Update app.py

app.py

@@ -1,16 +1,20 @@
 import ast
 import json
+import base64
 import spaces
 import requests
 import numpy as np
 import gradio as gr
 from PIL import Image
 from io import BytesIO
+import face_recognition
 from turtle import title
 from openai import OpenAI
 from collections import Counter
 from transformers import pipeline
 
+
+    
 client = OpenAI()
 
 pipe = pipeline("zero-shot-image-classification", model="patrickjohncyh/fashion-clip")
@@ -37,6 +41,7 @@ def shot(input, category):
     subColour,mainColour,score = get_colour(ast.literal_eval(str(input)),category)
     common_result = get_predicted_attributes(ast.literal_eval(str(input)),category)
     openai_parsed_response = get_openAI_tags(ast.literal_eval(str(input)))
+    face_embeddings = get_face_embeddings(ast.literal_eval(str(input)))
     return {
         "colors":{
             "main":mainColour,
@@ -44,7 +49,8 @@ def shot(input, category):
             "score":round(score*100,2)
         }, 
         "attributes":common_result,
-        "image_mapping":openai_parsed_response
+        "image_mapping":openai_parsed_response,
+        "face_embeddings":face_embeddings
     }
 
 
@@ -153,6 +159,43 @@ def get_openAI_tags(image_urls):
     response = json.loads(openai_response.choices[0].message.content)
     return response
 
+
+@spaces.GPU
+def get_face_embeddings(image_urls):
+    # Initialize a dictionary to store the face encodings or errors
+    results = {}
+
+    # Loop through each image URL
+    for index, url in enumerate(image_urls):
+        try:
+            # Try to download the image from the URL
+            response = requests.get(url)
+            # Raise an exception if the response is not successful
+            response.raise_for_status()
+
+            # Load the image using face_recognition
+            image = face_recognition.load_image_file(BytesIO(response.content))
+
+            # Get the face encodings for all faces in the image
+            face_encodings = face_recognition.face_encodings(image)
+
+            # If no faces are detected, store an empty list
+            if not face_encodings:
+                results[index] = []
+            else:
+                # Otherwise, store the first face encoding as a list
+                results[index] = face_encodings[0].tolist()
+        except Exception as e:
+            # If any error occurs during the download or processing, store the error message
+            results[index] = f"Error processing image: {str(e)}"
+
+    return results
+
+
+
+
+
+
 # Define the Gradio interface with the updated components
 iface = gr.Interface(
     fn=shot,