jyapayne/dify
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat(api): Add image multimodal support for LLMNode (#17372)

Browse source 
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>
This commit is contained in:
QuantumGhost 2025-04-30 17:28:02 +08:00 • committed by GitHub
commit 349c3cf7b8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
24 changed files with 971 additions and 191 deletions
Download patch file Download diff file Expand all files Collapse all files

12
api/models/engine.py
View file

@ -10,4 +10,16 @@ POSTGRES_INDEXES_NAMING_CONVENTION = {
}
metadata = MetaData(naming_convention=POSTGRES_INDEXES_NAMING_CONVENTION)
# ****** IMPORTANT NOTICE ******
#
# NOTE(QuantumGhost): Avoid directly importing and using `db` in modules outside of the
# `controllers` package.
#
# Instead, import `db` within the `controllers` package and pass it as an argument to
# functions or class constructors.
#
# Directly importing `db` in other modules can make the code more difficult to read, test, and maintain.
#
# Whenever possible, avoid this pattern in new code.
db = SQLAlchemy(metadata=metadata)