Skip to main content

​
mellea.backends.watsonx

A generic WatsonX.ai compatible backend that wraps around the watson_machine_learning library.

​
Classes

​
WatsonxAIBackend

A generic backend class for watsonx SDK. Methods:

​
filter_chat_completions_kwargs

filter_chat_completions_kwargs(self, model_options: dict) -> dict
Filter kwargs to only include valid watsonx chat.completions.create parameters.

​
generate_from_context

generate_from_context(self, action: Component | CBlock, ctx: Context)
See generate_from_chat_context.

​
generate_from_chat_context

generate_from_chat_context(self, action: Component | CBlock, ctx: Context) -> ModelOutputThunk
Generates a new completion from the provided Context using this backend’s Formatter.

​
processing

processing(self, mot: ModelOutputThunk, chunk: dict)
Called during generation to add information from a single ChatCompletion or ChatCompletionChunk to the ModelOutputThunk. For OpenAI-like APIs, tool call parsing is handled in the post processing step.

​
post_processing

post_processing(self, mot: ModelOutputThunk, conversation: list[dict], tools: dict[str, Callable], seed, format)
Called when generation is done.
⌘I