mirror of
https://github.com/katanemo/plano.git
synced 2026-04-25 16:56:24 +02:00
deploy: b30ad791f7
This commit is contained in:
salmanap
parent
f4b686c7fc
commit
3e881c6eec
28 changed files with 819 additions and 820 deletions
|
|
@ -101,9 +101,10 @@
|
|||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/terminology.html">Terminology</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/threading_model.html">Threading Model</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/listener.html">Listener</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/prompt.html">Prompts</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/model_serving.html">Model Serving</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/prompt.html">Prompt</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/request_lifecycle.html">Request Lifecycle</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/error_target.html">Error Target</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../concepts/llm_provider.html">LLM Provider</a></li>
|
||||
|
|
@ -128,7 +129,6 @@
|
|||
<p class="caption" role="heading"><span class="caption-text">Resources</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../resources/configuration_reference.html">Configuration Reference</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../resources/error_target.html">Error Targets</a></li>
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
|
|
@ -196,53 +196,50 @@ Below is an example configuration to get you started, including:</p>
|
|||
<li><p><code class="docutils literal notranslate"><span class="pre">prompt_targets</span></code>: Defines endpoints that handle specific types of prompts.</p></li>
|
||||
<li><p><code class="docutils literal notranslate"><span class="pre">error_target</span></code>: Specifies where to route errors for handling.</p></li>
|
||||
</ul>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="s">"0.1-beta"</span>
|
||||
</span><span id="line-2"><span class="nt">listen</span><span class="p">:</span>
|
||||
</span><span id="line-3"><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1 | 0.0.0.0</span>
|
||||
</span><span id="line-4"><span class="w"> </span><span class="nt">port_value</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8080</span><span class="w"> </span><span class="c1">#If you configure port 443, you'll need to update the listener with tls_certificates</span>
|
||||
</span><span id="line-5">
|
||||
</span><span id="line-6"><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">|</span>
|
||||
</span><span id="line-7"><span class="w"> </span><span class="no">You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.</span>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v0.1</span>
|
||||
</span><span id="line-2">
|
||||
</span><span id="line-3"><span class="nt">listen</span><span class="p">:</span>
|
||||
</span><span id="line-4"><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span><span class="w"> </span><span class="c1"># or 127.0.0.1</span>
|
||||
</span><span id="line-5"><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10000</span>
|
||||
</span><span id="line-6"><span class="w"> </span><span class="c1"># Defines how Arch should parse the content from application/json or text/pain Content-type in the http request</span>
|
||||
</span><span id="line-7"><span class="w"> </span><span class="nt">message_format</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">huggingface</span>
|
||||
</span><span id="line-8">
|
||||
</span><span id="line-9"><span class="nt">llm_providers</span><span class="p">:</span>
|
||||
</span><span id="line-10"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"OpenAI"</span>
|
||||
</span><span id="line-11"><span class="w"> </span><span class="nt">provider</span><span class="p">:</span><span class="w"> </span><span class="s">"openai"</span>
|
||||
</span><span id="line-12"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">OPENAI_API_KEY</span>
|
||||
</span><span id="line-13"><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
|
||||
</span><span id="line-14"><span class="w"> </span><span class="nt">stream</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-15">
|
||||
</span><span id="line-16"><span class="nt">prompt_targets</span><span class="p">:</span>
|
||||
</span><span id="line-17"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reboot_devices</span>
|
||||
</span><span id="line-18"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">></span>
|
||||
</span><span id="line-19"><span class="w"> </span><span class="no">This prompt target handles user requests to reboot devices.</span>
|
||||
</span><span id="line-20"><span class="w"> </span><span class="no">It ensures that when users request to reboot specific devices or device groups, the system processes the reboot commands accurately.</span>
|
||||
</span><span id="line-21">
|
||||
</span><span id="line-22"><span class="w"> </span><span class="no">**Examples of user prompts:**</span>
|
||||
</span><span id="line-23">
|
||||
</span><span id="line-24"><span class="w"> </span><span class="no">- "Please reboot device 12345."</span>
|
||||
</span><span id="line-25"><span class="w"> </span><span class="no">- "Restart all devices in tenant group tenant-XYZ</span>
|
||||
</span><span id="line-26"><span class="w"> </span><span class="no">- "I need to reboot devices A, B, and C."</span>
|
||||
</span><span id="line-27">
|
||||
</span><span id="line-28"><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/agent/device_reboot</span>
|
||||
</span><span id="line-29"><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
|
||||
</span><span id="line-30"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"device_ids"</span>
|
||||
</span><span id="line-31"><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">list</span><span class="w"> </span><span class="c1"># Options: integer | float | list | dictionary | set</span>
|
||||
</span><span id="line-32"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"A</span><span class="nv"> </span><span class="s">list</span><span class="nv"> </span><span class="s">of</span><span class="nv"> </span><span class="s">device</span><span class="nv"> </span><span class="s">identifiers</span><span class="nv"> </span><span class="s">(IDs)</span><span class="nv"> </span><span class="s">to</span><span class="nv"> </span><span class="s">reboot."</span>
|
||||
</span><span id="line-33"><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
|
||||
</span><span id="line-34"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"device_group"</span>
|
||||
</span><span id="line-35"><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">string</span><span class="w"> </span><span class="c1"># Options: string | integer | float | list | dictionary | set</span>
|
||||
