400 lines
19 KiB
HTML
400 lines
19 KiB
HTML
<!DOCTYPE HTML>
|
|
<html lang="en" class="light sidebar-visible" dir="ltr">
|
|
<head>
|
|
<!-- Book generated using mdBook -->
|
|
<meta charset="UTF-8">
|
|
<title>LLM Routing - VAPORA Platform Documentation</title>
|
|
|
|
|
|
<!-- Custom HTML head -->
|
|
|
|
<meta name="description" content="Comprehensive documentation for VAPORA, an intelligent development orchestration platform built entirely in Rust.">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
<meta name="theme-color" content="#ffffff">
|
|
|
|
<link rel="icon" href="../favicon.svg">
|
|
<link rel="shortcut icon" href="../favicon.png">
|
|
<link rel="stylesheet" href="../css/variables.css">
|
|
<link rel="stylesheet" href="../css/general.css">
|
|
<link rel="stylesheet" href="../css/chrome.css">
|
|
<link rel="stylesheet" href="../css/print.css" media="print">
|
|
|
|
<!-- Fonts -->
|
|
<link rel="stylesheet" href="../FontAwesome/css/font-awesome.css">
|
|
<link rel="stylesheet" href="../fonts/fonts.css">
|
|
|
|
<!-- Highlight.js Stylesheets -->
|
|
<link rel="stylesheet" id="highlight-css" href="../highlight.css">
|
|
<link rel="stylesheet" id="tomorrow-night-css" href="../tomorrow-night.css">
|
|
<link rel="stylesheet" id="ayu-highlight-css" href="../ayu-highlight.css">
|
|
|
|
<!-- Custom theme stylesheets -->
|
|
|
|
|
|
<!-- Provide site root and default themes to javascript -->
|
|
<script>
|
|
const path_to_root = "../";
|
|
const default_light_theme = "light";
|
|
const default_dark_theme = "dark";
|
|
</script>
|
|
<!-- Start loading toc.js asap -->
|
|
<script src="../toc.js"></script>
|
|
</head>
|
|
<body>
|
|
<div id="mdbook-help-container">
|
|
<div id="mdbook-help-popup">
|
|
<h2 class="mdbook-help-title">Keyboard shortcuts</h2>
|
|
<div>
|
|
<p>Press <kbd>←</kbd> or <kbd>→</kbd> to navigate between chapters</p>
|
|
<p>Press <kbd>S</kbd> or <kbd>/</kbd> to search in the book</p>
|
|
<p>Press <kbd>?</kbd> to show this help</p>
|
|
<p>Press <kbd>Esc</kbd> to hide this help</p>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div id="body-container">
|
|
<!-- Work around some values being stored in localStorage wrapped in quotes -->
|
|
<script>
|
|
try {
|
|
let theme = localStorage.getItem('mdbook-theme');
|
|
let sidebar = localStorage.getItem('mdbook-sidebar');
|
|
|
|
if (theme.startsWith('"') && theme.endsWith('"')) {
|
|
localStorage.setItem('mdbook-theme', theme.slice(1, theme.length - 1));
|
|
}
|
|
|
|
if (sidebar.startsWith('"') && sidebar.endsWith('"')) {
|
|
localStorage.setItem('mdbook-sidebar', sidebar.slice(1, sidebar.length - 1));
|
|
}
|
|
} catch (e) { }
|
|
</script>
|
|
|
|
<!-- Set the theme before any content is loaded, prevents flash -->
|
|
<script>
|
|
const default_theme = window.matchMedia("(prefers-color-scheme: dark)").matches ? default_dark_theme : default_light_theme;
|
|
let theme;
|
|
try { theme = localStorage.getItem('mdbook-theme'); } catch(e) { }
|
|
if (theme === null || theme === undefined) { theme = default_theme; }
|
|
const html = document.documentElement;
|
|
html.classList.remove('light')
|
|
html.classList.add(theme);
|
|
html.classList.add("js");
|
|
</script>
|
|
|
|
<input type="checkbox" id="sidebar-toggle-anchor" class="hidden">
|
|
|
|
<!-- Hide / unhide sidebar before it is displayed -->
|
|
<script>
|
|
let sidebar = null;
|
|
const sidebar_toggle = document.getElementById("sidebar-toggle-anchor");
|
|
if (document.body.clientWidth >= 1080) {
|
|
try { sidebar = localStorage.getItem('mdbook-sidebar'); } catch(e) { }
|
|
sidebar = sidebar || 'visible';
|
|
} else {
|
|
sidebar = 'hidden';
|
|
}
|
|
sidebar_toggle.checked = sidebar === 'visible';
|
|
html.classList.remove('sidebar-visible');
|
|
html.classList.add("sidebar-" + sidebar);
|
|
</script>
|
|
|
|
<nav id="sidebar" class="sidebar" aria-label="Table of contents">
|
|
<!-- populated by js -->
|
|
<mdbook-sidebar-scrollbox class="sidebar-scrollbox"></mdbook-sidebar-scrollbox>
|
|
<noscript>
|
|
<iframe class="sidebar-iframe-outer" src="../toc.html"></iframe>
|
|
</noscript>
|
|
<div id="sidebar-resize-handle" class="sidebar-resize-handle">
