Remove BAM provider and ibm-generative-ai dependency

[harche]

Summary

• Removes the BAM (Big AI Model) provider and its ibm-generative-ai dependency
• ibm-generative-ai was archived by IBM on March 7, 2025 with no releases since May 2024
• It pins httpx<0.28, which blocks adoption of modern Google Cloud SDKs (langchain-google-vertexai, google-genai, google-cloud-aiplatform) that require httpx>=0.28
• BAM was IBM Research's internal LLM playground, superseded by WatsonX (already supported via ibm-watsonx-ai)
• BAM was marked "not officially supported" in this project since August 2024 (PR Info: BAM is not officially supported #1418)

Motivation

Removing ibm-generative-ai unpins httpx<0.28, which enables adding support for:

• Google Vertex AI with Gemini models (langchain-google-vertexai)
• Other Google Cloud AI services that require httpx>=0.28

See PR #2824 for context on the dependency conflict.

Changes

• Deleted ols/src/llms/providers/bam.py and tests/unit/llms/providers/test_bam.py
• Removed PROVIDER_BAM, BAMConfig, BAMParameters, BAMParametersMapping from constants, config, and provider modules
• Removed parse_bam_error() from error parsing
• Removed ibm-generative-ai from pyproject.toml and regenerated requirements.txt
• Updated all test configs that used type: bam to type: openai
• Deleted BAM-specific test config files (valid_config_with_bam.yaml, valid_config_with_bam_2.yaml)
• Updated UML diagrams and provider docs

Test plan

• All 868 unit tests pass
• Ruff linting clean
• MyPy type checking clean
• CI pipeline validation

🤖 Generated with Claude Code

[openshift-ci]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by:
Once this PR has been reviewed and has the lgtm label, please assign onmete for approval. For more information see the Code Review Process.

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[openshift-ci]

@harche: The following tests failed, say /retest to rerun all failed tests or /retest-required to rerun all mandatory failed tests:

Test name	Commit	Details	Required	Rerun command
ci/prow/integration	18fd72d	link	true	/test integration
ci/prow/unit	18fd72d	link	true	/test unit

Full PR test history. Your PR dashboard.

Details

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. I understand the commands that are listed here.