[Feature]: Extend the APIs of other model providers to support image and video

[Vasilije1990]

Problem Statement

Currently Gemini and other providers can't process audio, image and video

Proposed Solution

Check OpenAI adapter and replicate logic to transcribe audio and images to text

Alternatives Considered

No response

Use Case

Send audio, video and image data to cognee

Implementation Ideas

Copy implementation from OpenAI adapter and improve if possible

Additional Context

No response

Pre-submission Checklist

• I have searched existing issues to ensure this feature hasn't been requested already
• I have provided a clear problem statement and proposed solution
• I have described my specific use case

[rajeevrajeshuni]

@Vasilije1990 Can I pick this up?

[hande-k]

thanks @rajeevrajeshuni, it is assigned to you! :)

[rajeevrajeshuni]

@Vasilije1990 @hande-k Have a look at this PR-1828. I need some guidance on couple of design decision and need help with running the test suite.