Function llama_chat_apply_template

llama_cpp/llama_cpp.py:4132–4154

Apply chat template. Args: tmpl: Template to use. If None, uses model's default chat: Array of chat messages n_msg: Number of messages add_ass: Whether to end prompt with assistant token buf: Output buffer length: Buffer length Returns:

(
    tmpl: bytes,
    chat: CtypesArray[llama_chat_message],
    n_msg: int,
    add_ass: bool,  # Added parameter
    buf: bytes,
    length: int,
    /,
)

    ctypes.c_int32,
)
def llama_chat_apply_template(
    tmpl: bytes,
    chat: CtypesArray[llama_chat_message],
    n_msg: int,
    add_ass: bool,  # Added parameter
    buf: bytes,
    length: int,
    /,
) -> int:
    """Apply chat template.

    Args:
        tmpl: Template to use. If None, uses model's default
        chat: Array of chat messages
        n_msg: Number of messages
        add_ass: Whether to end prompt with assistant token
        buf: Output buffer
        length: Buffer length

    Returns:
        Number of bytes written, or needed if buffer too small
    """
    ...


# // Get list of built-in chat templates