starred/karakeep

Fork 0

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

[GH-ISSUE #680] AI Tag Suggestions Based on Existing User Tags #441

New issue

Closed

opened 2026-03-02 11:49:54 +03:00 by kerem · 3 comments

kerem commented

2026-03-02 11:49:54 +03:00

Owner

Originally created by @LeonKohli on GitHub (Nov 20, 2024).
Original GitHub issue: https://github.com/karakeep-app/karakeep/issues/680

Describe the feature you'd like

Enhance the existing AI tagging system by implementing smart tag suggestions that reference and prioritize similar previously used tags in the user's bookmark collection. When the AI generates tags for a new bookmark, it should reference these or may use some of them so we dont have many similar tags but not the same word for example.

Describe the benefits this would bring to existing Hoarder users

Tag Consistency: Prevents tag proliferation (e.g., "programming", "coding", "dev" all meaning the same thing)
Improved Organization: Maintains a cleaner, more consolidated tag structure
Better Discoverability: Makes it easier to find related content since similar items use consistent tags
Time Savings: Users spend less time managing and consolidating duplicate tags
Enhanced Search: More reliable search results due to consistent tag usage

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

No. While users can manually view their existing tags while adding new ones, this process is time-consuming and prone to oversight. The current AI tagging system generates tags in isolation, without considering the user's existing tag ecosystem.

Have you searched for an existing open/closed issue?

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

Additional context

Idea for prompt with <PREVIOUS_TAGS_HERE>

You are a bot in a read-it-later app and your responsibility is to help with automatic tagging. Please analyze the text between the sentences "CONTENT START HERE" and "CONTENT END HERE" and suggest relevant tags that describe its key themes, topics, and main ideas. 

Here are your previously used tags that you should prioritize when appropriate:
<PREVIOUS_TAGS_HERE>

The rules are:
- First check if any of the previously used tags are relevant for this content. Reuse them when appropriate to maintain consistency.
- Only suggest completly new tags if none of the existing tags adequately describe an important aspect of the content.
- Aim for a variety of tags, including broad categories, specific keywords, and potential sub-genres.
- The tags language must be in english.
- If it's a famous website you may also include a tag for the website. If the tag is not generic enough, don't include it.
- The content can include text for cookie consent and privacy policy, ignore those while tagging.
- Aim for 3-5 tags.
- If there are no good tags, leave the array empty.

CONTENT START HERE
<CONTENT_HERE>
CONTENT END HERE

You must respond in JSON with the key "tags" and the value is an array of string tags.

Originally created by @LeonKohli on GitHub (Nov 20, 2024). Original GitHub issue: https://github.com/karakeep-app/karakeep/issues/680 ### Describe the feature you'd like Enhance the existing AI tagging system by implementing smart tag suggestions that reference and prioritize similar previously used tags in the user's bookmark collection. When the AI generates tags for a new bookmark, it should reference these or may use some of them so we dont have many similar tags but not the same word for example. ### Describe the benefits this would bring to existing Hoarder users - Tag Consistency: Prevents tag proliferation (e.g., "programming", "coding", "dev" all meaning the same thing) - Improved Organization: Maintains a cleaner, more consolidated tag structure Better Discoverability: Makes it easier to find related content since similar items use consistent tags - Time Savings: Users spend less time managing and consolidating duplicate tags - Enhanced Search: More reliable search results due to consistent tag usage ### Can the goal of this request already be achieved via other means? No. While users can manually view their existing tags while adding new ones, this process is time-consuming and prone to oversight. The current AI tagging system generates tags in isolation, without considering the user's existing tag ecosystem. ### Have you searched for an existing open/closed issue? - [X] I have searched for existing issues and none cover my fundamental request ### Additional context Idea for prompt with <PREVIOUS_TAGS_HERE> ``` You are a bot in a read-it-later app and your responsibility is to help with automatic tagging. Please analyze the text between the sentences "CONTENT START HERE" and "CONTENT END HERE" and suggest relevant tags that describe its key themes, topics, and main ideas. Here are your previously used tags that you should prioritize when appropriate: <PREVIOUS_TAGS_HERE> The rules are: - First check if any of the previously used tags are relevant for this content. Reuse them when appropriate to maintain consistency. - Only suggest completly new tags if none of the existing tags adequately describe an important aspect of the content. - Aim for a variety of tags, including broad categories, specific keywords, and potential sub-genres. - The tags language must be in english. - If it's a famous website you may also include a tag for the website. If the tag is not generic enough, don't include it. - The content can include text for cookie consent and privacy policy, ignore those while tagging. - Aim for 3-5 tags. - If there are no good tags, leave the array empty. CONTENT START HERE <CONTENT_HERE> CONTENT END HERE You must respond in JSON with the key "tags" and the value is an array of string tags. ```

kerem closed this issue

2026-03-02 11:49:54 +03:00

kerem commented

2026-03-02 11:49:55 +03:00

Author

Owner

@MohamedBassem commented on GitHub (Nov 20, 2024):

Hey, thanks a lot for taking the time and writing the feature request. We already have a PR implementing this idea in #612

@MohamedBassem commented on GitHub (Nov 20, 2024): Hey, thanks a lot for taking the time and writing the feature request. We already have a PR implementing this idea in #612

kerem commented

2026-03-02 11:49:55 +03:00

Author

Owner

@MohamedBassem commented on GitHub (Nov 20, 2024):

Closing the issue as duplicate

@MohamedBassem commented on GitHub (Nov 20, 2024): Closing the issue as duplicate

kerem commented

2026-03-02 11:49:55 +03:00

Author

Owner

@LeonKohli commented on GitHub (Nov 20, 2024):

My bad great work

@LeonKohli commented on GitHub (Nov 20, 2024): My bad great work

kerem referenced this issue

2026-03-02 11:55:01 +03:00

[GH-ISSUE #1767] [Feature Request] Enable LLM processing for Reader View content #1101

kerem referenced this issue

2026-03-02 11:55:01 +03:00

[GH-ISSUE #1767] [Feature Request] Enable LLM processing for Reader View content #1101

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#441

No description provided.

Rows
Columns