Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #2021] [FEAT]: Support Multiple Concurrent Preset Prompts #1318

New Issue
Closed
opened 2026-02-22 18:24:15 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:24:15 -05:00
Owner
Copy Link
Copy Source

Originally created by @MrSimonC on GitHub (Aug 1, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2021

Originally assigned to: @shatfield4 on GitHub.

What would you like to see?

Building on the previous feature request #2019 - for enhanced keyboard navigation (although the two are very much separate), I'd like to propose another feature that expands the capabilities of preset prompts.

Feature Request:

Currently, users can only use one preset prompt at a time by typing / followed by the prompt name. I propose allowing users to use multiple preset prompts side by side, separated by spaces. For example: /my-context /write-an-email-as-me

Expected Behavior:

When a user types multiple preset prompts, the model should:

  1. Expand the first preset prompt (/my-context) in the background.
  2. Append the second preset prompt (/write-an-email-as-me) to the expanded first prompt.

Use Case:

In my workflow, I've found that using a "grounding" prompt to establish context within the model's window size greatly improves the quality of the generated output. However, I often need to add a specific prompt to generate the desired content. With the current limitation of only one preset prompt, I have to either:

  • Use a single prompt preset to ground the model, then hand-type the "please do this" prompt, which can be cumbersome and prone to errors.
  • Combine the grounding prompt and the specific prompt into a single preset, which becomes difficult to maintain when the grounding prompt is large or needs to be updated frequently across more than one preset.

By allowing multiple preset prompts, I can:

  • Use a grounding prompt to establish context (/my-context).
  • Add a specific prompt to generate the desired content (/write-an-email-as-me).

This would significantly improve my workflow and enable more flexible and efficient use of preset prompts.

Benefits:

  • Increased flexibility in using preset prompts.
  • Improved workflow efficiency by reducing the need for manual typing or prompt maintenance.
  • Enhanced ability to combine different prompts to achieve specific goals.

Example Use Cases:

  • /my-domain-knowledge /generate-a-summary
  • /my-writing-style /write-a-blog-post
  • /my-industry-jargon /explain-a-concept

I believe this feature would be a valuable addition to the Anything LLM project, and I'm excited to hear your thoughts on this proposal! Thanks again for reading!

Originally created by @MrSimonC on GitHub (Aug 1, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2021 Originally assigned to: @shatfield4 on GitHub. ### What would you like to see? Building on the previous feature request #2019 - for enhanced keyboard navigation (although the two are very much separate), I'd like to propose another feature that expands the capabilities of preset prompts. **Feature Request:** Currently, users can only use one preset prompt at a time by typing `/` followed by the prompt name. I propose allowing users to use multiple preset prompts side by side, separated by spaces. For example: `/my-context /write-an-email-as-me` **Expected Behavior:** When a user types multiple preset prompts, the model should: 1. Expand the first preset prompt (`/my-context`) in the background. 2. Append the second preset prompt (`/write-an-email-as-me`) to the expanded first prompt. **Use Case:** In my workflow, I've found that using a "grounding" prompt to establish context within the model's window size greatly improves the quality of the generated output. However, I often need to add a specific prompt to generate the desired content. With the current limitation of only one preset prompt, I have to either: * Use a single prompt preset to ground the model, then hand-type the "please do this" prompt, which can be cumbersome and prone to errors. * Combine the grounding prompt and the specific prompt into a single preset, which becomes difficult to maintain when the grounding prompt is large or needs to be updated frequently across more than one preset. By allowing multiple preset prompts, I can: * Use a grounding prompt to establish context (`/my-context`). * Add a specific prompt to generate the desired content (`/write-an-email-as-me`). This would significantly improve my workflow and enable more flexible and efficient use of preset prompts. **Benefits:** * Increased flexibility in using preset prompts. * Improved workflow efficiency by reducing the need for manual typing or prompt maintenance. * Enhanced ability to combine different prompts to achieve specific goals. **Example Use Cases:** * `/my-domain-knowledge /generate-a-summary` * `/my-writing-style /write-a-blog-post` * `/my-industry-jargon /explain-a-concept` I believe this feature would be a valuable addition to the Anything LLM project, and I'm excited to hear your thoughts on this proposal! Thanks again for reading!
yindo added the enhancementfeature request labels 2026-02-22 18:24:15 -05:00
yindo closed this issue 2026-02-22 18:24:15 -05:00
yindo commented 2026-02-22 18:24:15 -05:00
Author
Owner
Copy Link
Copy Source

@MrSimonC commented on GitHub (Aug 6, 2024):

Thanks so much both!

@MrSimonC commented on GitHub (Aug 6, 2024): Thanks so much both!
yindo changed title from [FEAT]: Support Multiple Concurrent Preset Prompts to [GH-ISSUE #2021] [FEAT]: Support Multiple Concurrent Preset Prompts 2026-06-05 14:40:07 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label enhancement feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#1318
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?