Struct GeminiProvider 

pub struct GeminiProvider {
    pub api_key: String,
    pub base_url: String,
    pub model: String,
}

HTTP-based Google Gemini provider (Generative Language API).

Gemini uses a distinct authentication scheme (API key as a query parameter) and a unique response format where text and tool calls are returned as parts inside candidates[0].content.

Fields

api_key: String

API key for the Generative Language API.

base_url: String

Base URL (default: https://generativelanguage.googleapis.com).

model: String

Model identifier (e.g. gemini-2.0-flash).

Trait Implementations

impl LlmProvider for GeminiProvider

fn call<'life0, 'life1, 'async_trait>( &'life0 self, prompt: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<String, AppError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Call the LLM with a prompt and return the generated text. For backward compatibility, this returns just the text.

fn call_with_usage<'life0, 'life1, 'async_trait>( &'life0 self, prompt: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<LlmCallResponse, AppError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Call the LLM with a prompt and return the response with token usage. Default implementation calls call and returns unknown usage.

fn call_with_tools<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, prompt: &'life1 str, tools: Option<&'life2 [Value]>, ) -> Pin<Box<dyn Future<Output = Result<LlmCallResponse, AppError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Call the LLM with a prompt and optional tool schemas.