GenerativeModel(
model_name: str,
*,
generation_config: typing.Optional[
typing.Union[
vertexai.generative_models._generative_models.GenerationConfig,
typing.Dict[str, typing.Any],
]
] = None,
safety_settings: typing.Optional[
typing.Union[
typing.List[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,
system_instruction: typing.Optional[
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,
]
],
]
] = None
)
Initializes GenerativeModel.
Usage:
model = GenerativeModel("gemini-pro")
print(model.generate_content("Hello"))
```
Parameter |
|
---|---|
Name | Description |
model_name |
str
Model Garden model resource name. Alternatively, a tuned model endpoint resource name can be provided. |
Methods
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.ComputeTokensResponse
Computes tokens.
Parameter | |
---|---|
Name | Description |
contents |
typing.Union[typing.List[Content], typing.List[typing.Dict[str, typing.Any]], str, Image, Part, typing.List[typing.Union[str, Image, Part]]]
Contents to send to the model. Supports either a list of Content objects (passing a multi-turn conversation) or a value that can be converted to a single Content object (passing a single message). Supports * str, Image, Part, * List[Union[str, Image, Part]], * List[Content] |
Returns | |
---|---|
Type | Description |
A ComputeTokensResponse object that has the following attributes |
tokens_info: Lists of tokens_info from the input. The input contents: ContentsType could have multiple string instances and each tokens_info item represents each string instance. Each token info consists tokens list, token_ids list and a role. |
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.ComputeTokensResponse
Computes tokens asynchronously.
Parameter | |
---|---|
Name | Description |
contents |
typing.Union[typing.List[Content], typing.List[typing.Dict[str, typing.Any]], str, Image, Part, typing.List[typing.Union[str, Image, Part]]]
Contents to send to the model. Supports either a list of Content objects (passing a multi-turn conversation) or a value that can be converted to a single Content object (passing a single message). Supports * str, Image, Part, * List[Union[str, Image, Part]], * List[Content] |
Returns | |
---|---|
Type | Description |
And awaitable for a ComputeTokensResponse object that has the following attributes |
tokens_info: Lists of tokens_info from the input. The input contents: ContentsType could have multiple string instances and each tokens_info item represents each string instance. Each token info consists tokens list, token_ids list and a role. |
count_tokens
count_tokens(
contents: typing.Union[
typing.List[vertexai.generative_models._generative_models.Content],
typing.List[typing.Dict[str, typing.Any]],
str,
vertexai.generative_models._generative_models.Image,
vertexai.generative_models._generative_models.Part,
typing.List[
typing.Union[
str,
vertexai.generative_models._generative_models.Image,
vertexai.generative_models._generative_models.Part,
]
],
]
) -> google.cloud.aiplatform_v1beta1.types.prediction_service.CountTokensResponse
Counts tokens.
Parameter | |
---|---|
Name | Description |
contents |
typing.Union[typing.List[Content], typing.List[typing.Dict[str, typing.Any]], str, Image, Part, typing.List[typing.Union[str, Image, Part]]]
Contents to send to the model. Supports either a list of Content objects (passing a multi-turn conversation) or a value that can be converted to a single Content object (passing a single message). Supports * str, Image, Part, * List[Union[str, Image, Part]], * List[Content] |
Returns | |
---|---|
Type | Description |
A CountTokensResponse object that has the following attributes |
total_tokens: The total number of tokens counted across all instances from the request. total_billable_characters: The total number of billable characters counted across all instances from the request. |
count_tokens_async
count_tokens_async(
contents: typing.Union[
typing.List[vertexai.generative_models._generative_models.Content],
typing.List[typing.Dict[str, typing.Any]],
str,
vertexai.generative_models._generative_models.Image,
vertexai.generative_models._generative_models.Part,
typing.List[
typing.Union[
str,
vertexai.generative_models._generative_models.Image,
vertexai.generative_models._generative_models.Part,
]
],
]
) -> google.cloud.aiplatform_v1beta1.types.prediction_service.CountTokensResponse
Counts tokens asynchronously.
Parameter | |
---|---|
Name | Description |
contents |
typing.Union[typing.List[Content], typing.List[typing.Dict[str, typing.Any]], str, Image, Part, typing.List[typing.Union[str, Image, Part]]]
Contents to send to the model. Supports either a list of Content objects (passing a multi-turn conversation) or a value that can be converted to a single Content object (passing a single message). Supports * str, Image, Part, * List[Union[str, Image, Part]], * List[Content] |
Returns | |
---|---|
Type | Description |
And awaitable for a CountTokensResponse object that has the following attributes |
total_tokens: The total number of tokens counted across all instances from the request. total_billable_characters: The total number of billable characters counted across all instances from the request. |
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
) -> _GenerativeModel
Creates a model from cached content.
Creates a model instance with an existing cached content. The cached content becomes the prefix of the requesting contents.
Parameter | |
---|---|
Name | Description |
cached_content |
typing.Union[str, caching.CachedContent]
The cached content resource name or object. |
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,
stream: bool = False
) -> typing.Union[
vertexai.generative_models._generative_models.GenerationResponse,
typing.Iterable[vertexai.generative_models._generative_models.GenerationResponse],
]
Generates content.
Parameter | |
---|---|
Name | Description |
contents |
typing.Union[typing.List[Content], typing.List[typing.Dict[str, typing.Any]], str, Image, Part, typing.List[typing.Union[str, Image, Part]]]
Contents to send to the model. Supports either a list of Content objects (passing a multi-turn conversation) or a value that can be converted to a single Content object (passing a single message). Supports * str, Image, Part, * List[Union[str, Image, Part]], * List[Content] |
generate_content_async
generate_content_async(
contents: typing.Union[
typing.List[vertexai.generative_models._generative_models.Content],
typing.List[typing.Dict[str, typing.Any]],
str,
vertexai.generative_models._generative_models.Image,
vertexai.generative_models._generative_models.Part,
typing.List[
typing.Union[
str,
vertexai.generative_models._generative_models.Image,
vertexai.generative_models._generative_models.Part,
]
],
],
*,
generation_config: typing.Optional[
typing.Union[
vertexai.generative_models._generative_models.GenerationConfig,
typing.Dict[str, typing.Any],
]
] = None,
safety_settings: typing.Optional[
typing.Union[
typing.List[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,
stream: bool = False
) -> typing.Union[
vertexai.generative_models._generative_models.GenerationResponse,
typing.AsyncIterable[
vertexai.generative_models._generative_models.GenerationResponse
],
]
Generates content asynchronously.
Parameter | |
---|---|
Name | Description |
contents |
typing.Union[typing.List[Content], typing.List[typing.Dict[str, typing.Any]], str, Image, Part, typing.List[typing.Union[str, Image, Part]]]
Contents to send to the model. Supports either a list of Content objects (passing a multi-turn conversation) or a value that can be converted to a single Content object (passing a single message). Supports * str, Image, Part, * List[Union[str, Image, Part]], * List[Content] |
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.ChatSession
Creates a stateful chat session.