Summary of entries of Methods for aiplatform.
vertexai.init
init(
*,
project: typing.Optional[str] = None,
location: typing.Optional[str] = None,
experiment: typing.Optional[str] = None,
experiment_description: typing.Optional[str] = None,
experiment_tensorboard: typing.Optional[
typing.Union[
str,
google.cloud.aiplatform.tensorboard.tensorboard_resource.Tensorboard,
bool,
]
] = None,
staging_bucket: typing.Optional[str] = None,
credentials: typing.Optional[google.auth.credentials.Credentials] = None,
encryption_spec_key_name: typing.Optional[str] = None,
network: typing.Optional[str] = None,
service_account: typing.Optional[str] = None,
api_endpoint: typing.Optional[str] = None,
api_key: typing.Optional[str] = None,
api_transport: typing.Optional[str] = None,
request_metadata: typing.Optional[typing.Sequence[typing.Tuple[str, str]]] = None
)Updates common initialization parameters with provided options.
See more: vertexai.init
vertexai.preview.end_run
end_run(
state: google.cloud.aiplatform_v1.types.execution.Execution.State = State.COMPLETE,
)Ends the the current experiment run.
See more: vertexai.preview.end_run
vertexai.preview.get_experiment_df
get_experiment_df(
experiment: typing.Optional[str] = None, *, include_time_series: bool = True
) -> pd.DataFrameReturns a Pandas DataFrame of the parameters and metrics associated with one experiment.
See more: vertexai.preview.get_experiment_df
vertexai.preview.log_classification_metrics
log_classification_metrics(
*,
labels: typing.Optional[typing.List[str]] = None,
matrix: typing.Optional[typing.List[typing.List[int]]] = None,
fpr: typing.Optional[typing.List[float]] = None,
tpr: typing.Optional[typing.List[float]] = None,
threshold: typing.Optional[typing.List[float]] = None,
display_name: typing.Optional[str] = None
) -> (
google.cloud.aiplatform.metadata.schema.google.artifact_schema.ClassificationMetrics
)Create an artifact for classification metrics and log to ExperimentRun.
vertexai.preview.log_metrics
log_metrics(metrics: typing.Dict[str, typing.Union[float, int, str]])Log single or multiple Metrics with specified key and value pairs.
See more: vertexai.preview.log_metrics
vertexai.preview.log_params
log_params(params: typing.Dict[str, typing.Union[float, int, str]])Log single or multiple parameters with specified key and value pairs.
See more: vertexai.preview.log_params
vertexai.preview.log_time_series_metrics
log_time_series_metrics(
metrics: typing.Dict[str, float],
step: typing.Optional[int] = None,
wall_time: typing.Optional[google.protobuf.timestamp_pb2.Timestamp] = None,
)Logs time series metrics to to this Experiment Run.
See more: vertexai.preview.log_time_series_metrics
vertexai.preview.start_run
start_run(
run: str,
*,
tensorboard: typing.Optional[
typing.Union[
google.cloud.aiplatform.tensorboard.tensorboard_resource.Tensorboard, str
]
] = None,
resume=False
) -> google.cloud.aiplatform.metadata.experiment_run_resource.ExperimentRunStart a run to current session.
See more: vertexai.preview.start_run
vertexai.preview.tuning.sft.rebase_tuned_model
rebase_tuned_model(
tuned_model_ref: str,
*,
artifact_destination: typing.Optional[str] = None,
deploy_to_same_endpoint: typing.Optional[bool] = False
)Re-runs fine tuning on top of a new foundational model.
vertexai.preview.tuning.sft.train
train(
*,
source_model: typing.Union[str, vertexai.generative_models.GenerativeModel],
train_dataset: str,
validation_dataset: typing.Optional[str] = None,
tuned_model_display_name: typing.Optional[str] = None,
epochs: typing.Optional[int] = None,
learning_rate_multiplier: typing.Optional[float] = None,
adapter_size: typing.Optional[typing.Literal[1, 4, 8, 16]] = None,
labels: typing.Optional[typing.Dict[str, str]] = None
) -> vertexai.tuning._supervised_tuning.SupervisedTuningJobTunes a model using supervised training.
See more: vertexai.preview.tuning.sft.train
vertexai.evaluation.CustomMetric
CustomMetric(
name: str,
metric_function: typing.Callable[
[typing.Dict[str, typing.Any]], typing.Dict[str, typing.Any]
],
)Initializes the evaluation metric.
See more: vertexai.evaluation.CustomMetric
vertexai.evaluation.EvalTask
EvalTask(
*,
dataset: typing.Union[pd.DataFrame, str, typing.Dict[str, typing.Any]],
metrics: typing.List[
typing.Union[
typing.Literal[
"exact_match",
"bleu",
"rouge_1",
"rouge_2",
"rouge_l",
"rouge_l_sum",
"tool_call_valid",
"tool_name_match",
"tool_parameter_key_match",
"tool_parameter_kv_match",
],
vertexai.evaluation.CustomMetric,
vertexai.evaluation.metrics._base._AutomaticMetric,
vertexai.evaluation.metrics.pointwise_metric.PointwiseMetric,
vertexai.evaluation.metrics.pairwise_metric.PairwiseMetric,
]
],
experiment: typing.Optional[str] = None,
metric_column_mapping: typing.Optional[typing.Dict[str, str]] = None,
output_uri_prefix: typing.Optional[str] = ""
)Initializes an EvalTask.
See more: vertexai.evaluation.EvalTask
vertexai.evaluation.EvalTask.display_runs
display_runs()Displays experiment runs associated with this EvalTask.
vertexai.evaluation.EvalTask.evaluate
evaluate(
*,
model: typing.Optional[
typing.Union[
vertexai.generative_models.GenerativeModel, typing.Callable[[str], str]
]
] = None,
prompt_template: typing.Optional[str] = None,
experiment_run_name: typing.Optional[str] = None,
response_column_name: typing.Optional[str] = None,
baseline_model_response_column_name: typing.Optional[str] = None,
evaluation_service_qps: typing.Optional[float] = None,
retry_timeout: float = 120.0,
output_file_name: typing.Optional[str] = None
) -> vertexai.evaluation.EvalResultRuns an evaluation for the EvalTask.
See more: vertexai.evaluation.EvalTask.evaluate
vertexai.evaluation.MetricPromptTemplateExamples.get_prompt_template
get_prompt_template(metric_name: str) -> strReturns the prompt template for the given metric name.
See more: vertexai.evaluation.MetricPromptTemplateExamples.get_prompt_template
vertexai.evaluation.MetricPromptTemplateExamples.list_example_metric_names
list_example_metric_names() -> typing.List[str]Returns a list of all metric prompt templates.
See more: vertexai.evaluation.MetricPromptTemplateExamples.list_example_metric_names
vertexai.evaluation.PairwiseMetric
PairwiseMetric(
*,
metric: str,
metric_prompt_template: typing.Union[
vertexai.evaluation.metrics.metric_prompt_template.PairwiseMetricPromptTemplate,
str,
],
baseline_model: typing.Optional[
typing.Union[
vertexai.generative_models.GenerativeModel, typing.Callable[[str], str]
]
] = None
)Initializes a pairwise evaluation metric.
See more: vertexai.evaluation.PairwiseMetric
vertexai.evaluation.PairwiseMetricPromptTemplate
PairwiseMetricPromptTemplate(
*,
criteria: typing.Dict[str, str],
rating_rubric: typing.Dict[str, str],
input_variables: typing.Optional[typing.List[str]] = None,
instruction: typing.Optional[str] = None,
metric_definition: typing.Optional[str] = None,
evaluation_steps: typing.Optional[typing.Dict[str, str]] = None,
few_shot_examples: typing.Optional[typing.List[str]] = None
)Initializes a pairwise metric prompt template.
vertexai.evaluation.PairwiseMetricPromptTemplate.__str__
__str__()Serializes the pairwise metric prompt template to a string.
See more: vertexai.evaluation.PairwiseMetricPromptTemplate.str
vertexai.evaluation.PairwiseMetricPromptTemplate.assemble
assemble(**kwargs) -> vertexai.evaluation.prompt_template.PromptTemplateReplaces only the provided variables in the template with specific values.
See more: vertexai.evaluation.PairwiseMetricPromptTemplate.assemble
vertexai.evaluation.PairwiseMetricPromptTemplate.get_default_pairwise_evaluation_steps
get_default_pairwise_evaluation_steps() -> typing.Dict[str, str]Returns the default evaluation steps for the metric prompt template.
See more: vertexai.evaluation.PairwiseMetricPromptTemplate.get_default_pairwise_evaluation_steps
vertexai.evaluation.PairwiseMetricPromptTemplate.get_default_pairwise_instruction
get_default_pairwise_instruction() -> strReturns the default instruction for the metric prompt template.
See more: vertexai.evaluation.PairwiseMetricPromptTemplate.get_default_pairwise_instruction
vertexai.evaluation.PointwiseMetric
PointwiseMetric(
*,
metric: str,
metric_prompt_template: typing.Union[
vertexai.evaluation.metrics.metric_prompt_template.PointwiseMetricPromptTemplate,
str,
]
)Initializes a pointwise evaluation metric.
See more: vertexai.evaluation.PointwiseMetric
vertexai.evaluation.PointwiseMetricPromptTemplate
PointwiseMetricPromptTemplate(
*,
criteria: typing.Dict[str, str],
rating_rubric: typing.Dict[str, str],
input_variables: typing.Optional[typing.List[str]] = None,
instruction: typing.Optional[str] = None,
metric_definition: typing.Optional[str] = None,
evaluation_steps: typing.Optional[typing.Dict[str, str]] = None,
few_shot_examples: typing.Optional[typing.List[str]] = None
)Initializes a pointwise metric prompt template.
vertexai.evaluation.PointwiseMetricPromptTemplate.__str__
__str__()Serializes the pointwise metric prompt template to a string.
See more: vertexai.evaluation.PointwiseMetricPromptTemplate.str
vertexai.evaluation.PointwiseMetricPromptTemplate.assemble
assemble(**kwargs) -> vertexai.evaluation.prompt_template.PromptTemplateReplaces only the provided variables in the template with specific values.
See more: vertexai.evaluation.PointwiseMetricPromptTemplate.assemble
vertexai.evaluation.PointwiseMetricPromptTemplate.get_default_pointwise_evaluation_steps
get_default_pointwise_evaluation_steps() -> typing.Dict[str, str]Returns the default evaluation steps for the metric prompt template.
See more: vertexai.evaluation.PointwiseMetricPromptTemplate.get_default_pointwise_evaluation_steps
vertexai.evaluation.PointwiseMetricPromptTemplate.get_default_pointwise_instruction
get_default_pointwise_instruction() -> strReturns the default instruction for the metric prompt template.
See more: vertexai.evaluation.PointwiseMetricPromptTemplate.get_default_pointwise_instruction
vertexai.evaluation.PromptTemplate
PromptTemplate(template: str)Initializes the PromptTemplate with a given template.
