[GH-ISSUE #1002] [BUG]: Embedding ollama+llama2-chinese , chinese docx failed #614

Closed
opened 2026-02-22 18:20:28 -05:00 by yindo · 3 comments
Owner

Originally created by @wilsonlv on GitHub (Apr 1, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1002

How are you running AnythingLLM?

Docker (local)

What happened?

微信图片_20240401162520
微信图片_20240401162525

Are there known steps to reproduce?

No response

Originally created by @wilsonlv on GitHub (Apr 1, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1002 ### How are you running AnythingLLM? Docker (local) ### What happened? ![微信图片_20240401162520](https://github.com/Mintplex-Labs/anything-llm/assets/17563749/f46296f3-a839-49b7-8458-c35037a08686) ![微信图片_20240401162525](https://github.com/Mintplex-Labs/anything-llm/assets/17563749/7cb79beb-bec0-450a-8ee8-239d0791ad8e) ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:20:28 -05:00
yindo closed this issue 2026-02-22 18:20:28 -05:00
Author
Owner

@timothycarambat commented on GitHub (Apr 1, 2024):

It would seem to indicate that the Ollama embedder returned a zero-length vector. Can you confirm if this embedder is processing text chunks properly manually first?

@timothycarambat commented on GitHub (Apr 1, 2024): It would seem to indicate that the Ollama embedder returned a zero-length vector. Can you confirm if this embedder is processing text chunks properly manually first?
Author
Owner

@wilsonlv commented on GitHub (Apr 1, 2024):

image
Yea, if I add a English docx,it successes

@wilsonlv commented on GitHub (Apr 1, 2024): ![image](https://github.com/Mintplex-Labs/anything-llm/assets/17563749/6eafffad-4426-456e-b03e-20baaa76bea3) Yea, if I add a English docx,it successes
Author
Owner

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

Closing as wontfix, I did not notice prior but you have an LLM chat model llama2-chinese as your embedding model.
LLMs cannot embed text. Please use an embedding model like nomic-text-embed or mxbai for Chinese lang support embeddings

@timothycarambat commented on GitHub (Apr 19, 2024): Closing as wontfix, I did not notice prior but you have an LLM **chat** model `llama2-chinese` as your embedding model. LLMs cannot embed text. Please use an embedding model like `nomic-text-embed` or `mxbai` for Chinese lang support embeddings
yindo changed title from [BUG]: Embedding ollama+llama2-chinese , chinese docx failed to [GH-ISSUE #1002] [BUG]: Embedding ollama+llama2-chinese , chinese docx failed 2026-06-05 14:36:17 -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#614