[GH-ISSUE #3280] [BUG]: pinned documents that have ~200k tokens (~0.5MB .txt file) breaking AnythingLLM Docker version #2109

Closed
opened 2026-02-22 18:28:11 -05:00 by yindo · 3 comments
Owner

Originally created by @severfire on GitHub (Feb 19, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3280

How are you running AnythingLLM?

Docker (local)

What happened?

  1. Pin .5MB .txt file to workspace
  2. have Google Gemini with 1m token context window set
  3. CPU goes to 100%
  4. after some time AnythingLLM breaks

Are there known steps to reproduce?

No response

Originally created by @severfire on GitHub (Feb 19, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3280 ### How are you running AnythingLLM? Docker (local) ### What happened? 1. Pin .5MB .txt file to workspace 2. have Google Gemini with 1m token context window set 3. CPU goes to 100% 4. after some time AnythingLLM breaks ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:28:11 -05:00
yindo closed this issue 2026-02-22 18:28:11 -05:00
Author
Owner

@timothycarambat commented on GitHub (Feb 19, 2025):

Are you running docker on a single CPU core with minimal RAM?
How many words is this document and are you sure about the token count or are you estimating?

@timothycarambat commented on GitHub (Feb 19, 2025): Are you running docker on a single CPU core with minimal RAM? How many _words_ is this document and are you sure about the token count or are you estimating?
Author
Owner

@severfire commented on GitHub (Feb 19, 2025):

@timothycarambat
I tried it on my 32GB 24 core machine on docker desktop
and with real server, with 2 cores and 4GB of ram and 6GB of swam memory

both falied.
token count was made by Google AI Studio. Confirmed under the limit. ~150k tokens. Under 1m.

@severfire commented on GitHub (Feb 19, 2025): @timothycarambat I tried it on my 32GB 24 core machine on docker desktop and with real server, with 2 cores and 4GB of ram and 6GB of swam memory both falied. token count was made by Google AI Studio. Confirmed under the limit. ~150k tokens. Under 1m.
Author
Owner

@timothycarambat commented on GitHub (Oct 1, 2025):

We have resolved this with the #4261 PR

@timothycarambat commented on GitHub (Oct 1, 2025): We have resolved this with the #4261 PR
yindo changed title from [BUG]: pinned documents that have ~200k tokens (~0.5MB .txt file) breaking AnythingLLM Docker version to [GH-ISSUE #3280] [BUG]: pinned documents that have ~200k tokens (~0.5MB .txt file) breaking AnythingLLM Docker version 2026-06-05 14:44:34 -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#2109