Improvement Request: Add parameter to support decoding_method="sample"

[hirokik1]

Hello,

I have been using the watsonx-openapi.json file for creating an extension for the watsonx Assistant, and I would like to express my gratitude for making it available. integrations/extensions/starter-kits/language-model-watsonx/watsonx-openapi.json

I am writing to submit a request for an improvement. I would appreciate it if you could add the following parameters to the parameters section, so that it becomes possible to execute the API with the decoding_method set to "sample". The description below is quoted from the BAM explanation site. I have tested this in my environment and confirmed it works.

"decoding_method": {
  "type": "string",
  "description": "Represents the strategy used for picking the tokens during generation of the output text. Options are greedy and sample. Value defaults to sample if not specified.",
  "example": "greedy"
},
"top_k": {
  "type": "number",
  "description": "The number of highest probability vocabulary tokens to keep for top-k-filtering. Only applies for sampling mode, with range from 1 to 100. When decoding_strategy is set to sample, only the top_k most likely tokens are considered as candidates for the next generated token.",
  "example": "50"
},
"top_p": {
  "type": "number",
  "description": "Similar to top_k except the candidates to generate the next token are the most likely tokens with probabilities that add up to at least top_p. The valid range is 0.0 to 1.0 where 1.0 is equivalent to disabled and is the default. Also known as nucleus sampling.",
  "example": "1"
}