apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-04-27 09:46:28 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

deploy: a7fddf30f9

Browse source
This commit is contained in:
adilhafeez 2025-07-11 23:42:55 +00:00
parent c5b50a4b0e
commit b96c3c6cdd
10 changed files with 265 additions and 293 deletions
Download patch file Download diff file Expand all files Collapse all files

102
concepts/tech_overview/request_lifecycle.html
View file

@ -229,58 +229,56 @@ enables scaling to very high core count CPUs.</p>
</span><span id="line-9">
</span><span id="line-10"><span class="c1"># Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way</span>
</span><span id="line-11"><span class="nt">llm_providers</span><span class="p">:</span>
</span><span id="line-12"><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-13"><span class="w"> </span><span class="nt">provider_interface</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai</span>
</span><span id="line-14"><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-15"><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-16"><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-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_guards</span><span class="p">:</span>
</span><span id="line-22"><span class="w"> </span><span class="nt">input_guards</span><span class="p">:</span>
</span><span id="line-23"><span class="w"> </span><span class="nt">jailbreak</span><span class="p">:</span>
</span><span id="line-24"><span class="w"> </span><span class="nt">on_exception</span><span class="p">:</span>
</span><span id="line-25"><span class="w"> </span><span class="nt">message</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Looks like you're curious about my abilities, but I can only provide assistance within my programmed parameters.</span>
</span><span id="line-26">
</span><span id="line-27"><span class="nt">prompt_targets</span><span class="p">:</span>
</span><span id="line-28"><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">information_extraction</span>
</span><span id="line-29"><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-30"><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">handel all scenarios that are question and answer in nature. Like summarization, information extraction, etc.</span>
</span><span id="line-31"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-32"><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">app_server</span>
</span><span id="line-33"><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/summary</span>
</span><span id="line-34"><span class="w"> </span><span class="c1"># Arch uses the default LLM and treats the response from the endpoint as the prompt to send to the LLM</span>
</span><span id="line-35"><span class="w"> </span><span class="nt">auto_llm_dispatch_on_response</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-36"><span class="w"> </span><span class="c1"># override system prompt for this prompt target</span>
</span><span id="line-37"><span class="w"> </span><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 helpful information extraction assistant. Use the information that is provided to you.</span>
</span><span id="line-38">
</span><span id="line-39"><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_network_device</span>
</span><span id="line-40"><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 a specific network device</span>
</span><span id="line-41"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-42"><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">app_server</span>
</span><span id="line-43"><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/action</span>
</span><span id="line-44"><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</span><span id="line-45"><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_id</span>
</span><span id="line-46"><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-47"><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">Identifier of the network device to reboot.</span>
</span><span id="line-48"><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">true</span>
</span><span id="line-49"><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">confirmation</span>
</span><span id="line-50"><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">bool</span>
</span><span id="line-51"><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">Confirmation flag to proceed with reboot.</span>
</span><span id="line-52"><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">false</span>
</span><span id="line-53"><span class="w"> </span><span class="nt">enum</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">true</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">false</span><span class="p p-Indicator">]</span>
</span><span id="line-54">
</span><span id="line-55"><span class="c1"># Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.</span>
</span><span id="line-56"><span class="nt">endpoints</span><span class="p">:</span>
</span><span id="line-57"><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
</span><span id="line-58"><span class="w"> </span><span class="c1"># value could be ip address or a hostname with port</span>
</span><span id="line-59"><span class="w"> </span><span class="c1"># this could also be a list of endpoints for load balancing</span>
</span><span id="line-60"><span class="w"> </span><span class="c1"># for example endpoint: [ ip1:port, ip2:port ]</span>
</span><span id="line-61"><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-62"><span class="w"> </span><span class="c1"># max time to wait for a connection to be established</span>
</span><span id="line-63"><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-12"><span class="w"> </span><span class="p p-Indicator">-</span><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">openai/gpt-4o</span>
</span><span id="line-14"><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-15">
</span><span id="line-16"><span class="c1"># default system prompt used by all prompt targets</span>
</span><span id="line-17"><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-18">
</span><span id="line-19"><span class="nt">prompt_guards</span><span class="p">:</span>
</span><span id="line-20"><span class="w"> </span><span class="nt">input_guards</span><span class="p">:</span>
</span><span id="line-21"><span class="w"> </span><span class="nt">jailbreak</span><span class="p">:</span>
</span><span id="line-22"><span class="w"> </span><span class="nt">on_exception</span><span class="p">:</span>
</span><span id="line-23"><span class="w"> </span><span class="nt">message</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Looks like you're curious about my abilities, but I can only provide assistance within my programmed parameters.</span>
</span><span id="line-24">
</span><span id="line-25"><span class="nt">prompt_targets</span><span class="p">:</span>
</span><span id="line-26"><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">information_extraction</span>
</span><span id="line-27"><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-28"><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">handel all scenarios that are question and answer in nature. Like summarization, information extraction, etc.</span>
</span><span id="line-29"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-30"><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">app_server</span>
</span><span id="line-31"><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/summary</span>
</span><span id="line-32"><span class="w"> </span><span class="c1"># Arch uses the default LLM and treats the response from the endpoint as the prompt to send to the LLM</span>
</span><span id="line-33"><span class="w"> </span><span class="nt">auto_llm_dispatch_on_response</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-34"><span class="w"> </span><span class="c1"># override system prompt for this prompt target</span>
</span><span id="line-35"><span class="w"> </span><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 helpful information extraction assistant. Use the information that is provided to you.</span>
</span><span id="line-36">
</span><span id="line-37"><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_network_device</span>
</span><span id="line-38"><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 a specific network device</span>
</span><span id="line-39"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-40"><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">app_server</span>
</span><span id="line-41"><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/action</span>
</span><span id="line-42"><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</span><span id="line-43"><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_id</span>
</span><span id="line-44"><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-45"><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">Identifier of the network device to reboot.</span>
</span><span id="line-46"><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">true</span>
</span><span id="line-47"><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">confirmation</span>
</span><span id="line-48"><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">bool</span>
</span><span id="line-49"><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">Confirmation flag to proceed with reboot.</span>
</span><span id="line-50"><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">false</span>
</span><span id="line-51"><span class="w"> </span><span class="nt">enum</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">true</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">false</span><span class="p p-Indicator">]</span>
</span><span id="line-52">
</span><span id="line-53"><span class="c1"># Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.</span>
</span><span id="line-54"><span class="nt">endpoints</span><span class="p">:</span>
</span><span id="line-55"><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
</span><span id="line-56"><span class="w"> </span><span class="c1"># value could be ip address or a hostname with port</span>
</span><span id="line-57"><span class="w"> </span><span class="c1"># this could also be a list of endpoints for load balancing</span>
</span><span id="line-58"><span class="w"> </span><span class="c1"># for example endpoint: [ ip1:port, ip2:port ]</span>
</span><span id="line-59"><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-60"><span class="w"> </span><span class="c1"># max time to wait for a connection to be established</span>
</span><span id="line-61"><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>