Update templates/docs.html
Browse files- templates/docs.html +33 -24
templates/docs.html
CHANGED
@@ -19,55 +19,55 @@
|
|
19 |
<section class="mb-10">
|
20 |
<h2 class="text-2xl font-semibold mb-4 text-blue">What is MoA Chat?</h2>
|
21 |
<p class="mb-4 text-lg">
|
22 |
-
<strong>MoA (Model of Agents)</strong> is a method that
|
23 |
</p>
|
24 |
<p class="mb-4">
|
25 |
-
MoA Chat implements
|
26 |
</p>
|
27 |
<ul class="list-disc ml-6 text-lg">
|
28 |
-
<li>Querying several different models (LLM-A, LLM-B, LLM-C)
|
29 |
-
<li>Combining their answers using
|
30 |
-
<li>Delivering a smart,
|
31 |
</ul>
|
32 |
</section>
|
33 |
|
34 |
<section class="mb-10">
|
35 |
<h2 class="text-2xl font-semibold mb-4 text-blue">How MoA Works (Visual)</h2>
|
36 |
<p class="mb-4 text-center">
|
37 |
-
<img src="https://raw.githubusercontent.com/togethercomputer/MoA/main/assets/
|
38 |
</p>
|
39 |
-
<p class="text-center text-sm opacity-70">Source: Together MoA Architecture
|
40 |
</section>
|
41 |
|
42 |
<section class="mb-10">
|
43 |
-
<h2 class="text-2xl font-semibold mb-4 text-blue">How to Use</h2>
|
44 |
<ol class="list-decimal ml-6 text-lg">
|
45 |
-
<li>Click ⚙️ to open the configuration panel.</li>
|
46 |
<li>Select your preferred models for LLM-A, LLM-B, LLM-C, and Aggregator (LLM-D).</li>
|
47 |
-
<li>Type your message in the input box.</li>
|
48 |
-
<li>Press <strong>Send</strong
|
49 |
-
<li>Watch multiple models collaborate for the best response!</li>
|
50 |
</ol>
|
51 |
</section>
|
52 |
|
53 |
<section class="mb-10">
|
54 |
<h2 class="text-2xl font-semibold mb-4 text-blue">Features</h2>
|
55 |
<ul class="list-disc ml-6 text-lg">
|
56 |
-
<li>Parallel querying of multiple free
|
57 |
-
<li>Structured prompts for
|
58 |
-
<li>Aggregator model intelligently fuses outputs into
|
59 |
-
<li>Dynamic Light/Dark
|
60 |
-
<li>
|
|
|
61 |
</ul>
|
62 |
</section>
|
63 |
|
64 |
<section class="mb-10">
|
65 |
<h2 class="text-2xl font-semibold mb-4 text-blue">Deployment</h2>
|
66 |
<p class="mb-4 text-lg">
|
67 |
-
MoA Chat is optimized
|
68 |
</p>
|
69 |
<p class="text-lg">
|
70 |
-
|
71 |
</p>
|
72 |
</section>
|
73 |
|
@@ -75,22 +75,31 @@
|
|
75 |
<h2 class="text-2xl font-semibold mb-4 text-blue">File Structure</h2>
|
76 |
<ul class="list-disc ml-6 text-lg">
|
77 |
<li><code>app.py</code> — Flask backend server.</li>
|
78 |
-
<li><code>llm/agents.py</code> —
|
79 |
-
<li><code>llm/model_config.json</code> —
|
80 |
<li><code>templates/</code> — Contains <code>index.html</code> and <code>docs.html</code>.</li>
|
81 |
<li><code>static/</code> — Contains <code>style.css</code> and <code>script.js</code>.</li>
|
82 |
</ul>
|
83 |
</section>
|
84 |
|
85 |
<section class="mb-10">
|
86 |
-
<h2 class="text-2xl font-semibold mb-4 text-blue">Credits</h2>
|
87 |
-
<p class="text-lg">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
</section>
|
89 |
|
90 |
</div>
|
91 |
|
92 |
-
<div class="text-center mt-8">
|
93 |
<a href="/" class="px-6 py-2 bg-blue text-fg0 rounded hover:bg-purple transition text-lg font-semibold">← Back to Chat</a>
|
|
|
94 |
</div>
|
95 |
|
96 |
<script>
|
|
|
19 |
<section class="mb-10">
|
20 |
<h2 class="text-2xl font-semibold mb-4 text-blue">What is MoA Chat?</h2>
|
21 |
<p class="mb-4 text-lg">
|
22 |
+
<strong>MoA (Model of Agents)</strong> is a method that allows multiple AI models to collaborate to generate a higher-quality response than a single model could.
