Add model discovery docs and cross-link inference/TTS pages
This commit is contained in:
parent
eea1c51ce8
commit
e90ed3c14f
4 changed files with 59 additions and 12 deletions
|
|
@ -165,7 +165,7 @@ Disallow: /</code></pre>
|
|||
<p>If you have questions about our crawler or want to discuss our access to your site, please reach out:</p>
|
||||
<ul>
|
||||
<li><strong>Website</strong>: <a href="https://uncloseai.com">uncloseai.com</a></li>
|
||||
<li><strong>Discord</strong>: Join our community at <a href="https://discord.agents.ai.unturf.com">discord.agents.ai.unturf.com</a></li>
|
||||
<li><strong>Discord</strong>: Join our community at <a href="https://discord.gg/DnhPJG5w" target="_blank">discord.gg/DnhPJG5w</a></li>
|
||||
<li><strong>Email</strong>: Contact us through our website</li>
|
||||
</ul>
|
||||
|
||||
|
|
|
|||
|
|
@ -98,12 +98,14 @@
|
|||
<h2 id="introduction">Introducing uncloseai & Hermes & Qwen & TTS Speech Endpoints</h2>
|
||||
<p>At <strong>uncloseai.</strong>, we offer free AI services powered by multiple AI models 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><strong>Available Models:</strong></p>
|
||||
<p><strong>Available Endpoints:</strong></p>
|
||||
<ul>
|
||||
<li><a href="https://nousresearch.com/hermes3/" target="_blank">NousResearch/Hermes-3-Llama-3.1-8B</a> - General purpose conversational AI at <code>https://hermes.ai.unturf.com/v1</code></li>
|
||||
<li>Qwen 3 Coder 30B - Specialized coding model at <code>https://qwen.ai.unturf.com/v1</code></li>
|
||||
<li><a href="https://hermes.ai.unturf.com/v1/models" target="_blank">hermes.ai.unturf.com/v1</a> - General purpose conversational AI</li>
|
||||
<li><a href="https://qwen.ai.unturf.com/v1/models" target="_blank">qwen.ai.unturf.com/v1</a> - Specialized coding model</li>
|
||||
<li><a href="https://speech.ai.unturf.com/v1/models" target="_blank">speech.ai.unturf.com/v1</a> - Text-to-speech</li>
|
||||
</ul>
|
||||
|
||||
<p>See our <a href="/inference.html#model-discovery">Model Discovery docs</a> to query the current model IDs being hosted.</p>
|
||||
|
||||
<p>We intend to be a drop in replacement, you can use the existing open source OpenAI client to communicate with us.</p>
|
||||
|
||||
<h2 id="client-side">uncloseai.js - Client-Side AI for Everyone</h2>
|
||||
|
|
@ -138,13 +140,7 @@
|
|||
<p>📚 <a href="https://shop.unturf.com/p/8486f492-a93e-11f0-b477-02dfe05770ee/uncloseai-machine-learning-reference-guide-to-inference-clients" target="_blank"><strong>Purchase the uncloseai. book on unturf.com Shop →</strong></a></p>
|
||||
<p>Comprehensive reference guide covering inference clients, streaming implementations, and best practices for all 42 programming languages.</p>
|
||||
|
||||
<p>All examples use the OpenAI-compatible API interface, making it easy to integrate with existing code. Simply change the <code>base_url</code> to point to our endpoints:</p>
|
||||
|
||||
<ul>
|
||||
<li><strong>Hermes:</strong> <code>https://hermes.ai.unturf.com/v1</code></li>
|
||||
<li><strong>Qwen 3 Coder:</strong> <code>https://qwen.ai.unturf.com/v1</code></li>
|
||||
<li><strong>TTS:</strong> <code>https://speech.ai.unturf.com/v1</code></li>
|
||||
</ul>
|
||||
<p>All examples use the OpenAI-compatible API interface, making it easy to integrate with existing code. Simply change the <code>base_url</code> to point to our endpoints. See our <a href="/inference.html#model-discovery">Model Discovery docs</a> for endpoint URLs and how to query current model IDs.</p>
|
||||
|
||||
<h2 id="inference">How we run inference</h2>
|
||||
<p>Want to contribute idle GPU time or reproduce everything in your own cluster?</p>
|
||||
|
|
|
|||
|
|
@ -152,9 +152,55 @@ speech.ai.unturf.com {
