Module language_models (1.29.0)

Classes for working with language models.

Classes

ChatMessage

ChatMessage(content: str, author: str)

A chat message.

Author of the message.

ChatSession

ChatSession(
    model: vertexai.language_models._language_models.ChatModel,
    context: typing.Optional[str] = None,
    examples: typing.Optional[
        typing.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,
    message_history: typing.Optional[
        typing.List[vertexai.language_models._language_models.ChatMessage]
    ] = None,
)

ChatSession represents a chat session with a language model.

Within a chat session, the model keeps context and remembers the previous conversation.

CodeChatModel

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

CodeChatModel represents a model that is capable of completing code.

.. rubric:: Examples

code_chat_model = CodeChatModel.from_pretrained("codechat-bison@001")

code_chat = code_chat_model.start_chat( max_output_tokens=128, temperature=0.2, )

code_chat.send_message("Please help write a function to calculate the min of two numbers")

CodeChatSession

CodeChatSession(
    model: vertexai.language_models._language_models.CodeChatModel,
    max_output_tokens: int = 128,
    temperature: float = 0.5,
    message_history: typing.Optional[
        typing.List[vertexai.language_models._language_models.ChatMessage]
    ] = None,
)

CodeChatSession represents a chat session with code chat language model.

Within a code chat session, the model keeps context and remembers the previous converstion.

InputOutputTextPair

InputOutputTextPair(input_text: str, output_text: str)

InputOutputTextPair represents a pair of input and output texts.

TextEmbedding

TextEmbedding(
    values: typing.List[float], _prediction_response: typing.Optional[typing.Any] = None
)

Contains text embedding vector.

TextGenerationResponse

TextGenerationResponse(text: str, _prediction_response: typing.Any, is_blocked: bool = False, safety_attributes: typing.Dict[str, float] = <factory>)

TextGenerationResponse represents a response of a language model. .. attribute:: text

The generated text

Scores for safety attributes. Learn more about the safety attributes here: https://cloud.google.com/vertex-ai/docs/generative-ai/learn/responsible-ai#safety_attribute_descriptions