[BUG] Vector Store Retriever output can not be connected to Conversational Retrieval QA Chain's similar input

[vanetreg]

Describe the bug Vector Store Retriever output can not be connected to Conversational Retrieval QA Chain's relevant input

To Reproduce Steps to reproduce the behavior: using: flowise/1.3.6 win32-x64 node-v18.16.0 the 2 items can not be connected

Expected behavior They can be connected

Screenshots If applicable, add screenshots to help explain your problem.

Flow If applicable, add exported flow in order to help replicating the problem.

Setup npx flowise start flowise/1.3.6 win32-x64 node-v18.16.0 Chrome

Additional context Add any other context about the problem here.

[HenryHengZJ]

Do you have a screenshot?

[vanetreg]

Do you have a screenshot?

No I don't, you want me to show they are not connected? The node's name are exactly the ones I used before: Vector Store Retriever output Conversational Retrieval QA Chain's similar input so you can simply test whether you can connect them or not.

If you can, pls. refer to your system data; mine is: flowise/1.3.6 win32-x64 node-v18.16.0 Chrome

I have 5-6 nodes in the flow and all other required connections (10+) are set, all but this one. So probably a type validation fails.

[HenryHengZJ]

oh I get what you mean, take a look at Multi Retrieval QA Chain template to see how Vector Store Retriever is being used. And Conversational Retrieval QA Chain to see how to connect vector stores to Conversaitonal Retrieval QA Chain

[vanetreg]

[HenryHengZJ]

Select Faiss Retriever: