get_num_tokens_from_messages() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase calls 1

Entity Profile

LangChainCore→ LanguageModelBase→ get_num_tokens_from_messages() — langchain Function Reference

Dependency Diagram

graph TD
  20140000_1d28_439f_e76d_4451abf1068a["get_num_tokens_from_messages()"]
  f5a29046_740d_1358_3615_8cc689b26ca9["BaseLanguageModel"]
  20140000_1d28_439f_e76d_4451abf1068a -->|defined in| f5a29046_740d_1358_3615_8cc689b26ca9
  4b493e08_cb6e_df06_b3b7_c129ab4710fd["get_num_tokens()"]
  20140000_1d28_439f_e76d_4451abf1068a -->|calls| 4b493e08_cb6e_df06_b3b7_c129ab4710fd
  style 20140000_1d28_439f_e76d_4451abf1068a fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/language_models/base.py lines 338–373

    def get_num_tokens_from_messages(
        self,
        messages: list[BaseMessage],
        tools: Sequence | None = None,
    ) -> int:
        """Get the number of tokens in the messages.

        Useful for checking if an input fits in a model's context window.

        This should be overridden by model-specific implementations to provide accurate
        token counts via model-specific tokenizers.

        !!! note

            * The base implementation of `get_num_tokens_from_messages` ignores tool
                schemas.
            * The base implementation of `get_num_tokens_from_messages` adds additional
                prefixes to messages in represent user roles, which will add to the
                overall token count. Model-specific implementations may choose to
                handle this differently.

        Args:
            messages: The message inputs to tokenize.
            tools: If provided, sequence of dict, `BaseModel`, function, or
                `BaseTool` objects to be converted to tool schemas.

        Returns:
            The sum of the number of tokens across the messages.

        """
        if tools is not None:
            warnings.warn(
                "Counting tokens in tool schemas is not yet supported. Ignoring tools.",
                stacklevel=2,
            )
        return sum(self.get_num_tokens(get_buffer_string([m])) for m in messages)