I'm not sure if there's a way to trigger CI in the pull request, but here's the output when I ran the tests myself by hand:

====================================== test session starts ======================================
platform linux -- Python 3.11.6, pytest-8.3.4, pluggy-1.5.0
rootdir: /home/adam/src/my-llm-ollama
configfile: pyproject.toml
plugins: asyncio-0.25.3, anyio-4.8.0
asyncio: mode=Mode.STRICT, asyncio_default_fixture_loop_scope=None
collected 18 items
tests/test_ollama_integration.py ..                                                       [ 11%]
tests/test_ollama_unit.py ................                                                [100%]
====================================== 18 passed in 6.00s =======================================

Hi, thanks for contributing! GitHub requires maintainer's approval to run CI for first-time contributor's PRs, so for now I'll need to trigger it manually.

There seems to be a problem with version resolution. Could you have a look?

I'm currently on vacation and mostly AFK, so apologies in advance for high latency of responses.

Ah, I made a mistake. I did not realize that the python ollama library doesn't track the upstream ollama version. I reverted that change, so now the only dependency update is for llm itself, which is appropriate.