PromptTemplate Class — langchain Architecture

Source Code

libs/core/langchain_core/prompts/prompt.py lines 24–312

class PromptTemplate(StringPromptTemplate):
    """Prompt template for a language model.

    A prompt template consists of a string template. It accepts a set of parameters
    from the user that can be used to generate a prompt for a language model.

    The template can be formatted using either f-strings (default), jinja2, or mustache
    syntax.

    !!! warning "Security"

        Prefer using `template_format='f-string'` instead of `template_format='jinja2'`,
        or make sure to NEVER accept jinja2 templates from untrusted sources as they may
        lead to arbitrary Python code execution.

        As of LangChain 0.0.329, Jinja2 templates will be rendered using Jinja2's
        SandboxedEnvironment by default. This sand-boxing should be treated as a
        best-effort approach rather than a guarantee of security, as it is an opt-out
        rather than opt-in approach.

        Despite the sandboxing, we recommend to never use jinja2 templates from
        untrusted sources.

    Example:
        ```python
        from langchain_core.prompts import PromptTemplate

        # Instantiation using from_template (recommended)
        prompt = PromptTemplate.from_template("Say {foo}")
        prompt.format(foo="bar")

        # Instantiation using initializer
        prompt = PromptTemplate(template="Say {foo}")
        ```
    """

    @property
    @override
    def lc_attributes(self) -> dict[str, Any]:
        return {
            "template_format": self.template_format,
        }

    @classmethod
    @override
    def get_lc_namespace(cls) -> list[str]:
        """Get the namespace of the LangChain object.

        Returns:
            `["langchain", "prompts", "prompt"]`
        """
        return ["langchain", "prompts", "prompt"]

    template: str
    """The prompt template."""

    template_format: PromptTemplateFormat = "f-string"
    """The format of the prompt template.

    Options are: `'f-string'`, `'mustache'`, `'jinja2'`.
    """

    validate_template: bool = False
    """Whether or not to try validating the template."""

    @model_validator(mode="before")
    @classmethod
    def pre_init_validation(cls, values: dict) -> Any:
        """Check that template and input variables are consistent."""
        if values.get("template") is None:
            # Will let pydantic fail with a ValidationError if template
            # is not provided.
            return values

        # Set some default values based on the field defaults
        values.setdefault("template_format", "f-string")
        values.setdefault("partial_variables", {})

        if values.get("validate_template"):
            if values["template_format"] == "mustache":
                msg = "Mustache templates cannot be validated."