Russell Ballestrini
72c73b9a99
- Changed Node.js Examples from h2 to h3 to be subsection under Using the Hermes AI Model - Updated table of contents to group all Python and Node.js examples under main Hermes section - Improved logical document structure with consistent hierarchy - All AI model examples now properly organized under single main section 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
472 lines
18 KiB
HTML
472 lines
18 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="en">
|
|
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<meta name="theme-color" content="#43a047">
|
|
<meta name="color-scheme" content="light dark">
|
|
<title>Using Free LLM & Text To Speech Artificial Intelligence Service | uncloseai.com</title>
|
|
|
|
<!-- PicoCSS -->
|
|
<link rel="stylesheet" href="/css/pico.classless.min.css">
|
|
<!-- ChunkFive Font -->
|
|
<link rel="stylesheet" href="/css/chunkfive/stylesheet.css" type="text/css" charset="utf-8" />
|
|
|
|
<style>
|
|
body {
|
|
max-width: 960px;
|
|
margin: 0 auto;
|
|
}
|
|
|
|
/* Table of Contents Visual Hierarchy */
|
|
aside nav ul {
|
|
list-style-type: disc;
|
|
padding-left: 20px;
|
|
}
|
|
|
|
aside nav ul ul {
|
|
list-style-type: circle;
|
|
padding-left: 30px;
|
|
margin-top: 8px;
|
|
border-left: 2px solid rgba(67, 160, 71, 0.2);
|
|
padding-left: 20px;
|
|
margin-left: 10px;
|
|
}
|
|
|
|
aside nav li {
|
|
margin: 6px 0;
|
|
line-height: 1.4;
|
|
}
|
|
|
|
aside nav ul ul li {
|
|
margin: 4px 0;
|
|
font-size: 0.9em;
|
|
}
|
|
</style>
|
|
|
|
<!-- Highlight.js for syntax highlighting -->
|
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.10.0/styles/a11y-dark.min.css" />
|
|
<script src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.6.0/highlight.min.js"></script>
|
|
|
|
<!-- Theme Switcher Script -->
|
|
<script>
|
|
function switchTheme(theme) {
|
|
if (theme === "auto") {
|
|
document.documentElement.removeAttribute('data-theme');
|
|
} else {
|
|
document.documentElement.setAttribute('data-theme', theme);
|
|
}
|
|
}
|
|
|
|
// Disable custom styling for uncloseai.js - use PicoCSS instead
|
|
window.UNCLOSEAI_CUSTOM_STYLING = false;
|
|
</script>
|
|
|
|
<script src="https://uncloseai.com/uncloseai.js" type="module"></script>
|
|
<!--
|
|
<script defer data-domain="ai.unturf.com" src="https://analytics.unturf.com/js/plausible.js"></script>
|
|
-->
|
|
</head>
|
|
|
|
<body>
|
|
|
|
<header>
|
|
<hgroup>
|
|
<a href="https://uncloseai.com"><h1 class="unturf" style="font-family: 'ChunkFiveRegular';">russell@unturf. presents, uncloseai</h1></a>
|
|
<p>Welcome to uncloseai.com - Free LLM & Text To Speech Artificial Intelligence Service</p>
|
|
</hgroup>
|
|
<nav>
|
|
<ul>
|
|
<li><a href="#" onclick="switchTheme('auto')">Auto</a></li>
|
|
<li><a href="#" onclick="switchTheme('light')">Light</a></li>
|
|
<li><a href="#" onclick="switchTheme('dark')">Dark</a></li>
|
|
</ul>
|
|
</nav>
|
|
</header>
|
|
|
|
<main>
|
|
<h2 id="introduction">Introducing uncloseai & Hermes & TTS Speech Endpoints</h2>
|
|
<p>At <strong>uncloseai.</strong>, we offer free AI services powered by the <a href="https://nousresearch.com/hermes3/" target="_blank">NousResearch/Hermes-3-Llama-3.1-8B</a> model and a TTS (Text-to-Speech) endpoint. Our mission is to provide accessible AI tools for everyone, embodying the principles of both free as in beer & free as in freedom. You can interact with our models without any cost, and you are encouraged to contribute and build upon the open-source code & models that we use.</p>
|
|
|
|
