Add better messages for failing calls to AI assistance

[hguerrero]

Reason/Context

When trying the AI assistance, there might be errors that are just sending a generic message. No way for the user to understand where to start digging to fix it.

Description

The message shown when there is an error while calling the AI assistance is too generic.

Implementation ideas

The REST API call to OpenAI for example, returns some more context on what was failing. It would be interesting in checking if there is a way to capture the output and share it with the user.

[yada]

Not sure it will help the end users as he can not change or modify the prompt. Currently he can just retry. The idea behind the AI-copilot is to have a very easy and straightforward experience (currently exemple generation) without writing anything. But it required a clean and curated specification/contract. In which case have you noticed an issue for which the error message can be useful?

[hguerrero]

@yada, not on the prompt, but on the actual call. I got an HTTP 429 error with a clear message on checking my available quota. As we are using the user's API Key for the calls, it should be easy to add more context on why the request to the API failed.

I was only able to check what the issue was after checking the logs.

[yada]

Thanks @hguerrero, yep make sense for this one agree. Let's dig further how this can be improve +1

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity 😴

It will be closed in 30 days if no further activity occurs. To unstale this issue, add a comment with a detailed explanation.

There can be many reasons why some specific issue has no activity. The most probable cause is lack of time, not lack of interest. Microcks is a Cloud Native Computing Foundation project not owned by a single for-profit company. It is a community-driven initiative ruled under open governance model.

Let us figure out together how to push this issue forward. Connect with us through one of many communication channels we established here.

Thank you for your patience ❤️

[hguerrero]

keep open

[lbroudoux]

It would be nice to list here the different cases we'd need to handle. I've noticed that 429: resource quotas exhausted may be one of them 😉

[oliviernguyenquoc]

It would be nice to list here the different cases we'd need to handle. I've noticed that 429: resource quotas exhausted may be one of them 😉

Just for info(to help), here a different one:
401 Unauthorized: "{ "error": { "message": "Incorrect API key provided: sk-**********. You can find your API key at https://platform.openai.com/account/api-keys.", "type":

I missed something in my config.