Class GenerativeModel (1.43.0)

Version 1.43.0

• 1.72.0 (latest)
• 1.71.1
• 1.70.0
• 1.69.0
• 1.68.0
• 1.67.1
• 1.66.0
• 1.65.0
• 1.63.0
• 1.62.0
• 1.60.0
• 1.59.0
• 1.58.0
• 1.57.0
• 1.56.0
• 1.55.0
• 1.54.1
• 1.53.0
• 1.52.0
• 1.51.0
• 1.50.0
• 1.49.0
• 1.48.0
• 1.47.0
• 1.46.0
• 1.45.0
• 1.44.0
• 1.43.0
• 1.39.0
• 1.38.1
• 1.37.0
• 1.36.4
• 1.35.0
• 1.34.0
• 1.33.1
• 1.32.0
• 1.31.1
• 1.30.1
• 1.29.0
• 1.28.1
• 1.27.1
• 1.26.1
• 1.25.0
• 1.24.1
• 1.23.0
• 1.22.1
• 1.21.0
• 1.20.0
• 1.19.1
• 1.18.3
• 1.17.1
• 1.16.1
• 1.15.1
• 1.14.0
• 1.13.1
• 1.12.1
• 1.11.0
• 1.10.0
• 1.9.0
• 1.8.1
• 1.7.1
• 1.6.2
• 1.5.0
• 1.4.3
• 1.3.0
• 1.2.0
• 1.1.1
• 1.0.1
• 0.9.0
• 0.8.0
• 0.7.1
• 0.6.0
• 0.5.1
• 0.4.0
• 0.3.1

GenerativeModel(
    model_name: str,
    *,
    generation_config: typing.Optional[
        typing.Union[
            vertexai.generative_models._generative_models.GenerationConfig,
            typing.Dict[str, typing.Any],
        ]
    ] = None,
    safety_settings: typing.Optional[
        typing.Union[
            typing.List[google.cloud.aiplatform_v1beta1.types.content.SafetySetting],
            typing.Dict[
                google.cloud.aiplatform_v1beta1.types.content.HarmCategory,
                google.cloud.aiplatform_v1beta1.types.content.SafetySetting.HarmBlockThreshold,
            ],
        ]
    ] = None,
    tools: typing.Optional[
        typing.List[vertexai.generative_models._generative_models.Tool]
    ] = None
)

Initializes GenerativeModel.

Usage:

