You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am using n8n with LiteLLM (Gemini passthrough) for AI tasks. However, I noticed that only the chat model respects the defined API baseUrl, while the embedding model does not.
After reviewing the source code, it seems this issue is caused by the GoogleGenerativeAIEmbeddings function in the package, which does not provide a way to change the API baseUrl—unlike ChatGoogleGenerativeAI, which does.
Is there any particular reason why GoogleGenerativeAIEmbeddings does not support changing the baseUrl?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I am using n8n with LiteLLM (Gemini passthrough) for AI tasks. However, I noticed that only the chat model respects the defined API
baseUrl, while the embedding model does not.After reviewing the source code, it seems this issue is caused by the
GoogleGenerativeAIEmbeddingsfunction in the package, which does not provide a way to change the APIbaseUrl—unlikeChatGoogleGenerativeAI, which does.Is there any particular reason why
GoogleGenerativeAIEmbeddingsdoes not support changing thebaseUrl?Beta Was this translation helpful? Give feedback.
All reactions