182 lines
5.8 KiB
HTML
182 lines
5.8 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="en">
|
|
|
|
<head>
|
|
<title>{{ llm_middleware_name }}</title>
|
|
<meta content="width=device-width, initial-scale=1" name="viewport"/>
|
|
{{ analytics_tracking_code|safe }}
|
|
<style>
|
|
.container {
|
|
padding: 1em 3em;
|
|
}
|
|
|
|
#json {
|
|
background-color: rgb(229 231 235);
|
|
padding: 1em;
|
|
display: inline-block;
|
|
margin: auto;
|
|
max-width: 95%;
|
|
}
|
|
|
|
body {
|
|
background-color: #f3f4f6;
|
|
}
|
|
|
|
.info-box {
|
|
background-color: white;
|
|
padding: 1em;
|
|
margin: auto;
|
|
border-radius: 10px;
|
|
max-width: 95%;
|
|
}
|
|
|
|
pre code.hljs {
|
|
padding: 0 !important;
|
|
}
|
|
|
|
a, a:visited {
|
|
color: blue;
|
|
}
|
|
|
|
.footer {
|
|
font-size: 7pt;
|
|
text-align: center;
|
|
}
|
|
|
|
pre {
|
|
white-space: pre-wrap;
|
|
word-wrap: break-word;
|
|
text-align: justify;
|
|
}
|
|
|
|
@media only screen and (max-width: 600px) {
|
|
.container {
|
|
padding: 1em;
|
|
}
|
|
|
|
h1 {
|
|
font-size: 1.5em;
|
|
}
|
|
}
|
|
|
|
.hidden {
|
|
display: none;
|
|
}
|
|
|
|
.header-workers {
|
|
font-weight: normal;
|
|
font-size: 14pt;
|
|
}
|
|
|
|
h3 {
|
|
font-size: 16pt;
|
|
}
|
|
|
|
.no-marker {
|
|
list-style: none;
|
|
}
|
|
</style>
|
|
</head>
|
|
|
|
<body>
|
|
<script>
|
|
const backend_online = {% if current_model != 'offline' %}true{% else %}false{% endif %};
|
|
</script>
|
|
<div class="container">
|
|
<h1 style="text-align: center;margin-top: 0;">{{ llm_middleware_name }}</h1>
|
|
|
|
<div class="info-box">
|
|
<p><strong>Current Model:</strong> <span id="model">{{ default_model }}</span></p>
|
|
<p>
|
|
<strong>Estimated Wait Time:</strong> <span id="estimatedWait">{{ default_estimated_wait }}</span><br>
|
|
Processing: {{ default_active_gen_workers }}<br>
|
|
Queued: {{ default_proompters_in_queue }}
|
|
</p>
|
|
<br>
|
|
<p><strong>Client API URL:</strong> {{ client_api }}</p>
|
|
<p><strong>Streaming API URL:</strong> {{ ws_client_api if enable_streaming else 'Disabled' }}</p>
|
|
<p><strong>OpenAI-Compatible API URL:</strong> {{ openai_client_api }}</p>
|
|
{% if info_html|length > 1 %}
|
|
<br>
|
|
{{ info_html|safe }}
|
|
{% endif %}
|
|
</div>
|
|
|
|
<br>
|
|
|
|
<div class="info-box">
|
|
<h3>Instructions</h3>
|
|
<div id="instructions">
|
|
<ol>
|
|
<li>In Settings > Power User Options, enable <kbd>Relaxed API URLS</kbd>.</li>
|
|
<li>Set your API type to <kbd>{{ mode_name }}</kbd></li>
|
|
<li>Enter <kbd>{{ client_api }}</kbd> in the <kbd>{{ api_input_textbox }}</kbd> textbox.</li>
|
|
{% if enable_streaming %}
|
|
<li>Enter <kbd>{{ ws_client_api }}</kbd> in the <kbd>{{ streaming_input_textbox }}</kbd> textbox.</li>
|
|
{% endif %}
|
|
<li>If you have a token, check the <kbd>Mancer AI</kbd> checkbox and enter your token in the <kbd>Mancer
|
|
API key</kbd> textbox.
|
|
</li>
|
|
<li>Click <kbd>Connect</kbd> to test the connection.</li>
|
|
<li>Open your preset config and set <kbd>Context Size</kbd> to {{ default_context_size }}.</li>
|
|
<li>Follow this guide to get set up: <a href="https://rentry.org/freellamas" target="_blank">rentry.org/freellamas</a>
|
|
</li>
|
|
</ol>
|
|
</div>
|
|
{% if openai_client_api != 'disabled' and expose_openai_system_prompt %}
|
|
<br>
|
|
<div id="openai">
|
|
<strong>OpenAI-Compatible API</strong>
|
|
<p>The OpenAI-compatible API adds a system prompt to set the AI's behavior to a "helpful assistant". You can view this prompt <a href="/api/openai/v1/prompt">here</a>.</p>
|
|
</div>
|
|
{% endif %}
|
|
<br>
|
|
<div id="extra-info">{{ extra_info|safe }}</div>
|
|
</div>
|
|
|
|
<br>
|
|
|
|
<div class="info-box">
|
|
<h3>Statistics</h3>
|
|
Proompters:
|
|
<ul style="margin-top: 5px;">
|
|
<li class="no-marker">5 minutes: {{ proompters_5_min }}</li>
|
|
<li class="no-marker">24 hours: {{ proompters_24_hrs }}</li>
|
|
</ul>
|
|
</div>
|
|
<br>
|
|
|
|
{% for key, value in model_choices.items() %}
|
|
<div class="info-box">
|
|
<h3>{{ key }} <span class="header-workers">- {{ value.backend_count }} {% if value.backend_count == 1 %}worker{% else %}workers{% endif %}</span></h3>
|
|
|
|
{% if value.estimated_wait == 0 and value.estimated_wait >= value.concurrent_gens %}
|
|
{# There will be a wait if the queue is empty but prompts are processing, but we don't know how long. #}
|
|
{% set estimated_wait_sec = "less than " + value.estimated_wait|int|string + " seconds" %}
|
|
{% else %}
|
|
{% set estimated_wait_sec = value.estimated_wait|int|string + " seconds" %}
|
|
{% endif %}
|
|
|
|
<p>
|
|
<strong>Estimated Wait Time:</strong> {{ estimated_wait_sec }}<br>
|
|
Processing: {{ value.processing }}<br>
|
|
Queued: {{ value.queued }}<br>
|
|
</p>
|
|
<p>
|
|
<strong>Client API URL:</strong> {{ value.client_api }}<br>
|
|
<strong>Streaming API URL:</strong> {{ value.ws_client_api }}<br>
|
|
<strong>OpenAI-Compatible API URL:</strong> {{ value.openai_client_api }}
|
|
</p>
|
|
<p><strong>Context Size:</strong> {{ value.context_size }}</p>
|
|
<p><strong>Average Generation Time:</strong> {{ value.avg_generation_time | int }} seconds</p>
|
|
</div>
|
|
<br>
|
|
{% endfor %}
|
|
</div>
|
|
<div class="footer">
|
|
<a href="https://git.evulid.cc/cyberes/local-llm-server" target="_blank">git.evulid.cc/cyberes/local-llm-server</a>
|
|
</div>
|
|
</body>
|
|
|
|
</html>
|