See more: vertexai.evaluation.PromptTemplate
vertexai.evaluation.PromptTemplate.__repr__
__repr__() -> strReturns a string representation of the PromptTemplate.
See more: vertexai.evaluation.PromptTemplate.repr
vertexai.evaluation.PromptTemplate.__str__
__str__() -> strReturns the template string.
See more: vertexai.evaluation.PromptTemplate.str
vertexai.evaluation.PromptTemplate.assemble
assemble(**kwargs) -> vertexai.evaluation.prompt_template.PromptTemplateReplaces only the provided variables in the template with specific values.
vertexai.evaluation.Rouge
Rouge(
*,
rouge_type: typing.Literal[
"rouge1",
"rouge2",
"rouge3",
"rouge4",
"rouge5",
"rouge6",
"rouge7",
"rouge8",
"rouge9",
"rougeL",
"rougeLsum",
],
use_stemmer: bool = False,
split_summaries: bool = False
)Initializes the ROUGE metric.
See more: vertexai.evaluation.Rouge
vertexai.generative_models.ChatSession.send_message
Generates content.
See more: vertexai.generative_models.ChatSession.send_message
vertexai.generative_models.ChatSession.send_message_async
Generates content asynchronously.
See more: vertexai.generative_models.ChatSession.send_message_async
vertexai.generative_models.FunctionDeclaration
FunctionDeclaration(
*,
name: str,
parameters: typing.Dict[str, typing.Any],
description: typing.Optional[str] = None
)Constructs a FunctionDeclaration.
vertexai.generative_models.GenerationConfig
GenerationConfig(
*,
temperature: typing.Optional[float] = None,
top_p: typing.Optional[float] = None,
top_k: typing.Optional[int] = None,
candidate_count: typing.Optional[int] = None,
max_output_tokens: typing.Optional[int] = None,
stop_sequences: typing.Optional[typing.List[str]] = None,
presence_penalty: typing.Optional[float] = None,
frequency_penalty: typing.Optional[float] = None,
response_mime_type: typing.Optional[str] = None,
response_schema: typing.Optional[typing.Dict[str, typing.Any]] = None,
seed: typing.Optional[int] = None,
audio_timestamp: typing.Optional[bool] = None,
routing_config: typing.Optional[RoutingConfig] = None,
logprobs: typing.Optional[int] = None,
response_logprobs: typing.Optional[bool] = None
)Constructs a GenerationConfig object.
vertexai.generative_models.GenerationConfig.RoutingConfig.AutoRoutingMode
AutoRoutingMode(
*,
model_routing_preference: google.cloud.aiplatform_v1beta1.types.content.GenerationConfig.RoutingConfig.AutoRoutingMode.ModelRoutingPreference
)AutoRouingMode constructor .
See more: vertexai.generative_models.GenerationConfig.RoutingConfig.AutoRoutingMode
vertexai.generative_models.GenerationConfig.RoutingConfig.ManualRoutingMode
ManualRoutingMode(*, model_name: str)ManualRoutingMode constructor .
See more: vertexai.generative_models.GenerationConfig.RoutingConfig.ManualRoutingMode
vertexai.generative_models.GenerativeModel.compute_tokens
compute_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.llm_utility_service.ComputeTokensResponseComputes tokens.
See more: vertexai.generative_models.GenerativeModel.compute_tokens
vertexai.generative_models.GenerativeModel.compute_tokens_async
compute_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.llm_utility_service.ComputeTokensResponseComputes tokens asynchronously.
See more: vertexai.generative_models.GenerativeModel.compute_tokens_async
vertexai.generative_models.GenerativeModel.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,
]
],
],
*,
tools: typing.Optional[
typing.List[vertexai.generative_models._generative_models.Tool]
] = None
) -> google.cloud.aiplatform_v1beta1.types.prediction_service.CountTokensResponseCounts tokens.
See more: vertexai.generative_models.GenerativeModel.count_tokens
vertexai.generative_models.GenerativeModel.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,
]
],
],
*,
tools: typing.Optional[
typing.List[vertexai.generative_models._generative_models.Tool]
] = None
) -> google.cloud.aiplatform_v1beta1.types.prediction_service.CountTokensResponseCounts tokens asynchronously.
See more: vertexai.generative_models.GenerativeModel.count_tokens_async
vertexai.generative_models.GenerativeModel.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[vertexai.generative_models._generative_models.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,
tool_config: typing.Optional[
vertexai.generative_models._generative_models.ToolConfig
] = None,
labels: typing.Optional[typing.Dict[str, str]] = None,
stream: bool = False
) -> typing.Union[
vertexai.generative_models._generative_models.GenerationResponse,
typing.Iterable[vertexai.generative_models._generative_models.GenerationResponse],
]Generates content.
See more: vertexai.generative_models.GenerativeModel.generate_content
vertexai.generative_models.GenerativeModel.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[vertexai.generative_models._generative_models.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,
tool_config: typing.Optional[
vertexai.generative_models._generative_models.ToolConfig
] = None,
labels: typing.Optional[typing.Dict[str, str]] = None,
stream: bool = False
) -> typing.Union[
vertexai.generative_models._generative_models.GenerationResponse,
typing.AsyncIterable[
vertexai.generative_models._generative_models.GenerationResponse
],
]Generates content asynchronously.
See more: vertexai.generative_models.GenerativeModel.generate_content_async
vertexai.generative_models.GenerativeModel.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.ChatSessionCreates a stateful chat session.
See more: vertexai.generative_models.GenerativeModel.start_chat
vertexai.generative_models.Image.from_bytes
from_bytes(data: bytes) -> vertexai.generative_models._generative_models.ImageLoads image from image bytes.
vertexai.generative_models.Image.load_from_file
load_from_file(
location: str,
) -> vertexai.generative_models._generative_models.ImageLoads image from file.
vertexai.generative_models.ResponseValidationError.with_traceback
Exception.with_traceback(tb) -- set self.traceback to tb and return self.
See more: vertexai.generative_models.ResponseValidationError.with_traceback
vertexai.generative_models.SafetySetting
SafetySetting(
*,
category: google.cloud.aiplatform_v1beta1.types.content.HarmCategory,
threshold: google.cloud.aiplatform_v1beta1.types.content.SafetySetting.HarmBlockThreshold,
method: typing.Optional[
google.cloud.aiplatform_v1beta1.types.content.SafetySetting.HarmBlockMethod
] = None
)Safety settings.
See more: vertexai.generative_models.SafetySetting
vertexai.generative_models.grounding.GoogleSearchRetrieval
GoogleSearchRetrieval()Initializes a Google Search Retrieval tool.
See more: vertexai.generative_models.grounding.GoogleSearchRetrieval
vertexai.language_models.ChatModel
ChatModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a LanguageModel.
See more: vertexai.language_models.ChatModel
vertexai.language_models.ChatModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.language_models.ChatModel.from_pretrained
vertexai.language_models.ChatModel.get_tuned_model
get_tuned_model(
tuned_model_name: str,
) -> vertexai.language_models._language_models._LanguageModelLoads the specified tuned language model.
See more: vertexai.language_models.ChatModel.get_tuned_model
vertexai.language_models.ChatModel.list_tuned_model_names
list_tuned_model_names() -> typing.Sequence[str]Lists the names of tuned models.
See more: vertexai.language_models.ChatModel.list_tuned_model_names
vertexai.language_models.ChatModel.start_chat
start_chat(
*,
context: typing.Optional[str] = None,
examples: typing.Optional[
typing.List[vertexai.language_models.InputOutputTextPair]
] = None,
max_output_tokens: typing.Optional[int] = None,
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.ChatMessage]
] = None,
stop_sequences: typing.Optional[typing.List[str]] = None
) -> vertexai.language_models.ChatSessionStarts a chat session with the model.
vertexai.language_models.ChatModel.tune_model
tune_model(
training_data: typing.Union[str, pandas.core.frame.DataFrame],
*,
train_steps: typing.Optional[int] = None,
learning_rate_multiplier: typing.Optional[float] = None,
tuning_job_location: typing.Optional[str] = None,
tuned_model_location: typing.Optional[str] = None,
model_display_name: typing.Optional[str] = None,
default_context: typing.Optional[str] = None,
accelerator_type: typing.Optional[typing.Literal["TPU", "GPU"]] = None,
tuning_evaluation_spec: typing.Optional[
vertexai.language_models.TuningEvaluationSpec
] = None
) -> vertexai.language_models._language_models._LanguageModelTuningJobTunes a model based on training data.
vertexai.language_models.ChatModel.tune_model_rlhf
tune_model_rlhf(
*,
prompt_data: typing.Union[str, pandas.core.frame.DataFrame],
preference_data: typing.Union[str, pandas.core.frame.DataFrame],
model_display_name: typing.Optional[str] = None,
prompt_sequence_length: typing.Optional[int] = None,
target_sequence_length: typing.Optional[int] = None,
reward_model_learning_rate_multiplier: typing.Optional[float] = None,
reinforcement_learning_rate_multiplier: typing.Optional[float] = None,
reward_model_train_steps: typing.Optional[int] = None,
reinforcement_learning_train_steps: typing.Optional[int] = None,
kl_coeff: typing.Optional[float] = None,
default_context: typing.Optional[str] = None,
tuning_job_location: typing.Optional[str] = None,
accelerator_type: typing.Optional[typing.Literal["TPU", "GPU"]] = None,
tuning_evaluation_spec: typing.Optional[
vertexai.language_models.TuningEvaluationSpec
] = None
) -> vertexai.language_models._language_models._LanguageModelTuningJobTunes a model using reinforcement learning from human feedback.
See more: vertexai.language_models.ChatModel.tune_model_rlhf
vertexai.language_models.ChatSession.send_message
send_message(
message: str,
*,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
top_k: typing.Optional[int] = None,
top_p: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None,
candidate_count: typing.Optional[int] = None,
grounding_source: typing.Optional[
typing.Union[
vertexai.language_models._language_models.WebSearch,
vertexai.language_models._language_models.VertexAISearch,
vertexai.language_models._language_models.InlineContext,
]
] = None
) -> vertexai.language_models.MultiCandidateTextGenerationResponseSends message to the language model and gets a response.
vertexai.language_models.ChatSession.send_message_async
send_message_async(
message: str,
*,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
top_k: typing.Optional[int] = None,
top_p: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None,
candidate_count: typing.Optional[int] = None,
grounding_source: typing.Optional[
typing.Union[
vertexai.language_models._language_models.WebSearch,
vertexai.language_models._language_models.VertexAISearch,
vertexai.language_models._language_models.InlineContext,
]
] = None
) -> vertexai.language_models.MultiCandidateTextGenerationResponseAsynchronously sends message to the language model and gets a response.
See more: vertexai.language_models.ChatSession.send_message_async
vertexai.language_models.ChatSession.send_message_streaming
send_message_streaming(
message: str,
*,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
top_k: typing.Optional[int] = None,
top_p: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None
) -> typing.Iterator[vertexai.language_models.TextGenerationResponse]Sends message to the language model and gets a streamed response.
See more: vertexai.language_models.ChatSession.send_message_streaming
vertexai.language_models.ChatSession.send_message_streaming_async
send_message_streaming_async(
message: str,
*,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
top_k: typing.Optional[int] = None,
top_p: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None
) -> typing.AsyncIterator[vertexai.language_models.TextGenerationResponse]Asynchronously sends message to the language model and gets a streamed response.
See more: vertexai.language_models.ChatSession.send_message_streaming_async
vertexai.language_models.CodeChatModel
CodeChatModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a LanguageModel.
