Lee-W commented on code in PR #75369: URL: https://github.com/apache/airflow/pull/75369#discussion_r4519793251
########## providers/common/ai/docs/self_hosted_models.rst: ########## @@ -257,6 +257,94 @@ model doesn't have to guess a path. That matters because ``HttpHook`` raises on any response outside the 2xx/3xx range: if the model guessed wrong, the task would fail outright rather than the agent recovering gracefully. +Waiting for an Ollama model to load +------------------------------------- + +Ollama loads a model into memory on the first request, which can take long Review Comment: Yes — the case is a shorter `timeout` in `model_settings`. The guide now says pydantic-ai's default HTTP read timeout is 600 seconds, so with default settings the agent's first request already waits out the load, and the warm-up is for the shorter-timeout case. The 30s in `retry_policies.rst` is `LLMRetryPolicy.timeout` rather than a `model_settings` value. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
