Skip to content

Watsonx AI

Reference


IBM watsonx.ai AI studio is part of the IBM watsonx AI and data platform, bringing together new generative AI (gen AI) capabilities powered by foundation models and traditional machine learning (ML) into a powerful studio spanning the AI lifecycle.

Categories: [artificial-intelligence]

Version: 1


Connections

Version: 1

Bearer Token

Properties

NameTypeControl TypeDescription
RegionSTRINGSELECTURL to connect to.
Stream EndpointSTRINGTEXTThe streaming endpoint.
Text EndpointSTRINGTEXTThe text endpoint.
Project IDSTRINGTEXTThe project ID.
IAM TokenSTRINGTEXTThe IBM Cloud account IAM token.

Actions

Ask

Ask anything you want.

Properties

NameTypeControl TypeDescription
ModelSTRINGTEXTModel is the identifier of the LLM Model to be used.
Messages[{STRING(content), STRING(role)}]ARRAY_BUILDERA list of messages comprising the conversation so far.
Response FormatINTEGERSELECTIn which format do you want the response to be in?
Response SchemaSTRINGTEXT_AREADefine the JSON schema for the response.
Decoding MethodSTRINGTEXTDecoding is the process that a model uses to choose the tokens in the generated output.
Repetition PenaltyNUMBERNUMBERSets how strongly to penalize repetitions. A higher value (e.g., 1.8) will penalize repetitions more strongly, while a lower value (e.g., 1.1) will be more lenient.
Min TokensINTEGERINTEGERSets how many tokens must the LLM generate.
Max TokensINTEGERINTEGERThe maximum number of tokens to generate in the chat completion.
TemperatureNUMBERNUMBERControls randomness: Higher values will make the output more random, while lower values like will make it more focused and deterministic.
Top PNUMBERNUMBERAn alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
Top KINTEGERINTEGERSpecify the number of token choices the generative uses to generate the next token.
Stop[STRING]ARRAY_BUILDERUp to 4 sequences where the API will stop generating further tokens.
SeedINTEGERINTEGERKeeping the same seed would output the same response.