|
|
<div class="sidebar-resize-indicator"></div>
|
|
</div>
|
|
</nav>
|
|
|
|
<div id="page-wrapper" class="page-wrapper">
|
|
|
|
<div class="page">
|
|
<div id="menu-bar-hover-placeholder"></div>
|
|
<div id="menu-bar" class="menu-bar sticky">
|
|
<div class="left-buttons">
|
|
<label id="sidebar-toggle" class="icon-button" for="sidebar-toggle-anchor" title="Toggle Table of Contents" aria-label="Toggle Table of Contents" aria-controls="sidebar">
|
|
<i class="fa fa-bars"></i>
|
|
</label>
|
|
<button id="theme-toggle" class="icon-button" type="button" title="Change theme" aria-label="Change theme" aria-haspopup="true" aria-expanded="false" aria-controls="theme-list">
|
|
<i class="fa fa-paint-brush"></i>
|
|
</button>
|
|
<ul id="theme-list" class="theme-popup" aria-label="Themes" role="menu">
|
|
<li role="none"><button role="menuitem" class="theme" id="default_theme">Auto</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="light">Light</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="rust">Rust</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="coal">Coal</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="navy">Navy</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="ayu">Ayu</button></li>
|
|
</ul>
|
|
<button id="search-toggle" class="icon-button" type="button" title="Search (`/`)" aria-label="Toggle Searchbar" aria-expanded="false" aria-keyshortcuts="/ s" aria-controls="searchbar">
|
|
<i class="fa fa-search"></i>
|
|
</button>
|
|
</div>
|
|
|
|
<h1 class="menu-title">VAPORA Platform Documentation</h1>
|
|
|
|
<div class="right-buttons">
|
|
<a href="../print.html" title="Print this book" aria-label="Print this book">
|
|
<i id="print-button" class="fa fa-print"></i>
|
|
</a>
|
|
<a href="https://github.com/vapora-platform/vapora" title="Git repository" aria-label="Git repository">
|
|
<i id="git-repository-button" class="fa fa-github"></i>
|
|
</a>
|
|
<a href="https://github.com/vapora-platform/vapora/edit/main/docs/src/../tutorials/03-llm-routing.md" title="Suggest an edit" aria-label="Suggest an edit">
|
|
<i id="git-edit-button" class="fa fa-edit"></i>
|
|
</a>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
<div id="search-wrapper" class="hidden">
|
|
<form id="searchbar-outer" class="searchbar-outer">
|
|
<input type="search" id="searchbar" name="searchbar" placeholder="Search this book ..." aria-controls="searchresults-outer" aria-describedby="searchresults-header">
|
|
</form>
|
|
<div id="searchresults-outer" class="searchresults-outer hidden">
|
|
<div id="searchresults-header" class="searchresults-header"></div>
|
|
<ul id="searchresults">
|
|
</ul>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Apply ARIA attributes after the sidebar and the sidebar toggle button are added to the DOM -->
|
|
<script>
|
|
document.getElementById('sidebar-toggle').setAttribute('aria-expanded', sidebar === 'visible');
|
|
document.getElementById('sidebar').setAttribute('aria-hidden', sidebar !== 'visible');
|
|
Array.from(document.querySelectorAll('#sidebar a')).forEach(function(link) {
|
|
link.setAttribute('tabIndex', sidebar === 'visible' ? 0 : -1);
|
|
});
|
|
</script>
|
|
|
|
<div id="content" class="content">
|
|
<main>
|
|
<p>#Tutorial 3: LLM Routing</p>
|
|
<p>Route LLM requests to optimal providers based on task type and budget.</p>
|
|
<h2 id="prerequisites"><a class="header" href="#prerequisites">Prerequisites</a></h2>
|
|
<ul>
|
|
<li>Complete <a href="02-basic-agents.html">02-basic-agents.md</a></li>
|
|
</ul>
|
|
<h2 id="learning-objectives"><a class="header" href="#learning-objectives">Learning Objectives</a></h2>
|
|
<ul>
|
|
<li>Configure multiple LLM providers</li>
|
|
<li>Route requests to optimal providers</li>
|
|
<li>Understand provider pricing</li>
|
|
<li>Handle fallback providers</li>
|
|
</ul>
|
|
<h2 id="provider-options"><a class="header" href="#provider-options">Provider Options</a></h2>
|
|
<div class="table-wrapper"><table><thead><tr><th>Provider</th><th>Cost</th><th>Quality</th><th>Speed</th><th>Best For</th></tr></thead><tbody>
|
|
