Skip to content

test(vision): activate Ollama vision e2e once granite-vision-4.1 lands on Ollama #1187

Description

@planetf1

Context

PR #1185 fixes the failing Ollama vision tests by splitting them into two tiers:

  1. Structural payload tests — mocked unit tests that verify mellea correctly embeds ImageBlock instances into the Ollama conversation payload. These run in CI and locally with no vision model required.
  2. Dormant live e2e tests — a thin round-trip smoke test that is currently skipped because no current-generation Granite vision model runs on Ollama yet.

What needs to happen

granite-vision-4.1 (ibm-granite/granite-vision-4.1-4b) is the current Granite vision model. It is not yet in the Ollama library (ollama.com/library/granite-vision-4.1 → 404). When it lands, the dormant tests in test/backends/test_vision_ollama.py should be activated.

Activation steps

  1. Verify ollama pull granite-vision-4.1 works.
  2. In test/backends/test_vision_ollama.py:
    • Remove the pytest.skip(...) call from the vision_session fixture.
    • Remove this tracking comment.
  3. Add granite-vision-4.1 to the CI model-pull step in .github/workflows/quality.yml so the e2e tests run in CI.
  4. Optionally add IBM_GRANITE_VISION_4_1_4B to mellea/backends/model_ids.py and update the _VISION_MODEL constant to use it.

Related

Metadata

Metadata

Assignees

Labels

area/backendsProvider-specific work: Ollama, HF, LiteLLM, OpenAI, Bedrock, vLLMp2Medium/low: minor bugs, niche features, polish, docs, tests, cleanup. Scoped, lower urgency.testing

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions