LLM / Artificial Intelligence trained on my own BookStack library in order to find what past notes? #5282

New Issue

OVERLORD · 2026-02-05T09:53:53+03:00

OVERLORD commented

2026-02-05 09:53:53 +03:00

Originally created by @Wookbert on GitHub (May 15, 2025).

Describe the feature you'd like

Are there any plans to integrate an LLM into BookStack? It might sound like an insane, but it could be useful to locate information in one’s BookStack library or to refresh ones memory on what’s there. Think of using it for instance to create recaps of books or pages.

Describe the benefits this would bring to existing BookStack users

I'm collecting so much information and have so many projects going on, I find it increasingly difficult to keep track of my own recordings.

I assume many other have similar problems.

Can the goal of this request already be achieved via other means?

Only by manually browsing or searching for the right keywords.

Have you searched for an existing open/closed issue?

I have searched for existing issues and none cover my fundamental request

How long have you been using BookStack?

Over 5 years

Additional context

No response

Originally created by @Wookbert on GitHub (May 15, 2025). ### Describe the feature you'd like Are there any plans to integrate an LLM into BookStack? It might sound like an insane, but it could be useful to locate information in one’s BookStack library or to refresh ones memory on what’s there. Think of using it for instance to create recaps of books or pages. ### Describe the benefits this would bring to existing BookStack users I'm collecting so much information and have so many projects going on, I find it increasingly difficult to keep track of my own recordings. I assume many other have similar problems. ### Can the goal of this request already be achieved via other means? Only by manually browsing or searching for the right keywords. ### Have you searched for an existing open/closed issue? - [x] I have searched for existing issues and none cover my fundamental request ### How long have you been using BookStack? Over 5 years ### Additional context _No response_

OVERLORD added the 🔨 Feature Request label 2026-02-05 09:53:53 +03:00

OVERLORD commented

2026-02-05 09:53:56 +03:00

@ssddanbrown commented on GitHub (May 15, 2025):

Hi @Wookbert,

I started on a proof of concept of a somewhat native integration of LLM based search back in March.
My draft PR branch with research can be found in #5552.
I just added a video preview of my proof of concept in a comment there to provide some visuals: https://github.com/BookStackApp/BookStack/pull/5552#issuecomment-2884752947

There's quite a few questionables & considerations around this though.
It's on pause right now, while I crack on with the next feature release, but my plan was to come back to it to develop it out a little further after this current release cycle is done.

@ssddanbrown commented on GitHub (May 15, 2025): Hi @Wookbert, I started on a proof of concept of a somewhat native integration of LLM based search back in March. My draft PR branch with research can be found in #5552. I just added a video preview of my proof of concept in a comment there to provide some visuals: https://github.com/BookStackApp/BookStack/pull/5552#issuecomment-2884752947 There's quite a few questionables & considerations around this though. It's on pause right now, while I crack on with the next feature release, but my plan was to come back to it to develop it out a little further after this current release cycle is done.

OVERLORD commented

2026-02-05 09:54:01 +03:00

@Kristoffeh commented on GitHub (May 26, 2025):

Hello!

From what I've heard; The bigger LLMs are based on various calculations by using the GPU rather than the CPU. I actually currently don't even have a GPU in my homelab server.

It would be great if things like LLM is configurable, so that its not even in use in the first place - unless it is configured.

@Kristoffeh commented on GitHub (May 26, 2025): Hello! From what I've heard; The bigger LLMs are based on various calculations by using the GPU rather than the CPU. I actually currently don't even have a GPU in my homelab server. It would be great if things like LLM is configurable, so that its not even in use in the first place - unless it is configured.

OVERLORD commented

2026-02-05 09:54:02 +03:00

@ssddanbrown commented on GitHub (May 26, 2025):

Hi @Kristoffeh,
We probably wouldn't ship models directly part of BookStack at all, and this would be something that's optional upon the default system due to the external requirements.

My current implementation uses OpenAI-like APIs, which others seem to support as a somewhat non-official standard.
The idea is you'd be able to integration with an external system of your choice which supports this API, including a self-hosted instance of something like Ollama using self-hosted models (potentially on another system) or just existing LLM services.

@ssddanbrown commented on GitHub (May 26, 2025): Hi @Kristoffeh, We probably wouldn't ship models directly part of BookStack at all, and this would be something that's optional upon the default system due to the external requirements. My current implementation uses OpenAI-like APIs, which others seem to support as a somewhat non-official standard. The idea is you'd be able to integration with an external system of your choice which supports this API, including a self-hosted instance of something like Ollama using self-hosted models (potentially on another system) or just existing LLM services.