<p>We intend to be a drop in replacement, you can use the existing open source OpenAI client to communicate with us.</p>
|
|
|
|
<!-- Table of Contents -->
|
|
<aside>
|
|
<h3>📋 Table of Contents</h3>
|
|
<nav>
|
|
<ul>
|
|
<li><a href="#introduction">Introducing uncloseai & Hermes & TTS Speech Endpoints</a></li>
|
|
<li><a href="#client-side">Web Client-Only Solution</a>
|
|
<ul>
|
|
<li><a href="#quick-start">🚀 Quick Start: Install uncloseai.js</a></li>
|
|
<li><a href="#installation">✨ One-Line Installation</a></li>
|
|
<li><a href="#features">🎯 What You Get</a></li>
|
|
</ul>
|
|
</li>
|
|
<li><a href="#openai-client">Installing the OpenAI Client</a>
|
|
<ul>
|
|
<li><a href="#python-client">Python Client Installation</a></li>
|
|
<li><a href="#nodejs-client">Node.js Client Installation</a></li>
|
|
</ul>
|
|
</li>
|
|
<li><a href="#hermes-model">Using the Hermes AI Model</a>
|
|
<ul>
|
|
<li><a href="#python-hermes">Python Examples</a></li>
|
|
<li><a href="#python-non-streaming">Python Non-Streaming</a></li>
|
|
<li><a href="#python-streaming">Python Streaming</a></li>
|
|
<li><a href="#nodejs-examples">Node.js Examples</a></li>
|
|
<li><a href="#nodejs-non-streaming">Node.js Non-Streaming</a></li>
|
|
<li><a href="#nodejs-streaming">Node.js Streaming</a></li>
|
|
</ul>
|
|
</li>
|
|
<li><a href="#tts">Using the Text To Speech Endpoint</a>
|
|
<ul>
|
|
<li><a href="#python-tts">Python TTS Example</a></li>
|
|
<li><a href="#nodejs-tts">Node.js TTS Example</a></li>
|
|
</ul>
|
|
</li>
|
|
<li><a href="#inference">How we run inference</a></li>
|
|
<li><a href="#open-source">Open Source & Public Domain</a></li>
|
|
<li><a href="#discussions">Questions & Comments & Discussions</a></li>
|
|
</ul>
|
|
</nav>
|
|
|
|
<p><strong>🎮 Looking for examples and interactive demos?</strong> <a href="https://ai.unturf.com/demo.html">Visit our comprehensive demo page →</a></p>
|
|
</aside>
|
|
|
|
<h2 id="client-side">Web Client-Only Solution: Interact with AI Services Directly from Static Sites or CDNs</h2>
|
|
|
|
<p><b>Because we don't require a valid API key, we don't have any real need for a server.</b></p>
|
|
|
|
<p>Add this LLM to any static site or CDN.</p>
|
|
|
|
<p>This web client-only solution uses <a href="https://uncloseai.com/uncloseai.js" target="_blank">uncloseai.js</a> to make the browser act as a client, directly interacting with the API without needing an intermediary server. By eliminating the need for a valid API key, the API handles requests on behalf of the browser client, making it efficient and accessible thin client, especially those on battery power like phones & laptops.</p>
|
|
|
|
<h3 id="quick-start">🚀 Quick Start: Install uncloseai.js on any website</h3>
|
|
|
|
<p>Add AI capabilities to any website with just one line of code. The floating "uncloseai." button appears automatically, providing access to Hermes AI, text-to-speech, translation, and more.</p>
|
|
|
|
<h3 id="installation">✨ One-Line Installation</h3>
|
|
<p>Add this script tag to your HTML - that's it! The floating AI button appears automatically:</p>
|
|
<pre><code class="html"><script src="https://uncloseai.com/uncloseai.js" type="module"></script></code></pre>
|
|
|
|
<h3 id="features">🎯 What You Get</h3>
|
|
<ul>
|
|
<li><strong>🤖 Floating AI Assistant</strong> - Always-accessible "uncloseai." button in bottom right</li>
|
|
<li><strong>📖 Page-Aware</strong> - Hermes AI understands your page content and provides contextual help</li>
|
|
<li><strong>🔊 Text-to-Speech</strong> - Convert any text to speech with multiple voice options</li>
