Hey yall,<p>Very early release but wanted to get the idea out there.<p>Waffie is built for developers looking to operationalize LLM APIs into their solutions.<p>The first thing I'm tackling is automated testing of LLMs in the context of unstructured to structured data interpretation. For example, sentiment analysis.<p>Specify what you want in a YAML file and a test.csv and run waffie against your test cases.<p>Looking to bridge the gaps between software development and machine learning engineering.
One thing that could help:<p>Add to the top of the readme something that basically shows "put in this / do this" and "get this"<p>Kind of like a before and after.<p>Basically, I'd recommend exposing 2-3 of the examples on the readme, otherwise the readme just shows how to run it, which doesn't show what it does / what it's for.