[BUG]: Embedding ollama+llama2-chinese , chinese docx failed

[wilsonlv]

How are you running AnythingLLM?

Docker (local)

What happened?

Are there known steps to reproduce?

No response

[timothycarambat]

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?

[wilsonlv]

Yea, if I add a English docx，it successes

[timothycarambat]

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