Module language_models (1.25.0)

Classes for working with language models.

Classes

ChatModel

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?")

ChatSession

ChatSession(
    model: vertexai.language_models._language_models.ChatModel,
    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,
)

ChatSession represents a chat session with a language model.

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

InputOutputTextPair

InputOutputTextPair(input_text: str, output_text: str)

InputOutputTextPair represents a pair of input and output texts.

TextEmbedding

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

Contains text embedding vector.

TextEmbeddingModel

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

TextEmbeddingModel converts text into a vector of floating-point numbers.

.. rubric:: Examples

Getting embedding:

model = TextEmbeddingModel.from_pretrained("embedding-gecko@001") embeddings = model.get_embeddings(["What is life?"]) for embedding in embeddings: vector = embedding.values print(len(vector))

TextGenerationModel

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

TextGenerationModel represents a general language model.

.. rubric:: Examples

Getting answers:

model = TextGenerationModel.from_pretrained("text-bison@001") model.predict("What is life?")

TextGenerationResponse

TextGenerationResponse(text: str, _prediction_response: Any)

TextGenerationResponse represents a response of a language model.