Mathis/llamactl
1
0
Fork 0
mirror of https://github.com/lordmathis/llamactl.git synced 2025-12-23 09:34:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Deployed c776785 to dev with MkDocs 1.6.1 and mike 2.1.3

Browse Source
This commit is contained in:
lordmathis
2025-12-08 18:23:59 +00:00
parent 85205fc5d3
commit 8e8fb83fb3
9 changed files with 86 additions and 130 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
dev/quick-start/index.html
View File

@@ -564,6 +564,15 @@
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#create-an-inference-api-key" class="md-nav__link">
<span class="md-ellipsis">
Create an Inference API Key
</span>
</a>
</li>
<li class="md-nav__item">
@@ -773,10 +782,10 @@
<h2 id="authentication">Authentication<a class="headerlink" href="#authentication" title="Permanent link">&para;</a></h2>
<p>Llamactl uses two types of API keys: </p>
<ul>
<li><strong>Management API Key</strong>: Used to authenticate with the Llamactl management API (creating, starting, stopping instances). </li>
<li><strong>Inference API Key</strong>: Used to authenticate requests to the OpenAI-compatible endpoints (<code>/v1/chat/completions</code>, <code>/v1/completions</code>, etc.). </li>
<li><strong>Management API Key</strong>: Used to authenticate with the Llamactl management API and web UI. If not configured, one is auto-generated at startup and printed to the terminal. </li>
<li><strong>Inference API Key</strong>: Used to authenticate requests to the OpenAI-compatible endpoints (<code>/v1/chat/completions</code>, <code>/v1/completions</code>, etc.). These are created and managed via the web UI. </li>
</ul>
<p>By default, authentication is required. If you don't configure these keys in your configuration file, llamactl will auto-generate them and print them to the terminal on startup. You can also configure custom keys or disable authentication entirely in the <a href="../configuration/">Configuration</a> guide. </p>
<p>By default, authentication is required for both management and inference endpoints. You can configure custom management keys or disable authentication in the <a href="../configuration/">Configuration</a> guide. </p>
<h2 id="start-llamactl">Start Llamactl<a class="headerlink" href="#start-llamactl" title="Permanent link">&para;</a></h2>
<p>Start the Llamactl server: </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a>llamactl
@@ -789,22 +798,15 @@
<a id="__codelineno-1-6" name="__codelineno-1-6" href="#__codelineno-1-6"></a> sk-management-...
<a id="__codelineno-1-7" name="__codelineno-1-7" href="#__codelineno-1-7"></a>
<a id="__codelineno-1-8" name="__codelineno-1-8" href="#__codelineno-1-8"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-9" name="__codelineno-1-9" href="#__codelineno-1-9"></a>⚠️ INFERENCE AUTHENTICATION REQUIRED
<a id="__codelineno-1-9" name="__codelineno-1-9" href="#__codelineno-1-9"></a>⚠️ IMPORTANT
<a id="__codelineno-1-10" name="__codelineno-1-10" href="#__codelineno-1-10"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-11" name="__codelineno-1-11" href="#__codelineno-1-11"></a>🔑 Generated Inference API Key:
<a id="__codelineno-1-12" name="__codelineno-1-12" href="#__codelineno-1-12"></a>
<a id="__codelineno-1-13" name="__codelineno-1-13" href="#__codelineno-1-13"></a> sk-inference-...
