[GH-ISSUE #2042] [BUG]: Embed document of pdf failed #1330

Closed
opened 2026-02-22 18:24:18 -05:00 by yindo · 1 comment
Owner

Originally created by @sfdeggb on GitHub (Aug 4, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2042

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

When I tried to upload a text PDF document to use the embedded model, the embedding failed: an error message was displayed
image
When I tried embedding with a test txt document, it appeared correct.
image
When I tried to view the server log, it showed:
image

except helpful solution!

Are there known steps to reproduce?

  1. LLM: ollama gemma2:2b
    image
  2. vector database: LanceDB
    image
  3. embeding model : nomic_embed_text_least
    image
  4. Max Embedding Chunk Length: 509
    image
Originally created by @sfdeggb on GitHub (Aug 4, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2042 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? When I tried to upload a text PDF document to use the embedded model, the embedding failed: an error message was displayed ![image](https://github.com/user-attachments/assets/72c35ce1-9622-453d-b26c-757714c16b24) When I tried embedding with a test txt document, it appeared correct. ![image](https://github.com/user-attachments/assets/fd3a4e22-7d01-4256-9b83-817337541566) When I tried to view the server log, it showed: ![image](https://github.com/user-attachments/assets/12a7c1f9-1fb3-49b1-95e4-c0a9a5258100) except helpful solution! ### Are there known steps to reproduce? 1. LLM: ollama gemma2:2b ![image](https://github.com/user-attachments/assets/aa4b2a6d-7eb3-4c04-9f57-122df05d3fac) 2. vector database: LanceDB ![image](https://github.com/user-attachments/assets/3c02ef2f-a83c-49a9-aa4d-c5bdf2e5d59a) 3. embeding model : nomic_embed_text_least ![image](https://github.com/user-attachments/assets/b3949e90-cb54-4efe-9289-7cdd8c3a9ad1) 4. Max Embedding Chunk Length: 509 ![image](https://github.com/user-attachments/assets/11631b4e-f35e-46ee-a727-d83f90f47ee5)
yindo added the possible bug label 2026-02-22 18:24:18 -05:00
yindo closed this issue 2026-02-22 18:24:18 -05:00
Author
Owner

@timothycarambat commented on GitHub (Aug 5, 2024):

This is an error wth your Ollama client, not AnythingLLM. We are simply reporting the error back to let you know it failed. Ollama returning a 499 indicates the model could not be loaded due to VRAM constraints - you likely do not have the system specs to hot load both an LLM and embedder into the system memory. You should remove the keep alive setting you modified as that is probably locking up the system memory preventing the embedder from loading.

@timothycarambat commented on GitHub (Aug 5, 2024): This is an error wth your Ollama client, not AnythingLLM. We are simply reporting the error back to let you know it failed. Ollama returning a 499 indicates the model could not be loaded due to VRAM constraints - you likely do not have the system specs to hot load both an LLM and embedder into the system memory. You should remove the keep alive setting you modified as that is probably locking up the system memory preventing the embedder from loading.
yindo changed title from [BUG]: Embed document of pdf failed to [GH-ISSUE #2042] [BUG]: Embed document of pdf failed 2026-06-05 14:40:12 -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#1330