<tr><td>Claude</td><td>$15/1M</td><td>Highest</td><td>Good</td><td>Complex reasoning</td></tr>
|
|
<tr><td>GPT-4</td><td>$10/1M</td><td>Very High</td><td>Good</td><td>General purpose</td></tr>
|
|
<tr><td>Gemini</td><td>$5/1M</td><td>Good</td><td>Excellent</td><td>Budget-friendly</td></tr>
|
|
<tr><td>Ollama</td><td>Free</td><td>Good</td><td>Depends</td><td>Local, privacy</td></tr>
|
|
</tbody></table>
|
|
</div>
|
|
<h2 id="step-1-create-router"><a class="header" href="#step-1-create-router">Step 1: Create Router</a></h2>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>use vapora_llm_router::LLMRouter;
|
|
|
|
let router = LLMRouter::default();
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<h2 id="step-2-configure-providers"><a class="header" href="#step-2-configure-providers">Step 2: Configure Providers</a></h2>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>use std::collections::HashMap;
|
|
|
|
let mut rules = HashMap::new();
|
|
rules.insert("coding", "claude"); // Complex tasks → Claude
|
|
rules.insert("testing", "gpt-4"); // Testing → GPT-4
|
|
rules.insert("documentation", "ollama"); // Local → Ollama
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<h2 id="step-3-select-provider"><a class="header" href="#step-3-select-provider">Step 3: Select Provider</a></h2>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>let provider = if let Some(rule) = rules.get("coding") {
|
|
*rule
|
|
} else {
|
|
"claude" // default
|
|
};
|
|
|
|
println!("Selected provider: {}", provider);
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<h2 id="step-4-cost-estimation"><a class="header" href="#step-4-cost-estimation">Step 4: Cost Estimation</a></h2>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>// Token usage
|
|
let input_tokens = 1500;
|
|
let output_tokens = 800;
|
|
|
|
// Claude pricing: $3/1M input, $15/1M output
|
|
let input_cost = (input_tokens as f64 * 3.0) / 1_000_000.0;
|
|
let output_cost = (output_tokens as f64 * 15.0) / 1_000_000.0;
|
|
let total_cost = input_cost + output_cost;
|
|
|
|
println!("Estimated cost: ${:.4}", total_cost);
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<h2 id="running-the-example"><a class="header" href="#running-the-example">Running the Example</a></h2>
|
|
<pre><code class="language-bash">cargo run --example 01-provider-selection -p vapora-llm-router
|
|
</code></pre>
|
|
<h2 id="expected-output"><a class="header" href="#expected-output">Expected Output</a></h2>
|
|
<pre><code>=== LLM Provider Selection Example ===
|
|
|
|
Available Providers:
|
|
1. claude (models: claude-opus-4-5, claude-sonnet-4)
|
|
- Use case: Complex reasoning, code generation
|
|
- Cost: $15 per 1M input tokens
|
|
|
|
2. gpt-4 (models: gpt-4-turbo, gpt-4)
|
|
- Use case: General-purpose, multimodal
|
|
- Cost: $10 per 1M input tokens
|
|
|
|
3. ollama (models: llama2, mistral)
|
|
- Use case: Local execution, no cost
|
|
- Cost: $0.00 (local/on-premise)
|
|
|
|
Task: code_analysis
|
|
Selected provider: claude
|
|
Model: claude-opus-4-5
|
|
Cost: $0.075 per 1K tokens
|
|
Fallback: gpt-4 (if budget exceeded)
|
|
</code></pre>
|
|
<h2 id="routing-strategies"><a class="header" href="#routing-strategies">Routing Strategies</a></h2>
|
|
<h3 id="rule-based-routing"><a class="header" href="#rule-based-routing">Rule-Based Routing</a></h3>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>match task_type {
|
|
"code_generation" => "claude",
|
|
"documentation" => "ollama", // Free
|
|
"analysis" => "gpt-4",
|
|
_ => "claude", // default
|
|
}
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<h3 id="cost-aware-routing"><a class="header" href="#cost-aware-routing">Cost-Aware Routing</a></h3>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>if budget_remaining < 50 { // dollars
|
|
"gemini" // cheaper
|
|
} else if budget_remaining < 100 {
|
|
"gpt-4"
|
|
} else {
|
|
"claude" // most capable
|
|
}
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<h3 id="quality-aware-routing"><a class="header" href="#quality-aware-routing">Quality-Aware Routing</a></h3>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>match complexity_score {
