ConvoOutputParser Class — langchain Architecture

Architecture documentation for the ConvoOutputParser class in output_parser.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  7b6152a7_4385_b958_e4d1_bd4468e4393f["ConvoOutputParser"]
  d9685a4b_26b0_bca9_f857_03bb2ffc9dd4["AgentOutputParser"]
  7b6152a7_4385_b958_e4d1_bd4468e4393f -->|extends| d9685a4b_26b0_bca9_f857_03bb2ffc9dd4
  e19c3095_7c11_1cbd_db92_84d82e0878fb["output_parser.py"]
  7b6152a7_4385_b958_e4d1_bd4468e4393f -->|defined in| e19c3095_7c11_1cbd_db92_84d82e0878fb
  90ce7237_5395_03b2_b455_faeadc7dc075["get_format_instructions()"]
  7b6152a7_4385_b958_e4d1_bd4468e4393f -->|method| 90ce7237_5395_03b2_b455_faeadc7dc075
  e02d8b25_f4ba_35dc_2b02_b9697955f659["parse()"]
  7b6152a7_4385_b958_e4d1_bd4468e4393f -->|method| e02d8b25_f4ba_35dc_2b02_b9697955f659
  32728613_e370_e8d2_ab8d_f1a7b06466ab["_type()"]
  7b6152a7_4385_b958_e4d1_bd4468e4393f -->|method| 32728613_e370_e8d2_ab8d_f1a7b06466ab

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/conversational_chat/output_parser.py lines 12–55

class ConvoOutputParser(AgentOutputParser):
    """Output parser for the conversational agent."""

    format_instructions: str = FORMAT_INSTRUCTIONS
    """Default formatting instructions"""

    def get_format_instructions(self) -> str:
        """Returns formatting instructions for the given output parser."""
        return self.format_instructions

    def parse(self, text: str) -> AgentAction | AgentFinish:
        """Attempts to parse the given text into an AgentAction or AgentFinish.

        Raises:
             OutputParserException if parsing fails.
        """
        try:
            # Attempt to parse the text into a structured format (assumed to be JSON
            # stored as markdown)
            response = parse_json_markdown(text)

            # If the response contains an 'action' and 'action_input'
            if "action" in response and "action_input" in response:
                action, action_input = response["action"], response["action_input"]

                # If the action indicates a final answer, return an AgentFinish
                if action == "Final Answer":
                    return AgentFinish({"output": action_input}, text)
                # Otherwise, return an AgentAction with the specified action and
                # input
                return AgentAction(action, action_input, text)
            # If the necessary keys aren't present in the response, raise an
            # exception
            msg = f"Missing 'action' or 'action_input' in LLM output: {text}"
            raise OutputParserException(msg)
        except Exception as e:
            # If any other exception is raised during parsing, also raise an
            # OutputParserException
            msg = f"Could not parse LLM output: {text}"
            raise OutputParserException(msg) from e

    @property
    def _type(self) -> str:
        return "conversational_chat"