Is it possible to rate limit AIP blocks in pipeline

Hello,
We have a pipeline that has multiple AIP blocks making multiple AIP calls. Some of the calls don’t return anything due to the rate limits. Is there a way to configure that in pipeline builder so that it doesn’t hit the limits.

Thanks

Hey @stian, there is built-in retry logic to try to get around this issue but nothing directly configurable from the UI. Generally the suggestions (from the Pipeline Builder side, without bumping enrollment limits) would be to try a smaller profile or split the non-dependent parts of your pipeline into a separate pipeline so there’s not as many concurrent requests. Note that the smaller profile might be less helpful / can make builds take longer.

Is there anything Palantir is planning to make this more robust, Either it should retry the pipeline back off or give an option to use some kind of dedicated inference capacity.
How do we scale inferencing of Large datasets ?

1 Like