functions() — langchain Function Reference

Architecture documentation for the functions() function in base.py from the langchain codebase.

Function python AgentOrchestration ActionLogic

Entity Profile

AgentOrchestration→ ActionLogic→ functions() — langchain Function Reference

Dependency Diagram

graph TD
  a401586c_3e20_a72a_c862_b29ba9695ced["functions()"]
  4079b11a_3240_0a70_5830_e3af3b13b06e["OpenAIMultiFunctionsAgent"]
  a401586c_3e20_a72a_c862_b29ba9695ced -->|defined in| 4079b11a_3240_0a70_5830_e3af3b13b06e
  style a401586c_3e20_a72a_c862_b29ba9695ced fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/openai_functions_multi_agent/base.py lines 144–202

    def functions(self) -> list[dict]:
        """Get the functions for the agent."""
        enum_vals = [t.name for t in self.tools]
        tool_selection = {
            # OpenAI functions returns a single tool invocation
            # Here we force the single tool invocation it returns to
            # itself be a list of tool invocations. We do this by constructing
            # a new tool that has one argument which is a list of tools
            # to use.
            "name": "tool_selection",
            "description": "A list of actions to take.",
            "parameters": {
                "title": "tool_selection",
                "description": "A list of actions to take.",
                "type": "object",
                "properties": {
                    "actions": {
                        "title": "actions",
                        "type": "array",
                        "items": {
                            # This is a custom item which bundles the action_name
                            # and the action. We do this because some actions
                            # could have the same schema, and without this there
                            # is no way to differentiate them.
                            "title": "tool_call",
                            "type": "object",
                            "properties": {
                                # This is the name of the action to take
                                "action_name": {
                                    "title": "action_name",
                                    "enum": enum_vals,
                                    "type": "string",
                                    "description": (
                                        "Name of the action to take. The name "
                                        "provided here should match up with the "
                                        "parameters for the action below."
                                    ),
                                },
                                # This is the action to take.
                                "action": {
                                    "title": "Action",
                                    "anyOf": [
                                        {
                                            "title": t.name,
                                            "type": "object",
                                            "properties": t.args,
                                        }
                                        for t in self.tools
                                    ],
                                },
                            },
                            "required": ["action_name", "action"],
                        },
                    },
                },
                "required": ["actions"],
            },
        }
        return [tool_selection]