[GH-ISSUE #4560] BUG] Local LLM Overrides Embedder: Chat model name used for embedding requests regardless of Embedder setting. #2896

Closed
opened 2026-02-22 18:31:43 -05:00 by yindo · 1 comment
Owner

Originally created by @jackhouwing on GitHub (Oct 18, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4560

How are you running AnythingLLM?

Docker (local)

What happened?

Diagnosis: AnythingLLM's Document Parser Failure; only those files that have a .txt extension are embedded in AnythingLLM. Files with a .docx or .doc or .xls or .xlsx are not embedded in AnythingLLM; While AnythingLLM claims to support all these formats (search result 1.1), the process of extracting text from a complex binary format (like a DOCX or XLSX file) is handled by an internal parser within AnythingLLM. This parser often fails due to:

Missing Dependencies: The AnythingLLM Windows desktop app might be missing a necessary internal library to correctly read the Office format.

File Complexity: Complex formatting, images, or protected data within your specific Office files are causing the parser to crash or return empty text.

The text extraction step (before embedding) is failing locally, meaning there's no text to send to OpenAI.

Are there known steps to reproduce?

No response

Originally created by @jackhouwing on GitHub (Oct 18, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4560 ### How are you running AnythingLLM? Docker (local) ### What happened? Diagnosis: AnythingLLM's Document Parser Failure; only those files that have a .txt extension are embedded in AnythingLLM. Files with a .docx or .doc or .xls or .xlsx are not embedded in AnythingLLM; While AnythingLLM claims to support all these formats (search result 1.1), the process of extracting text from a complex binary format (like a DOCX or XLSX file) is handled by an internal parser within AnythingLLM. This parser often fails due to: Missing Dependencies: The AnythingLLM Windows desktop app might be missing a necessary internal library to correctly read the Office format. File Complexity: Complex formatting, images, or protected data within your specific Office files are causing the parser to crash or return empty text. The text extraction step (before embedding) is failing locally, meaning there's no text to send to OpenAI. ### Are there known steps to reproduce? _No response_
yindo added the possible bugneeds info / can't replicate labels 2026-02-22 18:31:43 -05:00
yindo closed this issue 2026-02-22 18:31:43 -05:00
Author
Owner

@timothycarambat commented on GitHub (Oct 22, 2025):

Do you have a repro or video/screenshot of this? I can upload docx, xlsx, and other types without issue. You also listed this as Docker, but then talk about desktop - which is it?

@timothycarambat commented on GitHub (Oct 22, 2025): Do you have a repro or video/screenshot of this? I can upload docx, xlsx, and other types without issue. You also listed this as Docker, but then talk about desktop - which is it?
yindo changed title from BUG] Local LLM Overrides Embedder: Chat model name used for embedding requests regardless of Embedder setting. to [GH-ISSUE #4560] BUG] Local LLM Overrides Embedder: Chat model name used for embedding requests regardless of Embedder setting. 2026-06-05 14:49:09 -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#2896