Update app.py

app.py

@@ -227,18 +227,19 @@ def StreamLLMChatResponse(prompt):
     except:
         st.write('Llama model is asleep. Starting up now on A10 - please give 5 minutes then retry as KEDA scales up from zero to activate running container(s).')
 
-def query(filename):
-    with open(filename, "rb") as f:
-        data = f.read
-    st.write('Posting request to model ' + API_URL_IE)
-    response = requests.post(API_URL_IE, headers=headers, data=data)
-    return response.json()
+#def query(filename):
+#    with open(filename, "rb") as f:
+#        data = f.read
+#    st.write('Posting request to model ' + API_URL_IE)
+#    response = requests.post(API_URL_IE, headers=headers, data=data)
+#    return response.json()
     
 # 4. Run query with payload
-#def query(payload):
-#    response = requests.post(API_URL, headers=headers, json=payload)
-#    st.markdown(response.json())
-#    return response.json()
+def query(payload):
+    st.write('Posting request to model ' + API_URL_IE)
+    response = requests.post(API_URL, headers=headers, json=payload)
+    st.markdown(response.json())
+    return response.json()
     
 def get_output(prompt):
     return query({"inputs": prompt})