See more: vertexai.language_models.CodeChatModel
vertexai.language_models.CodeChatModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.language_models.CodeChatModel.from_pretrained
vertexai.language_models.CodeChatModel.get_tuned_model
get_tuned_model(
tuned_model_name: str,
) -> vertexai.language_models._language_models._LanguageModelLoads the specified tuned language model.
See more: vertexai.language_models.CodeChatModel.get_tuned_model
vertexai.language_models.CodeChatModel.list_tuned_model_names
list_tuned_model_names() -> typing.Sequence[str]Lists the names of tuned models.
See more: vertexai.language_models.CodeChatModel.list_tuned_model_names
vertexai.language_models.CodeChatModel.start_chat
start_chat(
*,
context: typing.Optional[str] = None,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
message_history: typing.Optional[
typing.List[vertexai.language_models.ChatMessage]
] = None,
stop_sequences: typing.Optional[typing.List[str]] = None
) -> vertexai.language_models.CodeChatSessionStarts a chat session with the code chat model.
vertexai.language_models.CodeChatModel.tune_model
tune_model(
training_data: typing.Union[str, pandas.core.frame.DataFrame],
*,
train_steps: typing.Optional[int] = None,
learning_rate_multiplier: typing.Optional[float] = None,
tuning_job_location: typing.Optional[str] = None,
tuned_model_location: typing.Optional[str] = None,
model_display_name: typing.Optional[str] = None,
default_context: typing.Optional[str] = None,
accelerator_type: typing.Optional[typing.Literal["TPU", "GPU"]] = None,
tuning_evaluation_spec: typing.Optional[
vertexai.language_models.TuningEvaluationSpec
] = None
) -> vertexai.language_models._language_models._LanguageModelTuningJobTunes a model based on training data.
vertexai.language_models.CodeChatSession.send_message
send_message(
message: str,
*,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None,
candidate_count: typing.Optional[int] = None
) -> vertexai.language_models.MultiCandidateTextGenerationResponseSends message to the code chat model and gets a response.
See more: vertexai.language_models.CodeChatSession.send_message
vertexai.language_models.CodeChatSession.send_message_async
send_message_async(
message: str,
*,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
candidate_count: typing.Optional[int] = None
) -> vertexai.language_models.MultiCandidateTextGenerationResponseAsynchronously sends message to the code chat model and gets a response.
See more: vertexai.language_models.CodeChatSession.send_message_async
vertexai.language_models.CodeChatSession.send_message_streaming
send_message_streaming(
message: str,
*,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None
) -> typing.Iterator[vertexai.language_models.TextGenerationResponse]Sends message to the language model and gets a streamed response.
See more: vertexai.language_models.CodeChatSession.send_message_streaming
vertexai.language_models.CodeChatSession.send_message_streaming_async
send_message_streaming_async(
message: str,
*,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None
) -> typing.AsyncIterator[vertexai.language_models.TextGenerationResponse]Asynchronously sends message to the language model and gets a streamed response.
See more: vertexai.language_models.CodeChatSession.send_message_streaming_async
vertexai.language_models.CodeGenerationModel.batch_predict
batch_predict(
*,
dataset: typing.Union[str, typing.List[str]],
destination_uri_prefix: str,
model_parameters: typing.Optional[typing.Dict] = None
) -> google.cloud.aiplatform.jobs.BatchPredictionJobStarts a batch prediction job with the model.
See more: vertexai.language_models.CodeGenerationModel.batch_predict
vertexai.language_models.CodeGenerationModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.language_models.CodeGenerationModel.from_pretrained
vertexai.language_models.CodeGenerationModel.get_tuned_model
get_tuned_model(
tuned_model_name: str,
) -> vertexai.language_models._language_models._LanguageModelLoads the specified tuned language model.
See more: vertexai.language_models.CodeGenerationModel.get_tuned_model
vertexai.language_models.CodeGenerationModel.list_tuned_model_names
list_tuned_model_names() -> typing.Sequence[str]Lists the names of tuned models.
See more: vertexai.language_models.CodeGenerationModel.list_tuned_model_names
vertexai.language_models.CodeGenerationModel.predict
predict(
prefix: str,
suffix: typing.Optional[str] = None,
*,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None,
candidate_count: typing.Optional[int] = None
) -> vertexai.language_models.TextGenerationResponseGets model response for a single prompt.
See more: vertexai.language_models.CodeGenerationModel.predict
vertexai.language_models.CodeGenerationModel.predict_async
predict_async(
prefix: str,
suffix: typing.Optional[str] = None,
*,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None,
candidate_count: typing.Optional[int] = None
) -> vertexai.language_models.TextGenerationResponseAsynchronously gets model response for a single prompt.
See more: vertexai.language_models.CodeGenerationModel.predict_async
vertexai.language_models.CodeGenerationModel.predict_streaming
predict_streaming(
prefix: str,
suffix: typing.Optional[str] = None,
*,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None
) -> typing.Iterator[vertexai.language_models.TextGenerationResponse]Predicts the code based on previous code.
See more: vertexai.language_models.CodeGenerationModel.predict_streaming
vertexai.language_models.CodeGenerationModel.predict_streaming_async
predict_streaming_async(
prefix: str,
suffix: typing.Optional[str] = None,
*,
max_output_tokens: typing.Optional[int] = None,
temperature: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None
) -> typing.AsyncIterator[vertexai.language_models.TextGenerationResponse]Asynchronously predicts the code based on previous code.
See more: vertexai.language_models.CodeGenerationModel.predict_streaming_async
vertexai.language_models.CodeGenerationModel.tune_model
tune_model(
training_data: typing.Union[str, pandas.core.frame.DataFrame],
*,
train_steps: typing.Optional[int] = None,
learning_rate_multiplier: typing.Optional[float] = None,
tuning_job_location: typing.Optional[str] = None,
tuned_model_location: typing.Optional[str] = None,
model_display_name: typing.Optional[str] = None,
tuning_evaluation_spec: typing.Optional[
vertexai.language_models.TuningEvaluationSpec
] = None,
accelerator_type: typing.Optional[typing.Literal["TPU", "GPU"]] = None,
max_context_length: typing.Optional[str] = None
) -> vertexai.language_models._language_models._LanguageModelTuningJobTunes a model based on training data.
See more: vertexai.language_models.CodeGenerationModel.tune_model
vertexai.language_models.TextEmbeddingModel.batch_predict
batch_predict(
*,
dataset: typing.Union[str, typing.List[str]],
destination_uri_prefix: str,
model_parameters: typing.Optional[typing.Dict] = None
) -> google.cloud.aiplatform.jobs.BatchPredictionJobStarts a batch prediction job with the model.
See more: vertexai.language_models.TextEmbeddingModel.batch_predict
vertexai.language_models.TextEmbeddingModel.count_tokens
count_tokens(
prompts: typing.List[str],
) -> vertexai.preview.language_models.CountTokensResponseCounts the tokens and billable characters for a given prompt.
See more: vertexai.language_models.TextEmbeddingModel.count_tokens
vertexai.language_models.TextEmbeddingModel.deploy_tuned_model
deploy_tuned_model(
tuned_model_name: str,
machine_type: typing.Optional[str] = None,
accelerator: typing.Optional[str] = None,
accelerator_count: typing.Optional[int] = None,
) -> vertexai.language_models._language_models._LanguageModelLoads the specified tuned language model.
See more: vertexai.language_models.TextEmbeddingModel.deploy_tuned_model
vertexai.language_models.TextEmbeddingModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.language_models.TextEmbeddingModel.from_pretrained
vertexai.language_models.TextEmbeddingModel.get_embeddings
get_embeddings(
texts: typing.List[typing.Union[str, vertexai.language_models.TextEmbeddingInput]],
*,
auto_truncate: bool = True,
output_dimensionality: typing.Optional[int] = None
) -> typing.List[vertexai.language_models.TextEmbedding]Calculates embeddings for the given texts.
See more: vertexai.language_models.TextEmbeddingModel.get_embeddings
vertexai.language_models.TextEmbeddingModel.get_embeddings_async
get_embeddings_async(
texts: typing.List[typing.Union[str, vertexai.language_models.TextEmbeddingInput]],
*,
auto_truncate: bool = True,
output_dimensionality: typing.Optional[int] = None
) -> typing.List[vertexai.language_models.TextEmbedding]Asynchronously calculates embeddings for the given texts.
See more: vertexai.language_models.TextEmbeddingModel.get_embeddings_async
vertexai.language_models.TextEmbeddingModel.get_tuned_model
get_tuned_model(*args, **kwargs)Loads the specified tuned language model.
See more: vertexai.language_models.TextEmbeddingModel.get_tuned_model
vertexai.language_models.TextEmbeddingModel.list_tuned_model_names
list_tuned_model_names() -> typing.Sequence[str]Lists the names of tuned models.
See more: vertexai.language_models.TextEmbeddingModel.list_tuned_model_names
vertexai.language_models.TextEmbeddingModel.tune_model
tune_model(
*,
training_data: typing.Optional[str] = None,
corpus_data: typing.Optional[str] = None,
queries_data: typing.Optional[str] = None,
test_data: typing.Optional[str] = None,
validation_data: typing.Optional[str] = None,
batch_size: typing.Optional[int] = None,
train_steps: typing.Optional[int] = None,
tuned_model_location: typing.Optional[str] = None,
model_display_name: typing.Optional[str] = None,
task_type: typing.Optional[str] = None,
machine_type: typing.Optional[str] = None,
accelerator: typing.Optional[str] = None,
accelerator_count: typing.Optional[int] = None,
output_dimensionality: typing.Optional[int] = None,
learning_rate_multiplier: typing.Optional[float] = None
) -> vertexai.language_models._language_models._TextEmbeddingModelTuningJobTunes a model based on training data.
See more: vertexai.language_models.TextEmbeddingModel.tune_model
vertexai.language_models.TextGenerationModel.batch_predict
batch_predict(
*,
dataset: typing.Union[str, typing.List[str]],
destination_uri_prefix: str,
model_parameters: typing.Optional[typing.Dict] = None
) -> google.cloud.aiplatform.jobs.BatchPredictionJobStarts a batch prediction job with the model.
See more: vertexai.language_models.TextGenerationModel.batch_predict
vertexai.language_models.TextGenerationModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.language_models.TextGenerationModel.from_pretrained
vertexai.language_models.TextGenerationModel.get_tuned_model
get_tuned_model(
tuned_model_name: str,
) -> vertexai.language_models._language_models._LanguageModelLoads the specified tuned language model.
See more: vertexai.language_models.TextGenerationModel.get_tuned_model
vertexai.language_models.TextGenerationModel.list_tuned_model_names
list_tuned_model_names() -> typing.Sequence[str]Lists the names of tuned models.
See more: vertexai.language_models.TextGenerationModel.list_tuned_model_names
vertexai.language_models.TextGenerationModel.predict
predict(
prompt: str,
*,
max_output_tokens: typing.Optional[int] = 128,
temperature: typing.Optional[float] = None,
top_k: typing.Optional[int] = None,
top_p: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None,
candidate_count: typing.Optional[int] = None,
grounding_source: typing.Optional[
typing.Union[
vertexai.language_models._language_models.WebSearch,
vertexai.language_models._language_models.VertexAISearch,
vertexai.language_models._language_models.InlineContext,
]
] = None,
logprobs: typing.Optional[int] = None,
presence_penalty: typing.Optional[float] = None,
frequency_penalty: typing.Optional[float] = None,
logit_bias: typing.Optional[typing.Dict[str, float]] = None,
seed: typing.Optional[int] = None
) -> vertexai.language_models.MultiCandidateTextGenerationResponseGets model response for a single prompt.
