Overview

We strive to bring Artificial Intelligence features to Nextcloud. This section highlights these features, how they work and where to find them. All of these features are completely optional. If you want to have them on your server, you need install them via separate Nextcloud Apps.

Overview of AI features

Nextcloud uses modularity to separate raw AI functionality from the Graphical User interfaces and apps that make use of said functionality. Each instance can thus make use of various backends that provide the functionality for the same frontends and the same functionality can be implemented by multiple apps using on-premises processing or third-party AI service providers.

Feature	App	Rating	Open source	Freely available model	Freely available training data	Privacy: Keeps data on premises
Smart inbox	Mail	Green	Yes	Yes	Yes	Yes
Image object recognition	Recognize	Green	Yes	Yes	Yes	Yes
Image face recognition	Recognize	Green	Yes	Yes	Yes	Yes
Video action recognition	Recognize	Green	Yes	Yes	Yes	Yes
Audio music genre recognition	Recognize	Green	Yes	Yes	Yes	Yes
Suspicious login detection	Suspicious Login	Green	Yes	Yes	Yes	Yes
Related resources	Related Resources	Green	Yes	Yes	Yes	Yes
Recommended files	recommended_files	Green	Yes	Yes	Yes	Yes
Text processing using LLMs	llm2 (ExApp)	Green	Yes	Yes - Llama 3.1 model by Meta	Yes	Yes
	OpenAI and LocalAI integration (via OpenAI API)	Red	No	No	No	No
	OpenAI and LocalAI integration (via LocalAI)	Yellow	Yes	Yes - e.g. Llama models by Meta	No	Yes
Machine translation	Local Machine Translation 2 (ExApp)	Green	Yes	Yes - MADLAD models by Google	Yes	Yes
	DeepL integration	Red	No	No	No	No
	OpenAI and LocalAI integration (via OpenAI API)	Red	No	No	No	No
	OpenAI and LocalAI integration (via LocalAI)	Green	Yes	Yes	Yes	Yes
Speech to Text	Local Whisper Speech-To-Text 2 (ExApp)	Yellow	Yes	Yes - Whisper models by OpenAI	No	Yes
	OpenAI and LocalAI integration	Yellow	Yes	Yes - Whisper models by OpenAI	No	No
	Replicate integration	Yellow	Yes	Yes - Whisper models by OpenAI	No	No
Image generation	Local Stable Diffusion	Yellow	Yes	Yes - StableDiffusion XL model by StabilityAI	No	Yes
	OpenAI and LocalAI integration (via OpenAI API)	Red	No	No	No	No
	OpenAI and LocalAI integration (via LocalAI)	Yellow	Yes	Yes - StableDiffusion models by StabilityAI	No	Yes
	Replicate integration	Yellow	Yes	Yes - StableDiffusion models by StabilityAI	No	No
	Local large language model 2 (ExApp)	Yellow	Yes	Yes	No	Yes
	OpenAI and LocalAI integration (via OpenAI API)	Red	No	No	No	No
	OpenAI and LocalAI integration (via LocalAI)	Green	Yes	Yes	Yes	Yes
Context Chat	Nextcloud Assistant Context Chat	Yellow	Yes	Yes	No	Yes
	Nextcloud Assistant Context Chat (Backend)	Yellow	Yes	Yes	No	Yes

Ethical AI Rating

Until Hub 3, we succeeded in offering features without relying on proprietary blobs or third party services. Yet, while there is a large community developing ethical, safe and privacy-respecting technologies, there are many other relevant technologies users might want to use. We want to provide users with these cutting-edge technologies – but also be transparent. For some use cases, ChatGPT might be a reasonable solution, while for more private, professional or sensitive data, it is paramount to have a local, on-prem, open solution. To differentiate these, we developed an Ethical AI Rating.

The rating has four levels:

Red
Orange
Yellow
Green

It is based on points from these factors:

Is the software (both for inferencing and training) under a free and open source license?
Is the trained model freely available for self-hosting?
Is the training data available and free to use?

