fixes

Author: santiagxf

articles/machine-learning/reference-model-inference-embeddings.md

@@ -183,7 +183,7 @@ Represents an image generated.
 
 | Name      | Type                                | Description                                                                                      |
 | --------- | ----------------------------------- | ------------------------------------------------------------------------------------------------ |
-| embedding | number\[\]                          | The embedding vector, which is a list of floats. The length of vector depends on the model used. |
+| embedding | number\[\]                          | The embedding vector. The length of vector depends on the model used and the type depends on the `encoding_format` used. |
 | index     | integer                             | The index of the embedding in the list of embeddings.                                            |
 | object    | [EmbeddingObject](#embeddingobject) | The object type, which is always "embedding".                                                    |
 
@@ -206,9 +206,9 @@ The type of the input. Either `text`, `query`, or `document`. Returns a 422 erro
 
 | Name     | Type   | Description |
 | -------- | ------ | ----------- |
-| document | string |             |
-| query    | string |             |
-| text     | string |             |
+| document | string | Indicates the input represents a document that is stored in a vector database.            |
+| query    | string | Indicates the input represents a search queries to find the most relevant documents in your vector database. |
+| text     | string | Indicates the input is a general text input. |
 
 
 ### EmbeddingObject

articles/machine-learning/reference-model-inference-images-embeddings.md

@@ -87,7 +87,7 @@ POST /images/embeddings?api-version=2024-04-01-preview
   "input": [
     {
       "text": "A nice picture of a cat",
-      "image": "qwertyuiopasdfghjklqwrtyuio"
+      "image": "data:image/jpeg;base64,iVBORw0KG..."
     }
   ],
   "encoding_format": "float",
@@ -242,7 +242,7 @@ Represents an image with optional text.
 
 | Name | Type | Description |
 | --- | --- | --- |
-| image | string | The input image, in PNG format. |
+| image | string | The input image encoded in `base64` string as a data URL. Example: `data:image/{format};base64,{data}`. |
 | text | string | Optional. The text input to feed into the model (like DINO, CLIP). Returns a 422 error if the model doesn't support the value or parameter. |