436 lines
19 KiB
HTML
436 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>0007: Multi-Provider LLM - 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/../adrs/0007-multi-provider-llm.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>
|
|
<h1 id="adr-007-multi-provider-llm-support-claude-openai-gemini-ollama"><a class="header" href="#adr-007-multi-provider-llm-support-claude-openai-gemini-ollama">ADR-007: Multi-Provider LLM Support (Claude, OpenAI, Gemini, Ollama)</a></h1>
|
|
<p><strong>Status</strong>: Accepted | Implemented
|
|
<strong>Date</strong>: 2024-11-01
|
|
<strong>Deciders</strong>: LLM Architecture Team
|
|
<strong>Technical Story</strong>: Enabling fallback across multiple LLM providers with cost optimization</p>
|
|
<hr />
|
|
<h2 id="decision"><a class="header" href="#decision">Decision</a></h2>
|
|
<p>Soporte para <strong>4 providers: Claude, OpenAI, Gemini, Ollama</strong> via abstracción <code>LLMClient</code> trait con fallback chain automático.</p>
|
|
<hr />
|
|
<h2 id="rationale"><a class="header" href="#rationale">Rationale</a></h2>
|
|
<ol>
|
|
<li><strong>Cost Optimization</strong>: Barato (Ollama) → Rápido (Gemini) → Confiable (Claude/GPT-4)</li>
|
|
<li><strong>Resilience</strong>: Si un provider falla, fallback automático al siguiente</li>
|
|
<li><strong>Task-Specific Selection</strong>:
|
|
<ul>
|
|
<li>Architecture → Claude Opus (mejor reasoning)</li>
|
|
<li>Code generation → GPT-4 (mejor código)</li>
|
|
<li>Quick queries → Gemini Flash (más rápido)</li>
|
|
<li>Development/testing → Ollama (gratis)</li>
|
|
</ul>
|
|
</li>
|
|
<li><strong>Avoid Vendor Lock-in</strong>: Múltiples proveedores previene dependencia única</li>
|
|
</ol>
|
|
<hr />
|
|
<h2 id="alternatives-considered"><a class="header" href="#alternatives-considered">Alternatives Considered</a></h2>
|
|
<h3 id="-single-provider-only-claude"><a class="header" href="#-single-provider-only-claude">❌ Single Provider Only (Claude)</a></h3>
|
|
<ul>
|
|
<li><strong>Pros</strong>: Simplidad</li>
|
|
<li><strong>Cons</strong>: Vendor lock-in, sin fallback si servicio cae, costo alto</li>
|
|
</ul>
|
|
<h3 id="-custom-api-abstraction-diy"><a class="header" href="#-custom-api-abstraction-diy">❌ Custom API Abstraction (DIY)</a></h3>
|
|
<ul>
|
|
<li><strong>Pros</strong>: Control total</li>
|
|
<li><strong>Cons</strong>: Maintenance pesada, re-implementar streaming/errors/tokens para cada provider</li>
|
|
</ul>
|
|
<h3 id="-multiple-providers-with-fallback-chosen"><a class="header" href="#-multiple-providers-with-fallback-chosen">✅ Multiple Providers with Fallback (CHOSEN)</a></h3>
|
|
<ul>
|
|
<li>Flexible, resiliente, cost-optimized</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="trade-offs"><a class="header" href="#trade-offs">Trade-offs</a></h2>
|
|
<p><strong>Pros</strong>:</p>
|
|
<ul>
|
|
<li>✅ Fallback automático si provider primario no disponible</li>
|
|
<li>✅ Cost efficiency: Ollama $0, Gemini barato, Claude premium</li>
|
|
<li>✅ Resilience: No single point of failure</li>
|
|
<li>✅ Task-specific selection: Usar mejor tool para cada job</li>
|
|
<li>✅ No vendor lock-in</li>
|
|
</ul>
|
|
<p><strong>Cons</strong>:</p>
|
|
<ul>
|
|
<li>⚠️ Múltiples API keys a gestionar (secrets management)</li>
|
|
