Add new /prototype endpoint

[juliasilge]

Closes #197

[juliasilge]

This is working well, I think! I put a model deployed with this PR here:
https://colorado.posit.co/rsc/chicago-ridership/

This means we can finally resolve #116 like this:

url <- "https://colorado.posit.co/rsc/chicago-ridership/prototype"
r <- httr::GET(url)
prototype <- httr::content(r, as = "text", encoding = "UTF-8")
cereal::cereal_from_json(prototype)
#> # A tibble: 0 × 49
#> # ℹ 49 variables: Austin <dbl>, Quincy_Wells <dbl>, Belmont <dbl>,
#> #   Archer_35th <dbl>, Oak_Park <dbl>, Western <dbl>, Clark_Lake <dbl>,
#> #   Clinton <dbl>, Merchandise_Mart <dbl>, Irving_Park <dbl>,
#> #   Washington_Wells <dbl>, Harlem <dbl>, Monroe <dbl>, Polk <dbl>,
#> #   Ashland <dbl>, Kedzie <dbl>, Addison <dbl>, Jefferson_Park <dbl>,
#> #   Montrose <dbl>, California <dbl>, temp_min <dbl>, temp <dbl>,
#> #   temp_max <dbl>, temp_change <dbl>, dew <dbl>, humidity <dbl>, …

^{Created on 2023-06-09 with reprex v2.0.2}

[juliasilge]

When you get a chance @isabelizimm, I redeployed this model as well and you can see the /prototype endpoint here:

Could you try out what it would look like to use that from Python to determine what data needs to look like to make predictions? I'll do the same the other way around.

[isabelizimm]

When pulling the information given at the /prototype endpoint into a pandas DataFrame in Python, this is what the result looks like. All of the columns have the type object.