cosine sim python code

Author: PatrickFarley

articles/ai-services/computer-vision/how-to/image-retrieval.md

@@ -8,7 +8,7 @@ manager: nitinme
 
 ms.service: azure-ai-vision
 ms.topic: how-to
-ms.date: 02/21/2023
+ms.date: 01/30/2024
 ms.author: pafarley
 ms.custom: references_regions
 ---
@@ -90,7 +90,9 @@ The API call returns a **vector** JSON object, which defines the text string's c
 
 Cosine similarity is a method for measuring the similarity of two vectors. In an image retrieval scenario, you'll compare the search query vector with each image's vector. Images that are above a certain threshold of similarity can then be returned as search results.
 
-The following example C# code calculates the cosine similarity between two vectors. It's up to you to decide what similarity threshold to use for returning images as search results.
+The following example code calculates the cosine similarity between two vectors. It's up to you to decide what similarity threshold to use for returning images as search results.
+
+#### [C#](#tab/csharp)
 
 ```csharp
 public static float GetCosineSimilarity(float[] vector1, float[] vector2)
@@ -108,6 +110,17 @@ public static float GetCosineSimilarity(float[] vector1, float[] vector2)
 }
 ```
 
+#### [Python](#tab/python)
+
+```python
+import numpy as np
+
+def cosine_similarity(vector1, vector2):
+    return np.dot(vector1, vector2) / (np.linalg.norm(vector1) * np.linalg.norm(vector2))
+```
+
+---
+
 ## Next steps
 
 [Image retrieval concepts](../concept-image-retrieval.md)