Failure in Databricks Serving endpoint

Aarsh — Thu, 25 May 2023 09:14:34 GMT

Hello All,

We are trying to deploy some models using Databricks Serving endpoint,

But while deploying the artifact created during experiment run the serving endpoint build log says Pip failed due to conflicting dependency.

The model is logged in experiment we are able to use that logged model to do prediction within Databricks notebook:

But the same model when using for serving endpoint fails due to conflicting dependencies in requirements file which was automatically generated using model experiment.

What is the correct way to navigate this scenario? do we need to explicity pass pip dependency while running the experiment ? But that is not recommeded approach.

How to know which dependency would be required by Databrick Service endpoint ?

topic Failure in Databricks Serving endpoint <build log says Pip failed due to conflicting dependency.> in Machine Learning

Failure in Databricks Serving endpoint