OVERLORD commented

2026-02-05 09:54:04 +03:00

@Kristoffeh commented on GitHub (May 26, 2025):

Hi @Kristoffeh, We probably wouldn't ship models directly part of BookStack at all, and this would be something that's optional upon the default system due to the external requirements.

My current implementation uses OpenAI-like APIs, which others seem to support as a somewhat non-official standard. The idea is you'd be able to integration with an external system of your choice which supports this API, including a self-hosted instance of something like Ollama using self-hosted models (potentially on another system) or just existing LLM services.

Hello again @ssddanbrown and thanks for taking the time.
Okay, that sounds great!

@Kristoffeh commented on GitHub (May 26, 2025): > Hi [@Kristoffeh](https://github.com/Kristoffeh), We probably wouldn't ship models directly part of BookStack at all, and this would be something that's optional upon the default system due to the external requirements. > > My current implementation uses OpenAI-like APIs, which others seem to support as a somewhat non-official standard. The idea is you'd be able to integration with an external system of your choice which supports this API, including a self-hosted instance of something like Ollama using self-hosted models (potentially on another system) or just existing LLM services. Hello again @ssddanbrown and thanks for taking the time. Okay, that sounds great!

OVERLORD commented

2026-02-05 09:54:05 +03:00

@JinsoRaj commented on GitHub (Jun 18, 2025):

https://docs.onyx.app/connectors/bookstack An opensource project Onyx(previously Danswer) already have bookstack as a connector. I am using this from the past 1 year and its good. we can configure the update/delete intervals, agents based on different documents sets etc. sharing here if it is useful.

@JinsoRaj commented on GitHub (Jun 18, 2025): https://docs.onyx.app/connectors/bookstack An opensource project Onyx(previously Danswer) already have bookstack as a connector. I am using this from the past 1 year and its good. we can configure the update/delete intervals, agents based on different documents sets etc. sharing here if it is useful.

OVERLORD commented

2026-02-05 09:54:06 +03:00

@growricherwang commented on GitHub (Sep 23, 2025):

https://docs.onyx.app/connectors/bookstack An opensource project Onyx(previously Danswer) already have bookstack as a connector. I am using this from the past 1 year and its good. we can configure the update/delete intervals, agents based on different documents sets etc. sharing here if it is useful.

Does Onyx support book/document Access Control?

@growricherwang commented on GitHub (Sep 23, 2025): > https://docs.onyx.app/connectors/bookstack An opensource project Onyx(previously Danswer) already have bookstack as a connector. I am using this from the past 1 year and its good. we can configure the update/delete intervals, agents based on different documents sets etc. sharing here if it is useful. Does Onyx support book/document Access Control?

OVERLORD commented

2026-02-05 09:54:07 +03:00

@ssddanbrown commented on GitHub (Jan 20, 2026):

I haven't been too happy with my implementation attempts so far, much due to the variation in models, possible quality, prompting, outputs, scenarios etc...
At least not to a point I'd be happy to include it in the BookStack core.

Therefore, I've been testing going in a different direction recently, by attempting to put together an external solution which makes use of BookStack's methods of extension to provide something integrated.

I've published an initial version of this here:
https://codeberg.org/bookstack/query

This should work with current BookStack v25.12 versions.
Here's a preview of the functionality:

https://github.com/user-attachments/assets/84c147f1-0c39-4aa4-a3b5-8baf62a01d57

Note: Expect some turbulence in this. I'm thinking about further developing our extension/theme system out to work in a more modular way, using this customisation as an example/demo for that.
Plus there are many considerations and requirements to something like this (many of which are listed in the readme), and it's only been tested for a narrow scenario right now.

@ssddanbrown commented on GitHub (Jan 20, 2026): I haven't been too happy with my implementation attempts so far, much due to the variation in models, possible quality, prompting, outputs, scenarios etc... At least not to a point I'd be happy to include it in the BookStack core. Therefore, I've been testing going in a different direction recently, by attempting to put together an external solution which makes use of BookStack's methods of extension to provide something integrated. I've published an initial version of this here: https://codeberg.org/bookstack/query This should work with current BookStack v25.12 versions. Here's a preview of the functionality: https://github.com/user-attachments/assets/84c147f1-0c39-4aa4-a3b5-8baf62a01d57 Note: Expect some turbulence in this. I'm thinking about further developing our extension/theme system out to work in a more modular way, using this customisation as an example/demo for that. Plus there are many considerations and requirements to something like this (many of which are listed in the readme), and it's only been tested for a narrow scenario right now.

OVERLORD commented

2026-02-05 09:54:10 +03:00

@Wookbert commented on GitHub (Jan 21, 2026):

Nice! Voice-to-text query would be helpful/useful.

@Wookbert commented on GitHub (Jan 21, 2026): Nice! Voice-to-text query would be helpful/useful.

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: starred/BookStack#5282