|
|
high if high > 0.8 => "claude", // Best quality
|
|
medium if medium > 0.5 => "gpt-4", // Good balance
|
|
_ => "ollama", // Fast & cheap
|
|
}
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<h2 id="fallback-strategy"><a class="header" href="#fallback-strategy">Fallback Strategy</a></h2>
|
|
<p>Always have a fallback when budget is critical:</p>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>let primary = "claude";
|
|
let fallback = "ollama";
|
|
|
|
let provider = if budget_exceeded {
|
|
fallback
|
|
} else {
|
|
primary
|
|
};
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<h2 id="common-patterns"><a class="header" href="#common-patterns">Common Patterns</a></h2>
|
|
<h3 id="cost-optimization"><a class="header" href="#cost-optimization">Cost Optimization</a></h3>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>// Use cheaper models for high-volume tasks
|
|
if task_count > 100 {
|
|
"gemini" // $5/1M (cheaper than Claude $15/1M)
|
|
} else {
|
|
"claude"
|
|
}
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<h3 id="multi-step-tasks"><a class="header" href="#multi-step-tasks">Multi-Step Tasks</a></h3>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>// Step 1: Claude (expensive, high quality)
|
|
let analysis = route_to("claude", "analyze_code");
|
|
|
|
// Step 2: GPT-4 (medium cost)
|
|
let design = route_to("gpt-4", "design_solution");
|
|
|
|
// Step 3: Ollama (free)
|
|
let formatting = route_to("ollama", "format_output");
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<h2 id="troubleshooting"><a class="header" href="#troubleshooting">Troubleshooting</a></h2>
|
|
<p><strong>Q: "Provider not available"</strong>
|
|
A: Check API keys in environment:</p>
|
|
<pre><code class="language-bash">export ANTHROPIC_API_KEY=sk-ant-...
|
|
export OPENAI_API_KEY=sk-...
|
|
</code></pre>
|
|
<p><strong>Q: "Budget exceeded"</strong>
|
|
A: Use fallback provider or wait for budget reset</p>
|
|
<h2 id="next-steps"><a class="header" href="#next-steps">Next Steps</a></h2>
|
|
<ul>
|
|
<li>Tutorial 4: <a href="04-learning-profiles.html">Learning Profiles</a></li>
|
|
<li>Example: <code>crates/vapora-llm-router/examples/02-budget-enforcement.rs</code></li>
|
|
</ul>
|
|
<h2 id="reference"><a class="header" href="#reference">Reference</a></h2>
|
|
<ul>
|
|
<li>Source: <code>crates/vapora-llm-router/src/router.rs</code></li>
|
|
<li>API: <code>cargo doc --open -p vapora-llm-router</code></li>
|
|
</ul>
|
|
|
|
</main>
|
|
|
|
<nav class="nav-wrapper" aria-label="Page navigation">
|
|
<!-- Mobile navigation buttons -->
|
|
<a rel="prev" href="../../tutorials/02-basic-agents.html" class="mobile-nav-chapters previous" title="Previous chapter" aria-label="Previous chapter" aria-keyshortcuts="Left">
|
|
<i class="fa fa-angle-left"></i>
|
|
</a>
|
|
|
|
<a rel="next prefetch" href="../../operations/index.html" class="mobile-nav-chapters next" title="Next chapter" aria-label="Next chapter" aria-keyshortcuts="Right">
|
|
<i class="fa fa-angle-right"></i>
|
|
</a>
|
|
|
|
<div style="clear: both"></div>
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
|
|
<nav class="nav-wide-wrapper" aria-label="Page navigation">
|
|
<a rel="prev" href="../../tutorials/02-basic-agents.html" class="nav-chapters previous" title="Previous chapter" aria-label="Previous chapter" aria-keyshortcuts="Left">
|
|
<i class="fa fa-angle-left"></i>
|
|
</a>
|
|
|
|
<a rel="next prefetch" href="../../operations/index.html" class="nav-chapters next" title="Next chapter" aria-label="Next chapter" aria-keyshortcuts="Right">
|
|
<i class="fa fa-angle-right"></i>
|
|
</a>
|
|
</nav>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<script>
|
|
window.playground_copyable = true;
|
|
</script>
|
|
|
|
|
|
<script src="../elasticlunr.min.js"></script>
|
|
<script src="../mark.min.js"></script>
|
|
<script src="../searcher.js"></script>
|
|
|
|
<script src="../clipboard.min.js"></script>
|
|
<script src="../highlight.js"></script>
|
|
<script src="../book.js"></script>
|
|
|
|
<!-- Custom JS scripts -->
|
|
|
|
|
|
</div>
|
|
</body>
|
|
</html>
|