</span><span id="line-36"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"The</span><span class="nv"> </span><span class="s">name</span><span class="nv"> </span><span class="s">of</span><span class="nv"> </span><span class="s">the</span><span class="nv"> </span><span class="s">device</span><span class="nv"> </span><span class="s">group</span><span class="nv"> </span><span class="s">to</span><span class="nv"> </span><span class="s">reboot."</span>
|
||||
</span><span id="line-37"><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
|
||||
</span><span id="line-38">
|
||||
</span><span id="line-39"><span class="c1"># Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.</span>
|
||||
</span><span id="line-40"><span class="nt">endpoints</span><span class="p">:</span>
|
||||
</span><span id="line-41"><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
|
||||
</span><span id="line-42"><span class="w"> </span><span class="c1"># value could be ip address or a hostname with port</span>
|
||||
</span><span id="line-43"><span class="w"> </span><span class="c1"># this could also be a list of endpoints for load balancing for example endpoint: [ ip1:port, ip2:port ]</span>
|
||||
</span><span id="line-44"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="s">"127.0.0.1:80"</span>
|
||||
</span><span id="line-45"><span class="w"> </span><span class="c1"># max time to wait for a connection to be established</span>
|
||||
</span><span id="line-46"><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
|
||||
</span><span id="line-47"><span class="w"> </span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="s">"0.1-beta"</span>
|
||||
</span><span id="line-9"><span class="c1"># Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way</span>
|
||||
</span><span id="line-10"><span class="nt">llm_providers</span><span class="p">:</span>
|
||||
</span><span id="line-11"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">OpenAI</span>
|
||||
</span><span id="line-12"><span class="w"> </span><span class="nt">provider</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai</span>
|
||||
</span><span id="line-13"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">OPENAI_API_KEY</span>
|
||||
</span><span id="line-14"><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
|
||||
</span><span id="line-15"><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-16"><span class="w"> </span><span class="nt">stream</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-17">
|
||||
</span><span id="line-18"><span class="c1"># default system prompt used by all prompt targets</span>
|
||||
</span><span id="line-19"><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.</span>
|
||||
</span><span id="line-20">
|
||||
</span><span id="line-21"><span class="nt">prompt_targets</span><span class="p">:</span>
|
||||
</span><span id="line-22"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reboot_devices</span>
|
||||
</span><span id="line-23"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Reboot specific devices or device groups</span>
|
||||
</span><span id="line-24">
|
||||
</span><span id="line-25"><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/agent/device_reboot</span>
|
||||
</span><span id="line-26"><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
|
||||
</span><span id="line-27"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">device_ids</span>
|
||||
</span><span id="line-28"><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">list</span>
|
||||
</span><span id="line-29"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">A list of device identifiers (IDs) to reboot.</span>
|
||||
</span><span id="line-30"><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
|
||||
</span><span id="line-31"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">device_group</span>
|
||||
</span><span id="line-32"><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">str</span>
|
||||
</span><span id="line-33"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">The name of the device group to reboot</span>
|
||||
</span><span id="line-34"><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
|
||||
</span><span id="line-35">
|
||||
</span><span id="line-36"><span class="c1"># Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.</span>
|
||||
</span><span id="line-37"><span class="nt">endpoints</span><span class="p">:</span>
|
||||
</span><span id="line-38"><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
|
||||
</span><span id="line-39"><span class="w"> </span><span class="c1"># value could be ip address or a hostname with port</span>
|
||||
</span><span id="line-40"><span class="w"> </span><span class="c1"># this could also be a list of endpoints for load balancing</span>
|
||||
</span><span id="line-41"><span class="w"> </span><span class="c1"># for example endpoint: [ ip1:port, ip2:port ]</span>
|
||||
</span><span id="line-42"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:80</span>
|
||||
</span><span id="line-43"><span class="w"> </span><span class="c1"># max time to wait for a connection to be established</span>
|
||||
</span><span id="line-44"><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
|
|
@ -256,7 +253,7 @@ Below is an example configuration to get you started, including:</p>
|
|||
<h2>Next Steps<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#next-steps" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#next-steps'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
|
||||
<p>Congratulations! You’ve successfully set up Arch and made your first prompt-based request. To further enhance your GenAI applications, explore the following resources:</p>
|
||||
<ul class="simple">
|
||||
<li><p>Full Documentation: Comprehensive guides and references.</p></li>
|
||||
<li><p><a class="reference internal" href="overview.html#overview"><span class="std std-ref">Full Documentation</span></a>: Comprehensive guides and references.</p></li>
|
||||
<li><p><a class="reference external" href="https://github.com/katanemo/arch" rel="nofollow noopener">GitHub Repository<svg fill="currentColor" height="1em" stroke="none" viewbox="0 96 960 960" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M188 868q-11-11-11-28t11-28l436-436H400q-17 0-28.5-11.5T360 336q0-17 11.5-28.5T400 296h320q17 0 28.5 11.5T760 336v320q0 17-11.5 28.5T720 696q-17 0-28.5-11.5T680 656V432L244 868q-11 11-28 11t-28-11Z"></path></svg></a>: Access the source code, contribute, and track updates.</p></li>
|
||||
<li><p><a class="reference external" href="https://github.com/katanemo/arch#contact" rel="nofollow noopener">Support<svg fill="currentColor" height="1em" stroke="none" viewbox="0 96 960 960" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M188 868q-11-11-11-28t11-28l436-436H400q-17 0-28.5-11.5T360 336q0-17 11.5-28.5T400 296h320q17 0 28.5 11.5T760 336v320q0 17-11.5 28.5T720 696q-17 0-28.5-11.5T680 656V432L244 868q-11 11-28 11t-28-11Z"></path></svg></a>: Get help and connect with the Arch community .</p></li>
|
||||
</ul>
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue