CustomModel Class — langchain Architecture

Architecture documentation for the CustomModel class in test_response_format.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  d019482d_86bf_d8b3_7348_f29e9fcfe384["CustomModel"]
  0f829642_e361_67a1_cbca_f82839bbbd31["GenericFakeChatModel"]
  d019482d_86bf_d8b3_7348_f29e9fcfe384 -->|extends| 0f829642_e361_67a1_cbca_f82839bbbd31
  2970c11e_b43a_df0c_1a52_30da10d3689c["test_response_format.py"]
  d019482d_86bf_d8b3_7348_f29e9fcfe384 -->|defined in| 2970c11e_b43a_df0c_1a52_30da10d3689c
  0874fe8b_e998_4a85_2ac5_c9e21542b1cd["bind_tools()"]
  d019482d_86bf_d8b3_7348_f29e9fcfe384 -->|method| 0874fe8b_e998_4a85_2ac5_c9e21542b1cd

Relationship Graph

Source Code

libs/langchain_v1/tests/unit_tests/agents/test_response_format.py lines 802–812

        class CustomModel(GenericFakeChatModel):
            tool_bindings: list[Any] = Field(default_factory=list)

            def bind_tools(
                self,
                tools: Sequence[dict[str, Any] | type[BaseModel] | Callable[..., Any] | BaseTool],
                **kwargs: Any,
            ) -> Runnable[LanguageModelInput, AIMessage]:
                # Record every tool binding event.
                self.tool_bindings.append(tools)
                return self