[GH-ISSUE #4454] [FEAT]: embedder chunk and text-chunk is the same unit (character) #2839

Closed
opened 2026-02-22 18:31:29 -05:00 by yindo · 1 comment
Owner

Originally created by @kalle07 on GitHub (Sep 30, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4454

What would you like to see?

Image ALSO embedder chunk are character

its proved by two users, can you please mention "character" also there! like the emebdder-text-chunk

and maybe add a small calculation inernal that show up the estimated token (close to that numbers)
5000chars are ~1200token (I chose only 5000chars because that is one page)
chars / 4.2 ~ token

and if we are there "LLM chunk-size ... maybe mention there, that it must be setup in the provider, at least in LM-Studio model setup
THX

Originally created by @kalle07 on GitHub (Sep 30, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4454 ### What would you like to see? <img width="929" height="517" alt="Image" src="https://github.com/user-attachments/assets/fc532402-0371-41db-9dbf-676fd6e75823" /> ALSO embedder chunk are character its proved by two users, can you please mention "character" also there! like the emebdder-text-chunk and maybe add a small calculation inernal that show up the estimated token (close to that numbers) 5000chars are ~1200token (I chose only 5000chars because that is one page) chars / 4.2 ~ token and if we are there "LLM chunk-size ... maybe mention there, that it must be setup in the provider, at least in LM-Studio model setup THX
yindo added the enhancementcore-team-onlyfeature request labels 2026-02-22 18:31:29 -05:00
yindo closed this issue 2026-02-22 18:31:29 -05:00
Author
Owner

@Guru6163 commented on GitHub (Oct 8, 2025):

I would like to work on this @kalle07 @timothycarambat

@Guru6163 commented on GitHub (Oct 8, 2025): I would like to work on this @kalle07 @timothycarambat
yindo changed title from [FEAT]: embedder chunk and text-chunk is the same unit (character) to [GH-ISSUE #4454] [FEAT]: embedder chunk and text-chunk is the same unit (character) 2026-06-05 14:48:49 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#2839