Struct Provider

pub struct Provider {
    pub api: Api,
    pub url: String,
    pub key: String,
    pub model: Model,
    pub capability: Capability,
    pub fast: String,
    pub standard: String,
    pub planning: String,
    pub temperature: f64,
    pub max_tokens: u32,
    pub connection_timeout_ms: u64,
    pub request_timeout_ms: u64,
}

AI inference provider configuration

Contains all the settings needed to connect to and interact with an AI inference service. This struct is serializable/deserializable for configuration storage.

Fields

api: Api

The AI service API to use

url: String

Base URL for the API endpoint

Examples:

• Ollama: “http://localhost:11434”
• OpenAI: “https://api.openai.com/v1”
• OpenRouter: “https://openrouter.ai/api/v1”

key: String

API key for authentication (empty string for no authentication)

For OpenAI-compatible APIs, this should be a valid API key. For Ollama, this is typically empty.

model: Model

Model performance type to use

capability: Capability

Expected capability level of the model

fast: String

Model name for fast inference tasks

standard: String

Model name for standard inference tasks

planning: String

Model name for planning/advanced reasoning tasks

temperature: f64

Temperature setting for inference (0.0 to 1.0)

Controls randomness:

• Lower values (e.g., 0.2) = more focused and deterministic
• Higher values (e.g., 0.8) = more creative and random

max_tokens: u32

Maximum number of tokens to generate in the response

connection_timeout_ms: u64

Connection timeout in milliseconds

request_timeout_ms: u64

Request timeout in milliseconds

Implementations

impl Provider

pub fn model(&self) -> &str

Get the actual model name based on the selected model type

Returns the model name string configured for the current performance type.

Examples

use aimx::inference::provider::{Provider, Api, Model, Capability};

let provider = Provider {
    api: Api::Ollama,
    url: "http://localhost:11434".to_string(),
    key: "".to_string(),
    model: Model::Fast,
    capability: Capability::Standard,
    fast: "mistral:latest".to_string(),
    standard: "llama2:latest".to_string(),
    planning: "codellama:latest".to_string(),
    temperature: 0.7,
    max_tokens: 2048,
    connection_timeout_ms: 30000,
    request_timeout_ms: 120000,
};

assert_eq!(provider.model(), "mistral:latest");

Trait Implementations

impl Clone for Provider

fn clone(&self) -> Provider

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Provider

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Provider

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for Provider

fn eq(&self, other: &Provider) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for Provider

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for Provider