[GH-ISSUE #5096] [BUG]: Error: 1 documents failed to add. Could not embed document chunks! #4915

Closed
opened 2026-06-05 14:50:50 -04:00 by yindo · 1 comment
Owner

Originally created by @TCMAD on GitHub (Mar 1, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5096

How are you running AnythingLLM?

Docker (remote machine)

What happened?

Hello,

I have difficulty adding large PDF and EPUB files into my workspace. For shorter file, I don't have this problem.

The UI display the following output : Error: 1 documents failed to add. Could not embed document chunks! This document will not be recorded.

After a docker tail on the container.

# output
[backend] info: [VectorDB::LanceDb] Snippets created from document: 50
[backend] info: [OpenRouterEmbedder] Embedding 50 document chunks...
[backend] info: [VectorDB::LanceDb] addDocumentToNamespace Could not embed document chunks! This document will not be recorded.
[backend] error: Failed to vectorize large_book.pdf
[backend] info: [Event Logged] - workspace_documents_added
[backend] info: [VectorDB::LanceDb] Adding new vectorized document into namespace iaristote
[backend] info: [RecursiveSplitter] Will split with {"chunkSize":8191,"chunkOverlap":20,"chunkHeader":"<document_metadata>\nsourceDocument: Ne_faites_plus..."
}
[backend] info: [TELEMETRY SENT] {"event":"documents_embedded_in_workspace","distinctId":"3566098f-0483-4fe2-88d2-4d1e81d32a23","properties":{"LLMSelection":"
openrouter","Embedder":"openrouter","VectorDbSelection":"lancedb","TTSSelection":"native","LLMModel":"anthropic/claude-sonnet-4.5","runtime":"docker"}}

Does this issue come from the embedded model or the vector database ?
What is your advice to properly set up (change embedding model, vectorDB ???) my AnythingLLM instance and deal with large files ?

Are there known steps to reproduce?

No response

Originally created by @TCMAD on GitHub (Mar 1, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5096 ### How are you running AnythingLLM? Docker (remote machine) ### What happened? Hello, I have difficulty adding large PDF and EPUB files into my workspace. For shorter file, I don't have this problem. The UI display the following output : `Error: 1 documents failed to add. Could not embed document chunks! This document will not be recorded.` After a `docker tail` on the container. ``` # output [backend] info: [VectorDB::LanceDb] Snippets created from document: 50 [backend] info: [OpenRouterEmbedder] Embedding 50 document chunks... [backend] info: [VectorDB::LanceDb] addDocumentToNamespace Could not embed document chunks! This document will not be recorded. [backend] error: Failed to vectorize large_book.pdf [backend] info: [Event Logged] - workspace_documents_added [backend] info: [VectorDB::LanceDb] Adding new vectorized document into namespace iaristote [backend] info: [RecursiveSplitter] Will split with {"chunkSize":8191,"chunkOverlap":20,"chunkHeader":"<document_metadata>\nsourceDocument: Ne_faites_plus..." } [backend] info: [TELEMETRY SENT] {"event":"documents_embedded_in_workspace","distinctId":"3566098f-0483-4fe2-88d2-4d1e81d32a23","properties":{"LLMSelection":" openrouter","Embedder":"openrouter","VectorDbSelection":"lancedb","TTSSelection":"native","LLMModel":"anthropic/claude-sonnet-4.5","runtime":"docker"}} ``` Does this issue come from the embedded model or the vector database ? What is your advice to properly set up (change embedding model, vectorDB ???) my AnythingLLM instance and deal with large files ? ### Are there known steps to reproduce? _No response_
yindo added the possible bugneeds info / can't replicate labels 2026-06-05 14:50:50 -04:00
yindo closed this issue 2026-06-05 14:50:50 -04:00
Author
Owner

@timothycarambat commented on GitHub (Mar 2, 2026):

This is most certainly a config issue - what model are you using for the embedder?
I know it shows OpenRouterEmbedder, but you would not believe how many people try to use an LLM for embedding - which will result in exactly what you are seeing.

<!-- gh-comment-id:3985173721 --> @timothycarambat commented on GitHub (Mar 2, 2026): This is most certainly a config issue - what model are you using for the embedder? I know it shows `OpenRouterEmbedder`, but you would not believe how many people try to use an LLM for embedding - which will result in exactly what you are seeing.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#4915