See more: vertexai.language_models.TextGenerationModel.predict
vertexai.language_models.TextGenerationModel.predict_async
predict_async(
prompt: str,
*,
max_output_tokens: typing.Optional[int] = 128,
temperature: typing.Optional[float] = None,
top_k: typing.Optional[int] = None,
top_p: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None,
candidate_count: typing.Optional[int] = None,
grounding_source: typing.Optional[
typing.Union[
vertexai.language_models._language_models.WebSearch,
vertexai.language_models._language_models.VertexAISearch,
vertexai.language_models._language_models.InlineContext,
]
] = None,
logprobs: typing.Optional[int] = None,
presence_penalty: typing.Optional[float] = None,
frequency_penalty: typing.Optional[float] = None,
logit_bias: typing.Optional[typing.Dict[str, float]] = None,
seed: typing.Optional[int] = None
) -> vertexai.language_models.MultiCandidateTextGenerationResponseAsynchronously gets model response for a single prompt.
See more: vertexai.language_models.TextGenerationModel.predict_async
vertexai.language_models.TextGenerationModel.predict_streaming
predict_streaming(
prompt: str,
*,
max_output_tokens: int = 128,
temperature: typing.Optional[float] = None,
top_k: typing.Optional[int] = None,
top_p: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None,
logprobs: typing.Optional[int] = None,
presence_penalty: typing.Optional[float] = None,
frequency_penalty: typing.Optional[float] = None,
logit_bias: typing.Optional[typing.Dict[str, float]] = None,
seed: typing.Optional[int] = None
) -> typing.Iterator[vertexai.language_models.TextGenerationResponse]Gets a streaming model response for a single prompt.
See more: vertexai.language_models.TextGenerationModel.predict_streaming
vertexai.language_models.TextGenerationModel.predict_streaming_async
predict_streaming_async(
prompt: str,
*,
max_output_tokens: int = 128,
temperature: typing.Optional[float] = None,
top_k: typing.Optional[int] = None,
top_p: typing.Optional[float] = None,
stop_sequences: typing.Optional[typing.List[str]] = None,
logprobs: typing.Optional[int] = None,
presence_penalty: typing.Optional[float] = None,
frequency_penalty: typing.Optional[float] = None,
logit_bias: typing.Optional[typing.Dict[str, float]] = None,
seed: typing.Optional[int] = None
) -> typing.AsyncIterator[vertexai.language_models.TextGenerationResponse]Asynchronously gets a streaming model response for a single prompt.
See more: vertexai.language_models.TextGenerationModel.predict_streaming_async
vertexai.language_models.TextGenerationModel.tune_model
tune_model(
training_data: typing.Union[str, pandas.core.frame.DataFrame],
*,
train_steps: typing.Optional[int] = None,
learning_rate_multiplier: typing.Optional[float] = None,
tuning_job_location: typing.Optional[str] = None,
tuned_model_location: typing.Optional[str] = None,
model_display_name: typing.Optional[str] = None,
tuning_evaluation_spec: typing.Optional[
vertexai.language_models.TuningEvaluationSpec
] = None,
accelerator_type: typing.Optional[typing.Literal["TPU", "GPU"]] = None,
max_context_length: typing.Optional[str] = None
) -> vertexai.language_models._language_models._LanguageModelTuningJobTunes a model based on training data.
See more: vertexai.language_models.TextGenerationModel.tune_model
vertexai.language_models.TextGenerationModel.tune_model_rlhf
tune_model_rlhf(
*,
prompt_data: typing.Union[str, pandas.core.frame.DataFrame],
preference_data: typing.Union[str, pandas.core.frame.DataFrame],
model_display_name: typing.Optional[str] = None,
prompt_sequence_length: typing.Optional[int] = None,
target_sequence_length: typing.Optional[int] = None,
reward_model_learning_rate_multiplier: typing.Optional[float] = None,
reinforcement_learning_rate_multiplier: typing.Optional[float] = None,
reward_model_train_steps: typing.Optional[int] = None,
reinforcement_learning_train_steps: typing.Optional[int] = None,
kl_coeff: typing.Optional[float] = None,
default_context: typing.Optional[str] = None,
tuning_job_location: typing.Optional[str] = None,
accelerator_type: typing.Optional[typing.Literal["TPU", "GPU"]] = None,
tuning_evaluation_spec: typing.Optional[
vertexai.language_models.TuningEvaluationSpec
] = None
) -> vertexai.language_models._language_models._LanguageModelTuningJobTunes a model using reinforcement learning from human feedback.
See more: vertexai.language_models.TextGenerationModel.tune_model_rlhf
vertexai.language_models._language_models._TunableModelMixin
_TunableModelMixin(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a LanguageModel.
See more: vertexai.language_models._language_models._TunableModelMixin
vertexai.language_models._language_models._TunableModelMixin.tune_model
tune_model(
training_data: typing.Union[str, pandas.core.frame.DataFrame],
*,
corpus_data: typing.Optional[str] = None,
queries_data: typing.Optional[str] = None,
test_data: typing.Optional[str] = None,
validation_data: typing.Optional[str] = None,
batch_size: typing.Optional[int] = None,
train_steps: typing.Optional[int] = None,
learning_rate: typing.Optional[float] = None,
learning_rate_multiplier: typing.Optional[float] = None,
tuning_job_location: typing.Optional[str] = None,
tuned_model_location: typing.Optional[str] = None,
model_display_name: typing.Optional[str] = None,
tuning_evaluation_spec: typing.Optional[
vertexai.language_models.TuningEvaluationSpec
] = None,
default_context: typing.Optional[str] = None,
task_type: typing.Optional[str] = None,
machine_type: typing.Optional[str] = None,
accelerator: typing.Optional[str] = None,
accelerator_count: typing.Optional[int] = None,
accelerator_type: typing.Optional[typing.Literal["TPU", "GPU"]] = None,
max_context_length: typing.Optional[str] = None,
output_dimensionality: typing.Optional[int] = None
) -> vertexai.language_models._language_models._LanguageModelTuningJobTunes a model based on training data.
See more: vertexai.language_models._language_models._TunableModelMixin.tune_model
vertexai.preview.generative_models.AutomaticFunctionCallingResponder
AutomaticFunctionCallingResponder(max_automatic_function_calls: int = 1)Initializes the responder.
See more: vertexai.preview.generative_models.AutomaticFunctionCallingResponder
vertexai.preview.generative_models.CallableFunctionDeclaration
CallableFunctionDeclaration(
name: str,
function: typing.Callable[[...], typing.Any],
parameters: typing.Dict[str, typing.Any],
description: typing.Optional[str] = None,
)Constructs a FunctionDeclaration.
See more: vertexai.preview.generative_models.CallableFunctionDeclaration
vertexai.preview.generative_models.CallableFunctionDeclaration.from_func
from_func(
func: typing.Callable[[...], typing.Any]
) -> vertexai.generative_models._generative_models.CallableFunctionDeclarationAutomatically creates a CallableFunctionDeclaration from a Python function.
See more: vertexai.preview.generative_models.CallableFunctionDeclaration.from_func
vertexai.preview.generative_models.ChatSession.send_message
send_message(
content: typing.Union[
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[vertexai.generative_models._generative_models.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,
labels: typing.Optional[typing.Dict[str, str]] = None,
stream: bool = False
) -> typing.Union[
vertexai.generative_models._generative_models.GenerationResponse,
typing.Iterable[vertexai.generative_models._generative_models.GenerationResponse],
]Generates content.
See more: vertexai.preview.generative_models.ChatSession.send_message
vertexai.preview.generative_models.ChatSession.send_message_async
send_message_async(
content: typing.Union[
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[vertexai.generative_models._generative_models.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,
labels: typing.Optional[typing.Dict[str, str]] = None,
stream: bool = False
) -> typing.Union[
typing.Awaitable[vertexai.generative_models._generative_models.GenerationResponse],
typing.Awaitable[
typing.AsyncIterable[
vertexai.generative_models._generative_models.GenerationResponse
]
],
]Generates content asynchronously.
See more: vertexai.preview.generative_models.ChatSession.send_message_async
vertexai.preview.generative_models.FunctionDeclaration
FunctionDeclaration(
*,
name: str,
parameters: typing.Dict[str, typing.Any],
description: typing.Optional[str] = None
)Constructs a FunctionDeclaration.
See more: vertexai.preview.generative_models.FunctionDeclaration
vertexai.preview.generative_models.GenerationConfig
GenerationConfig(
*,
temperature: typing.Optional[float] = None,
top_p: typing.Optional[float] = None,
top_k: typing.Optional[int] = None,
candidate_count: typing.Optional[int] = None,
max_output_tokens: typing.Optional[int] = None,
stop_sequences: typing.Optional[typing.List[str]] = None,
presence_penalty: typing.Optional[float] = None,
frequency_penalty: typing.Optional[float] = None,
response_mime_type: typing.Optional[str] = None,
response_schema: typing.Optional[typing.Dict[str, typing.Any]] = None,
seed: typing.Optional[int] = None,
audio_timestamp: typing.Optional[bool] = None,
routing_config: typing.Optional[RoutingConfig] = None,
logprobs: typing.Optional[int] = None,
response_logprobs: typing.Optional[bool] = None
)Constructs a GenerationConfig object.
See more: vertexai.preview.generative_models.GenerationConfig
vertexai.preview.generative_models.GenerationConfig.RoutingConfig.AutoRoutingMode
AutoRoutingMode(
*,
model_routing_preference: google.cloud.aiplatform_v1beta1.types.content.GenerationConfig.RoutingConfig.AutoRoutingMode.ModelRoutingPreference
)AutoRouingMode constructor .
See more: vertexai.preview.generative_models.GenerationConfig.RoutingConfig.AutoRoutingMode
vertexai.preview.generative_models.GenerationConfig.RoutingConfig.ManualRoutingMode
ManualRoutingMode(*, model_name: str)ManualRoutingMode constructor .
See more: vertexai.preview.generative_models.GenerationConfig.RoutingConfig.ManualRoutingMode
vertexai.preview.generative_models.GenerativeModel.compute_tokens
compute_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.llm_utility_service.ComputeTokensResponseComputes tokens.
See more: vertexai.preview.generative_models.GenerativeModel.compute_tokens
vertexai.preview.generative_models.GenerativeModel.compute_tokens_async
compute_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.llm_utility_service.ComputeTokensResponseComputes tokens asynchronously.
See more: vertexai.preview.generative_models.GenerativeModel.compute_tokens_async
vertexai.preview.generative_models.GenerativeModel.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,
]
],
],
*,
tools: typing.Optional[
typing.List[vertexai.generative_models._generative_models.Tool]
] = None
) -> google.cloud.aiplatform_v1beta1.types.prediction_service.CountTokensResponseCounts tokens.
