wenjin272 commented on PR #596: URL: https://github.com/apache/flink-agents/pull/596#issuecomment-4287333625
> Regarding the skill e2e testing, I evaluated qwen3:8b, qwen3.5:4b, and qwen3.5:9b. I found that only qwen3.5:9b with thinking enabled could consistently follow the prompts. However, in the GitHub CI environment, the lack of GPU resources results in very slow model inference, causing tests to take over 30 minutes to complete. Consequently, I have temporarily skipped the skill e2e tests. > > I plan to dedicate time later to investigate and resolve this issue. To resolve this issue, I replace the chat model from ollama to openai, and create a api key. The key is saved as github action secrets. The secrets will exist in encrypted form and are not passed to the runner when a workflow is triggered from a forked repository. I created an API key on DashScope using my personal account. Developers can also replace it with any base_url and api_key compatible with the OpenAI v1 protocol during testing. -- 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]
