Adrian Gonzalez-Martin

Following the initial exploration done in PR #460, we identified that this task may need a explainer-by-explainer approach. Therefore, we've decided to split this into smaller tasks to assess how...

Hey @martapodarta , that's amazing! Thanks for the heads up and for taking the time to look into this one! :rocket: I haven't dived too much into the available options,...

Hey @martapodarta , Those are great points! Initially, those conventions were taken from the [original spec of the V2 Inference Protocol](https://github.com/kserve/kserve/blob/master/docs/predict-api/v2/required_api.md). However, I agree that some of those are not...

Hey @martapodarta , Wow, that sounds like really great progress! You raise a very good point. I think the core issue for `1.` and `2.` is mainly that `model_version` is...

Hey @gariepyalex , Thanks a lot for raising this one! As an OSS maintainer, it's great to see so well-formatted issues providing so much detail. :+1: In order to help...

Thanks for that extra context @gariepyalex. In that case, wouldn't it be enough to encode both columns as separate inputs and using the [`pd` content type](https://mlserver.readthedocs.io/en/latest/user-guide/content-type.html#pandas-dataframe)? As in, ```json {...

Thanks for clarifying that point @gariepyalex . In that case, would it make sense to add an extra dimension to the `y` and `ds` inputs above? This would represent the...

Right, I think I'm starting to understand the problem now. Based on your ideal solution, we would need to find a way to pass variable-length lists as the inputs of...

That's a great point @gariepyalex! That probably wouldn't work with adaptive batching... In that case, we could just include a new parameter that represents the lengths (i.e. moving the `lengths`...

Hey @BFAnas , My guess would be that the payload is missing the right [content type](https://mlserver.readthedocs.io/en/latest/user-guide/content-type.html). This is used by MLServer to convert the request to the right Python type...