mirror of
https://github.com/langgenius/dify.git
synced 2025-10-31 02:42:59 +00:00
349c3cf7b8
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>
20 lines
585 B
Python
20 lines
585 B
Python
from collections.abc import Callable
|
|
from typing import TYPE_CHECKING
|
|
|
|
if TYPE_CHECKING:
|
|
from core.tools.tool_file_manager import ToolFileManager
|
|
|
|
_tool_file_manager_factory: Callable[[], "ToolFileManager"] | None = None
|
|
|
|
|
|
class ToolFileParser:
|
|
@staticmethod
|
|
def get_tool_file_manager() -> "ToolFileManager":
|
|
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
|