model = GenerativeModel("gemini-pro")
print(model.generate_content("Hello"))
```

Parameter
Name	Description
model_name	str Model Garden model resource name.

Methods

count_tokens

count_tokens(
    contents: typing.Union[
        typing.List[vertexai.generative_models._generative_models.Content],
        typing.List[typing.Dict[str, typing.Any]],
        str,
        vertexai.generative_models._generative_models.Image,
        vertexai.generative_models._generative_models.Part,
        typing.List[
            typing.Union[
                str,
                vertexai.generative_models._generative_models.Image,
                vertexai.generative_models._generative_models.Part,
            ]
        ],
    ]
) -> google.cloud.aiplatform_v1beta1.types.prediction_service.CountTokensResponse

Counts tokens.

Parameter
Name	Description
contents	typing.Union[typing.List[Content], typing.List[typing.Dict[str, typing.Any]], str, Image, Part, typing.List[typing.Union[str, Image, Part]]] Contents to send to the model. Supports either a list of Content objects (passing a multi-turn conversation) or a value that can be converted to a single Content object (passing a single message). Supports * str, Image, Part, * List[Union[str, Image, Part]], * List[Content]

Returns
Type	Description
A CountTokensResponse object that has the following attributes	total_tokens: The total number of tokens counted across all instances from the request. total_billable_characters: The total number of billable characters counted across all instances from the request.

count_tokens_async

count_tokens_async(
    contents: typing.Union[
        typing.List[vertexai.generative_models._generative_models.Content],
        typing.List[typing.Dict[str, typing.Any]],
        str,
        vertexai.generative_models._generative_models.Image,
        vertexai.generative_models._generative_models.Part,
        typing.List[
            typing.Union[
                str,
                vertexai.generative_models._generative_models.Image,
                vertexai.generative_models._generative_models.Part,
            ]
        ],
    ]
) -> google.cloud.aiplatform_v1beta1.types.prediction_service.CountTokensResponse

Counts tokens asynchronously.

Parameter
Name	Description
contents	typing.Union[typing.List[Content], typing.List[typing.Dict[str, typing.Any]], str, Image, Part, typing.List[typing.Union[str, Image, Part]]] Contents to send to the model. Supports either a list of Content objects (passing a multi-turn conversation) or a value that can be converted to a single Content object (passing a single message). Supports * str, Image, Part, * List[Union[str, Image, Part]], * List[Content]

Returns
Type	Description
And awaitable for a CountTokensResponse object that has the following attributes	total_tokens: The total number of tokens counted across all instances from the request. total_billable_characters: The total number of billable characters counted across all instances from the request.

generate_content

generate_content(
    contents: typing.Union[
        typing.List[vertexai.generative_models._generative_models.Content],
        typing.List[typing.Dict[str, typing.Any]],
        str,
        vertexai.generative_models._generative_models.Image,
        vertexai.generative_models._generative_models.Part,
        typing.List[
            typing.Union[
                str,
                vertexai.generative_models._generative_models.Image,
                vertexai.generative_models._generative_models.Part,
            ]
        ],
    ],
    *,
    generation_config: typing.Optional[
        typing.Union[
            vertexai.generative_models._generative_models.GenerationConfig,
            typing.Dict[str, typing.Any],
        ]
    ] = None,
    safety_settings: typing.Optional[
        typing.Union[
            typing.List[google.cloud.aiplatform_v1beta1.types.content.SafetySetting],
            typing.Dict[
                google.cloud.aiplatform_v1beta1.types.content.HarmCategory,
                google.cloud.aiplatform_v1beta1.types.content.SafetySetting.HarmBlockThreshold,
            ],
        ]
    ] = None,
    tools: typing.Optional[
        typing.List[vertexai.generative_models._generative_models.Tool]
    ] = None,
    stream: bool = False
) -> typing.Union[
    vertexai.generative_models._generative_models.GenerationResponse,
    typing.Iterable[vertexai.generative_models._generative_models.GenerationResponse],
]

Generates content.

Parameter
Name	Description
contents	typing.Union[typing.List[Content], typing.List[typing.Dict[str, typing.Any]], str, Image, Part, typing.List[typing.Union[str, Image, Part]]] Contents to send to the model. Supports either a list of Content objects (passing a multi-turn conversation) or a value that can be converted to a single Content object (passing a single message). Supports * str, Image, Part, * List[Union[str, Image, Part]], * List[Content]

generate_content_async

generate_content_async(
    contents: typing.Union[
        typing.List[vertexai.generative_models._generative_models.Content],
        typing.List[typing.Dict[str, typing.Any]],
        str,
        vertexai.generative_models._generative_models.Image,
        vertexai.generative_models._generative_models.Part,
        typing.List[
            typing.Union[
                str,
                vertexai.generative_models._generative_models.Image,
                vertexai.generative_models._generative_models.Part,
            ]
        ],
    ],
    *,
    generation_config: typing.Optional[
        typing.Union[
            vertexai.generative_models._generative_models.GenerationConfig,
            typing.Dict[str, typing.Any],
        ]
    ] = None,
    safety_settings: typing.Optional[
        typing.Union[
            typing.List[google.cloud.aiplatform_v1beta1.types.content.SafetySetting],
            typing.Dict[
                google.cloud.aiplatform_v1beta1.types.content.HarmCategory,
                google.cloud.aiplatform_v1beta1.types.content.SafetySetting.HarmBlockThreshold,
            ],
        ]
    ] = None,
    tools: typing.Optional[
        typing.List[vertexai.generative_models._generative_models.Tool]
    ] = None,
    stream: bool = False
) -> typing.Union[
    vertexai.generative_models._generative_models.GenerationResponse,
    typing.AsyncIterable[
        vertexai.generative_models._generative_models.GenerationResponse
    ],
]

Generates content asynchronously.

Parameter
Name	Description
contents	typing.Union[typing.List[Content], typing.List[typing.Dict[str, typing.Any]], str, Image, Part, typing.List[typing.Union[str, Image, Part]]] Contents to send to the model. Supports either a list of Content objects (passing a multi-turn conversation) or a value that can be converted to a single Content object (passing a single message). Supports * str, Image, Part, * List[Union[str, Image, Part]], * List[Content]

get_tuned_model

get_tuned_model(
    tuned_model_name: str,
) -> vertexai.generative_models._generative_models._GenerativeModel

Loads the specified tuned language model.

Parameter
Name	Description
tuned_model_name	str A tuned model name returned by model.list_tuned_model_names()

list_tuned_model_names

list_tuned_model_names() -> typing.Sequence[str]

Lists the names of tuned models.

start_chat

start_chat(
    *,
    history: typing.Optional[
        typing.List[vertexai.generative_models._generative_models.Content]
    ] = None,
    response_validation: bool = True
) -> vertexai.generative_models._generative_models.ChatSession

Creates a stateful chat session.

tune_model

tune_model(
    training_data: typing.Union[str, tunable_models.pandas.core.frame.DataFrame],
    *,
    train_steps: typing.Optional[int] = None,
    learning_rate_multiplier: typing.Optional[float] = None,
    model_display_name: typing.Optional[str] = None,
    tuning_evaluation_spec: typing.Optional[TuningEvaluationSpec] = None,
    accelerator_type: typing.Optional[typing.Literal["TPU", "GPU"]] = None
) -> tunable_models._LanguageModelTuningJob

Tunes a model based on training data.

This method launches and returns an asynchronous model tuning job. Usage:

tuning_job = model.tune_model(...)
... do some other work
tuned_model = tuning_job.get_tuned_model()  # Blocks until tuning is complete
```

Parameter
Name	Description
training_data	typing.Union[str, tunable_models.pandas.core.frame.DataFrame] A Pandas DataFrame or a URI pointing to data in JSON lines format. The dataset schema is model-specific. See https://cloud.google.com/vertex-ai/docs/generative-ai/models/tune-models#dataset_format

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