feat: support base64 images on the Gemini provider

[cheahjs]

This PR adds support for inline base64 images when using vision models on the Gemini provider.

A couple of additional changes:

1. The check for what is a vision model on Gemini is updated to: a. The model has vision in the name b. The model has gemini-1.5-pro in the name.
2. Add Pillow as a dependency to requirements.txt

Addresses https://github.com/BerriAI/litellm/issues/2756

[vercel[bot]]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
litellm	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Apr 28, 2024 2:03pm

[ishaan-jaff]

Hi @cheahjs , thanks for your contributions to LiteLLM. Can we hop on a quick call sometime this week? I’d love to learn how we can improve litellm for you

My cal for your convenience: https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version?month=2023-10 My linkedin if you prefer DMs: https://www.linkedin.com/in/reffajnaahsi/