Class ChatModel (1.25.0)

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

ChatModel represents a language model that is capable of chat.

.. rubric:: 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?")

Inheritance

builtins.object > vertexai.language_models._language_models._LanguageModel > ChatModel

Methods

ChatModel

ChatModel(model_id: str, endpoint_name: 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)

Loads a LanguageModel.

Exceptions
Type	Description
`ValueError`	If model_name is unknown.
`ValueError`	If model does not support this class.

get_tuned_model

get_tuned_model(tuned_model_name: str)

Loads the specified tuned language model.

list_tuned_model_names

list_tuned_model_names()

Lists the names of tuned models.

start_chat

start_chat(
    *,
    context: Optional[str] = None,
    examples: Optional[
        List[vertexai.language_models._language_models.InputOutputTextPair]
    ] = None,
    max_output_tokens: int = 128,
    temperature: float = 0.0,
    top_k: int = 40,
    top_p: float = 0.95
)

Starts a chat session with the model.

tune_model

tune_model(
    training_data: Union[str, pandas.core.frame.DataFrame],
    *,
    train_steps: int = 1000,
    tuning_job_location: Optional[str] = None,
    tuned_model_location: Optional[str] = None,
    model_display_name: Optional[str] = None
)

Tunes a model based on training data.

This method launches a model tuning job that can take some time.

Exceptions
Type	Description
`ValueError`	If the "tuning_job_location" value is not supported
`ValueError`	If the "tuned_model_location" value is not supported
`RuntimeError`	If the model does not support tuning