nextcloud/all-in-one
1
1
Fork 0
mirror of https://github.com/nextcloud/all-in-one.git synced 2025-09-28 17:44:43 +08:00
Code Issues Projects Releases Packages Wiki Activity

update doc

Browse source 
Signed-off-by: Jean-Yves <7360784+docjyJ@users.noreply.github.com>
This commit is contained in:
Jean-Yves 2025-07-03 14:04:40 +02:00
parent f10276361c
commit 8d013cfbb2
No known key found for this signature in database
GPG key ID: 644C8B9C4CABAEF7
1 changed files with 5 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
community-containers/local-ai-vulkan/readme.md
View file

@ -2,28 +2,13 @@
> [!WARNING] > [!WARNING]
> ARM devices are not supported by this container. It is only for x86_64 devices. (See: https://github.com/mudler/LocalAI/issues/5778) > ARM devices are not supported by this container. It is only for x86_64 devices. (See: https://github.com/mudler/LocalAI/issues/5778)
> [!CAUTION] ## Local AI with Vulkan support
> If the configuration is not correct, it should still work but it will use the CPU only and will not benefit from hardware acceleration. This container bundles Local AI and auto-configures it for you. It support hardware acceleration with Vulkan.
## Local AI
This container bundles Local AI and auto-configures it for you.
### Notes ### Notes
- Make sure vulkan is enabled in the AIO settings. Run `vulkaninfo` in the terminal to check if it is enabled. Documentation is available on the container repository. This documentation is regularly updated and is intended to be as simple and detailed as possible. Thanks for all your feedback!
- Make sure to have enough storage space available. This container alone needs ~7GB storage.
- Make sure to have enabled DRI device by adding `--env NEXTCLOUD_ENABLE_DRI_DEVICE=true`, see https://github.com/nextcloud/all-in-one?tab=readme-ov-file#with-open-source-drivers-mesa-for-amd-intel-and-new-drivers-nouveau-for-nvidia. - See https://github.com/docjyJ/aio-local-ai-vulkan#getting-started for getting start with this container.
- To make it work, you first need to browse `https://your-nc-domain.com/settings/admin/ai` and enable or disable specific features for your models in the openAI settings. Afterwards using the Nextcloud Assistant should work.
- To access the Local AI web interface, you need to set reverse proxy rules for it.
```Cadyfile
http://local-ai.your-nc-domain.com {
# Local AI web interface haven't any authentication, so you should protect it
basic_auth {
# Username "Bob", password "hiccup"
Bob $2a$14$Zkx19XLiW6VYouLHR5NmfOFU0z2GTNmpkT/5qqR7hx4IjWJPDhjvG
}
reverse_proxy nenxtcloud-aio-local-ai-vulkan:8080
}
```
- See [this guide](https://github.com/nextcloud/all-in-one/discussions/5430) for how to improve AI task pickup speed - See [this guide](https://github.com/nextcloud/all-in-one/discussions/5430) for how to improve AI task pickup speed
- See https://github.com/nextcloud/all-in-one/tree/main/community-containers#community-containers how to add it to the AIO stack - See https://github.com/nextcloud/all-in-one/tree/main/community-containers#community-containers how to add it to the AIO stack
- Note that Nextcloud supports only one server for AI queries, so this container cannot be used at the same time as other AI containers. - Note that Nextcloud supports only one server for AI queries, so this container cannot be used at the same time as other AI containers.