Update app.py

app.py

@@ -23,17 +23,22 @@ def process_message(message, history, analysis_prompt, rethinking_prompt, refine
         conversation_history.append(f"User: {h[0]}\nEcho-Refraction: {h[1]}")
     
     context = "\n".join(conversation_history)
+    full_response = ""
     
     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")
-    yield from stream_words("Analysis: ", gpt4o_response)
+    for chunk in stream_words("Analysis: ", gpt4o_response):
+        full_response = chunk
+        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")
-    yield from stream_words("\n\nRethinking: ", llama_response)
+    for chunk in stream_words("\n\nRethinking: ", llama_response):
+        full_response += chunk
+        yield full_response
 
     if "<error>" in " ".join(llama_response):
         return
@@ -41,9 +46,12 @@ 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")
-        yield from stream_words("\n\nFinal Response: ", final_response)
+        for chunk in stream_words("\n\nFinal Response: ", final_response):
+            full_response += chunk
+            yield full_response
     else:
-        yield "\n\nFinal Response: The initial response is satisfactory and no further refinement is needed."
+        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
@@ -53,12 +61,8 @@ def stream_words(prefix, words):
         yield response
 
 def respond(message, history, analysis_prompt, rethinking_prompt, refinement_prompt):
-    full_response = ""
     for chunk in process_message(message, history, analysis_prompt, rethinking_prompt, refinement_prompt):
-        full_response = chunk
-        yield full_response
-    
-    return full_response
+        yield chunk
 
 # (The rest of the code remains the same: analysis_prompt, rethinking_prompt, refinement_prompt, and the Gradio
 # (Previous code remains the same)