prompt for AI Agents

In jupyter/trustyai/ubi9-python-3.11/requirements.txt around lines 3002–3004, the pinned transformers==4.53.3 cannot be found on the default PyPI index; either change the version to a valid release (e.g., 4.53.2 or 4.54.0) by updating the version string, or if this version exists on a private index add the appropriate --extra-index-url (or --index-url) entry for that registry and remove or adjust the broken pin; ensure the chosen version or index is tested by running pip index versions or pip install against the file.

check again

🧩 Analysis chain
</script>

🏁 Script executed:

#!/bin/bash set -euo pipefail echo "===> Checking transformers 4.53.3 on PyPI" VER=4.53.3 # Check if the version exists and show all files echo "Fetching release information for transformers ${VER}..." RESPONSE=$(curl -sS https://pypi.org/pypi/transformers/${VER}/json 2>&1) if echo "$RESPONSE" | grep -q "Not Found"; then echo "Version ${VER} not found on PyPI" echo "" echo "===> Checking latest available versions of transformers" curl -sS https://pypi.org/pypi/transformers/json | jq -r '.releases | keys[]' | tail -20 | sort -V else echo "Version ${VER} found!" echo "" echo "===> Available files and SHA256 hashes for transformers ${VER}:" echo "$RESPONSE" | jq -r '.urls[] | "\(.filename): \(.digests.sha256)"' echo "" echo "===> Verifying pinned hashes in requirements.txt:" HASH1="5aba81c92095806b6baf12df35d756cf23b66c356975fb2a7fa9e536138d7c75" HASH2="b2eda1a261de79b78b97f7888fe2005fc0c3fabf5dad33d52cc02983f9f675d8" for hash in $HASH1 $HASH2; do if echo "$RESPONSE" | jq -e --arg H "$hash" '.urls[] | select(.digests.sha256==$H)' > /dev/null 2>&1; then FILENAME=$(echo "$RESPONSE" | jq -r --arg H "$hash" '.urls[] | select(.digests.sha256==$H) | .filename') echo "✓ Hash $hash matches file: $FILENAME" else echo "✗ Hash $hash NOT found in PyPI release" fi done echo "" echo "===> Package metadata:" echo "$RESPONSE" | jq -r '.info | {version: .version, requires_python: .requires_python, summary: .summary}' fi

Length of output: 269516

@jiridanek Confirmed. transformers 4.53.3 is on PyPI and the pinned hashes match:

Wheel: transformers-4.53.3-py3-none-any.whl sha256=5aba81c92095806b6baf12df35d756cf23b66c356975fb2a7fa9e536138d7c75

sdist: transformers-4.53.3.tar.gz sha256=b2eda1a261de79b78b97f7888fe2005fc0c3fabf5dad33d52cc02983f9f675d8

Also sanity-checked requires_dist vs our env:

tokenizers 0.21.4 satisfies <0.22,>=0.21

huggingface-hub 0.34.4 satisfies <1.0,>=0.30.0

torch 2.6.0+cu126 satisfies >=2.1

Pillow 11.3.0 satisfies >=10.0.1 and <=15.0

Python >=3.9 satisfied

No changes needed; the requirements entry is correct.

🧠 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#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#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#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#1333 File: runtimes/datascience/ubi9-python-3.12/Pipfile:33-34 Timestamp: 2025-07-08T19:26:17.140Z Learning: jiridanek requested GitHub issue creation for jupyter-client dependency pinning inconsistency during PR #1333 review, specifically asking to note the implications of breaking changes in 9.x versions. Issue #1343 was created with comprehensive problem description covering inconsistent pinning style across all Python 3.12 runtime images, detailed breaking changes analysis (kernel protocol, session management, connection security, API changes, async/await modifications), reproducibility and security impact assessment, multiple solution options with code examples, phased acceptance criteria, implementation guidance, testing approach, and proper context linking, continuing the established pattern of systematic code quality improvements through detailed issue tracking.

Learnt from: jiridanek PR: opendatahub-io/notebooks#1333 File: runtimes/minimal/ubi9-python-3.12/Pipfile:23-27 Timestamp: 2025-07-09T08:12:05.822Z Learning: jiridanek corrected CodeRabbit's false positive about urllib3/requests version incompatibility in PR #1333 review. Investigation revealed that requests 2.32.3 actually requires `urllib3<3,>=1.21.1` (not `urllib3<2` as incorrectly stated), making urllib3 2.5.0 perfectly compatible. This demonstrates the importance of verifying technical assessments against actual build results and PyPI metadata before creating issues.

Learnt from: jiridanek PR: opendatahub-io/notebooks#1333 File: runtimes/minimal/ubi9-python-3.12/Pipfile:23-27 Timestamp: 2025-07-09T08:12:05.822Z Learning: jiridanek corrected CodeRabbit's false positive about urllib3/requests version incompatibility in PR #1333 review. Investigation revealed that requests 2.32.3 actually requires `urllib3<3,>=1.21.1` (not `urllib3<2` as incorrectly stated), making urllib3 2.5.0 perfectly compatible. This demonstrates the importance of verifying technical assessments against actual build results and PyPI metadata before creating issues.

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#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#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#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#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.

Learnt from: jiridanek PR: opendatahub-io/notebooks#0 File: :0-0 Timestamp: 2025-07-11T11:16:05.131Z Learning: jiridanek requested GitHub issue creation for RStudio py311 Tekton push pipelines during PR #1379 review. Issue #1384 was successfully created covering two RStudio variants (CPU and CUDA) found in manifests/base/params-latest.env, with comprehensive problem description, implementation requirements following the same pattern as other workbench pipelines, clear 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#0 File: :0-0 Timestamp: 2025-08-05T17:24:08.616Z Learning: jiridanek requested PR review for #1521 covering s390x architecture support improvements, demonstrating continued focus on systematic multi-architecture compatibility enhancements in the opendatahub-io/notebooks repository through clean implementation with centralized configuration, proper CI integration, and architecture-aware testing patterns.

