Hi, I would like to do a RAG using deepseek as LLM in n8n cloud. But I found that there is no deepseek embedding API. Anyone know how to do it ? Thanks
You can use HTTP Request node . refer to https://api-docs.deepseek.com/
Hi,
Yes, But how to use it as embedding node ?
Thanks
Marco
Hi,
Thank you for your prompt reply. I mean the embedding node, I can connect Deepseek LLM using Deepseek chat node. But this cannot use as embedding.
Thanks
Marco
Why use Deepseek in the first place? If you really need to use it, you may use openrouter.ai
Hi Peter,
Same issue that n8n hasn’t provided embedding node for openrouter. Please correct me if i am wrong.
Thanks.
Marco
You are absolutely right. Embedding doesn’t seem to work for vector storing.