See more: vertexai.preview.generative_models.GenerativeModel.count_tokens
vertexai.preview.generative_models.GenerativeModel.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,
]
],
],
*,
tools: typing.Optional[
typing.List[vertexai.generative_models._generative_models.Tool]
] = None
) -> google.cloud.aiplatform_v1beta1.types.prediction_service.CountTokensResponseCounts tokens asynchronously.
See more: vertexai.preview.generative_models.GenerativeModel.count_tokens_async
vertexai.preview.generative_models.GenerativeModel.from_cached_content
from_cached_content(
cached_content: typing.Union[str, caching.CachedContent],
*,
generation_config: typing.Optional[
typing.Union[GenerationConfig, typing.Dict[str, typing.Any]]
] = None,
safety_settings: typing.Optional[
typing.Union[
typing.List[SafetySetting],
typing.Dict[
google.cloud.aiplatform_v1beta1.types.content.HarmCategory,
google.cloud.aiplatform_v1beta1.types.content.SafetySetting.HarmBlockThreshold,
],
]
] = None
) -> _GenerativeModelCreates a model from cached content.
See more: vertexai.preview.generative_models.GenerativeModel.from_cached_content
vertexai.preview.generative_models.GenerativeModel.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[vertexai.generative_models._generative_models.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,
tool_config: typing.Optional[
vertexai.generative_models._generative_models.ToolConfig
] = None,
labels: typing.Optional[typing.Dict[str, str]] = None,
stream: bool = False
) -> typing.Union[
vertexai.generative_models._generative_models.GenerationResponse,
typing.Iterable[vertexai.generative_models._generative_models.GenerationResponse],
]Generates content.
See more: vertexai.preview.generative_models.GenerativeModel.generate_content
vertexai.preview.generative_models.GenerativeModel.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[vertexai.generative_models._generative_models.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,
tool_config: typing.Optional[
vertexai.generative_models._generative_models.ToolConfig
] = None,
labels: typing.Optional[typing.Dict[str, str]] = None,
stream: bool = False
) -> typing.Union[
vertexai.generative_models._generative_models.GenerationResponse,
typing.AsyncIterable[
vertexai.generative_models._generative_models.GenerationResponse
],
]Generates content asynchronously.
See more: vertexai.preview.generative_models.GenerativeModel.generate_content_async
vertexai.preview.generative_models.GenerativeModel.start_chat
start_chat(
*,
history: typing.Optional[
typing.List[vertexai.generative_models._generative_models.Content]
] = None,
response_validation: bool = True,
responder: typing.Optional[
vertexai.generative_models._generative_models.AutomaticFunctionCallingResponder
] = None
) -> vertexai.generative_models._generative_models.ChatSessionCreates a stateful chat session.
See more: vertexai.preview.generative_models.GenerativeModel.start_chat
vertexai.preview.generative_models.Image.from_bytes
from_bytes(data: bytes) -> vertexai.generative_models._generative_models.ImageLoads image from image bytes.
See more: vertexai.preview.generative_models.Image.from_bytes
vertexai.preview.generative_models.Image.load_from_file
load_from_file(
location: str,
) -> vertexai.generative_models._generative_models.ImageLoads image from file.
See more: vertexai.preview.generative_models.Image.load_from_file
vertexai.preview.generative_models.ResponseBlockedError.with_traceback
Exception.with_traceback(tb) -- set self.traceback to tb and return self.
See more: vertexai.preview.generative_models.ResponseBlockedError.with_traceback
vertexai.preview.generative_models.ResponseValidationError.with_traceback
Exception.with_traceback(tb) -- set self.traceback to tb and return self.
See more: vertexai.preview.generative_models.ResponseValidationError.with_traceback
vertexai.preview.generative_models.SafetySetting
SafetySetting(
*,
category: google.cloud.aiplatform_v1beta1.types.content.HarmCategory,
threshold: google.cloud.aiplatform_v1beta1.types.content.SafetySetting.HarmBlockThreshold,
method: typing.Optional[
google.cloud.aiplatform_v1beta1.types.content.SafetySetting.HarmBlockMethod
] = None
)Safety settings.
vertexai.preview.reasoning_engines.LangchainAgent
LangchainAgent(
model: str,
*,
system_instruction: typing.Optional[str] = None,
prompt: typing.Optional[RunnableSerializable] = None,
tools: typing.Optional[typing.Sequence[_ToolLike]] = None,
output_parser: typing.Optional[RunnableSerializable] = None,
chat_history: typing.Optional[GetSessionHistoryCallable] = None,
model_kwargs: typing.Optional[typing.Mapping[str, typing.Any]] = None,
model_tool_kwargs: typing.Optional[typing.Mapping[str, typing.Any]] = None,
agent_executor_kwargs: typing.Optional[typing.Mapping[str, typing.Any]] = None,
runnable_kwargs: typing.Optional[typing.Mapping[str, typing.Any]] = None,
model_builder: typing.Optional[typing.Callable] = None,
runnable_builder: typing.Optional[typing.Callable] = None,
enable_tracing: bool = False
)Initializes the LangchainAgent.
vertexai.preview.reasoning_engines.LangchainAgent.clone
clone() -> vertexai.preview.reasoning_engines.templates.langchain.LangchainAgentReturns a clone of the LangchainAgent.
See more: vertexai.preview.reasoning_engines.LangchainAgent.clone
vertexai.preview.reasoning_engines.LangchainAgent.query
query(
*,
input: typing.Union[str, typing.Mapping[str, typing.Any]],
config: typing.Optional[RunnableConfig] = None,
**kwargs: typing.Any
) -> typing.Dict[str, typing.Any]Queries the Agent with the given input and config.
See more: vertexai.preview.reasoning_engines.LangchainAgent.query
vertexai.preview.reasoning_engines.LangchainAgent.set_up
set_up()Sets up the agent for execution of queries at runtime.
See more: vertexai.preview.reasoning_engines.LangchainAgent.set_up
vertexai.preview.reasoning_engines.Queryable.query
query(**kwargs)Runs the Reasoning Engine to serve the user query.
See more: vertexai.preview.reasoning_engines.Queryable.query
vertexai.preview.reasoning_engines.ReasoningEngine
ReasoningEngine(reasoning_engine_name: str)Retrieves a Reasoning Engine resource.
See more: vertexai.preview.reasoning_engines.ReasoningEngine
vertexai.preview.reasoning_engines.ReasoningEngine.create
create(
reasoning_engine: vertexai.reasoning_engines._reasoning_engines.Queryable,
*,
requirements: typing.Optional[typing.Union[str, typing.Sequence[str]]] = None,
reasoning_engine_name: typing.Optional[str] = None,
display_name: typing.Optional[str] = None,
description: typing.Optional[str] = None,
gcs_dir_name: str = "reasoning_engine",
sys_version: typing.Optional[str] = None,
extra_packages: typing.Optional[typing.Sequence[str]] = None
) -> vertexai.reasoning_engines._reasoning_engines.ReasoningEngineCreates a new ReasoningEngine.
See more: vertexai.preview.reasoning_engines.ReasoningEngine.create
vertexai.preview.reasoning_engines.ReasoningEngine.delete
delete(sync: bool = True) -> NoneDeletes this Vertex AI resource.
See more: vertexai.preview.reasoning_engines.ReasoningEngine.delete
vertexai.preview.reasoning_engines.ReasoningEngine.list
list(
filter: typing.Optional[str] = None,
order_by: typing.Optional[str] = None,
project: typing.Optional[str] = None,
location: typing.Optional[str] = None,
credentials: typing.Optional[google.auth.credentials.Credentials] = None,
parent: typing.Optional[str] = None,
) -> typing.List[google.cloud.aiplatform.base.VertexAiResourceNoun]List all instances of this Vertex AI Resource.
See more: vertexai.preview.reasoning_engines.ReasoningEngine.list
vertexai.preview.reasoning_engines.ReasoningEngine.operation_schemas
operation_schemas() -> typing.Sequence[typing.Dict[str, typing.Any]]Returns the (Open)API schemas for the Reasoning Engine.
See more: vertexai.preview.reasoning_engines.ReasoningEngine.operation_schemas
vertexai.preview.reasoning_engines.ReasoningEngine.query
query(**kwargs) -> typing.Dict[str, typing.Any]Runs the Reasoning Engine to serve the user query.
See more: vertexai.preview.reasoning_engines.ReasoningEngine.query
vertexai.preview.reasoning_engines.ReasoningEngine.to_dict
to_dict() -> typing.Dict[str, typing.Any]Returns the resource proto as a dictionary.
See more: vertexai.preview.reasoning_engines.ReasoningEngine.to_dict
vertexai.preview.reasoning_engines.ReasoningEngine.update
update(
*,
reasoning_engine: typing.Optional[
vertexai.reasoning_engines._reasoning_engines.Queryable
] = None,
requirements: typing.Optional[typing.Union[str, typing.Sequence[str]]] = None,
display_name: typing.Optional[str] = None,
description: typing.Optional[str] = None,
gcs_dir_name: str = "reasoning_engine",
sys_version: typing.Optional[str] = None,
extra_packages: typing.Optional[typing.Sequence[str]] = None
) -> vertexai.reasoning_engines._reasoning_engines.ReasoningEngineUpdates an existing ReasoningEngine.
See more: vertexai.preview.reasoning_engines.ReasoningEngine.update
vertexai.preview.reasoning_engines.ReasoningEngine.wait
wait()Helper method that blocks until all futures are complete.
See more: vertexai.preview.reasoning_engines.ReasoningEngine.wait
vertexai.preview.tuning.TuningJob
TuningJob(tuning_job_name: str)Initializes class with project, location, and api_client.
See more: vertexai.preview.tuning.TuningJob
vertexai.preview.tuning.TuningJob.list
list(
filter: typing.Optional[str] = None,
) -> typing.List[vertexai.tuning._tuning.TuningJob]Lists TuningJobs.
See more: vertexai.preview.tuning.TuningJob.list
vertexai.preview.tuning.TuningJob.refresh
refresh() -> vertexai.tuning._tuning.TuningJobRefreshed the tuning job from the service.
vertexai.preview.tuning.TuningJob.to_dict
to_dict() -> typing.Dict[str, typing.Any]Returns the resource proto as a dictionary.
vertexai.preview.tuning.sft.SupervisedTuningJob.list
list(
filter: typing.Optional[str] = None,
) -> typing.List[vertexai.tuning._tuning.TuningJob]Lists TuningJobs.
See more: vertexai.preview.tuning.sft.SupervisedTuningJob.list
vertexai.preview.tuning.sft.SupervisedTuningJob.refresh
refresh() -> vertexai.tuning._tuning.TuningJobRefreshed the tuning job from the service.
See more: vertexai.preview.tuning.sft.SupervisedTuningJob.refresh
vertexai.preview.tuning.sft.SupervisedTuningJob.to_dict
to_dict() -> typing.Dict[str, typing.Any]Returns the resource proto as a dictionary.
See more: vertexai.preview.tuning.sft.SupervisedTuningJob.to_dict
vertexai.preview.vision_models.GeneratedImage
GeneratedImage(
image_bytes: typing.Optional[bytes],
generation_parameters: typing.Dict[str, typing.Any],
gcs_uri: typing.Optional[str] = None,
)Creates a GeneratedImage object.
vertexai.preview.vision_models.GeneratedImage.load_from_file
load_from_file(location: str) -> vertexai.preview.vision_models.GeneratedImageLoads image from file.