<li>⚠️ Complicación de testing (mocks para múltiples providers)</li>
|
|
<li>⚠️ Latency variance (diferentes speeds entre providers)</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="implementation"><a class="header" href="#implementation">Implementation</a></h2>
|
|
<p><strong>Provider Trait Abstraction</strong>:</p>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>// crates/vapora-llm-router/src/providers.rs
|
|
pub trait LLMClient: Send + Sync {
|
|
async fn complete(&self, prompt: &str) -> Result<String>;
|
|
async fn stream_complete(&self, prompt: &str) -> Result<BoxStream<String>>;
|
|
fn provider_name(&self) -> &str;
|
|
fn cost_per_token(&self) -> f64;
|
|
}
|
|
|
|
// Implementations
|
|
impl LLMClient for ClaudeClient { /* ... */ }
|
|
impl LLMClient for OpenAIClient { /* ... */ }
|
|
impl LLMClient for GeminiClient { /* ... */ }
|
|
impl LLMClient for OllamaClient { /* ... */ }
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<p><strong>Fallback Chain Router</strong>:</p>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>// crates/vapora-llm-router/src/router.rs
|
|
pub async fn route_task(task: &Task) -> Result<String> {
|
|
let providers = vec![
|
|
select_primary_provider(&task), // Task-specific: Claude/GPT-4/Gemini
|
|
"gemini".to_string(), // Fallback: Gemini
|
|
"openai".to_string(), // Fallback: OpenAI
|
|
"ollama".to_string(), // Last resort: Local
|
|
];
|
|
|
|
for provider_name in providers {
|
|
match self.clients.get(provider_name).complete(&prompt).await {
|
|
Ok(response) => {
|
|
metrics::increment_provider_success(&provider_name);
|
|
return Ok(response);
|
|
}
|
|
Err(e) => {
|
|
tracing::warn!("Provider {} failed: {:?}, trying next", provider_name, e);
|
|
metrics::increment_provider_failure(&provider_name);
|
|
}
|
|
}
|
|
}
|
|
Err(VaporaError::AllProvidersFailed)
|
|
}
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<p><strong>Configuration</strong>:</p>
|
|
<pre><code class="language-toml"># config/llm-routing.toml
|
|
[[providers]]
|
|
name = "claude"
|
|
model = "claude-3-opus-20240229"
|
|
api_key_env = "ANTHROPIC_API_KEY"
|
|
priority = 1
|
|
cost_per_1k_tokens = 0.015
|
|
|
|
[[providers]]
|
|
name = "openai"
|
|
model = "gpt-4"
|
|
api_key_env = "OPENAI_API_KEY"
|
|
priority = 2
|
|
cost_per_1k_tokens = 0.03
|
|
|
|
[[providers]]
|
|
name = "gemini"
|
|
model = "gemini-2.0-flash"
|
|
api_key_env = "GOOGLE_API_KEY"
|
|
priority = 3
|
|
cost_per_1k_tokens = 0.005
|
|
|
|
[[providers]]
|
|
name = "ollama"
|
|
url = "http://localhost:11434"
|
|
model = "llama2"
|
|
priority = 4
|
|
cost_per_1k_tokens = 0.0
|
|
|
|
[[routing_rules]]
|
|
pattern = "architecture"
|
|
provider = "claude"
|
|
|
|
[[routing_rules]]
|
|
pattern = "code_generation"
|
|
provider = "openai"
|
|
|
|
[[routing_rules]]
|
|
pattern = "quick_query"
|
|
provider = "gemini"
|
|
</code></pre>
|
|
<p><strong>Key Files</strong>:</p>
|
|
<ul>
|
|
<li><code>/crates/vapora-llm-router/src/providers.rs</code> (trait implementations)</li>
|
|
<li><code>/crates/vapora-llm-router/src/router.rs</code> (routing logic + fallback)</li>
|
|
<li><code>/crates/vapora-llm-router/src/cost_tracker.rs</code> (token counting per provider)</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="verification"><a class="header" href="#verification">Verification</a></h2>
