watsonx.ai

WatsonxLLM

Bases: BaseLLM

A wrapper class for interacting with a IBM watsonx.ai large language models (LLMs). For more information, see here.

Attributes:

Name	Type	Description
model	str	The identifier of the LLM model to use (e.g., "openai/gpt-oss-120b", "meta-llama/llama-3-3-70b-instruct").
api_key	str	API key used for authenticating with the LLM provider.
region	Region	The region where watsonx.ai is hosted when using IBM Cloud. Defaults to us-south.
project_id	str	The project ID in watsonx.ai.
space_id	str	The space ID in watsonx.ai.
additional_kwargs	dict[str, Any]	A dictionary of additional parameters passed to the LLM during completion. This allows customization of the request beyond the standard parameters.
callback_manager	BaseObservability | None	(PromptMonitor, optional): The callback manager is used for observability.

completion

completion(prompt: str, guardrails: bool = False, params: dict[str, Any] = {}, **kwargs: Any) -> CompletionResponse

Creates a completion for the provided prompt and parameters. Using OpenAI's standard endpoint (/completions).

Parameters:

Name	Type	Description	Default
prompt	str	The input prompt to generate a completion for.	required
guardrails	bool	The detection filter for potentially hateful, abusive, and/or profane language (HAP).	False
params	dict	MetaProps for text generation. Method-provided params override class-level params.	{}
**kwargs	Any	Additional keyword arguments to customize the LLM completion request.	{}

chat_completion

chat_completion(messages: list[ChatMessage | dict], params: dict[str, Any] = {}, **kwargs: Any) -> ChatResponse

Creates a chat completion for LLM. Using OpenAI's standard endpoint (/chat/completions).

Parameters:

Name	Type	Description	Default
messages	list[ChatMessage]	A list of chat messages as input for the LLM.	required
params	dict	MetaProps for text generation. Method-provided params override class-level params.	{}
**kwargs	Any	Additional keyword arguments to customize the LLM completion request.	{}