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 #5173] [FEAT]: LLM expansion prior to RAG query #4951

New Issue
Closed
opened 2026-06-05 14:51:05 -04:00 by yindo · 2 comments
yindo commented 2026-06-05 14:51:05 -04:00
Owner
Copy Link
Copy Source

Originally created by @karelo911 on GitHub (Mar 8, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5173

What would you like to see?

I'm developing a rag agent where I want to ask the llm to generate relevant keywords to my prompt and initiate a more extensive query on my saved documents. Will this be possible in future versions of anythingllm?

Originally created by @karelo911 on GitHub (Mar 8, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5173 ### What would you like to see? I'm developing a rag agent where I want to ask the llm to generate relevant keywords to my prompt and initiate a more extensive query on my saved documents. Will this be possible in future versions of anythingllm?
yindo added the enhancementfeature request labels 2026-06-05 14:51:05 -04:00
yindo closed this issue 2026-06-05 14:51:05 -04:00
yindo commented 2026-06-05 14:51:05 -04:00
Author
Owner
Copy Link
Copy Source

@spider-yamet commented on GitHub (Mar 9, 2026):

I would like to work on this issue, hope this project open for contribution.
cc: @timothycarambat

<!-- gh-comment-id:4022141078 --> @spider-yamet commented on GitHub (Mar 9, 2026): I would like to work on this issue, hope this project open for contribution. cc: @timothycarambat
yindo commented 2026-06-05 14:51:05 -04:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Mar 9, 2026):

The reason we dont have this is due to the overhead in latency and the innate black-box output that could lead to even more issues where users type in a prompt and the LLM makes vast assumptions on the query that then is passed to final inference making the final output worse.

As a user, my prompt should be my prompt. If i wanted something more I would ask!

<!-- gh-comment-id:4025589771 --> @timothycarambat commented on GitHub (Mar 9, 2026): The reason we dont have this is due to the overhead in latency and the innate black-box output that could lead to _even more_ issues where users type in a prompt and the LLM makes vast assumptions on the query that then is passed to final inference making the final output worse. As a user, my prompt should be my prompt. If i wanted something more I would ask!
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#4951
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?