starred/karakeep

Fork 0

mirror of https://github.com/karakeep-app/karakeep.git synced 2026-04-25 16:06:04 +03:00

[GH-ISSUE #1080] Filtering of summary result #711

New issue

Open

opened 2026-03-02 11:52:05 +03:00 by kerem · 7 comments

kerem commented

2026-03-02 11:52:05 +03:00

Owner

Originally created by @jangrewe on GitHub (Mar 1, 2025).
Original GitHub issue: https://github.com/karakeep-app/karakeep/issues/1080

Describe the feature you'd like

Hi, i'm currently setting up Hoarder will all the bells and whistles (and it is amazing!), but the one think that bugs me is that the "AI" summary always looks like " Hmm, so i should This is the summary.", so it includes the <think></think> tags that Ollama/DeepSeek-R1 returns.

Is there any way to add e.g. a regex to filter out this thinking/reasoning output?

Describe the benefits this would bring to existing Hoarder users

Cleaner and more concise summaries.

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

Have you searched for an existing open/closed issue?

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

Additional context

No response

Originally created by @jangrewe on GitHub (Mar 1, 2025). Original GitHub issue: https://github.com/karakeep-app/karakeep/issues/1080 ### Describe the feature you'd like Hi, i'm currently setting up Hoarder will all the bells and whistles (and it is amazing!), but the one think that bugs me is that the "AI" summary always looks like "<think> Hmm, so i should</think> This is the summary.", so it includes the `<think></think>` tags that Ollama/DeepSeek-R1 returns. Is there any way to add e.g. a regex to filter out this thinking/reasoning output? ### Describe the benefits this would bring to existing Hoarder users Cleaner and more concise summaries. ### Can the goal of this request already be achieved via other means? No ### Have you searched for an existing open/closed issue? - [x] I have searched for existing issues and none cover my fundamental request ### Additional context _No response_

kerem added the

feature request

status/icebox

labels

2026-03-02 11:52:05 +03:00

kerem commented

2026-03-02 11:52:06 +03:00

Author

Owner

@MohamedBassem commented on GitHub (Mar 2, 2025):

hmmm, this is an interesting one. I don't think a lot of people have been using reasoning models with hoarder. Does this even work for tagging?

@MohamedBassem commented on GitHub (Mar 2, 2025): hmmm, this is an interesting one. I don't think a lot of people have been using reasoning models with hoarder. Does this even work for tagging?

kerem commented

2026-03-02 11:52:06 +03:00

Author

Owner

@jangrewe commented on GitHub (Mar 2, 2025):

Oh, absolutely! 😁

@jangrewe commented on GitHub (Mar 2, 2025): Oh, absolutely! 😁 ![Image](https://github.com/user-attachments/assets/64d4b12d-589f-4719-9a95-12c5e28fa51a)

kerem commented

2026-03-02 11:52:06 +03:00

Author

Owner

@Ishiguro872 commented on GitHub (Mar 5, 2025):

Interesting. How did you get this to work? I recently tried using deepseek-r1 but the tags never work. Not sure if it's because of the thinking portion of the model that just times it out

@Ishiguro872 commented on GitHub (Mar 5, 2025): Interesting. How did you get this to work? I recently tried using deepseek-r1 but the tags never work. Not sure if it's because of the thinking portion of the model that just times it out

kerem commented

2026-03-02 11:52:06 +03:00

Author

Owner

@jangrewe commented on GitHub (Mar 6, 2025):

Uhm, i didn't do anything special, i just made sure that it works in Ollama (with Open WebUI) and then set it as the model to be used for text inference in Hoarder. 🙂

@jangrewe commented on GitHub (Mar 6, 2025): Uhm, i didn't do anything special, i just made sure that it works in Ollama (with Open WebUI) and then set it as the model to be used for text inference in Hoarder. 🙂

kerem commented

2026-03-02 11:52:06 +03:00

Author

Owner

@insanemal commented on GitHub (Mar 10, 2025):

I'm also successfully using R1. It's fantastic for tagging. However there are two issues, both already have tickets.

This one is the most pressing however. It makes the summaries almost useless, especially in terms of formatting.

So being able to filter them out would be fantastic. So would being able to edit the default prompts a bit more.

Just let me know what you need to assist with this, I can get logs/examples.

@insanemal commented on GitHub (Mar 10, 2025): I'm also successfully using R1. It's fantastic for tagging. However there are two issues, both already have tickets. This one is the most pressing however. It makes the summaries almost useless, especially in terms of formatting. So being able to filter them out would be fantastic. So would being able to edit the default prompts a bit more. Just let me know what you need to assist with this, I can get logs/examples.

kerem commented

2026-03-02 11:52:06 +03:00

Author

Owner

@huyz commented on GitHub (Mar 14, 2025):

Out of curiosity, how are reasoning models better? More appropriate tags? Just better choice of words?

@huyz commented on GitHub (Mar 14, 2025): Out of curiosity, how are reasoning models better? More appropriate tags? Just better choice of words?

kerem commented

2026-03-02 11:52:06 +03:00

Author

Owner

@cultpony commented on GitHub (May 22, 2025):

I've encountered this issue with Nebius' API offering, which seems to sometimes go for a thinking model and the tags just end up in the summary, even when I try to pick a model that has no reasoning mode like this. The Tags are fine however. The output modes for structured, plain or json all yield the same result.

@cultpony commented on GitHub (May 22, 2025): I've encountered this issue with Nebius' API offering, which seems to sometimes go for a thinking model and the <think> tags just end up in the summary, even when I try to pick a model that has no reasoning mode like this. The Tags are fine however. The output modes for structured, plain or json all yield the same result.

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

starred/karakeep#711

No description provided.

Rows
Columns