Feat: Add support for Vision API and Input Images

[jainammm]

trafficstars

Hello,

We are trying to extract features from an Image using Vision API of OpenAI.

Currently, TypeChat only supports text information. It would be much appreciated if we can allow users to pass extra content like images.

I would like to work on adding this feature.

Approach

• In the translate function we can allow users to pass extra content parameters like images... this can be extended to passing context to the model too... like if user wants to pass some user prompt or whole context of previous conversation