import streamlit as st
import groq
import os
import json
import time

client = groq.Groq()

def make_api_call(messages, max_tokens, is_final_answer=False):
    for attempt in range(3):
        try:
            response = client.chat.completions.create(
                model="llama-3.1-70b-versatile",
                messages=messages,
                max_tokens=max_tokens,
                temperature=0.2,
                response_format={"type": "json_object"}
            )
            return json.loads(response.choices[0].message.content)
        except Exception as e:
            if attempt == 2:
                if is_final_answer:
                    return {"title": "Error", "content": f"Failed to generate final answer after 3 attempts. Error: {str(e)}"}
                else:
                    return {"title": "Error", "content": f"Failed to generate step after 3 attempts. Error: {str(e)}", "next_action": "final_answer"}
            time.sleep(1)  # Wait for 1 second before retrying

def generate_response(prompt):
    messages = [
        {"role": "system", "content": """You are an expert AI assistant with advanced reasoning capabilities. Your task is to provide detailed, step-by-step explanations of your thought process. For each step:

1. Provide a clear, concise title describing the current reasoning phase.
2. Elaborate on your thought process in the content section.
3. Decide whether to continue reasoning or provide a final answer.

Response Format:
Use JSON with keys: 'title', 'content', 'next_action' (values: 'continue' or 'final_answer')

Key Instructions:
- Employ at least 5 distinct reasoning steps.
- Acknowledge your limitations as an AI and explicitly state what you can and cannot do.
- Actively explore and evaluate alternative answers or approaches.
- Critically assess your own reasoning; identify potential flaws or biases.
- When re-examining, employ a fundamentally different approach or perspective.
- Utilize at least 3 diverse methods to derive or verify your answer.
- Incorporate relevant domain knowledge and best practices in your reasoning.
- Quantify certainty levels for each step and the final conclusion when applicable.
- Consider potential edge cases or exceptions to your reasoning.
- Provide clear justifications for eliminating alternative hypotheses.


Example of a valid JSON response:
```json
{
    "title": "Initial Problem Analysis",
    "content": "To approach this problem effectively, I'll first break down the given information into key components. This involves identifying...[detailed explanation]... By structuring the problem this way, we can systematically address each aspect.",
    "next_action": "continue"
}```
"""},
        {"role": "user", "content": prompt},
        {"role": "assistant", "content": "Thank you! I will now think step by step following my instructions, starting at the beginning after decomposing the problem."}
    ]
    
    steps = []
    step_count = 1
    total_thinking_time = 0
    
    while True:
        start_time = time.time()
        step_data = make_api_call(messages, 300)
        end_time = time.time()
        thinking_time = end_time - start_time
        total_thinking_time += thinking_time
        
        steps.append((f"Step {step_count}: {step_data['title']}", step_data['content'], thinking_time))
        
        messages.append({"role": "assistant", "content": json.dumps(step_data)})
        
        if step_data['next_action'] == 'final_answer':
            break
        
        step_count += 1

        # Yield after each step for Streamlit to update
        yield steps, None  # We're not yielding the total time until the end

    # Generate final answer
    messages.append({"role": "user", "content": "Please provide the final answer based on your reasoning above."})
    
    start_time = time.time()
    final_data = make_api_call(messages, 200, is_final_answer=True)
    end_time = time.time()
    thinking_time = end_time - start_time
    total_thinking_time += thinking_time
    
    steps.append(("Final Answer", final_data['content'], thinking_time))

    yield steps, total_thinking_time

def main():
    st.set_page_config(page_title="g1 prototype", page_icon="🧠", layout="wide")
    
    st.title("g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains")
    
    st.markdown("""
    This is an early prototype of using prompting to create o1-like reasoning chains to improve output accuracy. It is not perfect and accuracy has yet to be formally evaluated. It is powered by Groq so that the reasoning step is fast!
                
    Forked from [bklieger-groq](https://github.com/bklieger-groq)
    Open source [repository here](https://github.com/win4r/o1)
    """)
    
    # Text input for user query
    user_query = st.text_input("Enter your query:", placeholder="e.g., How many 'R's are in the word strawberry?")
    
    if user_query:
        st.write("Generating response...")
        
        # Create empty elements to hold the generated text and total time
        response_container = st.empty()
        time_container = st.empty()
        
        # Generate and display the response
        for steps, total_thinking_time in generate_response(user_query):
            with response_container.container():
                for i, (title, content, thinking_time) in enumerate(steps):
                    if title.startswith("Final Answer"):
                        st.markdown(f"### {title}")
                        st.markdown(content.replace('\n', '<br>'), unsafe_allow_html=True)
                    else:
                        with st.expander(title, expanded=True):
                            st.markdown(content.replace('\n', '<br>'), unsafe_allow_html=True)
            
            # Only show total time when it's available at the end
            if total_thinking_time is not None:
                time_container.markdown(f"**Total thinking time: {total_thinking_time:.2f} seconds**")

if __name__ == "__main__":
    main()