Skip to main content

​
Parameters

ParameterTypeDefaultDescription
model_nameGoogleModelNameNoneThe name of the model to use
providerLiteral['google-gla', 'google-vertex'] | Provider[Client]'google-gla'The provider to use for authentication and API access. Can be either the string ‘google-gla’ or ‘google-vertex’ or an instance of Provider[httpx.AsyncClient]. If not provided, a new provider will be created using the other parameters
profileModelProfileSpec | NoneNoneThe model profile to use. Defaults to a profile picked by the provider based on the model name
settingsModelSettings | NoneNoneThe model settings to use. Defaults to None

​
Functions

​
__init__

Initialize a Gemini model. Parameters:
  • model_name (GoogleModelName): The name of the model to use
  • provider (Literal[‘google-gla’, ‘google-vertex’] | Provider[Client]): The provider to use for authentication and API access. Can be either the string ‘google-gla’ or ‘google-vertex’ or an instance of Provider[httpx.AsyncClient]. If not provided, a new provider will be created using the other parameters
  • profile (ModelProfileSpec | None): The model profile to use. Defaults to a profile picked by the provider based on the model name
  • settings (ModelSettings | None): The model settings to use. Defaults to None

​
base_url

Get the base URL for the provider API. Returns:
  • str: The base URL for the provider API

​
model_name

Get the model name. Returns:
  • GoogleModelName: The model name

​
system

Get the model provider. Returns:
  • str: The model provider

​
request

Make a request to the model. Parameters:
  • messages (list[ModelMessage]): The messages to send to the model
  • model_settings (ModelSettings | None): Model-specific settings
  • model_request_parameters (ModelRequestParameters): Request parameters
Returns:
  • ModelResponse: The model response

​
count_tokens

Make a request to the model for counting tokens. Parameters:
  • messages (list[ModelMessage]): The messages to send to the model
  • model_settings (ModelSettings | None): Model-specific settings
  • model_request_parameters (ModelRequestParameters): Request parameters
Returns:
  • RequestUsage: The token usage information

​
request_stream

Make a request to the model and return a streaming response. Parameters:
  • messages (list[ModelMessage]): The messages to send to the model
  • model_settings (ModelSettings | None): Model-specific settings
  • model_request_parameters (ModelRequestParameters): Request parameters
Returns:
  • AsyncIterator[StreamedResponse]: An async iterator of streamed responses

​
_get_tools

Get the tools for the model request. Parameters:
  • model_request_parameters (ModelRequestParameters): Request parameters
Returns:
  • list[ToolDict] | None: The tools for the request

​
_get_tool_config

Get the tool configuration for the model request. Parameters:
  • model_request_parameters (ModelRequestParameters): Request parameters
  • tools (list[ToolDict] | None): The tools to configure
Returns:
  • ToolConfigDict | None: The tool configuration

​
_generate_content

Generate content using the Gemini API. Parameters:
  • messages (list[ModelMessage]): The messages to send to the model
  • stream (bool): Whether to stream the response
  • model_settings (GoogleModelSettings): Google-specific model settings
  • model_request_parameters (ModelRequestParameters): Request parameters
Returns:
  • GenerateContentResponse | Awaitable[AsyncIterator[GenerateContentResponse]]: The response from Gemini

​
_build_content_and_config

Build content and configuration for the Gemini API. Parameters:
  • messages (list[ModelMessage]): The messages to send to the model
  • model_settings (GoogleModelSettings): Google-specific model settings
  • model_request_parameters (ModelRequestParameters): Request parameters
Returns:
  • tuple[list[ContentUnionDict], GenerateContentConfigDict]: The content and configuration

​
_process_response

Process a non-streamed response, and prepare a message to return. Parameters:
  • response (GenerateContentResponse): The response from Gemini
Returns:
  • ModelResponse: The processed model response

​
_process_streamed_response

Process a streamed response, and prepare a streaming response to return. Parameters:
  • response (AsyncIterator[GenerateContentResponse]): The streamed response from Gemini
  • model_request_parameters (ModelRequestParameters): Request parameters
Returns:
  • StreamedResponse: The processed streamed response

​
_map_messages

Map messages to Gemini format. Parameters:
  • messages (list[ModelMessage]): The messages to map
Returns:
  • tuple[ContentDict | None, list[ContentUnionDict]]: The mapped messages

​
_map_user_prompt

Map a user prompt to Gemini format. Parameters:
  • part (UserPromptPart): The user prompt part to map
Returns:
  • list[PartDict]: The mapped user prompt

​
_map_response_schema

Map a response schema to Gemini format. Parameters:
  • o (OutputObjectDefinition): The output object definition to map
Returns:
  • dict[str, Any]: The mapped response schema
⌘I