Update app.py

app.py

@@ -7,14 +7,15 @@ import random
 def get_llm_response(prompt, model, max_retries=3):
     for attempt in range(max_retries):
         try:
-            return DDGS().chat(prompt, model=model)
+            response = DDGS().chat(prompt, model=model)
+            return response.split()  # Split the response into words
         except Exception as e:
             if attempt < max_retries - 1:
                 print(f"Error occurred: {e}. Retrying in {2**attempt} seconds...")
                 time.sleep(2**attempt + random.random())
             else:
                 print(f"Max retries reached. Error: {e}")
-                return f"<error>Unable to get response from {model} after {max_retries} attempts.</error>"
+                return f"<error>Unable to get response from {model} after {max_retries} attempts.</error>".split()
 
 def process_message(message, history, analysis_prompt, rethinking_prompt, refinement_prompt):
     conversation_history = deque(maxlen=5)
@@ -25,25 +26,32 @@ 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")
-    yield f"Analysis: {gpt4o_response}"
+    yield from stream_words("Analysis: ", gpt4o_response)
 
-    if "<error>" in gpt4o_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: {gpt4o_response}\n\nPlease review and suggest improvements or confirm if satisfactory."
+    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 f"Analysis: {gpt4o_response}\nRethinking: {llama_response}"
+    yield from stream_words("\nRethinking: ", llama_response)
 
-    if "<error>" in llama_response:
-        return gpt4o_response
+    if "<error>" in " ".join(llama_response):
+        return " ".join(gpt4o_response)
 
-    if "done" not in llama_response.lower():
-        final_gpt4o_prompt = f"{refinement_prompt}\n\nConversation history:\n{context}\n\nOriginal user query: {message}\n\nInitial response: {gpt4o_response}\n\nSuggestion: {llama_response}\n\nPlease provide a final response considering the suggestion."
+    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 f"Analysis: {gpt4o_response}\nRethinking: {llama_response}\nFinal Response: {final_response}"
-        return final_response
+        yield from stream_words("\nFinal Response: ", final_response)
+        return " ".join(final_response)
     else:
-        return gpt4o_response
+        return " ".join(gpt4o_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):
     response = ""
@@ -52,9 +60,12 @@ def respond(message, history, analysis_prompt, rethinking_prompt, refinement_pro
         yield response
     
     # Extract the final response from the last chunk
-    final_response = response.split("Final Response: ")[-1] if "Final Response: " in response else response
+    final_response = response.split("Final Response: ")[-1] if "Final Response: " in response else response.split("Analysis: ")[-1]
     return final_response
 
+# (The rest of the code remains the same: analysis_prompt, rethinking_prompt, refinement_prompt, and the Gradio
+# (Previous code remains the same)
+
 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.
@@ -93,13 +104,8 @@ Enclose your response in <output> tags.
 
 demo = gr.ChatInterface(
     respond,
-    additional_inputs=[
-        gr.Textbox(value=analysis_prompt, label="Analysis Prompt", lines=10),
-        gr.Textbox(value=rethinking_prompt, label="Rethinking Prompt", lines=10),
-        gr.Textbox(value=refinement_prompt, label="Refinement Prompt", lines=10),
-    ],
-    title="Echo-Refraction AI Assistant",
-    description="Chat with Echo-Refraction, an AI assistant that analyzes, rethinks, and refines responses.",
+    title="Open-O1",
+    description="Chat with Open-O1, an AI assistant that analyzes, rethinks, and refines responses. Watch as it streams its thought process word by word!",
     examples=[
         ["How many 'r' are there in the word 'strawberry'"],
         ["Explain the concept of quantum entanglement."],