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/file/file_manager.py

@@ -10,12 +10,12 @@ from core.model_runtime.entities import (
     VideoPromptMessageContent,
 )
 from core.model_runtime.entities.message_entities import PromptMessageContentUnionTypes
+from core.tools.signature import sign_tool_file
 from extensions.ext_storage import storage
 
 from . import helpers
 from .enums import FileAttribute
 from .models import File, FileTransferMethod, FileType
-from .tool_file_parser import ToolFileParser
 
 
 def get_attr(*, file: File, attr: FileAttribute):
@@ -130,6 +130,6 @@ def _to_url(f: File, /):
         # add sign url
         if f.related_id is None or f.extension is None:
             raise ValueError("Missing file related_id or extension")
-        return ToolFileParser.get_tool_file_manager().sign_file(tool_file_id=f.related_id, extension=f.extension)
+        return sign_tool_file(tool_file_id=f.related_id, extension=f.extension)
     else:
         raise ValueError(f"Unsupported transfer method: {f.transfer_method}")

api/core/file/models.py

@@ -4,11 +4,11 @@ from typing import Any, Optional
 from pydantic import BaseModel, Field, model_validator
 
 from core.model_runtime.entities.message_entities import ImagePromptMessageContent
+from core.tools.signature import sign_tool_file
 
 from . import helpers
 from .constants import FILE_MODEL_IDENTITY
 from .enums import FileTransferMethod, FileType
-from .tool_file_parser import ToolFileParser
 
 
 class ImageConfig(BaseModel):
@@ -34,13 +34,21 @@ class FileUploadConfig(BaseModel):
 
 
 class File(BaseModel):
+    # NOTE: dify_model_identity is a special identifier used to distinguish between
+    # new and old data formats during serialization and deserialization.
     dify_model_identity: str = FILE_MODEL_IDENTITY
 
     id: Optional[str] = None  # message file id
     tenant_id: str
     type: FileType
     transfer_method: FileTransferMethod
+    # If `transfer_method` is `FileTransferMethod.remote_url`, the
+    # `remote_url` attribute must not be `None`.
     remote_url: Optional[str] = None  # remote url
+    # If `transfer_method` is `FileTransferMethod.local_file` or
+    # `FileTransferMethod.tool_file`, the `related_id` attribute must not be `None`.
+    #
+    # It should be set to `ToolFile.id` when `transfer_method` is `tool_file`.
     related_id: Optional[str] = None
     filename: Optional[str] = None
     extension: Optional[str] = Field(default=None, description="File extension, should contains dot")
@@ -110,9 +118,7 @@ class File(BaseModel):
         elif self.transfer_method == FileTransferMethod.TOOL_FILE:
             assert self.related_id is not None
             assert self.extension is not None
-            return ToolFileParser.get_tool_file_manager().sign_file(
-                tool_file_id=self.related_id, extension=self.extension
-            )
+            return sign_tool_file(tool_file_id=self.related_id, extension=self.extension)
 
     def to_plugin_parameter(self) -> dict[str, Any]:
         return {

api/core/file/tool_file_parser.py

@@ -1,12 +1,19 @@
-from typing import TYPE_CHECKING, Any, cast
+from collections.abc import Callable
+from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
     from core.tools.tool_file_manager import ToolFileManager
 
-tool_file_manager: dict[str, Any] = {"manager": None}
+_tool_file_manager_factory: Callable[[], "ToolFileManager"] | None = None
 
 
 class ToolFileParser:
     @staticmethod
     def get_tool_file_manager() -> "ToolFileManager":
-        return cast("ToolFileManager", tool_file_manager["manager"])
+        assert _tool_file_manager_factory is not None
+        return _tool_file_manager_factory()
+
+
+def set_tool_file_manager_factory(factory: Callable[[], "ToolFileManager"]) -> None:
+    global _tool_file_manager_factory
+    _tool_file_manager_factory = factory