Find answers from the community

Updated last year

If I use LlamaIndex, I know I can view

At a glance
If I use LlamaIndex, I know I can view the top-k nodes that were retrieved, e.g. with response.source_nodes[0]. Is there any way to actually figure out which nodes ended up being used in the output? e.g. only 3 out of 5 nodes (e.g. 1, 2, 5) were used in the answer.
W
L
S
5 comments
I think @Logan M recently worked on something similar for idea. Let me check
This will help you to identify the nodes being used to create the response
Yea! It's very cool. It tracks down exact sentences actually (and also nodes)
this is slick
Add a reply
Sign up and join the conversation on Discord