Feature: Send screenshots to AI APIs with vision capabilities in order to learn more about each site

[tristanbob]

Is your feature request related to a problem? Please describe.

No.

Describe the solution you'd like

Add the ability to use one of the multimodal AI APIs that support vision.
These AI tools are easy to use. You send the image and a prompt with instructions for the AI.
This prompt can include a JSON structure with multiple fields for the AI to complete, based on what it "sees" in the image.
The data from this structured response can then be saved and included in the gowitness user interface

Describe alternatives you've considered

None.

Additional context

Popular AI vision services include:

https://platform.openai.com/docs/guides/vision?lang=curl
https://docs.anthropic.com/en/docs/build-with-claude/vision
https://ai.google.dev/gemini-api/docs/vision?lang=go

Cost estimates (as of Nov 2024):