If all of these points are met, we give a Green label. If none are met, it is Red. If 1 condition is met, it is Orange and if 2 conditions are met, Yellow.

Features used by other apps

Some of our AI features are realized as generic APIs that any app can use and any app can provide an implementation for by registering a provider. So far, these are Machine translation, Speech-To-Text, Image generation, Text processing and Context Chat.

Text processing

As you can see in the table above we have multiple apps offering text processing using Large language models. In downstream apps like Context Chat and assistant, users can use the text processing functionality regardless of which app implements it behind the scenes.

Frontend apps

Text for offering an inline graphical UI for the various tasks
Assistant for offering a graphical UI for the various tasks and a smart picker
Mail for summarizing mail threads (see the Nextcloud Mail docs for how to enable this)
Summary Bot for summarizing chat histories in Talk

Backend apps

llm2 - Runs open source AI LLM models on your own server hardware (Customer support available upon request)
OpenAI and LocalAI integration (via OpenAI API) - Integrates with the OpenAI API to provide AI functionality from OpenAI servers (Customer support available upon request; see AI as a Service)

Machine translation

As you can see in the table above we have multiple apps offering machine translation capabilities. Each app brings its own set of supported languages. In downstream apps like the Text app, users can use the translation functionality regardless of which app implements it behind the scenes.

Frontend apps

Text for offering the translation menu
Assistant offering a graphical translation UI
Analytics for translating graph labels

Backend apps

translate2 (ExApp) - Runs open source AI translation models locally on your own server hardware (Customer support available upon request)
integration_deepl - Integrates with the deepl API to provide translation functionality from Deepl.com servers (Only community supported)

Speech-To-Text

As you can see in the table above we have multiple apps offering Speech-To-Text capabilities. In downstream apps like the Talk app, users can use the transcription functionality regardless of which app implements it behind the scenes.

Frontend apps

Assistant offering a graphical translation UI and a smart picker
Talk for transcribing calls (see Nextcloud Talk docs for how to enable this)

Backend apps

stt_whisper2 - Runs open source AI Speech-To-Text models on your own server hardware (Customer support available upon request)
OpenAI and LocalAI integration (via OpenAI API) - Integrates with the OpenAI API to provide AI functionality from OpenAI servers (Customer support available upon request; see AI as a Service)

Image generation

As you can see in the table above we have multiple apps offering Image generation capabilities. In downstream apps like the Text-to-Image helper app, users can use the image generation functionality regardless of which app implements it behind the scenes.

Frontend apps

Assistant for offering a graphical UI and a smart picker

Backend apps

text2image_stablediffusion (Customer support available upon request)
OpenAI and LocalAI integration (via OpenAI API) - Integrates with the OpenAI API to provide AI functionality from OpenAI servers (Customer support available upon request; see AI as a Service)
integration_replicate - Integrates with the replicate API to provide AI functionality from replicate servers (see AI as a Service)

Context Chat

Our Context Chat feature was introduced in Nextcloud Hub 7 (v28). It allows asking questions to the assistant related to your documents in Nextcloud. You will need to install both the context_chat app as well as the context_chat_backend External App. Be prepared that things might break or be a little rough around the edges. We look forward to your feedback!

Frontend apps

Assistant for offering a graphical UI for the context chat tasks

Backend apps

context_chat + context_chat_backend - (Customer support available upon request)

Provider apps

Apps can integrate their content with Context Chat to make it available for querying using Context Chat. The following apps have implemented this integration so far:

files
Analytics

Frequently Asked Questions

Why is my prompt slow?

Reasons for slow performance from a user perspective can be

Using CPU processing instead of GPU (sometimes this limit is imposed by the used app)

High user demand for the feature: User prompts and AI tasks are usually processed in the order they are received, which can cause delays when a lot of users access these features at the same time.