Struct LiteLLM 

pub struct LiteLLM { /* private fields */ }

Simple wrapper around any LLM that follows the OpenAI‑compatible API.

Implementations

impl LiteLLM

pub fn new(config: Config) -> Self

Create a new instance with the given configuration.

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

Override the base URL (e.g., http://192.168.3.40:8000/v1)

pub fn without_auth(self) -> Self

Disable authentication for local/open endpoints.

pub fn with_auth_token(self, token: Option<impl Into<String>>) -> Self

Set a custom auth token (Bearer). Use None to disable.

Trait Implementations

impl Model for LiteLLM

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

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

Sends a chat completion request to the configured endpoint.

fn get_response<'life0, 'life1, 'life2, 'life3, 'life4, 'life5, 'life6, 'life7, 'life8, 'async_trait>( &'life0 self, system_instructions: Option<&'life1 str>, input: &'life2 str, _model_settings: Option<HashMap<String, String>>, messages: Option<&'life3 [Value]>, tools: Option<&'life4 [Value]>, tool_choice: Option<Value>, _output_schema: Option<&'life5 str>, _handoffs: Option<&'life6 [String]>, _tracing_enabled: bool, _previous_response_id: Option<&'life7 str>, _prompt_config: Option<&'life8 str>, ) -> Pin<Box<dyn Future<Output = Result<ModelResponse, AgentError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait, 'life3: 'async_trait, 'life4: 'async_trait, 'life5: 'async_trait, 'life6: 'async_trait, 'life7: 'async_trait, 'life8: 'async_trait,

Rich response method (scaffold) to align with Python’s get_response signature. Default implementation wraps generate with a simple string prompt.