apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-04-26 17:26:26 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

deploy: e40b13be05

Browse source
This commit is contained in:
adilhafeez 2025-02-15 03:28:43 +00:00
parent c62b95e38e
commit 2b5bfe09dc
8 changed files with 262 additions and 298 deletions
Download patch file Download diff file Expand all files Collapse all files

28
concepts/llm_provider.html
View file

@ -166,20 +166,20 @@ across applications.</p>
<div class="code-block-caption"><span class="caption-text">Example Configuration</span><a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $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="#id2"><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></div>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="linenos"> 1</span><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 class="linenos"> 2</span>
</span><span id="line-3"><span class="linenos"> 3</span><span class="nt">listener</span><span class="p">:</span>
</span><span id="line-4"><span class="linenos"> 4</span><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="linenos"> 5</span><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="linenos"> 6</span><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="linenos"> 7</span><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 class="linenos"> 8</span>
</span><span id="line-9"><span class="linenos"> 9</span><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"><mark><span class="linenos">10</span><span class="nt">llm_providers</span><span class="p">:</span>
</mark></span><span id="line-11"><mark><span class="linenos">11</span><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>
</mark></span><span id="line-12"><mark><span class="linenos">12</span><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>
</mark></span><span id="line-13"><mark><span class="linenos">13</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>
</mark></span><span id="line-14"><mark><span class="linenos">14</span><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>
</mark></span><span id="line-15"><mark><span class="linenos">15</span><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>
</mark></span><span id="line-16"><mark><span class="linenos">16</span><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-3"><span class="linenos"> 3</span><span class="nt">listeners</span><span class="p">:</span>
</span><span id="line-4"><span class="linenos"> 4</span><span class="w"> </span><span class="nt">ingress_traffic</span><span class="p">:</span>
</span><span id="line-5"><span class="linenos"> 5</span><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><span id="line-6"><span class="linenos"> 6</span><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-7"><span class="linenos"> 7</span><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">openai</span>
</span><span id="line-8"><span class="linenos"> 8</span><span class="w"> </span><span class="nt">timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">30s</span>
</span><span id="line-9"><span class="linenos"> 9</span>
</span><span id="line-10"><mark><span class="linenos">10</span><span class="c1"># Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way</span>
</mark></span><span id="line-11"><mark><span class="linenos">11</span><span class="nt">llm_providers</span><span class="p">:</span>
</mark></span><span id="line-12"><mark><span class="linenos">12</span><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>
</mark></span><span id="line-13"><mark><span class="linenos">13</span><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>
</mark></span><span id="line-14"><mark><span class="linenos">14</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>
</mark></span><span id="line-15"><mark><span class="linenos">15</span><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>
</mark></span><span id="line-16"><mark><span class="linenos">16</span><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>
</mark></span><span id="line-17"><span class="linenos">17</span>
</span><span id="line-18"><span class="linenos">18</span><span class="c1"># default system prompt used by all prompt targets</span>
</span><span id="line-19"><span class="linenos">19</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 network assistant that just offers facts; not advice on manufacturers or purchasing decisions.</span>