Struct OllamaClient 

pub struct OllamaClient {
    endpoint: String,
    model: String,
    client: Client,
}

Ollama local LLM client.

Fields

endpoint: String

API endpoint.

model: String

Model to use.

client: Client

HTTP client.

Implementations

impl OllamaClient

pub const DEFAULT_ENDPOINT: &'static str = "http://localhost:11434"

Default API endpoint.

pub const DEFAULT_MODEL: &'static str = "llama3.2"

Default model.

pub fn new() -> Self

Creates a new Ollama client.

pub fn with_endpoint(self, endpoint: impl Into<String>) -> Self

Sets the API endpoint.

pub fn with_model(self, model: impl Into<String>) -> Self

Sets the model.

pub fn with_http_config(self, config: LlmHttpConfig) -> Self

Sets HTTP client timeouts for LLM requests.

pub fn is_available(&self) -> bool

Checks if Ollama is available.

fn request(&self, prompt: &str) -> Result<String>

Makes a request to the Ollama API.

fn chat(&self, messages: Vec<ChatMessage>) -> Result<String>

Makes a chat request to the Ollama API.

Trait Implementations

impl Default for OllamaClient

fn default() -> Self

Returns the “default value” for a type.

impl LlmProvider for OllamaClient

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

The provider name.

fn complete(&self, prompt: &str) -> Result<String>

Generates a completion for the given prompt.

fn analyze_for_capture(&self, content: &str) -> Result<CaptureAnalysis>

Analyzes content for memory capture.

fn complete_with_system(&self, system: &str, user: &str) -> Result<String>

Generates a completion with a system prompt.

fn analyze_for_capture_extended( &self, content: &str, existing_memories: Option<&str>, ) -> Result<ExtendedCaptureAnalysis>

Analyzes content for memory capture with extended security analysis.

fn classify_search_intent(&self, prompt: &str) -> Result<ExtendedSearchIntent>

Classifies search intent with namespace weights.

fn analyze_for_consolidation( &self, memories: &str, ) -> Result<ConsolidationAnalysis>

Analyzes memories for consolidation.