fix: gemini system prompt with variable raise error

[hjlarry]

Summary

Tip

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

when add variables into system prompt of LLM node will raise error:

[on_llm_invoke_error]
2024-12-21 12:42:11,077.077 ERROR [Thread-574 (_generate_worker)] [logging_callback.py:169] - Could not create `Blob`, expected `Blob`, `dict` or an `Image` type(`PIL.Image.Image` or `IPython.display.Image`).
Got a: <class 'list'>
Value: [TextPromptMessageContent(type=<PromptMessageContentType.TEXT: 'text'>, data='你是一个友好的AI助理'), TextPromptMessageContent(type=<PromptMessageContentType.TEXT: 'text'>, data='2024-12-21 12:42:11')]
Traceback (most recent call last):
  File "/home/njue/software/code/dify/api/core/model_runtime/model_providers/__base/large_language_model.py", line 110, in invoke
    result = self._invoke(
             ^^^^^^^^^^^^^
  File "/home/njue/software/code/dify/api/core/model_runtime/model_providers/google/llm/llm.py", line 66, in _invoke
    return self._generate(model, credentials, prompt_messages, model_parameters, tools, stop, stream, user)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/njue/software/code/dify/api/core/model_runtime/model_providers/google/llm/llm.py", line 195, in _generate
    content = self._format_message_to_glm_content(msg)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/njue/software/code/dify/api/core/model_runtime/model_providers/google/llm/llm.py", line 407, in _format_message_to_glm_content
    return {"role": "user", "parts": [to_part(message.content)]}
                                      ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/njue/anaconda3/envs/dify/lib/python3.12/site-packages/google/generativeai/types/content_types.py", line 249, in to_part
    return protos.Part(inline_data=to_blob(part))
                                   ^^^^^^^^^^^^^
  File "/home/njue/anaconda3/envs/dify/lib/python3.12/site-packages/google/generativeai/types/content_types.py", line 195, in to_blob
    raise TypeError(
TypeError: Could not create `Blob`, expected `Blob`, `dict` or an `Image` type(`PIL.Image.Image` or `IPython.display.Image`).
Got a: 

also make the system prompt message to google's system_instructions.

Screenshots

Before	After
...	...

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

[laipz8200]

Thanks