OpenSource/dify - dify - 浩瀚星图

文件历史

QuantumGhost 349c3cf7b8 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>		6 个月前
..
__init__.py	chore(lint): sort __all__ definitions (#11243)	11 个月前
constants.py	feat/enhance the multi-modal support (#8818)	1年前
enums.py	fix: workflow file add related-id in iteration node (#16255)	7 个月前
file_manager.py	feat(api): Add image multimodal support for LLMNode (#17372)	6 个月前
helpers.py	Introduce Plugins (#13836)	8 个月前
models.py	feat(api): Add image multimodal support for LLMNode (#17372)	6 个月前
tool_file_parser.py	feat(api): Add image multimodal support for LLMNode (#17372)	6 个月前
upload_file_parser.py	chore: docstring not match the function parameter (#17162)	7 个月前