Mason Daugherty 0346ac0fa2 fix(ollama): trace invoke model override (#37502) ...

If you override the model at invoke time — e.g. `chat.invoke(messages,
model="llama3.2")` or `chat.bind(model="llama3.2")` - traces previously
logged the model the `ChatOllama` instance was constructed with, not the
one that ran. Tracing now reflects the runtime override, so dashboards,
filters, and cost/latency breakdowns line up with what really executed.

2026-05-18 13:51:35 -05:00

..

__init__.py

…

_compat.py

…

_utils.py

fix(ollama): respect scheme-less base_url (#34042)

2026-04-06 21:39:33 -04:00

chat_models.py

fix(ollama): trace invoke model override (#37502)

2026-05-18 13:51:35 -05:00

embeddings.py

feat(ollama): add dimensions to OllamaEmbeddings (#36543)

2026-04-06 21:50:54 -04:00

llms.py

…

py.typed

…