fix

Author: santiagxf

articles/ai-foundry/model-inference/includes/use-chat-multi-modal/rest.md

@@ -145,8 +145,8 @@ The following example sends audio content encoded in `base64` data in the chat h
                     "text": "Please translate this audio snippet to spanish."
                 },
                 {
-                    "type": "audio_input",
-                    "audio_input": {
+                    "type": "input_audio",
+                    "input_audio": {
                         "data": "0xABCDFGHIJKLMNOPQRSTUVWXYZ...",
                         "format": "mp3"
                     }

articles/ai-foundry/model-inference/includes/use-image-generations/rest.md

@@ -0,0 +1,150 @@
+---
+title: How to generate image embeddings with Azure AI model inference
+titleSuffix: Azure AI Foundry
+description: Learn how to generate embeddings with Azure AI model inference
+manager: scottpolly
+author: msakande
+reviewer: santiagxf
+ms.service: azure-ai-model-inference
+ms.topic: how-to
+ms.date: 01/22/2025
+ms.author: mopeakande
+ms.reviewer: fasantia
+ms.custom: generated
+zone_pivot_groups: azure-ai-inference-samples
+---
+
+[!INCLUDE [Feature preview](~/reusable-content/ce-skilling/azure/includes/ai-studio/includes/feature-preview.md)]
+
+This article explains how to use image embeddings API with models deployed to Azure AI model inference in Azure AI Foundry.
+
+## Prerequisites
+
+To use embedding models in your application, you need:
+
+[!INCLUDE [how-to-prerequisites](../how-to-prerequisites.md)]
+
+* An image embeddings model deployment. If you don't have one read [Add and configure models to Azure AI services](../../how-to/create-model-deployments.md) to add an embeddings model to your resource.
+
+  * This example uses `Cohere-embed-v3-english` from Cohere.
+
+## Use image embeddings
+
+To use the text embeddings, use the route `/images/embeddings` appended to your base URL along with your credential indicated in `api-key`. `Authorization` header is also supported with the format `Bearer <key>`.
+
+```http
+POST https://<resource>.services.ai.azure.com/models/images/embeddings?api-version=2024-05-01-preview
+Content-Type: application/json
+api-key: <key>
+```
+
+If you configured the resource with **Microsoft Entra ID** support, pass you token in the `Authorization` header:
+
+```http
+POST https://<resource>.services.ai.azure.com/models/images/embeddings?api-version=2024-05-01-preview
+Content-Type: application/json
+Authorization: Bearer <token>
+```
+
+### Create embeddings
+
+To create image embeddings, you need to pass the image data as part of your request. Image data should be in PNG format and encoded as base64.
+
+```json
+{
+    "model": "Cohere-embed-v3-english",
+    "input": [
+        {
+            "image": "data:image/png;base64,iVBORw0KGgoAAAANSUh..."
+        }
+    ]
+}
+```
+
+> [!TIP]
+> When creating a request, take into account the token's input limit for the model. If you need to embed larger portions of text, you would need a chunking strategy.
+
+The response is as follows, where you can see the model's usage statistics:
+
+
+```json
+{
+    "id": "0ab1234c-d5e6-7fgh-i890-j1234k123456",
+    "object": "list",
+    "data": [
+        {
+            "index": 0,
+            "object": "embedding",
+            "embedding": [
+                0.017196655,
+                // ...
+                -0.000687122,
+                -0.025054932,
+                -0.015777588
+            ]
+        }
+    ],
+    "model": "Cohere-embed-v3-english",
+    "usage": {
+        "prompt_tokens": 9,
+        "completion_tokens": 0,
+        "total_tokens": 9
+    }
+}
+```
+
+> [!IMPORTANT]
+> Computing embeddings in batches may not be supported for all the models. For example, for `Cohere-embed-v3-english` model, you need to send one image at a time.
+
+#### Embedding images and text pairs
+
+Some models can generate embeddings from images and text pairs. In this case, you can use the `image` and `text` fields in the request to pass the image and text to the model. The following example shows how to create embeddings for images and text pairs:
+
+
+```json
+{
+    "model": "Cohere-embed-v3-english",
+    "input": [
+        {
+            "image": "data:image/png;base64,iVBORw0KGgoAAAANSUh...",
+            "text": "A photo of a cat"
+        }
+    ]
+}
+```
+
+#### Create different types of embeddings
+
+Some models can generate multiple embeddings for the same input depending on how you plan to use them. This capability allows you to retrieve more accurate embeddings for RAG patterns. 
+
+The following example shows how to create embeddings that are used to create an embedding for a document that will be stored in a vector database:
+
+
+```json
+{
+    "model": "Cohere-embed-v3-english",
+    "input": [
+        {
+            "image": "data:image/png;base64,iVBORw0KGgoAAAANSUh..."
+        }
+    ],
+    "input_type": "document"
+}
+```
+
+When you work on a query to retrieve such a document, you can use the following code snippet to create the embeddings for the query and maximize the retrieval performance.
+
+
+```json
+{
+    "model": "Cohere-embed-v3-english",
+    "input": [
+        {
+            "image": "data:image/png;base64,iVBORw0KGgoAAAANSUh..."
+        }
+    ],
+    "input_type": "query"
+}
+```
+
+Notice that not all the embedding models support indicating the input type in the request and on those cases a 422 error is returned.