See more: vertexai.preview.vision_models.GeneratedImage.load_from_file
vertexai.preview.vision_models.GeneratedImage.save
save(location: str, include_generation_parameters: bool = True)Saves image to a file.
See more: vertexai.preview.vision_models.GeneratedImage.save
vertexai.preview.vision_models.GeneratedImage.show
show()Shows the image.
See more: vertexai.preview.vision_models.GeneratedImage.show
vertexai.preview.vision_models.GeneratedMask
GeneratedMask(
image_bytes: typing.Optional[bytes],
gcs_uri: typing.Optional[str] = None,
labels: typing.Optional[
typing.List[vertexai.preview.vision_models.EntityLabel]
] = None,
)Creates a GeneratedMask object.
vertexai.preview.vision_models.GeneratedMask.load_from_file
load_from_file(location: str) -> vertexai.vision_models.ImageLoads image from local file or Google Cloud Storage.
See more: vertexai.preview.vision_models.GeneratedMask.load_from_file
vertexai.preview.vision_models.GeneratedMask.save
save(location: str)Saves image to a file.
vertexai.preview.vision_models.GeneratedMask.show
show()Shows the image.
vertexai.preview.vision_models.Image
Image(
image_bytes: typing.Optional[bytes] = None, gcs_uri: typing.Optional[str] = None
)Creates an Image object.
See more: vertexai.preview.vision_models.Image
vertexai.preview.vision_models.Image.load_from_file
load_from_file(location: str) -> vertexai.vision_models.ImageLoads image from local file or Google Cloud Storage.
See more: vertexai.preview.vision_models.Image.load_from_file
vertexai.preview.vision_models.Image.save
save(location: str)Saves image to a file.
vertexai.preview.vision_models.Image.show
show()Shows the image.
vertexai.preview.vision_models.ImageCaptioningModel
ImageCaptioningModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a _ModelGardenModel.
See more: vertexai.preview.vision_models.ImageCaptioningModel
vertexai.preview.vision_models.ImageCaptioningModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.preview.vision_models.ImageCaptioningModel.from_pretrained
vertexai.preview.vision_models.ImageCaptioningModel.get_captions
get_captions(
image: vertexai.vision_models.Image,
*,
number_of_results: int = 1,
language: str = "en",
output_gcs_uri: typing.Optional[str] = None
) -> typing.List[str]Generates captions for a given image.
See more: vertexai.preview.vision_models.ImageCaptioningModel.get_captions
vertexai.preview.vision_models.ImageGenerationModel
ImageGenerationModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a _ModelGardenModel.
See more: vertexai.preview.vision_models.ImageGenerationModel
vertexai.preview.vision_models.ImageGenerationModel.edit_image
edit_image(
*,
prompt: str,
base_image: vertexai.vision_models.Image,
mask: typing.Optional[vertexai.vision_models.Image] = None,
negative_prompt: typing.Optional[str] = None,
number_of_images: int = 1,
guidance_scale: typing.Optional[float] = None,
edit_mode: typing.Optional[
typing.Literal[
"inpainting-insert", "inpainting-remove", "outpainting", "product-image"
]
] = None,
mask_mode: typing.Optional[
typing.Literal["background", "foreground", "semantic"]
] = None,
segmentation_classes: typing.Optional[typing.List[str]] = None,
mask_dilation: typing.Optional[float] = None,
product_position: typing.Optional[typing.Literal["fixed", "reposition"]] = None,
output_mime_type: typing.Optional[typing.Literal["image/png", "image/jpeg"]] = None,
compression_quality: typing.Optional[float] = None,
language: typing.Optional[str] = None,
seed: typing.Optional[int] = None,
output_gcs_uri: typing.Optional[str] = None,
safety_filter_level: typing.Optional[
typing.Literal["block_most", "block_some", "block_few", "block_fewest"]
] = None,
person_generation: typing.Optional[
typing.Literal["dont_allow", "allow_adult", "allow_all"]
] = None
) -> vertexai.preview.vision_models.ImageGenerationResponseEdits an existing image based on text prompt.
See more: vertexai.preview.vision_models.ImageGenerationModel.edit_image
vertexai.preview.vision_models.ImageGenerationModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.preview.vision_models.ImageGenerationModel.from_pretrained
vertexai.preview.vision_models.ImageGenerationModel.generate_images
generate_images(
prompt: str,
*,
negative_prompt: typing.Optional[str] = None,
number_of_images: int = 1,
aspect_ratio: typing.Optional[
typing.Literal["1:1", "9:16", "16:9", "4:3", "3:4"]
] = None,
guidance_scale: typing.Optional[float] = None,
language: typing.Optional[str] = None,
seed: typing.Optional[int] = None,
output_gcs_uri: typing.Optional[str] = None,
add_watermark: typing.Optional[bool] = True,
safety_filter_level: typing.Optional[
typing.Literal["block_most", "block_some", "block_few", "block_fewest"]
] = None,
person_generation: typing.Optional[
typing.Literal["dont_allow", "allow_adult", "allow_all"]
] = None
) -> vertexai.preview.vision_models.ImageGenerationResponseGenerates images from text prompt.
See more: vertexai.preview.vision_models.ImageGenerationModel.generate_images
vertexai.preview.vision_models.ImageGenerationModel.upscale_image
upscale_image(
image: typing.Union[
vertexai.vision_models.Image, vertexai.preview.vision_models.GeneratedImage
],
new_size: typing.Optional[int] = 2048,
upscale_factor: typing.Optional[typing.Literal["x2", "x4"]] = None,
output_mime_type: typing.Optional[
typing.Literal["image/png", "image/jpeg"]
] = "image/png",
output_compression_quality: typing.Optional[int] = None,
output_gcs_uri: typing.Optional[str] = None,
) -> vertexai.vision_models.ImageUpscales an image.
See more: vertexai.preview.vision_models.ImageGenerationModel.upscale_image
vertexai.preview.vision_models.ImageGenerationResponse.__getitem__
__getitem__(idx: int) -> vertexai.preview.vision_models.GeneratedImageGets the generated image by index.
See more: vertexai.preview.vision_models.ImageGenerationResponse.getitem
vertexai.preview.vision_models.ImageGenerationResponse.__iter__
__iter__() -> typing.Iterator[vertexai.preview.vision_models.GeneratedImage]Iterates through the generated images.
See more: vertexai.preview.vision_models.ImageGenerationResponse.iter
vertexai.preview.vision_models.ImageQnAModel
ImageQnAModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a _ModelGardenModel.
vertexai.preview.vision_models.ImageQnAModel.ask_question
ask_question(
image: vertexai.vision_models.Image, question: str, *, number_of_results: int = 1
) -> typing.List[str]Answers questions about an image.
See more: vertexai.preview.vision_models.ImageQnAModel.ask_question
vertexai.preview.vision_models.ImageQnAModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.preview.vision_models.ImageQnAModel.from_pretrained
vertexai.preview.vision_models.ImageSegmentationModel
ImageSegmentationModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a _ModelGardenModel.
See more: vertexai.preview.vision_models.ImageSegmentationModel
vertexai.preview.vision_models.ImageSegmentationModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.preview.vision_models.ImageSegmentationModel.from_pretrained
vertexai.preview.vision_models.ImageSegmentationModel.segment_image
segment_image(
base_image: vertexai.vision_models.Image,
prompt: typing.Optional[str] = None,
scribble: typing.Optional[vertexai.preview.vision_models.Scribble] = None,
mode: typing.Literal[
"foreground", "background", "semantic", "prompt", "interactive"
] = "foreground",
max_predictions: typing.Optional[int] = None,
confidence_threshold: typing.Optional[float] = 0.1,
mask_dilation: typing.Optional[float] = None,
) -> vertexai.preview.vision_models.ImageSegmentationResponseSegments an image.
See more: vertexai.preview.vision_models.ImageSegmentationModel.segment_image
vertexai.preview.vision_models.ImageSegmentationResponse.__getitem__
__getitem__(idx: int) -> vertexai.preview.vision_models.GeneratedMaskGets the generated masks by index.
See more: vertexai.preview.vision_models.ImageSegmentationResponse.getitem
vertexai.preview.vision_models.ImageSegmentationResponse.__iter__
__iter__() -> typing.Iterator[vertexai.preview.vision_models.GeneratedMask]Iterates through the generated masks.
See more: vertexai.preview.vision_models.ImageSegmentationResponse.iter
vertexai.preview.vision_models.ImageTextModel
ImageTextModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a _ModelGardenModel.
vertexai.preview.vision_models.ImageTextModel.ask_question
ask_question(
image: vertexai.vision_models.Image, question: str, *, number_of_results: int = 1
) -> typing.List[str]Answers questions about an image.
See more: vertexai.preview.vision_models.ImageTextModel.ask_question
vertexai.preview.vision_models.ImageTextModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.preview.vision_models.ImageTextModel.from_pretrained
vertexai.preview.vision_models.ImageTextModel.get_captions
get_captions(
image: vertexai.vision_models.Image,
*,
number_of_results: int = 1,
language: str = "en",
output_gcs_uri: typing.Optional[str] = None
) -> typing.List[str]Generates captions for a given image.
See more: vertexai.preview.vision_models.ImageTextModel.get_captions
vertexai.preview.vision_models.MultiModalEmbeddingModel
MultiModalEmbeddingModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a _ModelGardenModel.
See more: vertexai.preview.vision_models.MultiModalEmbeddingModel
vertexai.preview.vision_models.MultiModalEmbeddingModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.preview.vision_models.MultiModalEmbeddingModel.from_pretrained
vertexai.preview.vision_models.MultiModalEmbeddingModel.get_embeddings
get_embeddings(
image: typing.Optional[vertexai.vision_models.Image] = None,
video: typing.Optional[vertexai.vision_models.Video] = None,
contextual_text: typing.Optional[str] = None,
dimension: typing.Optional[int] = None,
video_segment_config: typing.Optional[
vertexai.vision_models.VideoSegmentConfig
] = None,
) -> vertexai.vision_models.MultiModalEmbeddingResponseGets embedding vectors from the provided image.
See more: vertexai.preview.vision_models.MultiModalEmbeddingModel.get_embeddings
vertexai.preview.vision_models.Scribble
Scribble(image_bytes: typing.Optional[bytes], gcs_uri: typing.Optional[str] = None)Creates a Scribble object.
See more: vertexai.preview.vision_models.Scribble
vertexai.preview.vision_models.Video
Video(
video_bytes: typing.Optional[bytes] = None, gcs_uri: typing.Optional[str] = None
)Creates a Video object.
See more: vertexai.preview.vision_models.Video
vertexai.preview.vision_models.Video.load_from_file
load_from_file(location: str) -> vertexai.vision_models.VideoLoads video from local file or Google Cloud Storage.
See more: vertexai.preview.vision_models.Video.load_from_file
vertexai.preview.vision_models.Video.save
save(location: str)Saves video to a file.
vertexai.preview.vision_models.VideoEmbedding
VideoEmbedding(
start_offset_sec: int, end_offset_sec: int, embedding: typing.List[float]
)Creates a VideoEmbedding object.
vertexai.preview.vision_models.VideoSegmentConfig
VideoSegmentConfig(
start_offset_sec: int = 0, end_offset_sec: int = 120, interval_sec: int = 16
)Creates a VideoSegmentConfig object.
vertexai.preview.vision_models.WatermarkVerificationModel
WatermarkVerificationModel(
model_id: str, endpoint_name: typing.Optional[str] = None
)Creates a _ModelGardenModel.
