feat(api): Add image multimodal support for LLMNode (#17372)

Enhance `LLMNode` with multimodal capability, introducing support for
image outputs.

This implementation extracts base64-encoded images from LLM responses,
saves them to the storage service, and records the file metadata in the
`ToolFile` table. In conversations, these images are rendered as
markdown-based inline images.
Additionally, the images are included in the LLMNode's output as
file variables, enabling subsequent nodes in the workflow to utilize them.

To integrate file outputs into workflows, adjustments to the frontend code
are necessary.

For multimodal output functionality, updates to related model configurations
are required. Currently, this capability has been applied exclusively to
Google's Gemini models.

Close #15814.

Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>

api/core/model_runtime/utils/helper.py

@@ -1,8 +1,6 @@
 import pydantic
 from pydantic import BaseModel
 
-from core.model_runtime.entities.message_entities import PromptMessageContentUnionTypes
-
 
 def dump_model(model: BaseModel) -> dict:
     if hasattr(pydantic, "model_dump"):
@@ -10,18 +8,3 @@ def dump_model(model: BaseModel) -> dict:
         return pydantic.model_dump(model)  # type: ignore
     else:
         return model.model_dump()
-
-
-def convert_llm_result_chunk_to_str(content: None | str | list[PromptMessageContentUnionTypes]) -> str:
-    if content is None:
-        message_text = ""
-    elif isinstance(content, str):
-        message_text = content
-    elif isinstance(content, list):
-        # Assuming the list contains PromptMessageContent objects with a "data" attribute
-        message_text = "".join(
-            item.data if hasattr(item, "data") and isinstance(item.data, str) else str(item) for item in content
-        )
-    else:
-        message_text = str(content)
-    return message_text