gcgj-dify-1.7.0

Commit Graph

Author	SHA1	Message	Date
baonudesifeizhai	b3f138fa10	fix: resolve mypy type errors and editorconfig issues - Add type annotations for json_output and agent_thoughts variables - Fix trailing whitespace in modified files - Update .gitignore to not ignore api/core directory	11 months ago
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>	1 year ago
-LAN-	3599751f93	chore(db): use a better way to export models and remove unused table (#11838 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	1 year ago

Author

SHA1

Message

Date

baonudesifeizhai

b3f138fa10

fix: resolve mypy type errors and editorconfig issues

- Add type annotations for json_output and agent_thoughts variables
- Fix trailing whitespace in modified files
- Update .gitignore to not ignore api/core directory

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>

-LAN-

3599751f93

chore(db): use a better way to export models and remove unused table (#11838 )

Signed-off-by: -LAN- <laipz8200@outlook.com>

3 Commits (815791e0b4584591f8091c56922ffb70dd0d44e2)