|
|
<li><strong>🌐 Translation</strong> - Translate content into 19 languages with formatting preservation</li>
|
|
<li><strong>💾 Conversation History</strong> - Persistent chat history stored in browser</li>
|
|
<li><strong>🎨 Framework Compatible</strong> - Works with any CSS framework</li>
|
|
</ul>
|
|
|
|
<p><strong>🎮 Live Demo & Complete Documentation:</strong> <a href="https://ai.unturf.com/demo.html" style="font-weight: bold; color: #43a047;">See uncloseai.js in action with 12+ integration examples →</a></p>
|
|
|
|
<p>The demo page includes configuration options, embedded widgets, custom implementations, direct API usage, and more advanced features.</p>
|
|
|
|
<h2 id="openai-client">Installing the OpenAI Client</h2>
|
|
<h3 id="python-client">Python Client Installation</h3>
|
|
<p>To install the OpenAI package for Python, use <code>pip</code>:</p>
|
|
<pre><code>pip install openai</code></pre>
|
|
|
|
<h3 id="nodejs-client">Node.js Client Installation</h3>
|
|
<p>To install the OpenAI package for Node.js, you can use <code>npm</code> in your <code>package.json</code>:</p>
|
|
<pre><code>{
|
|
"dependencies": {
|
|
"openai": "^v4.67.3" // Use the latest version
|
|
}
|
|
}
|
|
</code></pre>
|
|
<p>Run the following command to install it:</p>
|
|
<pre><code>npm install</code></pre>
|
|
|
|
<h2 id="hermes-model">Using the Hermes AI Model</h2>
|
|
<h3 id="python-hermes">Python Examples</h3>
|
|
<h3 id="python-non-streaming">Python Non-Streaming</h3>
|
|
<pre><code class="python"># Python Fizzbuzz Example
|
|
from openai import OpenAI
|
|
|
|
client = OpenAI(base_url="https://hermes.ai.unturf.com/v1", api_key="choose-any-value")
|
|
|
|
#MODEL = "NousResearch/Hermes-3-Llama-3.1-8B"
|
|
MODEL = "adamo1139/Hermes-3-Llama-3.1-8B-FP8-Dynamic"
|
|
|
|
messages = [{"role": "user", "content": "Give a Python Fizzbuzz solution in one line of code?"}]
|
|
|
|
response = client.chat.completions.create(
|
|
model=MODEL,
|
|
messages=messages,
|
|
temperature=0.5,
|
|
max_tokens=150
|
|
)
|
|
|
|
print(response.choices[0].message.content)
|
|
</code></pre>
|
|
|
|
<h3 id="python-streaming">Python Streaming</h3>
|
|
<pre><code class="python"># Streaming response in Python
|
|
from openai import OpenAI
|
|
|
|
client = OpenAI(base_url="https://hermes.ai.unturf.com/v1", api_key="choose-any-value")
|
|
|
|
MODEL = "adamo1139/Hermes-3-Llama-3.1-8B-FP8-Dynamic"
|
|
|
|
messages = [
|
|
{"role": "user", "content": "Give a Python Fizzbuzz solution in one line of code?"}
|
|
]
|
|
|
|
response = client.chat.completions.create(
|
|
model=MODEL,
|
|
messages=messages,
|
|
temperature=0.5,
|
|
max_tokens=150,
|
|
stream=True, # Enable streaming
|
|
)
|
|
|
|
for chunk in response:
|
|
if hasattr(chunk.choices[0].delta, "content"):
|
|
print(chunk.choices[0].delta.content, end="")
|
|
</code></pre>
|
|
|
|
<h3 id="nodejs-examples">Node.js Examples</h3>
|
|
<h3 id="nodejs-non-streaming">Node.js Non-Streaming</h3>
|
|
<pre><code class="javascript">const OpenAI = require('openai');
|
|
|
|
const client = new OpenAI({
|
|
baseURL: "https://hermes.ai.unturf.com/v1",
|
|
apiKey: "dummy-api-key",
|
|
});
|
|
|
|
const MODEL = "adamo1139/Hermes-3-Llama-3.1-8B-FP8-Dynamic";
|
|
|
|
const messages = [{"role": "user", "content": "Give a Python Fizzbuzz solution in one line of code?"}];
|
|
|
|
async function getResponse() {
|
|
try {
|
|
const response = await client.chat.completions.create({
|
|
model: MODEL,
|
|
messages: messages,
|
|
temperature: 0.5,
|
|
max_tokens: 150,
|