See more: vertexai.preview.vision_models.WatermarkVerificationModel
vertexai.preview.vision_models.WatermarkVerificationModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.preview.vision_models.WatermarkVerificationModel.from_pretrained
vertexai.preview.vision_models.WatermarkVerificationModel.verify_image
verify_image(
image: vertexai.vision_models.Image,
) -> vertexai.preview.vision_models.WatermarkVerificationResponseVerifies the watermark of an image.
See more: vertexai.preview.vision_models.WatermarkVerificationModel.verify_image
vertexai.resources.preview.ml_monitoring.ModelMonitor
ModelMonitor(
model_monitor_name: str,
project: typing.Optional[str] = None,
location: typing.Optional[str] = None,
credentials: typing.Optional[google.auth.credentials.Credentials] = None,
)Initializes class with project, location, and api_client.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor
vertexai.resources.preview.ml_monitoring.ModelMonitor.create
create(
model_name: str,
model_version_id: str,
training_dataset: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.MonitoringInput
] = None,
display_name: typing.Optional[str] = None,
model_monitoring_schema: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.schema.ModelMonitoringSchema
] = None,
tabular_objective_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.TabularObjective
] = None,
output_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.output.OutputSpec
] = None,
notification_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.notification.NotificationSpec
] = None,
explanation_spec: typing.Optional[
google.cloud.aiplatform_v1beta1.types.explanation.ExplanationSpec
] = None,
project: typing.Optional[str] = None,
location: typing.Optional[str] = None,
credentials: typing.Optional[google.auth.credentials.Credentials] = None,
model_monitor_id: typing.Optional[str] = None,
) -> vertexai.resources.preview.ml_monitoring.model_monitors.ModelMonitorCreates a new ModelMonitor.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.create
vertexai.resources.preview.ml_monitoring.ModelMonitor.create_schedule
create_schedule(
cron: str,
target_dataset: vertexai.resources.preview.ml_monitoring.spec.objective.MonitoringInput,
display_name: typing.Optional[str] = None,
model_monitoring_job_display_name: typing.Optional[str] = None,
start_time: typing.Optional[google.protobuf.timestamp_pb2.Timestamp] = None,
end_time: typing.Optional[google.protobuf.timestamp_pb2.Timestamp] = None,
tabular_objective_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.TabularObjective
] = None,
baseline_dataset: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.MonitoringInput
] = None,
output_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.output.OutputSpec
] = None,
notification_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.notification.NotificationSpec
] = None,
explanation_spec: typing.Optional[
google.cloud.aiplatform_v1beta1.types.explanation.ExplanationSpec
] = None,
) -> google.cloud.aiplatform_v1beta1.types.schedule.ScheduleCreates a new Scheduled run for model monitoring job.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.create_schedule
vertexai.resources.preview.ml_monitoring.ModelMonitor.delete
delete(force: bool = False, sync: bool = True) -> NoneForce delete the model monitor.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.delete
vertexai.resources.preview.ml_monitoring.ModelMonitor.delete_model_monitoring_job
delete_model_monitoring_job(model_monitoring_job_name: str) -> NoneDelete a model monitoring job.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.delete_model_monitoring_job
vertexai.resources.preview.ml_monitoring.ModelMonitor.delete_schedule
delete_schedule(schedule_name: str) -> NoneDeletes an existing Schedule.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.delete_schedule
vertexai.resources.preview.ml_monitoring.ModelMonitor.get_model_monitoring_job
get_model_monitoring_job(
model_monitoring_job_name: str,
) -> vertexai.resources.preview.ml_monitoring.model_monitors.ModelMonitoringJobGet the specified ModelMonitoringJob.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.get_model_monitoring_job
vertexai.resources.preview.ml_monitoring.ModelMonitor.get_schedule
get_schedule(
schedule_name: str,
) -> google.cloud.aiplatform_v1beta1.types.schedule.ScheduleGets an existing Schedule.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.get_schedule
vertexai.resources.preview.ml_monitoring.ModelMonitor.get_schema
get_schema() -> (
google.cloud.aiplatform_v1beta1.types.model_monitor.ModelMonitoringSchema
)Get the schema of the model monitor.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.get_schema
vertexai.resources.preview.ml_monitoring.ModelMonitor.list
list(
filter: typing.Optional[str] = None,
order_by: typing.Optional[str] = None,
project: typing.Optional[str] = None,
location: typing.Optional[str] = None,
credentials: typing.Optional[google.auth.credentials.Credentials] = None,
parent: typing.Optional[str] = None,
) -> typing.List[google.cloud.aiplatform.base.VertexAiResourceNoun]List all instances of this Vertex AI Resource.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.list
vertexai.resources.preview.ml_monitoring.ModelMonitor.list_jobs
list_jobs(
page_size: typing.Optional[int] = None, page_token: typing.Optional[str] = None
) -> ListJobsResponse.list_jobsList ModelMonitoringJobs.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.list_jobs
vertexai.resources.preview.ml_monitoring.ModelMonitor.list_schedules
list_schedules(
filter: typing.Optional[str] = None,
page_size: typing.Optional[int] = None,
page_token: typing.Optional[str] = None,
) -> ListSchedulesResponse.list_schedulesList Schedules.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.list_schedules
vertexai.resources.preview.ml_monitoring.ModelMonitor.pause_schedule
pause_schedule(schedule_name: str) -> NonePauses an existing Schedule.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.pause_schedule
vertexai.resources.preview.ml_monitoring.ModelMonitor.resume_schedule
resume_schedule(schedule_name: str) -> NoneResumes an existing Schedule.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.resume_schedule
vertexai.resources.preview.ml_monitoring.ModelMonitor.run
run(
target_dataset: vertexai.resources.preview.ml_monitoring.spec.objective.MonitoringInput,
display_name: typing.Optional[str] = None,
model_monitoring_job_id: typing.Optional[str] = None,
sync: typing.Optional[bool] = False,
tabular_objective_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.TabularObjective
] = None,
baseline_dataset: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.MonitoringInput
] = None,
output_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.output.OutputSpec
] = None,
notification_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.notification.NotificationSpec
] = None,
explanation_spec: typing.Optional[
google.cloud.aiplatform_v1beta1.types.explanation.ExplanationSpec
] = None,
) -> vertexai.resources.preview.ml_monitoring.model_monitors.ModelMonitoringJobCreates a new ModelMonitoringJob.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.run
vertexai.resources.preview.ml_monitoring.ModelMonitor.search_alerts
search_alerts(
stats_name: typing.Optional[str] = None,
objective_type: typing.Optional[str] = None,
model_monitoring_job_name: typing.Optional[str] = None,
start_time: typing.Optional[google.protobuf.timestamp_pb2.Timestamp] = None,
end_time: typing.Optional[google.protobuf.timestamp_pb2.Timestamp] = None,
page_size: typing.Optional[int] = None,
page_token: typing.Optional[str] = None,
) -> typing.Dict[str, typing.Any]Search ModelMonitoringAlerts.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.search_alerts
vertexai.resources.preview.ml_monitoring.ModelMonitor.search_metrics
search_metrics(
stats_name: typing.Optional[str] = None,
objective_type: typing.Optional[str] = None,
model_monitoring_job_name: typing.Optional[str] = None,
schedule_name: typing.Optional[str] = None,
algorithm: typing.Optional[str] = None,
start_time: typing.Optional[google.protobuf.timestamp_pb2.Timestamp] = None,
end_time: typing.Optional[google.protobuf.timestamp_pb2.Timestamp] = None,
page_size: typing.Optional[int] = None,
page_token: typing.Optional[str] = None,
) -> MetricsSearchResponse.monitoring_statsSearch ModelMonitoringStats.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.search_metrics
vertexai.resources.preview.ml_monitoring.ModelMonitor.show_feature_attribution_drift_stats
show_feature_attribution_drift_stats(model_monitoring_job_name: str) -> NoneThe method to visualize the feature attribution drift result from a model monitoring job as a histogram chart and a table.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.show_feature_attribution_drift_stats
vertexai.resources.preview.ml_monitoring.ModelMonitor.show_feature_drift_stats
show_feature_drift_stats(model_monitoring_job_name: str) -> NoneThe method to visualize the feature drift result from a model monitoring job as a histogram chart and a table.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.show_feature_drift_stats
vertexai.resources.preview.ml_monitoring.ModelMonitor.show_output_drift_stats
show_output_drift_stats(model_monitoring_job_name: str) -> NoneThe method to visualize the prediction output drift result from a model monitoring job as a histogram chart and a table.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.show_output_drift_stats
vertexai.resources.preview.ml_monitoring.ModelMonitor.to_dict
to_dict() -> typing.Dict[str, typing.Any]Returns the resource proto as a dictionary.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.to_dict
vertexai.resources.preview.ml_monitoring.ModelMonitor.update
update(
display_name: typing.Optional[str] = None,
training_dataset: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.MonitoringInput
] = None,
model_monitoring_schema: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.schema.ModelMonitoringSchema
] = None,
tabular_objective_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.TabularObjective
] = None,
output_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.output.OutputSpec
] = None,
notification_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.notification.NotificationSpec
] = None,
explanation_spec: typing.Optional[
google.cloud.aiplatform_v1beta1.types.explanation.ExplanationSpec
] = None,
) -> vertexai.resources.preview.ml_monitoring.model_monitors.ModelMonitorUpdates an existing ModelMonitor.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.update
vertexai.resources.preview.ml_monitoring.ModelMonitor.update_schedule
update_schedule(
schedule_name: str,
display_name: typing.Optional[str] = None,
model_monitoring_job_display_name: typing.Optional[str] = None,
cron: typing.Optional[str] = None,
baseline_dataset: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.MonitoringInput
] = None,
target_dataset: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.MonitoringInput
] = None,
tabular_objective_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.TabularObjective
] = None,
output_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.output.OutputSpec
] = None,
notification_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.notification.NotificationSpec
] = None,
explanation_spec: typing.Optional[
google.cloud.aiplatform_v1beta1.types.explanation.ExplanationSpec
] = None,
end_time: typing.Optional[google.protobuf.timestamp_pb2.Timestamp] = None,
) -> google.cloud.aiplatform_v1beta1.types.schedule.ScheduleUpdates an existing Schedule.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.update_schedule
vertexai.resources.preview.ml_monitoring.ModelMonitor.wait
wait()Helper method that blocks until all futures are complete.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitor.wait
vertexai.resources.preview.ml_monitoring.ModelMonitoringJob
ModelMonitoringJob(
model_monitoring_job_name: str,
model_monitor_id: typing.Optional[str] = None,
project: typing.Optional[str] = None,
location: typing.Optional[str] = None,
credentials: typing.Optional[google.auth.credentials.Credentials] = None,
)Initializes class with project, location, and api_client.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitoringJob
vertexai.resources.preview.ml_monitoring.ModelMonitoringJob.create
create(
model_monitor_name: typing.Optional[str] = None,
target_dataset: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.MonitoringInput
] = None,
display_name: typing.Optional[str] = None,
model_monitoring_job_id: typing.Optional[str] = None,
project: typing.Optional[str] = None,
location: typing.Optional[str] = None,
credentials: typing.Optional[google.auth.credentials.Credentials] = None,
baseline_dataset: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.MonitoringInput
] = None,
tabular_objective_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.objective.TabularObjective
] = None,
output_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.output.OutputSpec
] = None,
notification_spec: typing.Optional[
vertexai.resources.preview.ml_monitoring.spec.notification.NotificationSpec
] = None,
explanation_spec: typing.Optional[
google.cloud.aiplatform_v1beta1.types.explanation.ExplanationSpec
] = None,
sync: bool = False,
) -> vertexai.resources.preview.ml_monitoring.model_monitors.ModelMonitoringJobCreates a new ModelMonitoringJob.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitoringJob.create
vertexai.resources.preview.ml_monitoring.ModelMonitoringJob.delete
delete() -> NoneDeletes an Model Monitoring Job.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitoringJob.delete
vertexai.resources.preview.ml_monitoring.ModelMonitoringJob.done
done() -> boolMethod indicating whether a job has completed.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitoringJob.done
vertexai.resources.preview.ml_monitoring.ModelMonitoringJob.list
list(
filter: typing.Optional[str] = None,
order_by: typing.Optional[str] = None,
project: typing.Optional[str] = None,
location: typing.Optional[str] = None,
credentials: typing.Optional[google.auth.credentials.Credentials] = None,
parent: typing.Optional[str] = None,
) -> typing.List[google.cloud.aiplatform.base.VertexAiResourceNoun]List all instances of this Vertex AI Resource.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitoringJob.list
vertexai.resources.preview.ml_monitoring.ModelMonitoringJob.to_dict
to_dict() -> typing.Dict[str, typing.Any]Returns the resource proto as a dictionary.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitoringJob.to_dict
vertexai.resources.preview.ml_monitoring.ModelMonitoringJob.wait
wait()Helper method that blocks until all futures are complete.