|
23 |
</p>
|
24 |
<p class="mb-4">
|
25 |
+
MoA Chat implements this idea by:
|
26 |
</p>
|
27 |
<ul class="list-disc ml-6 text-lg">
|
28 |
+
<li>Querying several different models (LLM-A, LLM-B, LLM-C) simultaneously.</li>
|
29 |
+
<li>Combining their answers using a special model (LLM-D, the aggregator).</li>
|
30 |
+
<li>Delivering a smart, clear, and polished reply to the user.</li>
|
31 |
</ul>
|
32 |
</section>
|
33 |
|
34 |
<section class="mb-10">
|
35 |
<h2 class="text-2xl font-semibold mb-4 text-blue">How MoA Works (Visual)</h2>
|
36 |
<p class="mb-4 text-center">
|
37 |
+
<img src="https://raw.githubusercontent.com/togethercomputer/MoA/main/assets/moa-explained.png" alt="MoA Architecture Explained" class="mx-auto rounded shadow-md">
|
38 |
</p>
|
39 |
+
<p class="text-center text-sm opacity-70">Source: Together Computer, MoA Architecture Overview</p>
|
40 |
</section>
|
41 |
|
42 |
<section class="mb-10">
|
43 |
+
<h2 class="text-2xl font-semibold mb-4 text-blue">How to Use MoA Chat</h2>
|
44 |
<ol class="list-decimal ml-6 text-lg">
|
45 |
+
<li>Click ⚙️ to open the model configuration panel.</li>
|
46 |
<li>Select your preferred models for LLM-A, LLM-B, LLM-C, and Aggregator (LLM-D).</li>
|
47 |
+
<li>Type your message in the chat input box.</li>
|
48 |
+
<li>Press <strong>Send</strong> and watch the system generate a unified, better answer!</li>
|
|
|
49 |
</ol>
|
50 |
</section>
|
51 |
|
52 |
<section class="mb-10">
|
53 |
<h2 class="text-2xl font-semibold mb-4 text-blue">Features</h2>
|
54 |
<ul class="list-disc ml-6 text-lg">
|
55 |
+
<li>Parallel querying of multiple free and premium LLMs (OpenRouter, Together, Grok, etc.).</li>
|
56 |
+
<li>Structured system prompts for consistent quality.</li>
|
57 |
+
<li>Aggregator model intelligently fuses outputs into a coherent final response.</li>
|
58 |
+
<li>Dynamic Light/Dark Gruvbox Material theme.</li>
|
59 |
+
<li>Secure: No API keys exposed to frontend.</li>
|
60 |
+
<li>Minimal, fast, mobile-friendly interface.</li>
|
61 |
</ul>
|
62 |
</section>
|
63 |
|
64 |
<section class="mb-10">
|
65 |
<h2 class="text-2xl font-semibold mb-4 text-blue">Deployment</h2>
|
66 |
<p class="mb-4 text-lg">
|
67 |
+
MoA Chat is optimized for <strong>Hugging Face Spaces</strong> or any platform supporting Python 3.11+, Flask, and Docker containers.
|
68 |
</p>
|
69 |
<p class="text-lg">
|
70 |
+
API keys should be stored securely using Hugging Face's <strong>Secrets</strong> system.
|
71 |
</p>
|
72 |
</section>
|
73 |
|
|
|
75 |
<h2 class="text-2xl font-semibold mb-4 text-blue">File Structure</h2>
|
76 |
<ul class="list-disc ml-6 text-lg">
|
77 |
<li><code>app.py</code> — Flask backend server.</li>
|
78 |
+
<li><code>llm/agents.py</code> — Core querying and aggregation logic.</li>
|
79 |
+
<li><code>llm/model_config.json</code> — Configures models and providers.</li>
|
80 |
<li><code>templates/</code> — Contains <code>index.html</code> and <code>docs.html</code>.</li>
|
81 |
<li><code>static/</code> — Contains <code>style.css</code> and <code>script.js</code>.</li>
|
82 |
</ul>
|
83 |
</section>
|
84 |
|
85 |
<section class="mb-10">
|
86 |
+
<h2 class="text-2xl font-semibold mb-4 text-blue">Credits and License</h2>
|
87 |
+
<p class="mb-4 text-lg">
|
88 |
+
Inspired by <a href="https://github.com/togethercomputer/MoA" class="text-blue underline hover:text-purple" target="_blank">Together Computer's MoA project</a>.
|
89 |
+
</p>
|
90 |
+
<p class="mb-4 text-lg">
|
91 |
+
This project is based on the concept of collaborative AI agents.
|
92 |
+
</p>
|
93 |
+
<p class="text-lg">
|
94 |
+
Together Computer's original project is licensed under the <strong>Apache 2.0 License</strong>.
|
95 |
+
</p>
|
96 |
</section>
|
97 |
|
98 |
</div>
|
99 |
|
100 |
+
<div class="text-center mt-8 space-x-4">
|
101 |
<a href="/" class="px-6 py-2 bg-blue text-fg0 rounded hover:bg-purple transition text-lg font-semibold">← Back to Chat</a>
|
102 |
+
<a href="https://github.com/togethercomputer/MoA" target="_blank" class="px-6 py-2 bg-blue text-fg0 rounded hover:bg-purple transition text-lg font-semibold">GitHub</a>
|
103 |
</div>
|
104 |
|
105 |
<script>
|