Struct OllamaAdapter 

pub struct OllamaAdapter { /* private fields */ }

Ollama adapter for local models.

Implementations

impl OllamaAdapter

pub fn new(model: impl Into<String>) -> Self

Create a new Ollama adapter.

Arguments

• model - Model to use (e.g., “llama3.2”, “qwen2.5-coder”)

pub fn with_base_url(self, base_url: impl Into<String>) -> Self

Set the base URL for Ollama server.

pub const fn with_temperature(self, temperature: f32) -> Self

Set the temperature for generation.

Trait Implementations

impl LLMAdapter for OllamaAdapter

fn provider(&self) -> &'static str

Get the provider name (e.g., “openai”, “anthropic”).

fn model(&self) -> &str

Get the model name being used.

fn generate<'life0, 'life1, 'async_trait>( &'life0 self, messages: &'life1 [LLMMessage], ) -> Pin<Box<dyn Future<Output = Result<LLMResponse, LLMError>> + Send + 'async_trait>>

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

Generate a completion from messages.

fn generate_stream( &self, messages: &[LLMMessage], ) -> Pin<Box<dyn Stream<Item = Result<StreamChunk, LLMError>> + Send + '_>>

Generate a streaming completion.

fn health_check<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = Result<bool, LLMError>> + Send + 'async_trait>>

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

Check if the LLM provider is accessible.