feat: enhance gemini models

[hjlarry]

Summary

Tip

Close issue syntax: Fixes #<issue number> or Resolves #<issue number>, see documentation for more details.

1. all the google models support video file. can close LLM video understanding #10720 . maybe resolve Concurrent API requests to Gemini vision model cause non-responsive behavior and block all tasks forever #9273
2. use google's upload file API instead of base64 string. Now we can cache the uploaded file instead of transfer base64 string each talk. Google support 1 hour video, transfer file each time is so terriable.
3. "gemini-pro-vision" was deprecated, remove this part of logic.
4. make the DocumentPromptMessageContent ImagePromptMessageContent VideoPromptMessageContent and AudioPromptMessageContent unified, both include format and contains mime_type in their data.
5. please help test pdf of claude and audio of openai

Screenshots

Checklist

Important

Please review the checklist below before submitting your pull request.

• This change requires a documentation update, included: Dify Document
• I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
• I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
• I've updated the documentation accordingly.
• I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods