Update app.py

app.py

@@ -27,8 +27,10 @@ def process_message(message, history, analysis_prompt, rethinking_prompt, refine
     
     gpt4o_prompt = f"{analysis_prompt}\n\nConversation history:\n{context}\n\nUser query: {message}\n\nPlease analyze this query and respond accordingly."
     gpt4o_response = get_llm_response(gpt4o_prompt, "gpt-4o-mini")
-    for chunk in stream_words("Analysis: ", gpt4o_response):
-        full_response = chunk
+    full_response += "Analysis:\n"
+    for word in gpt4o_response:
+        full_response += word + " "
+        time.sleep(0.1)
         yield full_response
 
     if "<error>" in " ".join(gpt4o_response):
@@ -36,8 +38,10 @@ def process_message(message, history, analysis_prompt, rethinking_prompt, refine
 
     llama_prompt = f"{rethinking_prompt}\n\nConversation history:\n{context}\n\nOriginal user query: {message}\n\nInitial response: {' '.join(gpt4o_response)}\n\nPlease review and suggest improvements or confirm if satisfactory."
     llama_response = get_llm_response(llama_prompt, "gpt-4o-mini")
-    for chunk in stream_words("\n\nRethinking: ", llama_response):
-        full_response += chunk
+    full_response += "\n\nRethinking:\n"
+    for word in llama_response:
+        full_response += word + " "
+        time.sleep(0.1)
         yield full_response
 
     if "<error>" in " ".join(llama_response):
@@ -46,20 +50,15 @@ def process_message(message, history, analysis_prompt, rethinking_prompt, refine
     if "done" not in " ".join(llama_response).lower():
         final_gpt4o_prompt = f"{refinement_prompt}\n\nConversation history:\n{context}\n\nOriginal user query: {message}\n\nInitial response: {' '.join(gpt4o_response)}\n\nSuggestion: {' '.join(llama_response)}\n\nPlease provide a final response considering the suggestion."
         final_response = get_llm_response(final_gpt4o_prompt, "gpt-4o-mini")
-        for chunk in stream_words("\n\nFinal Response: ", final_response):
-            full_response += chunk
+        full_response += "\n\nFinal Response:\n"
+        for word in final_response:
+            full_response += word + " "
+            time.sleep(0.1)
             yield full_response
     else:
         full_response += "\n\nFinal Response: The initial response is satisfactory and no further refinement is needed."
         yield full_response
 
-def stream_words(prefix, words):
-    response = prefix
-    for word in words:
-        response += word + " "
-        time.sleep(0.1)  # Adjust this value to control the speed of word streaming
-        yield response
-
 def respond(message, history, analysis_prompt, rethinking_prompt, refinement_prompt):
     for chunk in process_message(message, history, analysis_prompt, rethinking_prompt, refinement_prompt):
         yield chunk