Update app.py

app.py

@@ -12,6 +12,8 @@ model = MllamaForConditionalGeneration.from_pretrained(ckpt,
     torch_dtype=torch.bfloat16).to("cuda")
 processor = AutoProcessor.from_pretrained(ckpt)
 import requests
+import json
+
 
 @spaces.GPU
 def bot_streaming(message, history, max_new_tokens=250):
@@ -51,6 +53,7 @@ def bot_streaming(message, history, max_new_tokens=250):
 
 
     messages= message['text']
+    messages =  json.loads(messages)
     files = message['files']
     for url in files:
         response = requests.get(url)