Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 22:23:50 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #2262] [FEAT]: Name threads with AI generated summary text #1479

New Issue
Closed
opened 2026-02-22 18:25:01 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:25:01 -05:00
Owner
Copy Link
Copy Source

Originally created by @glinkot on GitHub (Sep 10, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2262

What would you like to see?

Right now I just see conversations shown as 'thread' and 'new thread'. Other similar tools I've used use a lighter/cheaper LLM to generate a brief name for the chat, like "asking about dog breeds" or whatever. This request was asking for it I believe (https://github.com/Mintplex-Labs/anything-llm/issues/701) but what was implemented was different to what I'm referring to.

Originally created by @glinkot on GitHub (Sep 10, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2262 ### What would you like to see? Right now I just see conversations shown as 'thread' and 'new thread'. Other similar tools I've used use a lighter/cheaper LLM to generate a brief name for the chat, like "asking about dog breeds" or whatever. This request was asking for it I believe (https://github.com/Mintplex-Labs/anything-llm/issues/701) but what was implemented was different to what I'm referring to.
yindo added the enhancementfeature request labels 2026-02-22 18:25:01 -05:00
yindo closed this issue 2026-02-22 18:25:01 -05:00
yindo commented 2026-02-22 18:25:01 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Sep 11, 2024):

Yes, and the primary reason is latency. Not everyone is using a high (or even mid) tier performance device and the latency to a load the model, run inference, and store the text, with a high speed. Most would not be willing to wait an additional 1-2s for inference completion just to name a thread, which is why the implementation was different.

So as it stands now, which is naming a thread based on the first chat, this is both fast for any device and LLM implementation but gets the idea of delineating chat threads without the user needing to explicitly rename them. Add an LLM into that process for what amounts to a very minor UX improvement was considered extraneous and would hurt the UX on lower-end systems using local models.

This consideration makes sense on a cloud platform where some minimum performance can be assured. Give the variability of systems, LLM runtimes and models, and other factors lead to its current state.

@timothycarambat commented on GitHub (Sep 11, 2024): Yes, and the primary reason is latency. Not everyone is using a high (or even mid) tier performance device and the latency to a load the model, run inference, and store the text, with a high speed. Most would not be willing to wait an additional 1-2s for inference completion just to name a thread, which is why the implementation was different. So as it stands now, which is naming a thread based on the first chat, this is both fast for any device and LLM implementation but gets the idea of delineating chat threads without the user needing to explicitly rename them. Add an LLM into that process for what amounts to a very minor UX improvement was considered extraneous and would hurt the UX on lower-end systems using local models. This consideration makes sense on a cloud platform where some minimum performance can be assured. Give the variability of systems, LLM runtimes and models, and other factors lead to its current state.
yindo changed title from [FEAT]: Name threads with AI generated summary text to [GH-ISSUE #2262] [FEAT]: Name threads with AI generated summary text 2026-06-05 14:40:58 -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#1479
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?