Closed hjlarry closed 5 hours ago
Thank you for this awesome contribution! Some changes in #10679 are still in processing, I'll review this PR after #10679 is merged.
the vision settings is strange, Resolution only affect Image type files, Upload Method and Upload Limit affect all type files.
I think this resolution config should be removed in the future.
Hi @hjlarry! #10679 is merged, could you please sync the code with the main branch?
Hi @hjlarry! #10679 is merged, could you please sync the code with the main branch?
Done :)
Screen.Recording.2024-11-22.at.5.56.05.PM.mov
seems the icon has been overwrite by the merge action, please try again
Summary
Currently, lots of LLM( gemini, sonnet ...) can directly process document, and make user's chat context based on these documents. This PR aimed to support this feature in a dify agent app. For the chatflow app, maybe this PR can resolve.
ChangeList
Backend
DocumentPromptMessageContent
and more model features, copied from https://github.com/langgenius/dify/pull/10679video
feature to support video models,document
feature to support document modelsFrontend
file.allowed_file_types
has any valueremaining issues
Resolution
only affect Image type files,Upload Method
andUpload Limit
affect all type files.Screenshots
Checklist
dev/reformat
(backend) andcd web && npx lint-staged
(frontend) to appease the lint gods