OpenSource
/
dify
关注 4
点赞 0
派生 0
代码 工单 0 合并请求 0 版本发布 152 百科 动态
您最多选择25个主题 主题必须以字母或数字开头，可以包含连字符 (-)，并且长度不得超过35个字符
7117 提交
4 分支
目录树: a78339a040
分支列表 标签列表
${ item.name }
创建分支 ${ searchTerm }
从 'a78339a040'
${ noResults }
dify/api/core/file/tool_file_parser.py

tool_file_parser.py 383B
原始文件 普通视图 文件历史

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
​
feat/enhance the multi-modal support (#8818)
1年前
​
​
​
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
chore(api/core): apply ruff reformatting (#7624)
1年前
Feat/assistant app (#2086) Co-authored-by: chenhe <guchenhe@gmail.com> Co-authored-by: Pascal M <11357019+perzeuss@users.noreply.github.com>
1年前
remove bare list, dict, Sequence, None, Any (#25058) Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: -LAN- <laipz8200@outlook.com>
1 个月前
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
​
 123456789101112 
  1. from collections.abc import Callable

  2. from typing import TYPE_CHECKING

  3. 

  4. if TYPE_CHECKING:

  5.     from core.tools.tool_file_manager import ToolFileManager

  6. 

  7. _tool_file_manager_factory: Callable[[], "ToolFileManager"] | None = None

  8. 

  9. 

  10. def set_tool_file_manager_factory(factory: Callable[[], "ToolFileManager"]):

  11.     global _tool_file_manager_factory

  12.     _tool_file_manager_factory = factory