|
});
|
|
|
|
console.log(response.choices[0].message.content);
|
|
} catch (error) {
|
|
console.error("Error:", error.response ? error.response.data : error.message);
|
|
}
|
|
}
|
|
|
|
getResponse();
|
|
</code></pre>
|
|
|
|
<h3 id="nodejs-streaming">Node.js Streaming</h3>
|
|
<pre><code class="javascript">
|
|
const OpenAI = require('openai');
|
|
|
|
const client = new OpenAI({
|
|
baseURL: "https://hermes.ai.unturf.com/v1",
|
|
apiKey: "dummy-api-key",
|
|
});
|
|
|
|
const MODEL = "adamo1139/Hermes-3-Llama-3.1-8B-FP8-Dynamic";
|
|
|
|
const messages = [{"role": "user", "content": "Give a Python Fizzbuzz solution in one line of code?"}];
|
|
|
|
async function streamResponse() {
|
|
try {
|
|
const stream = await client.chat.completions.create({
|
|
model: MODEL,
|
|
messages: messages,
|
|
temperature: 0.5,
|
|
max_tokens: 150,
|
|
stream: true, // Enable streaming
|
|
});
|
|
|
|
// Use async iterator to read each chunk
|
|
for await (const chunk of stream) {
|
|
const msg = chunk.choices[0].delta.content;
|
|
process.stdout.write(msg); // Print each chunk as it arrives
|
|
}
|
|
} catch (error) {
|
|
console.error("Error:", error.response ? error.response.data : error.message);
|
|
}
|
|
}
|
|
|
|
streamResponse();
|
|
</code></pre>
|
|
|
|
<h2 id="tts">Using the Text To Speech Endpoint</h2>
|
|
<h3 id="python-tts">Python TTS Example</h3>
|
|
<pre><code class="python"># TTS Speech Example in Python
|
|
import openai
|
|
|
|
client = openai.OpenAI(
|
|
api_key = "YOLO",
|
|
base_url = "https://speech.ai.unturf.com/v1",
|
|
)
|
|
|
|
with client.audio.speech.with_streaming_response.create(
|
|
model="tts-1",
|
|
voice="alloy",
|
|
speed=0.9,
|
|
input="I think so therefore, Today is a wonderful day to build something people love!"
|
|
) as response:
|
|
response.stream_to_file("speech.mp3")
|
|
</code></pre>
|
|
|
|
<h3 id="nodejs-tts">Node.js TTS Example</h3>
|
|
<pre><code class="javascript">const OpenAI = require('openai');
|
|
|
|
const client = new OpenAI({
|
|
baseURL: "https://speech.ai.unturf.com/v1",
|
|
apiKey: "YOLO",
|
|
});
|
|
|
|
async function getSpeech() {
|
|
try {
|
|
const response = await client.audio.speech.with_streaming_response.create({
|
|
model: "tts-1",
|
|
voice: "alloy",
|
|
speed: 0.9,
|
|
input: "I think so therefore, Today is a wonderful day to build something people love!"
|
|
});
|
|
|
|
response.stream_to_file("speech.mp3");
|
|
} catch (error) {
|
|
console.error("Error:", error.response ? error.response.data : error.message);
|
|
}
|
|
}
|
|
|
|
getSpeech();
|
|
</code></pre>
|
|
|
|
<h2 id="inference">How we run inference</h2>
|
|
|
|
<p>This section is optional. This is only if you wanted to try to contribute idle GPU time to the project or if you wanted to reproduce everything in your own cluster.</p>
|
|
|
|
<p>We use vLLM to run models, currently full f16 safetensors. We make sure to use a virtualenv to hold the dependencies.</p>
|
|
<p>We are considering supporting ollama for better quant support.</p>
|
|
<p>Stand up a replica cluster on a new domain.</p>
|
|
<pre><code>
|
|
sudo apt-get install gcc python3.12-dev
|
|
cd ~
|
|
python3 -m venv env
|
|
source env/bin/activate
|
|
pip install vllm
|
|
python -m vllm.entrypoints.openai.api_server --model adamo1139/Hermes-3-Llama-3.1-8B-FP8-Dynamic --host 0.0.0.0 --port 18888 --max-model-len 82000
|
|
</code></pre>
|
|
|
|
<p>The Speech endpoint or TTS uses <a href="https://github.com/matatonic/openedai-speech?tab=readme-ov-file#nvidia-gpu-cuda">openedai-speech</a> running via Docker.
