class

Gemini::GenerativeModel

Inherits JSON::Serializable < Reference < Object

Generates a model response given an input.

API Reference

Constants

HEADERS = HTTP::Headers {"Content-Type" => "application/json"}

Constructors

new(pull : JSON::PullParser)

Source

new(model_name : String, system_instruction : Gemini::Content | Nil = nil, generation_config : Gemini::GenerationConfig | Nil = nil, safety_settings : Nil | Array(Gemini::SafetySetting) = nil, tools : Nil | Array(Gemini::Tool) = nil, tool_config : Gemini::ToolConfig | Nil = nil, cached_content : Nil | String = nil)

Configuration parameters are optional and non-initialized, so they must be defined later

Source

new(*, __pull_for_json_serializable pull : JSON::PullParser)

Source

Instance methods

cached_content

The name of the content cached to use as context to serve the prediction. (Optional)

Source

cached_content=(cached_content : String | Nil)

The name of the content cached to use as context to serve the prediction. (Optional)

Source

contents

The content of the current conversation with the model. (Required) For single-turn queries, this is a single instance. For multi-turn queries like chat, this is a repeated field that contains the conversation history and the latest request.

Source

contents=(contents : Array(Content) | Deque(Content) | Content)

Source

contents?

Source

generate_content(text : String) : GenerateContentResponse

Source

generate_content(data : Array | Deque) : GenerateContentResponse

Source

generation_config

Configuration options for model generation and outputs. (Optional)

Source