|
|||
}
|
||||
</code></pre>
|
||||
|
||||
<h3 id="model-discovery">Model Discovery</h3>
|
||||
<p>vLLM provides an OpenAI-compatible API with built-in documentation. You can discover available models and explore the full API using these endpoints:</p>
|
||||
|
||||
<h4>Swagger Documentation</h4>
|
||||
<p>Access the interactive API docs at the <code>/docs</code> endpoint:</p>
|
||||
<ul>
|
||||
<li><a href="https://hermes.ai.unturf.com/docs" target="_blank">hermes.ai.unturf.com/docs</a> - Hermes endpoint Swagger docs</li>
|
||||
<li><a href="https://qwen.ai.unturf.com/docs" target="_blank">qwen.ai.unturf.com/docs</a> - Qwen endpoint Swagger docs</li>
|
||||
</ul>
|
||||
<p>The Swagger UI lets you explore all available endpoints, see request/response schemas, and test API calls directly in your browser.</p>
|
||||
|
||||
<h4>Model Discovery</h4>
|
||||
<p>To get the current model ID being hosted, query the <code>/v1/models</code> endpoint:</p>
|
||||
<ul>
|
||||
<li><a href="https://hermes.ai.unturf.com/v1/models" target="_blank">hermes.ai.unturf.com/v1/models</a> - Hermes models</li>
|
||||
<li><a href="https://qwen.ai.unturf.com/v1/models" target="_blank">qwen.ai.unturf.com/v1/models</a> - Qwen models</li>
|
||||
</ul>
|
||||
<p>Or via curl:</p>
|
||||
<pre><code class="language-bash">curl https://hermes.ai.unturf.com/v1/models
|
||||
curl https://qwen.ai.unturf.com/v1/models
|
||||
</code></pre>
|
||||
|
||||
<p>Example response:</p>
|
||||
<pre><code class="language-json">{
|
||||
"object": "list",
|
||||
"data": [
|
||||
{
|
||||
"id": "adamo1139/Hermes-3-Llama-3.1-8B-FP8-Dynamic",
|
||||
"object": "model",
|
||||
"created": 1735689600,
|
||||
"owned_by": "vllm",
|
||||
"root": "adamo1139/Hermes-3-Llama-3.1-8B-FP8-Dynamic",
|
||||
"max_model_len": 82000
|
||||
}
|
||||
]
|
||||
}
|
||||
</code></pre>
|
||||
|
||||
<p>The <code>id</code> field contains the model name you should use in your API calls. The <code>max_model_len</code> field tells you the maximum context length supported.</p>
|
||||
|
||||
<p><strong>Tip:</strong> Always query <code>/v1/models</code> programmatically rather than hardcoding model names. This ensures your code works even when models are updated or swapped.</p>
|
||||
|
||||
<h3 id="rate-limiting">Rate Limiting</h3>
|
||||
<p>Rate limiting is configured based on client IP address: 3 requests per second per IP per endpoint.</p>
|
||||
|
||||
<h3 id="next-steps">Next Steps</h3>
|
||||
<p>Ready to add text-to-speech to your application?</p>
|
||||
<p><a href="/text-to-speech.html"><strong>📖 Read the Text-to-Speech documentation →</strong></a></p>
|
||||
|
||||
<script>hljs.highlightAll();</script>
|
||||
|
||||
<footer>
|
||||
|
|
@ -209,6 +255,7 @@ speech.ai.unturf.com {
|
|||
<li><a href="#vllm-setup">vLLM Setup</a></li>
|
||||
<li><a href="#tts-setup">TTS Setup</a></li>
|
||||
<li><a href="#proxy-setup">Proxy Setup</a></li>
|
||||
<li><a href="#model-discovery">Model Discovery</a></li>
|
||||
<li><a href="#rate-limiting">Rate Limiting</a></li>
|
||||
</ul>
|
||||
</nav>
|
||||
|
|
|
|||
|
|
@ -331,6 +331,10 @@ client.audio.speech.create(
|
|||
|
||||
<p><strong>That's the power of open source TTS.</strong> No API keys, no usage limits, your voice, your infrastructure.</p>
|
||||
|
||||
<h2 id="next-steps">Next Steps</h2>
|
||||
<p>Want to run your own LLM inference alongside TTS?</p>
|
||||
<p><a href="/inference.html"><strong>📖 Read the Inference Setup documentation →</strong></a></p>
|
||||
|
||||
<h2 id="discussions">Questions & Community</h2>
|
||||
|
||||
<p>Ask questions, share your deployments, or discuss TTS research below!</p>
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue