I can see for the inference api which is serverless but let's say I want to access endpoint models how to do it .

Also would like to know , what strategy to follow when indexing 2000 pages PDFs without llamaparse . It is a native pdf file .
It is taking lot of time to generate a index .

I am unable to get the page label and file name in for PDFs in llamaparse

Hi everyone, is instrumentation working for you guys . The notebook given for tracing all events gives me no attribute error for querystartevent

Hey everyone, when can we expect to have more documentation on the instrumentation module .

Hey everyone, just wanted to check if we have an open source observability and evaluation platform to test with azure openai keys ...
Thanks