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 #1534] [BUG]: tried to load a PDF book of size 383MB. It worked fine in an i7 Windows (16GB RAM), but it failed to embed the doc in Mac i7 (intel mac) 16GB RAM #985

New Issue
Closed
opened 2026-02-22 18:22:32 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:22:32 -05:00
Owner
Copy Link
Copy Source

Originally created by @annamalaiarunachalam on GitHub (May 25, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1534

How are you running AnythingLLM?

Docker (local)

What happened?

in the mac (16GB RAM, i7 processor with 4 core), I am able to load the pdf doc (383MB size), I moved it to the workspace. when I clicked embed and save, it takes 5 to 6 mins, then throws the message below:
[1 doc failed to load
cannot embed doc]
I think it has nothing to do with the embed model and the LLM. I chose nomic-1.5 as embedding model. Both these models are served by ollama server which was running.

I used LM Studio in windows, but there is no Intel Mac version of LM studio, hence chose ollama for Intel MAC

Are there known steps to reproduce?

adding a 383MB size PDF - for chatting with pdf locally - embed and save throwing error - in a i7 intel based MAC with 16GB RAM, using Nomic-1.5 embedding model served by ollama from the same mac instance.

Originally created by @annamalaiarunachalam on GitHub (May 25, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1534 ### How are you running AnythingLLM? Docker (local) ### What happened? in the mac (16GB RAM, i7 processor with 4 core), I am able to load the pdf doc (383MB size), I moved it to the workspace. when I clicked embed and save, it takes 5 to 6 mins, then throws the message below: [1 doc failed to load cannot embed doc] I think it has nothing to do with the embed model and the LLM. I chose nomic-1.5 as embedding model. Both these models are served by ollama server which was running. I used LM Studio in windows, but there is no Intel Mac version of LM studio, hence chose ollama for Intel MAC ### Are there known steps to reproduce? adding a 383MB size PDF - for chatting with pdf locally - embed and save throwing error - in a i7 intel based MAC with 16GB RAM, using Nomic-1.5 embedding model served by ollama from the same mac instance.
yindo added the possible bug label 2026-02-22 18:22:32 -05:00
yindo closed this issue 2026-02-22 18:22:32 -05:00
yindo commented 2026-02-22 18:22:33 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (May 25, 2024):

In this particular circumstance I think that the ollama process is running out of memory processing all the document chunks at once - resulting in too many concurrent chunks. What do the ollama logs say? It should be exiting with some kind of OOM memory error.

Also, I have a similar setup (windows comp with GPU and Intel Mac) and all i do is run ngrok http 1234 after starting the windows LMStudio server, and then use that URL in my Intel Mac LMStudio integration in AnythingLLM and you get the best of both worlds.

@timothycarambat commented on GitHub (May 25, 2024): In this particular circumstance I think that the ollama process is running out of memory processing all the document chunks at once - resulting in too many concurrent chunks. What do the ollama logs say? It should be exiting with some kind of OOM memory error. Also, I have a similar setup (windows comp with GPU and Intel Mac) and all i do is run `ngrok http 1234` after starting the windows LMStudio server, and then use that URL in my Intel Mac LMStudio integration in AnythingLLM and you get the best of both worlds.
yindo changed title from [BUG]: tried to load a PDF book of size 383MB. It worked fine in an i7 Windows (16GB RAM), but it failed to embed the doc in Mac i7 (intel mac) 16GB RAM to [GH-ISSUE #1534] [BUG]: tried to load a PDF book of size 383MB. It worked fine in an i7 Windows (16GB RAM), but it failed to embed the doc in Mac i7 (intel mac) 16GB RAM 2026-06-05 14:38:19 -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 possible bug
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#985
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?