See more: vertexai.resources.preview.ml_monitoring.ModelMonitoringJob.wait
vertexai.resources.preview.ml_monitoring.spec.ModelMonitoringSchema.to_json
to_json(output_dir: typing.Optional[str] = None) -> strTransform ModelMonitoringSchema to json format.
See more: vertexai.resources.preview.ml_monitoring.spec.ModelMonitoringSchema.to_json
vertexai.vision_models.GeneratedImage
GeneratedImage(
image_bytes: typing.Optional[bytes],
generation_parameters: typing.Dict[str, typing.Any],
gcs_uri: typing.Optional[str] = None,
)Creates a GeneratedImage object.
See more: vertexai.vision_models.GeneratedImage
vertexai.vision_models.GeneratedImage.load_from_file
load_from_file(location: str) -> vertexai.preview.vision_models.GeneratedImageLoads image from file.
See more: vertexai.vision_models.GeneratedImage.load_from_file
vertexai.vision_models.GeneratedImage.save
save(location: str, include_generation_parameters: bool = True)Saves image to a file.
vertexai.vision_models.GeneratedImage.show
show()Shows the image.
vertexai.vision_models.Image
Image(
image_bytes: typing.Optional[bytes] = None, gcs_uri: typing.Optional[str] = None
)Creates an Image object.
See more: vertexai.vision_models.Image
vertexai.vision_models.Image.load_from_file
load_from_file(location: str) -> vertexai.vision_models.ImageLoads image from local file or Google Cloud Storage.
vertexai.vision_models.Image.save
save(location: str)Saves image to a file.
See more: vertexai.vision_models.Image.save
vertexai.vision_models.Image.show
show()Shows the image.
See more: vertexai.vision_models.Image.show
vertexai.vision_models.ImageCaptioningModel
ImageCaptioningModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a _ModelGardenModel.
vertexai.vision_models.ImageCaptioningModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.vision_models.ImageCaptioningModel.from_pretrained
vertexai.vision_models.ImageCaptioningModel.get_captions
get_captions(
image: vertexai.vision_models.Image,
*,
number_of_results: int = 1,
language: str = "en",
output_gcs_uri: typing.Optional[str] = None
) -> typing.List[str]Generates captions for a given image.
See more: vertexai.vision_models.ImageCaptioningModel.get_captions
vertexai.vision_models.ImageGenerationModel
ImageGenerationModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a _ModelGardenModel.
vertexai.vision_models.ImageGenerationModel.edit_image
edit_image(
*,
prompt: str,
base_image: vertexai.vision_models.Image,
mask: typing.Optional[vertexai.vision_models.Image] = None,
negative_prompt: typing.Optional[str] = None,
number_of_images: int = 1,
guidance_scale: typing.Optional[float] = None,
edit_mode: typing.Optional[
typing.Literal[
"inpainting-insert", "inpainting-remove", "outpainting", "product-image"
]
] = None,
mask_mode: typing.Optional[
typing.Literal["background", "foreground", "semantic"]
] = None,
segmentation_classes: typing.Optional[typing.List[str]] = None,
mask_dilation: typing.Optional[float] = None,
product_position: typing.Optional[typing.Literal["fixed", "reposition"]] = None,
output_mime_type: typing.Optional[typing.Literal["image/png", "image/jpeg"]] = None,
compression_quality: typing.Optional[float] = None,
language: typing.Optional[str] = None,
seed: typing.Optional[int] = None,
output_gcs_uri: typing.Optional[str] = None,
safety_filter_level: typing.Optional[
typing.Literal["block_most", "block_some", "block_few", "block_fewest"]
] = None,
person_generation: typing.Optional[
typing.Literal["dont_allow", "allow_adult", "allow_all"]
] = None
) -> vertexai.preview.vision_models.ImageGenerationResponseEdits an existing image based on text prompt.
See more: vertexai.vision_models.ImageGenerationModel.edit_image
vertexai.vision_models.ImageGenerationModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.vision_models.ImageGenerationModel.from_pretrained
vertexai.vision_models.ImageGenerationModel.generate_images
generate_images(
prompt: str,
*,
negative_prompt: typing.Optional[str] = None,
number_of_images: int = 1,
aspect_ratio: typing.Optional[
typing.Literal["1:1", "9:16", "16:9", "4:3", "3:4"]
] = None,
guidance_scale: typing.Optional[float] = None,
language: typing.Optional[str] = None,
seed: typing.Optional[int] = None,
output_gcs_uri: typing.Optional[str] = None,
add_watermark: typing.Optional[bool] = True,
safety_filter_level: typing.Optional[
typing.Literal["block_most", "block_some", "block_few", "block_fewest"]
] = None,
person_generation: typing.Optional[
typing.Literal["dont_allow", "allow_adult", "allow_all"]
] = None
) -> vertexai.preview.vision_models.ImageGenerationResponseGenerates images from text prompt.
See more: vertexai.vision_models.ImageGenerationModel.generate_images
vertexai.vision_models.ImageGenerationModel.upscale_image
upscale_image(
image: typing.Union[
vertexai.vision_models.Image, vertexai.preview.vision_models.GeneratedImage
],
new_size: typing.Optional[int] = 2048,
upscale_factor: typing.Optional[typing.Literal["x2", "x4"]] = None,
output_mime_type: typing.Optional[
typing.Literal["image/png", "image/jpeg"]
] = "image/png",
output_compression_quality: typing.Optional[int] = None,
output_gcs_uri: typing.Optional[str] = None,
) -> vertexai.vision_models.ImageUpscales an image.
See more: vertexai.vision_models.ImageGenerationModel.upscale_image
vertexai.vision_models.ImageGenerationResponse.__getitem__
__getitem__(idx: int) -> vertexai.preview.vision_models.GeneratedImageGets the generated image by index.
See more: vertexai.vision_models.ImageGenerationResponse.getitem
vertexai.vision_models.ImageGenerationResponse.__iter__
__iter__() -> typing.Iterator[vertexai.preview.vision_models.GeneratedImage]Iterates through the generated images.
See more: vertexai.vision_models.ImageGenerationResponse.iter
vertexai.vision_models.ImageQnAModel
ImageQnAModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a _ModelGardenModel.
See more: vertexai.vision_models.ImageQnAModel
vertexai.vision_models.ImageQnAModel.ask_question
ask_question(
image: vertexai.vision_models.Image, question: str, *, number_of_results: int = 1
) -> typing.List[str]Answers questions about an image.
vertexai.vision_models.ImageQnAModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.vision_models.ImageQnAModel.from_pretrained
vertexai.vision_models.ImageTextModel
ImageTextModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a _ModelGardenModel.
See more: vertexai.vision_models.ImageTextModel
vertexai.vision_models.ImageTextModel.ask_question
ask_question(
image: vertexai.vision_models.Image, question: str, *, number_of_results: int = 1
) -> typing.List[str]Answers questions about an image.
See more: vertexai.vision_models.ImageTextModel.ask_question
vertexai.vision_models.ImageTextModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.vision_models.ImageTextModel.from_pretrained
vertexai.vision_models.ImageTextModel.get_captions
get_captions(
image: vertexai.vision_models.Image,
*,
number_of_results: int = 1,
language: str = "en",
output_gcs_uri: typing.Optional[str] = None
) -> typing.List[str]Generates captions for a given image.
See more: vertexai.vision_models.ImageTextModel.get_captions
vertexai.vision_models.MultiModalEmbeddingModel
MultiModalEmbeddingModel(model_id: str, endpoint_name: typing.Optional[str] = None)Creates a _ModelGardenModel.
vertexai.vision_models.MultiModalEmbeddingModel.from_pretrained
from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.TLoads a _ModelGardenModel.
See more: vertexai.vision_models.MultiModalEmbeddingModel.from_pretrained
vertexai.vision_models.MultiModalEmbeddingModel.get_embeddings
get_embeddings(
image: typing.Optional[vertexai.vision_models.Image] = None,
video: typing.Optional[vertexai.vision_models.Video] = None,
contextual_text: typing.Optional[str] = None,
dimension: typing.Optional[int] = None,
video_segment_config: typing.Optional[
vertexai.vision_models.VideoSegmentConfig
] = None,
) -> vertexai.vision_models.MultiModalEmbeddingResponseGets embedding vectors from the provided image.
See more: vertexai.vision_models.MultiModalEmbeddingModel.get_embeddings
vertexai.vision_models.Video
Video(
video_bytes: typing.Optional[bytes] = None, gcs_uri: typing.Optional[str] = None
)Creates a Video object.
See more: vertexai.vision_models.Video
vertexai.vision_models.Video.load_from_file
load_from_file(location: str) -> vertexai.vision_models.VideoLoads video from local file or Google Cloud Storage.
vertexai.vision_models.Video.save
save(location: str)Saves video to a file.
See more: vertexai.vision_models.Video.save
vertexai.vision_models.VideoEmbedding
VideoEmbedding(
start_offset_sec: int, end_offset_sec: int, embedding: typing.List[float]
)Creates a VideoEmbedding object.
See more: vertexai.vision_models.VideoEmbedding
vertexai.vision_models.VideoSegmentConfig
VideoSegmentConfig(
start_offset_sec: int = 0, end_offset_sec: int = 120, interval_sec: int = 16
)Creates a VideoSegmentConfig object.