weblmListAvailableModels function

Retrieves the list of web language models available.

This function retrieves the list of web language models currently available.

Internally, this function invokes the Microsoft Cognitive Services Web Language Model REST API documented at https://www.microsoft.com/cognitive-services/en-us/web-language-model-api/documentation.

You MUST have a valid Microsoft Cognitive Services account and an API key for this function to work properly. See https://www.microsoft.com/cognitive-services/en-us/pricing

for details.

weblmListAvailableModels()

Returns

An S3 object of the class weblm. The list of available language models is stored in the results dataframe inside this object. The dataframe includes a short description of the corpus used to build the model, the name of the model, the max N-gram order supported, and a list of Web Language Model REST API methods supported by each model.

Examples

## Not run:

 tryCatch({

   # Retrieve a list of supported web language models
   modelList <- weblmListAvailableModels()

   # Class and structure of modelList
   class(modelList)          # weblm
   #> [1] "weblm"

   str(modelList, max.level = 1)
   #> List of 3
   #>  $ results:'data.frame':  4 obs. of  7 variables:
   #>  $ json   : chr "{"models":[{"corpus":"bing webpage title text 2013-12", __truncated__ }]}
   #>  $ request:List of 7
   #>   ..- attr(*, "class")= chr "request"
   #>  - attr(*, "class")= chr "weblm"

   # Print partial results
   pandoc.table(modelList$results[1:3])
   #> -------------------------------------------------
   #>             corpus              model   maxOrder
   #> ------------------------------ ------- ----------
   #>    bing webpage title text      title      5
   #>            2013-12
   #>
   #> bing webpage body text 2013-12   body      5
   #>
   #>  bing web query text 2013-12    query      5
   #>
   #>    bing webpage anchor text    anchor      5
   #>            2013-12
   #> -------------------------------------------------

 }, error = function(err) {

   # Print error
   geterrmessage()

 })
## End(Not run)

Author(s)

Phil Ferriere pferriere@hotmail.com