Class ChatModel (1.31.0)

ChatModel(model_id: str, endpoint_name: typing.Optional[str] = None)

ChatModel represents a language model that is capable of chat.

Examples::

chat_model = ChatModel.from_pretrained("chat-bison@001")

chat = chat_model.start_chat(
    context="My name is Ned. You are my personal assistant. My favorite movies are Lord of the Rings and Hobbit.",
    examples=[
        InputOutputTextPair(
            input_text="Who do you work for?",
            output_text="I work for Ned.",
        ),
        InputOutputTextPair(
            input_text="What do I like?",
            output_text="Ned likes watching movies.",
        ),
    ],
    temperature=0.3,
)

chat.send_message("Do you know any cool events this weekend?")

Methods

ChatModel

ChatModel(model_id: str, endpoint_name: typing.Optional[str] = None)

Creates a LanguageModel.

This constructor should not be called directly. Use LanguageModel.from_pretrained(model_name=...) instead.

from_pretrained

from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.T

Loads a _ModelGardenModel.

Exceptions
TypeDescription
ValueErrorIf model_name is unknown.
ValueErrorIf model does not support this class.

start_chat

start_chat(
    *,
    context: typing.Optional[str] = None,
    examples: typing.Optional[
        typing.List[vertexai.language_models._language_models.InputOutputTextPair]
    ] = None,
    max_output_tokens: typing.Optional[int] = 128,
    temperature: typing.Optional[float] = None,
    top_k: typing.Optional[int] = None,
    top_p: typing.Optional[float] = None,
    message_history: typing.Optional[
        typing.List[vertexai.language_models._language_models.ChatMessage]
    ] = None,
    stop_sequences: typing.Optional[typing.List[str]] = None
) -> vertexai.language_models._language_models.ChatSession

Starts a chat session with the model.