FlorianPydde
FlorianPydde
Hi Jonathan. Apologies for the (very) late reply. It's a very pertinent question and, if I understand it correctly, my answer is "it depends". For teams starting with MLOps, I'd...
Indeed, the debugging is not the most user-friendly approach. The fastest would be to test it with a local model or use this: https://docs.microsoft.com/en-us/azure/machine-learning/how-to-troubleshoot-deployment-local
what's the current recommended way to create a custom chunker ? If I understand correctly, one would have do the following: 1. In documentLoader.py -> add a new custom _FORMAT_PROCESSORS...