Update app.py

Fix json return error

app.py

@@ -40,7 +40,7 @@ def predict(message, chatbot):
                       "temperature":0.9,}
     }
 
-    response = requests.post(api_url, headers=headers, data=json.dumps(data), auth=('hf', hf_token), stream=True)
+    response = requests.post(api_url, headers=headers, data=json.dumps(data), auth=('Bearer', hf_token), stream=True)
     
     partial_message = ""
     for line in response.iter_lines():
@@ -53,13 +53,14 @@ def predict(message, chatbot):
                 json_line = decoded_line[5:]  # Exclude the first 5 characters ('data:')
             else:
                 gr.Warning(f"This line does not start with 'data:': {decoded_line}")
+                json_line = decoded_line 
                 continue
 
             # Load as JSON
             try:
-                json_obj = json.loads(json_line)
-                if 'token' in json_obj:
-                    partial_message = partial_message + json_obj['token']['text'] 
+                json_obj = json.loads(json_line)[0]
+                if 'generated_text' in json_obj:
+                    partial_message = partial_message + json_obj['generated_text']#['token']['text']
                     yield partial_message
                 elif 'error' in json_obj:
                     yield json_obj['error'] + '. Please refresh and try again with an appropriate smaller input prompt.'
@@ -73,4 +74,4 @@ def predict(message, chatbot):
                 gr.Warning(f"KeyError: {e} occurred for JSON object: {json_obj}")
                 continue
 
-gr.ChatInterface(predict, title=title, description=description, css=css, examples=examples, cache_examples=True).queue(concurrency_count=75).launch(debug=True) 
+gr.ChatInterface(predict, title=title, description=description, css=css, examples=examples, cache_examples=True).queue(concurrency_count=75).launch()