FakeTokenCountingModel Class — langchain Architecture

Architecture documentation for the FakeTokenCountingModel class in test_utils.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  efd1a281_0799_19b5_98b8_1d70ef32aedf["FakeTokenCountingModel"]
  08f149d6_0ef5_52a4_96df_fceeb68e4ea8["FakeChatModel"]
  efd1a281_0799_19b5_98b8_1d70ef32aedf -->|extends| 08f149d6_0ef5_52a4_96df_fceeb68e4ea8
  03f6a5ae_d57a_eb66_626a_b9e082b763ea["test_utils.py"]
  efd1a281_0799_19b5_98b8_1d70ef32aedf -->|defined in| 03f6a5ae_d57a_eb66_626a_b9e082b763ea
  daeb82e7_d1da_efa6_b2c9_ba1828bc0d34["get_num_tokens_from_messages()"]
  efd1a281_0799_19b5_98b8_1d70ef32aedf -->|method| daeb82e7_d1da_efa6_b2c9_ba1828bc0d34

Relationship Graph

Source Code

libs/core/tests/unit_tests/messages/test_utils.py lines 756–763

class FakeTokenCountingModel(FakeChatModel):
    @override
    def get_num_tokens_from_messages(
        self,
        messages: list[BaseMessage],
        tools: Sequence[dict[str, Any] | type | Callable | BaseTool] | None = None,
    ) -> int:
        return dummy_token_counter(messages)