Update app.py

app.py

@@ -27,26 +27,22 @@ 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")
-    full_response += "<analyzing>\n"
+    full_response += "Analysis:\n"
     for word in gpt4o_response:
         full_response += word + " "
         time.sleep(0.1)
         yield full_response
-    full_response += "\n</analyzing>"
-    yield full_response
 
     if "<error>" in " ".join(gpt4o_response):
         return
 
     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")
-    full_response += "\n\n<rethinking>\n"
+    full_response += "\n\nRethinking:\n"
     for word in llama_response:
         full_response += word + " "
         time.sleep(0.1)
         yield full_response
-    full_response += "\n</rethinking>"
-    yield full_response
 
     if "<error>" in " ".join(llama_response):
         return
@@ -54,21 +50,24 @@ 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")
-        full_response += "\n\n<output>\n"
+        full_response += "\n\nFinal Response:\n"
         for word in final_response:
             full_response += word + " "
             time.sleep(0.1)
             yield full_response
-        full_response += "\n</output>"
-        yield full_response
     else:
-        full_response += "\n\n<output>The initial response is satisfactory and no further refinement is needed.</output>"
+        full_response += "\n\nFinal Response: The initial response is satisfactory and no further refinement is needed."
         yield full_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
 
+# (The rest of the code remains the same: analysis_prompt, rethinking_prompt, refinement_prompt, and the Gradio interface setup)
+
+if __name__ == "__main__":
+    demo.launch()
+
 analysis_prompt = """
 You are Echo-Refraction, an AI assistant tasked with analyzing user queries. Your role is to:
 1. Carefully examine the user's input for clarity, completeness, and potential ambiguities.