tdpeuter/open-webui
tdpeuter/open-webui
1
Fork 0
forked from open-webui/open-webui
Code Issues Pull requests 1 Releases 2 Packages Activity Actions

set default to cpu

Browse source
This commit is contained in:
Jannik Streidl 2024-03-18 17:09:43 +01:00
parent 5abe0089cb
commit 132d741c55
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
Dockerfile
View file

@ -54,7 +54,7 @@ ENV RAG_EMBEDDING_MODEL="all-MiniLM-L6-v2" \
# Important: # Important:
# If you want to use CUDA you need to install the nvidia-container-toolkit (https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html) # If you want to use CUDA you need to install the nvidia-container-toolkit (https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)
# you can set this to "cuda" but its recomended to use --build-arg CUDA_ENABLED=true flag when building the image # you can set this to "cuda" but its recomended to use --build-arg CUDA_ENABLED=true flag when building the image
RAG_EMBEDDING_MODEL_DEVICE_TYPE="cuda" RAG_EMBEDDING_MODEL_DEVICE_TYPE="cpu"
# device type for whisper tts and embbeding models - "cpu" (default), "cuda" (nvidia gpu and CUDA required) or "mps" (apple silicon) - choosing this right can lead to better performance # device type for whisper tts and embbeding models - "cpu" (default), "cuda" (nvidia gpu and CUDA required) or "mps" (apple silicon) - choosing this right can lead to better performance
#### Preloaded models ########################################################## #### Preloaded models ##########################################################