Skip to main content
View source

IBM Watson

View as Markdown

A RocketRide LLM node that connects IBM watsonx foundation models to a pipeline via the IBM Cloud API.

What it does

Connects IBM watsonx foundation models to your pipeline via the IBM Cloud API. Used primarily as an llm invoke connection by agents and other nodes that need an LLM. Can also be used directly via lanes.

Uses the ibm-watsonx-ai SDK (ModelInference with TextChatParameters). The service URL is derived from the configured location as https://<location>.ml.cloud.ibm.com. The location is validated against a fixed allowlist of known IBM Cloud regions before any connection is made. Temperature is fixed at 1.

All four configuration fields are required. The node raises a configuration error at pipeline start if the API key, location, model ID, or project ID is missing, or if the location is not a known IBM Cloud region.

Token counts are estimated with a simple word-based approximation (roughly 0.75 tokens per word) rather than the model's native tokenizer.


Configuration

Lanes

Lane inLane outDescription
questionsanswersSend a question directly, receive a generated answer

Fields

FieldTypeDescription
apikeystringIBM Cloud API key (required)
locationenumIBM Cloud region (required, see below)
modelstringwatsonx model ID, specified directly; no preset profiles (required)
project_idstringIBM watsonx project ID (required)

Locations

The location value must be one of the following known IBM Cloud regions. Any other value is rejected at startup.

ValueRegion
us-southDallas
us-eastWashington DC
eu-gbLondon
eu-deFrankfurt
eu-esMadrid
jp-tokTokyo
jp-osaOsaka
au-sydSydney
ca-torToronto
br-saoSao Paulo

Invoke functions

When used as an llm invoke connection, the node exposes the following functions to connected agents and other nodes:

FunctionDescription
askSend a question and receive the generated answer
getContextLengthTotal context window size, in tokens
getOutputLengthMaximum output size, in tokens
getTokenCounterToken-counting function (word-based approximation)