google_client#

Google GenAI ModelClient integration.

Classes

GoogleGenAIClient([api_key])

A component wrapper for the Google GenAI API client.

class GoogleGenAIClient(api_key: str | None = None)[source]#

Bases: ModelClient

A component wrapper for the Google GenAI API client.

Visit https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference for more api details.

Info: 8/1/2024 Tested: gemini-1.0-pro, gemini-1.5-pro-latest class UsageMetadata(proto.Message):

prompt_token_count: int = proto.Field(
proto.INT32, number=1,

) cached_content_token_count: int = proto.Field(

proto.INT32, number=4,

) candidates_token_count: int = proto.Field(

proto.INT32, number=2,

) total_token_count: int = proto.Field(

proto.INT32, number=3,

)

init_sync_client()[source]#

parse_chat_completion(completion: GenerateContentResponse) → GeneratorOutput[source]#: Parse the completion to a structure your sytem standarizes. (here is str)

track_completion_usage(completion: GenerateContentResponse) → CompletionUsage[source]#: Track the chat completion usage. Use OpenAI standard API for tracking.

convert_inputs_to_api_kwargs(input: Any | None = None, model_kwargs: Dict = {}, model_type: ModelType = ModelType.UNDEFINED) → Dict[source]#: Specify the API input type and output api_kwargs that will be used in _call and _acall methods. Convert the Component’s standard input, and system_input(chat model) and model_kwargs into API-specific format

call(api_kwargs: Dict = {}, model_type: ModelType = ModelType.UNDEFINED)[source]#: kwargs is the combined input and model_kwargs