|
|
<pre><code class="language-bash"># Test each provider individually
|
|
cargo test -p vapora-llm-router test_claude_provider
|
|
cargo test -p vapora-llm-router test_openai_provider
|
|
cargo test -p vapora-llm-router test_gemini_provider
|
|
cargo test -p vapora-llm-router test_ollama_provider
|
|
|
|
# Test fallback chain
|
|
cargo test -p vapora-llm-router test_fallback_chain
|
|
|
|
# Benchmark costs and latencies
|
|
cargo run -p vapora-llm-router --bin benchmark -- --providers all --samples 100
|
|
|
|
# Test task routing
|
|
cargo test -p vapora-llm-router test_task_routing
|
|
</code></pre>
|
|
<p><strong>Expected Output</strong>:</p>
|
|
<ul>
|
|
<li>All 4 providers respond correctly when available</li>
|
|
<li>Fallback triggers when primary provider fails</li>
|
|
<li>Cost tracking accurate per provider</li>
|
|
<li>Task routing selects appropriate provider</li>
|
|
<li>Claude used for architecture, GPT-4 for code, etc.</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="consequences"><a class="header" href="#consequences">Consequences</a></h2>
|
|
<h3 id="operational"><a class="header" href="#operational">Operational</a></h3>
|
|
<ul>
|
|
<li>4 API keys required (managed via secrets)</li>
|
|
<li>Cost monitoring per provider (see ADR-015, Budget Enforcement)</li>
|
|
<li>Provider status pages monitored for incidents</li>
|
|
</ul>
|
|
<h3 id="metrics--monitoring"><a class="header" href="#metrics--monitoring">Metrics & Monitoring</a></h3>
|
|
<ul>
|
|
<li>Track success rate per provider</li>
|
|
<li>Track latency per provider</li>
|
|
<li>Alert if primary provider consistently fails</li>
|
|
<li>Report costs broken down by provider</li>
|
|
</ul>
|
|
<h3 id="development"><a class="header" href="#development">Development</a></h3>
|
|
<ul>
|
|
<li>Mocking tests for each provider</li>
|
|
<li>Integration tests with real providers (limited to avoid costs)</li>
|
|
<li>Provider selection logic well-documented</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="references"><a class="header" href="#references">References</a></h2>
|
|
<ul>
|
|
<li><a href="https://docs.anthropic.com/claude">Claude API Documentation</a></li>
|
|
<li><a href="https://platform.openai.com/docs">OpenAI API Documentation</a></li>
|
|
<li><a href="https://ai.google.dev/">Google Gemini API</a></li>
|
|
<li><a href="https://ollama.ai/">Ollama Documentation</a></li>
|
|
<li><code>/crates/vapora-llm-router/src/providers.rs</code> (provider implementations)</li>
|
|
<li><code>/crates/vapora-llm-router/src/cost_tracker.rs</code> (token tracking)</li>
|
|
<li>ADR-012 (Three-Tier LLM Routing)</li>
|
|
<li>ADR-015 (Budget Enforcement)</li>
|
|
</ul>
|
|
<hr />
|
|
<p><strong>Related ADRs</strong>: ADR-006 (Rig Framework), ADR-012 (Routing Tiers), ADR-015 (Budget)</p>
|
|
|
|
</main>
|
|
|
|
<nav class="nav-wrapper" aria-label="Page navigation">
|
|
<!-- Mobile navigation buttons -->
|
|
<a rel="prev" href="../../adrs/0006-rig-framework.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="../../adrs/0008-tokio-runtime.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="../../adrs/0006-rig-framework.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="../../adrs/0008-tokio-runtime.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>
|