Module provider

Inference Provider Configuration

This module defines the configuration types for AI inference providers used by AIMX. It supports multiple AI APIs with configurable models, capabilities, and performance characteristics.

Overview

The provider system allows AIMX workflows to interact with different AI inference services through a unified interface. Providers can be configured for various use cases:

• Fast inference: Quick responses for simple tasks
• Standard inference: Balanced performance for general use
• Planning inference: Advanced reasoning for complex tasks

Supported APIs

• Ollama: Local model inference (e.g., http://localhost:11434)
• OpenAI: Cloud-based inference (e.g., OpenAI API, OpenRouter)

Example Usage

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

// Create a provider for local Ollama
let provider = Provider {
    api: Api::Ollama,
    url: "http://localhost:11434".to_string(),
    key: "".to_string(),  // No API key needed for local Ollama
    model: Model::Standard,
    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,
};

Structs

Provider

AI inference provider configuration

Enums

Api

Supported AI inference APIs

Capability

Model capability levels

Model

Model performance types