Update app.py

app.py

@@ -1,63 +1,112 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+from duckduckgo_search import DDGS
+from collections import deque
+import time
+import random
 
+def get_llm_response(prompt, model, max_retries=3):
+    for attempt in range(max_retries):
+        try:
+            return DDGS().chat(prompt, model=model)
+        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>"
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def process_message(message, history, analysis_prompt, rethinking_prompt, refinement_prompt):
+    conversation_history = deque(maxlen=5)
+    for h in history:
+        conversation_history.append(f"User: {h[0]}\nEcho-Refraction: {h[1]}")
+    
+    context = "\n".join(conversation_history)
+    
+    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}"
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    if "<error>" in gpt4o_response:
+        return
 
-    messages.append({"role": "user", "content": message})
+    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_response = get_llm_response(llama_prompt, "gpt-4o-mini")
+    yield f"Analysis: {gpt4o_response}\nRethinking: {llama_response}"
 
-    response = ""
+    if "<error>" in llama_response:
+        return gpt4o_response
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    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."
+        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
+    else:
+        return gpt4o_response
 
-        response += token
+def respond(message, history, analysis_prompt, rethinking_prompt, refinement_prompt):
+    response = ""
+    for chunk in process_message(message, history, analysis_prompt, rethinking_prompt, refinement_prompt):
+        response = chunk
         yield response
+    
+    # Extract the final response from the last chunk
+    final_response = response.split("Final Response: ")[-1] if "Final Response: " in response else response
+    return final_response
 
+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.
+2. Identify if the query needs refinement or additional information.
+3. If refinement is needed, suggest specific improvements or ask clarifying questions.
+4. If the query is clear, respond with "Query is clear and ready for processing."
+5. Provide a brief explanation of your analysis in all cases.
+Enclose your response in <analyzing> tags.
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+
+rethinking_prompt = """
+You are Echo-Refraction, an advanced AI model responsible for critically evaluating and improving responses. Your task is to:
+1. Carefully review the original user query and the initial response.
+2. Analyze the response for accuracy, relevance, completeness, and potential improvements.
+3. Consider perspectives or approaches that might enhance the response.
+4. If you identify areas for improvement:
+   a. Clearly explain what aspects need refinement and why.
+   b. Provide specific suggestions for how the response could be enhanced.
+   c. If necessary, propose additional information or context that could be included.
+5. If the initial response is satisfactory and you have no suggestions for improvement, respond with "Done."
+Enclose your response in <rethinking> tags.
 """
+
+refinement_prompt = """
+You are Echo-Refraction, an AI assistant tasked with providing a final, refined response to the user. Your role is to:
+1. Review the original user query, your initial response, and the suggestions provided.
+2. Consider the feedback and suggestions for improvement.
+3. Integrate the suggested improvements into your response, ensuring that:
+   a. The information is accurate and up-to-date.
+   b. The response is comprehensive and addresses all aspects of the user's query.
+   c. The language is clear, concise, and appropriate for the user's level of understanding.
+4. If you disagree with any suggestions, provide a brief explanation of why you chose not to incorporate them.
+5. Deliver a final response that represents the best possible answer to the user's query.
+Enclose your response in <output> tags.
+"""
+
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        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.",
+    examples=[
+        ["How many 'r' are there in the word 'strawberry'"],
+        ["Explain the concept of quantum entanglement."],
+        ["How does photosynthesis work?"],
+    ],
+    cache_examples=False,
 )
 
-
 if __name__ == "__main__":
     demo.launch()