Update app.py

app.py

@@ -9,6 +9,7 @@ from llama_index import ServiceContext, VectorStoreIndex, Document
 from llama_index.memory import ChatMemoryBuffer
 import os
 import base64
+import tempfile
 
 
 # Function to get image caption via Kosmos2 (as in your original code)
@@ -20,14 +21,14 @@ def get_image_caption(image_array):
     # Convert the numpy array to a PIL Image
     image = Image.fromarray(image_array.astype('uint8'), 'RGB')
 
-    # Save the PIL Image to a BytesIO object
-    buffered = BytesIO()
-    image.save(buffered, format="JPEG")
-    img_base64 = base64.b64encode(buffered.getvalue()).decode()
+    # Save the PIL Image to a temporary file
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".jpeg") as tmp_file:
+        image.save(tmp_file, format="JPEG")
+        tmp_file_path = tmp_file.name
 
     # Prepare the input data for the model
     input_data = {
-        "image": img_base64,
+        "image": open(tmp_file_path, "rb"),
         "description_type": "Brief"
     }