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 #3243] [BUG]: Failed to vectorize more than 1 chunk of text #2088

New Issue
Closed
opened 2026-02-22 18:28:06 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:28:06 -05:00
Owner
Copy Link
Copy Source

Originally created by @ltcstar on GitHub (Feb 17, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3243

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

Big file in more than 1 chunk will fail to be vectorized

[backend] info: Adding new vectorized document into namespace deekseek-r1-7b-rag
[backend] info: [RecursiveSplitter] Will split with {"chunkSize":8192,"chunkOverlap":20}
[backend] info: Chunks created from document: 13
[backend] info: [wa] Embedding 13 chunks of text with jeffh/intfloat-multilingual-e5-large-instruct:f16.
[backend] info: [wa] Ollama returned an empty embedding for chunk!
[backend] error: addDocumentToNamespace Ollama Failed to embed: Ollama returned an empty embedding for chunk!
[backend] error: Failed to vectorize 20241104133825982.pdf
[backend] info: [TELEMETRY SENT] {"event":"documents_embedded_in_workspace","distinctId":"a891237d-cdae-4e62-a7c8-ed7da4fdf488","properties":{"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"lancedb","TTSSelection":"native","runtime":"desktop"}}
[backend] info: [Event Logged] - workspace_documents_added

However, small file in 1 chunk will be successful

[backend] info: Adding new vectorized document into namespace deekseek-r1-7b-rag
[backend] info: [RecursiveSplitter] Will split with {"chunkSize":8192,"chunkOverlap":20}
[backend] info: Chunks created from document: 1
[backend] info: [wa] Embedding 1 chunks of text with jeffh/intfloat-multilingual-e5-large-instruct:f16.
[backend] info: Inserting vectorized chunks into LanceDB collection.
[backend] info: Caching vectorized results of custom-documents/test.txt-5cce7bde-25c3-4f98-a735-ee962ee7858b.json to prevent duplicated embedding.
[backend] info: [TELEMETRY SENT] {"event":"documents_embedded_in_workspace","distinctId":"a891237d-cdae-4e62-a7c8-ed7da4fdf488","properties":{"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"lancedb","TTSSelection":"native","runtime":"desktop"}}
[backend] info: [Event Logged] - workspace_documents_added

Are there known steps to reproduce?

model provider is Ollama
LLM is deepseek-r1:7b
Embedding model is jeffh/intfloat-multilingual-e5-large-instruct:f16

Originally created by @ltcstar on GitHub (Feb 17, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3243 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? Big file in more than 1 chunk will fail to be vectorized > [backend] info: Adding new vectorized document into namespace deekseek-r1-7b-rag [backend] info: [RecursiveSplitter] Will split with {"chunkSize":8192,"chunkOverlap":20} [backend] info: Chunks created from document: 13 [backend] info: [wa] Embedding 13 chunks of text with jeffh/intfloat-multilingual-e5-large-instruct:f16. [backend] info: [wa] **Ollama returned an empty embedding for chunk!** [backend] **error**: addDocumentToNamespace Ollama Failed to embed: Ollama returned an empty embedding for chunk! [backend] **error**: Failed to vectorize 20241104133825982.pdf [backend] info: [TELEMETRY SENT] {"event":"documents_embedded_in_workspace","distinctId":"a891237d-cdae-4e62-a7c8-ed7da4fdf488","properties":{"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"lancedb","TTSSelection":"native","runtime":"desktop"}} [backend] info: [Event Logged] - workspace_documents_added However, small file in 1 chunk will be successful > [backend] info: Adding new vectorized document into namespace deekseek-r1-7b-rag [backend] info: [RecursiveSplitter] Will split with {"chunkSize":8192,"chunkOverlap":20} [backend] info: Chunks created from document: 1 [backend] info: [wa] Embedding 1 chunks of text with jeffh/intfloat-multilingual-e5-large-instruct:f16. [backend] info: Inserting vectorized chunks into LanceDB collection. [backend] info: Caching vectorized results of custom-documents/test.txt-5cce7bde-25c3-4f98-a735-ee962ee7858b.json to prevent duplicated embedding. [backend] info: [TELEMETRY SENT] {"event":"documents_embedded_in_workspace","distinctId":"a891237d-cdae-4e62-a7c8-ed7da4fdf488","properties":{"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"lancedb","TTSSelection":"native","runtime":"desktop"}} [backend] info: [Event Logged] - workspace_documents_added ### Are there known steps to reproduce? model provider is Ollama LLM is deepseek-r1:7b Embedding model is jeffh/intfloat-multilingual-e5-large-instruct:f16
yindo added the possible bug label 2026-02-22 18:28:06 -05:00
yindo closed this issue 2026-02-22 18:28:06 -05:00
yindo commented 2026-02-22 18:28:06 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Feb 17, 2025):

Most commonly, when this happens it is because:

  • Ollama is not being reached (probably not the case here)
  • Ollama is crashing trying to embed your text for some reason (usually memory).

Youll need to check Ollama's logs to see what the crash or 500 error is.

@timothycarambat commented on GitHub (Feb 17, 2025): Most commonly, when this happens it is because: - Ollama is not being reached (probably not the case here) - Ollama is crashing trying to embed your text for some reason (usually memory). Youll need to check Ollama's logs to see what the crash or 500 error is.
yindo changed title from [BUG]: Failed to vectorize more than 1 chunk of text to [GH-ISSUE #3243] [BUG]: Failed to vectorize more than 1 chunk of text 2026-06-05 14:44:28 -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#2088
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?