How does Model Selector node process fallbacks?

Questions
, ,
1

There is a new Model Selector node. Documentation says it “enables implementing fallback mechanisms for error handling“.

image
image803×358 26.1 KB

The problem is – it’s completely not clear how to use this node for implementing fallbacks. It only receives data from incoming nodes. Sub-nodes or responses are not working here.

Are there any clarifications on how to create fallbacks in Model Selector?

BTW, I’m not talking about built-in fallback feature inside LLM-root nodes. They only support a single fallback option.

1 Like
2

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.

3

Bump, I agree I have no idea how to enable that functionality, expect some tricky way like settings/on fail=error_output and adding some logic to catch error, but I understood selected by OP docs text as builin fuctionality for this node (model selector)