Silei Xu

I don't think we want this to be merged into master any time soon

This tutorial needs some updates. We will keep you posted once we have a newer version.

It won't take long to deploy. The only endpoint opened for the nlu server is `/en/query`. For example, if you want to get the result for utterance "get restaurants", you...

Here is some documentation about the API provided in our production server: https://wiki.genie.stanford.edu/en/api-references/nlp - it is the same as the self-served one here. And the endpoint is implemented here: https://github.com/stanford-oval/genie-toolkit/blob/235171b1d1610a2b02a5a979d43a27e7ec6b9528/tool/server.ts#L222....

Both localhost and our production server share the same implementation of the API call. We don't have separate documentation for API for genie-server at the moment, but simply replace the...

> It looks like it doesn't die miserably on Travis. Maybe we can enable this? yeah, it seems synthesis time is reasonable too. so I suppose I can merge this?

> The PR is not finished because synthesis is not done, but I got to the point where the agent works at inference time, and the agent tests pass, so...

> Alright, synthesis is not done yet but at least tests pass now. @rayslxu how do you want to review this? Do we want to merge this first PR somewhere?...

This tutorial needs some updates. We will keep you posted once we have a newer version.

> This is literally a bug in the tokenizer, right? We can fix it without significant changes. yeah, I will just use this issue to report a list of bugs...