Add provider and model feature flags for filtering

Merge request here: https://git.drupalcode.org/project/ai/-/merge_requests/45

Maybe I'm nit-picky but I feel like ChatWithImageVision is a bit redundant and ChatWithVision is more in line with convention:
https://docs.anthropic.com/en/docs/build-with-claude/vision
https://platform.openai.com/docs/guides/vision

I think if they add Video support it would in integration in Vision API and not a separate VideoVision api.

It actually exists on one model already in Gemini that is a vision model that does both, see here: https://cloud.google.com/vertex-ai/docs/samples/aiplatform-gemini-single.... Thus adding the feature flags for ChatWithImageVision and later ChatWithVideoVision when needed.

Smaller and simpler models like Phi-3 or open source like FireLlava, will probably not be able to do video anytime soon, if ever, so its good to have the option to split those .

This is now merged into 1.0.x-dev branch and available on the dev release.

Automatically closed - issue fixed for 2 weeks with no activity.