[Feature] I hope the error messages during demo runtime can be more prominent

[Ethereal-O]

Search before asking

• I had searched in the feature and found no similar feature requirement.

Feature Description (功能描述)

When I run the demo program hugegraph_1lm.demo.rag_demo.app, I complete the LLM configuration and receive a prompt stating that it has been successfully configured. My account limit is insufficient to meet the request, so an error occurred when making the request. However, the error only told me 'str object has no attribute 'usage' ', which took me some time to discover the real reason.

Another method that is relatively easy to replicate is to try modifying the api_mase address and removing the suffix '/v1'. The application configuration still shows a success message, but an error message will be generated during runtime. The error message does not clearly indicate that there may be a configuration issue.

I hope to display the information returned by the LLM interface, whether in the log or on the frontend interface. This may help users better identify configuration issues.

Are you willing to submit a PR?

• Yes I am willing to submit a PR!

Code of Conduct

• I agree to follow this project's Code of Conduct

[goldigd05]

Hi, I would like to enhance the HugeGraph LLM demo error handling.

Currently, when a configuration issue occurs (e.g., account limit exceeded or wrong API base),
the demo shows a success message, but the runtime error is unclear, e.g.:

'str' object has no attribute 'usage'

I propose to display the actual LLM API response in logs or frontend so users
can quickly identify configuration issues. I am happy to submit a PR implementing this improvement.

[imbajin]

Hi, I would like to enhance the HugeGraph LLM demo error handling.

Currently, when a configuration issue occurs (e.g., account limit exceeded or wrong API base), the demo shows a success message, but the runtime error is unclear, e.g.:

'str' object has no attribute 'usage'

I propose to display the actual LLM API response in logs or frontend so users can quickly identify configuration issues. I am happy to submit a PR implementing this improvement.

@goldigd05 nice to see your PR~