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

chore: the consistency of MultiModalPromptMessageContent (#11721)

Browse source
This commit is contained in:
非法操作 2024-12-17 15:01:38 +08:00 • committed by GitHub
commit c9b4029ce7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 108 additions and 99 deletions
Download patch file Download diff file Expand all files Collapse all files

7
docker/.env.example
View file

@ -614,13 +614,12 @@ CODE_GENERATION_MAX_TOKENS=1024
# Multi-modal Configuration
# ------------------------------
# The format of the image/video sent when the multi-modal model is input,
# The format of the image/video/audio/document sent when the multi-modal model is input,
# the default is base64, optional url.
# The delay of the call in url mode will be lower than that in base64 mode.
# It is generally recommended to use the more compatible base64 mode.
# If configured as url, you need to configure FILES_URL as an externally accessible address so that the multi-modal model can access the image/video.
MULTIMODAL_SEND_IMAGE_FORMAT=base64
MULTIMODAL_SEND_VIDEO_FORMAT=base64
# If configured as url, you need to configure FILES_URL as an externally accessible address so that the multi-modal model can access the image/video/audio/document.
MULTIMODAL_SEND_FORMAT=base64
# Upload image file size limit, default 10M.
UPLOAD_IMAGE_FILE_SIZE_LIMIT=10