<a id="__codelineno-1-14" name="__codelineno-1-14" href="#__codelineno-1-14"></a>
<a id="__codelineno-1-15" name="__codelineno-1-15" href="#__codelineno-1-15"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-16" name="__codelineno-1-16" href="#__codelineno-1-16"></a>⚠️ IMPORTANT
<a id="__codelineno-1-17" name="__codelineno-1-17" href="#__codelineno-1-17"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-18" name="__codelineno-1-18" href="#__codelineno-1-18"></a>• These keys are auto-generated and will change on restart
<a id="__codelineno-1-19" name="__codelineno-1-19" href="#__codelineno-1-19"></a>• For production, add explicit keys to your configuration
<a id="__codelineno-1-20" name="__codelineno-1-20" href="#__codelineno-1-20"></a>• Copy these keys before they disappear from the terminal
<a id="__codelineno-1-21" name="__codelineno-1-21" href="#__codelineno-1-21"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-22" name="__codelineno-1-22" href="#__codelineno-1-22"></a>Llamactl server listening on 0.0.0.0:8080
<a id="__codelineno-1-11" name="__codelineno-1-11" href="#__codelineno-1-11"></a>• This key is auto-generated and will change on restart
<a id="__codelineno-1-12" name="__codelineno-1-12" href="#__codelineno-1-12"></a>• For production, add explicit management_keys to your configuration
<a id="__codelineno-1-13" name="__codelineno-1-13" href="#__codelineno-1-13"></a>• Copy this key before it disappears from the terminal
<a id="__codelineno-1-14" name="__codelineno-1-14" href="#__codelineno-1-14"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-15" name="__codelineno-1-15" href="#__codelineno-1-15"></a>Llamactl server listening on 0.0.0.0:8080
</code></pre></div>
<p>Copy the <strong>Management</strong> and <strong>Inference</strong> API Keys from the terminal - you'll need them to access the web UI and make inference requests. </p>
<p>Copy the <strong>Management API Key</strong> from the terminal - you'll need it to access the web UI. </p>
<p>By default, Llamactl will start on <code>http://localhost:8080</code>. </p>
<h2 id="access-the-web-ui">Access the Web UI<a class="headerlink" href="#access-the-web-ui" title="Permanent link">&para;</a></h2>
<p>Open your web browser and navigate to: </p>
@@ -826,7 +828,7 @@
</ul>
<div class="admonition tip">
<p class="admonition-title">Auto-Assignment</p>
<p>Llamactl automatically assigns ports from the configured port range (default: 8000-9000) and generates API keys if authentication is enabled. You typically don't need to manually specify these values. </p>
<p>Llamactl automatically assigns ports from the configured port range (default: 8000-9000) and manages API keys if authentication is enabled. You typically don't need to manually specify these values. </p>
</div>
<div class="admonition note">
<p class="admonition-title">Remote Node Deployment</p>
@@ -845,6 +847,21 @@
<li><strong>View logs</strong> by clicking the logs button </li>
<li><strong>Stop</strong> the instance when needed </li>
</ul>
<h2 id="create-an-inference-api-key">Create an Inference API Key<a class="headerlink" href="#create-an-inference-api-key" title="Permanent link">&para;</a></h2>
<p>To make inference requests to your instances, you'll need an inference API key: </p>
<ol>
<li>In the web UI, click the <strong>Settings</strong> icon (gear icon in the top-right) </li>
<li>Navigate to the <strong>API Keys</strong> tab </li>
<li>Click <strong>Create API Key</strong> </li>
<li>Configure your key: </li>
<li><strong>Name</strong>: Give it a descriptive name (e.g., "Production Key", "Development Key") </li>
<li><strong>Expiration</strong>: Optionally set an expiration date for the key </li>
<li><strong>Permissions</strong>: Choose whether the key can access all instances or only specific ones </li>
<li>Click <strong>Create</strong> </li>
<li><strong>Copy the generated key</strong> - it will only be shown once! </li>
</ol>
<p>The key will look like: <code>llamactl-...</code> </p>
<p>You can create multiple inference keys with different permissions for different use cases (e.g., one for development, one for production, or keys limited to specific instances). </p>
<h2 id="example-configurations">Example Configurations<a class="headerlink" href="#example-configurations" title="Permanent link">&para;</a></h2>
<p>Here are basic example configurations for each backend: </p>
<p><strong>llama.cpp backend:</strong><br />
@@ -966,7 +983,7 @@
</code></pre></div>
<div class="admonition note">
<p class="admonition-title">API Key</p>
<p>If you disabled authentication in your config, you can use any value for <code>api_key</code> (e.g., <code>"not-needed"</code>). Otherwise, use the inference API key shown in the terminal output on startup. </p>
<p>If you disabled authentication in your config, you can use any value for <code>api_key</code> (e.g., <code>"not-needed"</code>). Otherwise, use the inference API key you created via the web UI (Settings → API Keys). </p>
</div>
<h3 id="list-available-models">List Available Models<a class="headerlink" href="#list-available-models" title="Permanent link">&para;</a></h3>
<p>Get a list of running instances (models) in OpenAI-compatible format: </p>
@@ -998,7 +1015,7 @@
<span class="md-icon" title="Last update">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M21 13.1c-.1 0-.3.1-.4.2l-1 1 2.1 2.1 1-1c.2-.2.2-.6 0-.8l-1.3-1.3c-.1-.1-.2-.2-.4-.2m-1.9 1.8-6.1 6V23h2.1l6.1-6.1zM12.5 7v5.2l4 2.4-1 1L11 13V7zM11 21.9c-5.1-.5-9-4.8-9-9.9C2 6.5 6.5 2 12 2c5.3 0 9.6 4.1 10 9.3-.3-.1-.6-.2-1-.2s-.7.1-1 .2C19.6 7.2 16.2 4 12 4c-4.4 0-8 3.6-8 8 0 4.1 3.1 7.5 7.1 7.9l-.1.2z"/></svg>
</span>
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date" title="October 26, 2025 16:19:53 UTC">October 26, 2025</span>
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date" title="December 8, 2025 18:15:42 UTC">December 8, 2025</span>
</span>