parse() — langchain Function Reference

Architecture documentation for the parse() function in output_parser.py from the langchain codebase.

Function python AgentOrchestration ActionLogic

Entity Profile

AgentOrchestration→ ActionLogic→ parse() — langchain Function Reference

Dependency Diagram

graph TD
  c7b49729_4166_704a_aecf_f39c2616b986["parse()"]
  3ad96f4e_9c83_f4d2_9ced_687b8a7dd6a9["ConvoOutputParser"]
  c7b49729_4166_704a_aecf_f39c2616b986 -->|defined in| 3ad96f4e_9c83_f4d2_9ced_687b8a7dd6a9
  style c7b49729_4166_704a_aecf_f39c2616b986 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/conversational/output_parser.py lines 23–44

    def parse(self, text: str) -> AgentAction | AgentFinish:
        """Parse the output from the agent into an AgentAction or AgentFinish object.

        Args:
            text: The text to parse.

        Returns:
            An AgentAction or AgentFinish object.
        """
        if f"{self.ai_prefix}:" in text:
            return AgentFinish(
                {"output": text.rsplit(f"{self.ai_prefix}:", maxsplit=1)[-1].strip()},
                text,
            )
        regex = r"Action: (.*?)[\n]*Action Input: ([\s\S]*)"
        match = re.search(regex, text, re.DOTALL)
        if not match:
            msg = f"Could not parse LLM output: `{text}`"
            raise OutputParserException(msg)
        action = match.group(1)
        action_input = match.group(2)
        return AgentAction(action.strip(), action_input.strip(" ").strip('"'), text)