Skip to main content
Parser which receives Granite 3.3 model output and returns the constituents of the output. The output from the lowest level of the parser is a dictionary as follows:
  • “citations”: List of citations
  • “docs”: List of document references
  • “hallucinations”: List of hallucinations
  • “response”: Model response text without the above constituents
This dict is further refined into dataclasses before being returned as an extended AssistantMessage.

​
Classes

​
CLASS Granite33OutputProcessor

Output processor for version 3.3 of the main Granite models, all sizes.
Methods:

​
FUNC transform 

transform(self, model_output: str, chat_completion: ChatCompletion | None = None) -> AssistantMessage
Parse Granite 3.3 model output into a structured assistant message. Args:
  • model_output: Raw text output from the Granite 3.3 model.
  • chat_completion: The original chat completion request that produced model_output. Used to determine which output features (thinking, tools, citations, hallucinations) to parse. Defaults to None.
Returns:
  • A :class:Granite3AssistantMessage containing the parsed response text, optional tool calls, chain-of-thought reasoning, citations, documents, and hallucination annotations.
Raises:
  • ValueError: If parsing citations, documents, or hallucinations from the model output fails.