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 #1163] [BUG]: failing to add multiple documents at the same time. #717

New Issue
Closed
opened 2026-02-22 18:20:58 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:20:58 -05:00
Owner
Copy Link
Copy Source

Originally created by @itsbaraa on GitHub (Apr 21, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1163

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

uplading more than 5 documents in the embedding tab fails, I have to add them one by one.
if you have a lot of documents it will be a hassle.

Are there known steps to reproduce?

to reproduce the error simply drag 5 or more documents and drop them in the documents tab and some files will fail to be added.

Originally created by @itsbaraa on GitHub (Apr 21, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1163 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? uplading more than 5 documents in the embedding tab fails, I have to add them one by one. if you have a lot of documents it will be a hassle. ### Are there known steps to reproduce? to reproduce the error simply drag 5 or more documents and drop them in the documents tab and some files will fail to be added.
yindo added the possible bug label 2026-02-22 18:20:58 -05:00
yindo closed this issue 2026-02-22 18:20:58 -05:00
yindo commented 2026-02-22 18:20:59 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Apr 21, 2024):

This is because you likely do not have enough resources to be able to embed that many text chunks at the same time - exhausting the CPU resources for the thread. We do what we can to parallelize embeddings but this is ultimately limited by your device's ability to do the work required for that demand. It is possible your device could do it, but also may be artificially throttle by some other kind of process manager.

The alternative is to use an offloaded service to do embeddings locally or on a cloud. (Ollama, OpenAi, etc) or upload the documents one-by-one to ensure the CPU can handle the workload.

@timothycarambat commented on GitHub (Apr 21, 2024): This is because you likely do not have enough resources to be able to embed that many text chunks at the same time - exhausting the CPU resources for the thread. We do what we can to parallelize embeddings but this is ultimately limited by your device's ability to do the work required for that demand. It is possible your device _could_ do it, but also may be artificially throttle by some other kind of process manager. The alternative is to use an offloaded service to do embeddings locally or on a cloud. (Ollama, OpenAi, etc) or upload the documents one-by-one to ensure the CPU can handle the workload.
yindo changed title from [BUG]: failing to add multiple documents at the same time. to [GH-ISSUE #1163] [BUG]: failing to add multiple documents at the same time. 2026-06-05 14:36:49 -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#717
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?