Adding VoyageAI embeddings documentation

Author: fzowl

en/embedding.html

@@ -553,6 +553,18 @@ <h4 id="voyageai-embedder-models">VoyageAI embedder models</h4>
     <li>voyage-multilingual-2 produces <code>tensor&lt;float&gt;(x[1024])</code> - supports 100+ languages</li>
 </ul>
 
+<p>Contextual model:</p>
+<ul>
+    <li><strong>voyage-context-3</strong> produces <code>tensor&lt;float&gt;(x[1024])</code> (configurable: 256, 512, 1024, 2048) -
+        contextualized embeddings for document chunks with surrounding context awareness</li>
+</ul>
+
+<p>Multimodal model (preview):</p>
+<ul>
+    <li><strong>voyage-multimodal-3.5</strong> produces <code>tensor&lt;float&gt;(x[1024])</code> (configurable: 256, 512, 1024, 2048) -
+        multimodal embeddings for text, images, and video in a shared vector space</li>
+</ul>
+
 <h4 id="voyageai-input-types">Input type detection</h4>
 <p>VoyageAI models distinguish between query and document embeddings for improved retrieval quality.
 The embedder automatically detects the context and sets the appropriate input type:</p>

en/reference/embedding-reference.html

@@ -540,6 +540,8 @@ <h3 id="voyageai-embedder-reference-config">VoyageAI embedder reference config</
           <li><code>voyage-finance-2</code> (1024 dims) - Financial documents</li>
           <li><code>voyage-law-2</code> (1024 dims) - Legal documents</li>
           <li><code>voyage-multilingual-2</code> (1024 dims) - Multilingual support</li>
+          <li><code>voyage-context-3</code> (1024 dims, configurable: 256/512/1024/2048) - Contextualized document chunk embeddings</li>
+          <li><code>voyage-multimodal-3.5</code> (1024 dims, configurable: 256/512/1024/2048) - Multimodal embeddings (text, images, video) [preview]</li>
         </ul>
       </td>
       <td>string</td>