Find answers from the community

Updated 3 months ago

@Logan M or anyone avaliable. I am

@Logan M or anyone avaliable. I am running into an issue of VERY dense neighborhoods in my Graph for instance if I have a common person that is mentioned often in the documents I am injesting they could have 100s-1000s of relationships. Are there any best practices worked out for getting the most relevant relationships to a query?

4 comments

LLogan M

Sorry, I haven't worked anywhere near enough with the neighborhood graph stuff to best answer this

But gut says just use vector similarity on the subset though

CCallam

Yeah like sort by similarity of the second entity to the original query?

CCallam

I think that makes sense also

CCallam

thanks anyways I was just curious if this was something you had faced

Add a reply