Learnt from: jiridanek PR: opendatahub-io/notebooks#1306 File: jupyter/trustyai/ubi9-python-3.12/test/test_notebook.ipynb:71-88 Timestamp: 2025-07-04T06:05:30.580Z Learning: jiridanek requested GitHub issue creation for TrustyAI test notebook URL configurability and network error handling improvements during PR #1306 review. Issue #1323 was created with ⚠️ emoji in title for visibility, comprehensive problem description covering incorrect hardcoded URLs (pointing to Python 3.11 instead of 3.12), missing network error handling, maintenance burden, multiple solution options with code examples, phased acceptance criteria, implementation guidance, testing approach, and proper context linking, continuing the established pattern of systematic code quality improvements through detailed issue tracking.

-Original file 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"
     datasets = "~=3.4.1"
     accelerate = "~=1.5.2"
     trustyai = "~=0.6.1"
@@ Expand Down @@

-Original file line number
+Diff line change
@@ Expand Up / @@ -2999,9 +2999,9 @@ tqdm==4.67.1; python_version >= '3.7' \ @@
     traitlets==5.14.3; python_version >= '3.8' \
         --hash=sha256:9ed0579d3502c94b4b3732ac120375cda96f923114522847de4b3bb98b96b6b7 \
         --hash=sha256:b74e89e397b1ed28cc831db7aea759ba6640cb3de13090ca145426688ff1ac4f
-    transformers==4.52.4; python_full_version >= '3.9.0' \
-        --hash=sha256:203f5c19416d5877e36e88633943761719538a25d9775977a24fe77a1e5adfc7 \
-        --hash=sha256:aff3764441c1adc192a08dba49740d3cbbcb72d850586075aed6bd89b98203e6
+    transformers==4.53.3; python_full_version >= '3.9.0' \
+        --hash=sha256:5aba81c92095806b6baf12df35d756cf23b66c356975fb2a7fa9e536138d7c75 \
+        --hash=sha256:b2eda1a261de79b78b97f7888fe2005fc0c3fabf5dad33d52cc02983f9f675d8
     triton==3.2.0; platform_system == 'Linux' and platform_machine == 'x86_64' \
         --hash=sha256:30ceed0eff2c4a73b14eb63e052992f44bbdf175f3fad21e1ac8097a772de7ee \
         --hash=sha256:8009a1fb093ee8546495e96731336a33fb8856a38e45bb4ab6affd6dbc3ba220 \
@@ Expand Down @@

-Original file 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 @@

-Original file line number
+Diff line change
@@ Expand Up / @@ -3040,9 +3040,9 @@ tqdm==4.67.1; python_version >= '3.7' \ @@
     traitlets==5.14.3; python_version >= '3.8' \
         --hash=sha256:9ed0579d3502c94b4b3732ac120375cda96f923114522847de4b3bb98b96b6b7 \
         --hash=sha256:b74e89e397b1ed28cc831db7aea759ba6640cb3de13090ca145426688ff1ac4f
-    transformers==4.52.4; python_full_version >= '3.9.0' \
-        --hash=sha256:203f5c19416d5877e36e88633943761719538a25d9775977a24fe77a1e5adfc7 \
-        --hash=sha256:aff3764441c1adc192a08dba49740d3cbbcb72d850586075aed6bd89b98203e6
+    transformers==4.55.0; python_full_version >= '3.9.0' \
+        --hash=sha256:15aa138a05d07a15b30d191ea2c45e23061ebf9fcc928a1318e03fe2234f3ae1 \
+        --hash=sha256:29d9b8800e32a4a831bb16efb5f762f6a9742fef9fce5d693ed018d19b106490
     triton==3.2.0; platform_system == 'Linux' and platform_machine == 'x86_64' \
         --hash=sha256:30ceed0eff2c4a73b14eb63e052992f44bbdf175f3fad21e1ac8097a772de7ee \
         --hash=sha256:8009a1fb093ee8546495e96731336a33fb8856a38e45bb4ab6affd6dbc3ba220 \
@@ Expand Down @@

-Original file 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 @@

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

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

Uh oh!

Diff view

Diff view

There are no files selected for viewing

coderabbitai bot Aug 11, 2025 •

edited

Loading

Uh oh!

jiridanek Aug 11, 2025

Uh oh!

coderabbitai bot Aug 11, 2025

Uh oh!

Uh oh!

coderabbitai bot Aug 11, 2025 •

edited

Loading

Uh oh!

jiridanek Aug 11, 2025

Uh oh!

coderabbitai bot Aug 11, 2025

Uh oh!

Uh oh!

Uh oh!

Uh oh!

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

Uh oh!

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

Uh oh!

Uh oh!

Diff view

Diff view

There are no files selected for viewing

coderabbitai bot Aug 11, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

jiridanek Aug 11, 2025

Choose a reason for hiding this comment

Uh oh!

coderabbitai bot Aug 11, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

coderabbitai bot Aug 11, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

jiridanek Aug 11, 2025

Choose a reason for hiding this comment

Uh oh!

coderabbitai bot Aug 11, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

coderabbitai bot Aug 11, 2025 •

edited

Loading

coderabbitai bot Aug 11, 2025 •

edited

Loading