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 #1720] [BUG]: Failed to add document, document extraction failed. #1123

New Issue
Closed
opened 2026-02-22 18:23:12 -05:00 by yindo · 3 comments
yindo commented 2026-02-22 18:23:12 -05:00
Owner
Copy Link
Copy Source

Originally created by @sonlige on GitHub (Jun 18, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1720

How are you running AnythingLLM?

Docker (local)

What happened?

Hello, I am from China, and I am running AnythingLLM on a server using Docker and accessing its interface in a browser. Then I upload files, and after the files are uploaded, I submit them to the workspace. However, I get an extraction failure. My ollama already has the qwen2 model downloaded, and AnythingLLM is able to connect to the qwen2 model during initialization.

Are there known steps to reproduce?

No response

Originally created by @sonlige on GitHub (Jun 18, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1720 ### How are you running AnythingLLM? Docker (local) ### What happened? Hello, I am from China, and I am running AnythingLLM on a server using Docker and accessing its interface in a browser. Then I upload files, and after the files are uploaded, I submit them to the workspace. However, I get an extraction failure. My ollama already has the qwen2 model downloaded, and AnythingLLM is able to connect to the qwen2 model during initialization. ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:23:12 -05:00
yindo closed this issue 2026-02-22 18:23:12 -05:00
yindo commented 2026-02-22 18:23:13 -05:00
Author
Owner
Copy Link
Copy Source

@dalekirkwood commented on GitHub (Jun 19, 2024):

I'm getting this error every time I try to upload a file - I'm running on Railway but we are considering the cloud version. We just wanted to test. Is the cloud version more reliable?

Error: Unexpected token '<', "<!doctype "... is not valid JSON

Could this be the same bug or should I open a new ticket?

@dalekirkwood commented on GitHub (Jun 19, 2024): I'm getting this error every time I try to upload a file - I'm running on Railway but we are considering the cloud version. We just wanted to test. Is the cloud version more reliable? Error: Unexpected token '<', "<!doctype "... is not valid JSON Could this be the same bug or should I open a new ticket?
yindo commented 2026-02-22 18:23:13 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jun 19, 2024):

@sonlige - Qwen is an LLM, what are you using for your embedding model. I have seen people try to use an LLM as their embedder and that usually is the issue for some. If you are using the default embedder this shouldn't be an issue. What is your setup?

@dalekirkwood the error you got indicates that the upload failed from trying to embed a large file. Its worth noting that the built-in embedder runs on CPU and even a moderate document on Railways default container size is one 1vCPU and like 512MB of RAM and will crash unless you allocate more resources.

Check the logs and/or resources and you'll probably see it maxed out and that is why it crashed. Railway will auto-reboot on crash, but the logs will persist from the crash. If it crashes with no exit code, that is the reason.

@timothycarambat commented on GitHub (Jun 19, 2024): @sonlige - Qwen is an LLM, what are you using for your embedding model. I have seen people try to use an LLM as their embedder and that usually is the issue for some. If you are using the default embedder this shouldn't be an issue. What is your setup? @dalekirkwood the error you got indicates that the upload failed from trying to embed a large file. Its worth noting that the built-in embedder runs on CPU and even a moderate document on Railways _default_ container size is one 1vCPU and like 512MB of RAM and will crash unless you allocate more resources. Check the logs and/or resources and you'll probably see it maxed out and that is why it crashed. Railway will auto-reboot on crash, but the logs will persist from the crash. If it crashes with no exit code, that is the reason.
yindo commented 2026-02-22 18:23:13 -05:00
Author
Owner
Copy Link
Copy Source

@sonlige commented on GitHub (Jun 19, 2024):

@timothycarambat Thank you for your reply. I successfully uploaded the file by modifying the embedder and changing it to the Ollama connection.

@sonlige commented on GitHub (Jun 19, 2024): @timothycarambat Thank you for your reply. I successfully uploaded the file by modifying the embedder and changing it to the Ollama connection.
yindo changed title from [BUG]: Failed to add document, document extraction failed. to [GH-ISSUE #1720] [BUG]: Failed to add document, document extraction failed. 2026-06-05 14:39:06 -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#1123
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?