Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 from PIL import Image
 from inference.main import MultiModalPhi2
+import base64
 
 messages = []
 
@@ -51,11 +52,15 @@ def run(history, text, image, audio_upload, audio_mic):
     print("image", image)
     print("audio", audio)
 
-    if image is not None:
-        image = Image.open(image)
-    outputs = multimodal_phi2(text, audio, image)
-    # outputs = ""
+    try:
+        if image is not None:
+            image_data = base64.b64decode(image.split(",")[1])
+            image = Image.open(BytesIO(image_data))
+    except Exception as e:
+        print(f"Error decoding image: {e}")
+        image = None
 
+    outputs = multimodal_phi2(text, audio, image)
     history.append((None, outputs.title()))
     return history, None, None, None, None