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/entities/message_entities.py

@@ -1,4 +1,5 @@
-from collections.abc import Sequence
+from abc import ABC
+from collections.abc import Mapping, Sequence
 from enum import Enum, StrEnum
 from typing import Annotated, Any, Literal, Optional, Union
 
@@ -60,8 +61,12 @@ class PromptMessageContentType(StrEnum):
     DOCUMENT = "document"
 
 
-class PromptMessageContent(BaseModel):
-    pass
+class PromptMessageContent(ABC, BaseModel):
+    """
+    Model class for prompt message content.
+    """
+
+    type: PromptMessageContentType
 
 
 class TextPromptMessageContent(PromptMessageContent):
@@ -125,7 +130,16 @@ PromptMessageContentUnionTypes = Annotated[
 ]
 
 
-class PromptMessage(BaseModel):
+CONTENT_TYPE_MAPPING: Mapping[PromptMessageContentType, type[PromptMessageContent]] = {
+    PromptMessageContentType.TEXT: TextPromptMessageContent,
+    PromptMessageContentType.IMAGE: ImagePromptMessageContent,
+    PromptMessageContentType.AUDIO: AudioPromptMessageContent,
+    PromptMessageContentType.VIDEO: VideoPromptMessageContent,
+    PromptMessageContentType.DOCUMENT: DocumentPromptMessageContent,
+}
+
+
+class PromptMessage(ABC, BaseModel):
     """
     Model class for prompt message.
     """
@@ -142,6 +156,23 @@ class PromptMessage(BaseModel):
         """
         return not self.content
 
+    @field_validator("content", mode="before")
+    @classmethod
+    def validate_content(cls, v):
+        if isinstance(v, list):
+            prompts = []
+            for prompt in v:
+                if isinstance(prompt, PromptMessageContent):
+                    if not isinstance(prompt, TextPromptMessageContent | MultiModalPromptMessageContent):
+                        prompt = CONTENT_TYPE_MAPPING[prompt.type].model_validate(prompt.model_dump())
+                elif isinstance(prompt, dict):
+                    prompt = CONTENT_TYPE_MAPPING[prompt["type"]].model_validate(prompt)
+                else:
+                    raise ValueError(f"invalid prompt message {prompt}")
+                prompts.append(prompt)
+            return prompts
+        return v
+
     @field_serializer("content")
     def serialize_content(
         self, content: Optional[Union[str, Sequence[PromptMessageContent]]]