|
|
|
|
<p>If you want to see how we setup the proxy, check out <a href="https://git.unturf.com/-/snippets/3">/etc/caddy/Caddyfile</a></p>
|
|
|
|
<pre><code>
|
|
|
|
ai.unturf.com {
|
|
root * /opt/www
|
|
file_server
|
|
log {
|
|
output file /var/log/caddy/ai.unturf.com.log {
|
|
roll_size 50mb
|
|
roll_keep 5
|
|
}
|
|
}
|
|
tls {
|
|
on_demand
|
|
}
|
|
}
|
|
|
|
hermes.ai.unturf.com {
|
|
reverse_proxy <removed>:18888
|
|
log {
|
|
output file /var/log/caddy/hermes.ai.unturf.com.log {
|
|
roll_size 50mb
|
|
roll_keep 5
|
|
}
|
|
}
|
|
tls {
|
|
on_demand
|
|
}
|
|
}
|
|
|
|
speech.ai.unturf.com {
|
|
reverse_proxy <removed>:8000
|
|
log {
|
|
output file /var/log/caddy/speech.ai.unturf.com.log {
|
|
roll_size 50mb
|
|
roll_keep 5
|
|
}
|
|
}
|
|
tls {
|
|
on_demand
|
|
}
|
|
}
|
|
|
|
</code></pre>
|
|
|
|
<p>We will likely implement a rate limit based on client IP address.</p>
|
|
|
|
<h2 id="open-source">Open Source & Public Domain</h2>
|
|
|
|
<p><strong>uncloseai.</strong> is completely <strong>public domain</strong> - free as in beer, free as in freedom. AI for all, internet for all, open web for everyone.</p>
|
|
|
|
<p>📦 <strong>Source Code:</strong> <a href="https://git.unturf.com/engineering/unturf/uncloseai.com" target="_blank">https://git.unturf.com/engineering/unturf/uncloseai.com</a></p>
|
|
|
|
<p>📄 <strong>Full Documentation:</strong> See README.rst in the repository for complete technical details, architecture, and contribution guidelines.</p>
|
|
|
|
<h2 id="discussions">Questions & Comments & Discussions</h2>
|
|
|
|
Use the <a href="https://www.remarkbox.com" target="_blank">Remarkbox</a> below to tell us what you think!
|
|
|
|
<div id="remarkbox-div">
|
|
<noscript>
|
|
<iframe id=remarkbox-iframe src="https://my.remarkbox.com/embed?nojs=true" style="height:600px;width:100%;border:none!important" tabindex=0></iframe>
|
|
</noscript>
|
|
</div>
|
|
<script src="https://my.remarkbox.com/static/js/iframe-resizer/iframeResizer.min.js"></script>
|
|
<script>
|
|
var rb_owner_key = "944c8dfa-8b2b-11ef-af0e-29ab4fb285a0";
|
|
var thread_uri = window.location.href;
|
|
var thread_title = window.document.title;
|
|
var thread_fragment = window.location.hash;
|
|
|
|
var rb_src = "https://my.remarkbox.com/embed" +
|
|
"?rb_owner_key=" + rb_owner_key +
|
|
"&thread_title=" + encodeURI(thread_title) +
|
|
"&thread_uri=" + encodeURIComponent(thread_uri) +
|
|
thread_fragment;
|
|
|
|
function create_remarkbox_iframe() {
|
|
var ifrm = document.createElement("iframe");
|
|
ifrm.setAttribute("id", "remarkbox-iframe");
|
|
ifrm.setAttribute("scrolling", "no");
|
|
ifrm.setAttribute("src", rb_src);
|
|
ifrm.setAttribute("frameborder", "0");
|
|
ifrm.setAttribute("tabindex", "0");
|
|
ifrm.setAttribute("title", "Remarkbox");
|
|
ifrm.style.width = "100%";
|
|
document.getElementById("remarkbox-div").appendChild(ifrm);
|
|
}
|
|
create_remarkbox_iframe();
|
|
iFrameResize(
|
|
{
|
|
checkOrigin: ["https://my.remarkbox.com"],
|
|
inPageLinks: true,
|
|
initCallback: function(e) { e.iFrameResizer.moveToAnchor(thread_fragment) }
|
|
},
|
|
document.getElementById("remarkbox-iframe")
|
|
);
|
|
</script>
|
|
|
|
<script>hljs.highlightAll();</script>
|
|
</main>
|
|
|
|
<footer>
|
|
<small>Stylesheets by <a href="https://picocss.com" target="_blank">PicoCSS</a></small>
|
|
<small>& <a href="https://highlightjs.org/" target="_blank">highlight.js</a></small>
|
|
</footer>
|
|
|
|
</body>
|
|
|
|
</html>
|