Update app.py

app.py

@@ -113,6 +113,7 @@ def StreamLLMChatResponse(prompt):
         res_box = st.empty()
         collected_chunks=[]
         collected_messages=[]
+        allresults=''
         for r in stream:
             if r.token.special:
                 continue
@@ -126,9 +127,10 @@ def StreamLLMChatResponse(prompt):
                 if len(r.token.text) > 0:
                     result="".join(report).strip()
                     res_box.markdown(f'*{result}*')
+                    allresults=allresults+result
             except:
                 st.write(' ')
-        return "".join(report).strip().
+        return allresults
     except:
         st.write('DromeLlama is asleep. Starting up now on A10 - please give 5 minutes then retry as KEDA scales up from zero to activate running container(s).')