app.py

# ref: https://github.com/kram254/Mixture-of-Agents-running-on-Groq/tree/main
import streamlit as st
import json
import asyncio
from typing import Union, Iterable, AsyncIterable
from moa.agent import MOAgent
from moa.agent.moa import ResponseChunk
from streamlit_ace import st_ace
import copy

# Default configuration
default_config = {
    "main_model": "llama3-70b-8192",
    "cycles": 3,
    "layer_agent_config": {}
}

layer_agent_config_def = {
    "layer_agent_1": {
        "system_prompt": "Think through your response step by step. {helper_response}",
        "model_name": "llama3-8b-8192"
    },
    "layer_agent_2": {
        "system_prompt": "Respond with a thought and then your response to the question. {helper_response}",
        "model_name": "gemma-7b-it",
        "temperature": 0.7
    },
    "layer_agent_3": {
        "system_prompt": "You are an expert at logic and reasoning. Always take a logical approach to the answer. {helper_response}",
        "model_name": "llama3-8b-8192"
    },
}

# Recommended configuration
rec_config = {
    "main_model": "llama3-70b-8192",
    "cycles": 2,
    "layer_agent_config": {}
}

layer_agent_config_rec = {
    "layer_agent_1": {
        "system_prompt": "Think through your response step by step. {helper_response}",
        "model_name": "llama3-8b-8192",
        "temperature": 0.1
    },
    "layer_agent_2": {
        "system_prompt": "Respond with a thought and then your response to the question. {helper_response}",
        "model_name": "llama3-8b-8192",
        "temperature": 0.2
    },
    "layer_agent_3": {
        "system_prompt": "You are an expert at logic and reasoning. Always take a logical approach to the answer. {helper_response}",
        "model_name": "llama3-8b-8192",
        "temperature": 0.4
    },
    "layer_agent_4": {
        "system_prompt": "You are an expert planner agent. Create a plan for how to answer the human's query. {helper_response}",
        "model_name": "mixtral-8x7b-32768",
        "temperature": 0.5
    },
}

# Unified streaming function to handle async and sync responses
async def stream_or_async_response(messages: Union[Iterable[ResponseChunk], AsyncIterable[ResponseChunk]]):
    layer_outputs = {}

    async def process_message(message):
        if message['response_type'] == 'intermediate':
            layer = message['metadata']['layer']
            if layer not in layer_outputs:
                layer_outputs[layer] = []
            layer_outputs[layer].append(message['delta'])
        else:
            for layer, outputs in layer_outputs.items():
                st.write(f"Layer {layer}")
                cols = st.columns(len(outputs))
                for i, output in enumerate(outputs):
                    with cols[i]:
                        st.expander(label=f"Agent {i+1}", expanded=False).write(output)

            layer_outputs.clear()
            yield message['delta']

    if isinstance(messages, AsyncIterable):
        # Process asynchronous messages
        async for message in messages:
            await process_message(message)
    else:
        # Process synchronous messages
        for message in messages:
            await process_message(message)

# Set up the MOAgent
def set_moa_agent(
    main_model: str = default_config['main_model'],
    cycles: int = default_config['cycles'],
    layer_agent_config: dict[dict[str, any]] = copy.deepcopy(layer_agent_config_def),
    main_model_temperature: float = 0.1,
    override: bool = False
):
    if override or ("main_model" not in st.session_state):
        st.session_state.main_model = main_model

    if override or ("cycles" not in st.session_state):
        st.session_state.cycles = cycles

    if override or ("layer_agent_config" not in st.session_state):
        st.session_state.layer_agent_config = layer_agent_config

    if override or ("main_temp" not in st.session_state):
        st.session_state.main_temp = main_model_temperature

    cls_ly_conf = copy.deepcopy(st.session_state.layer_agent_config)

    if override or ("moa_agent" not in st.session_state):
        st.session_state.moa_agent = MOAgent.from_config(
            main_model=st.session_state.main_model,
            cycles=st.session_state.cycles,
            layer_agent_config=cls_ly_conf,
            temperature=st.session_state.main_temp
        )

    del cls_ly_conf
    del layer_agent_config

# Streamlit app layout
st.set_page_config(
    page_title="Mixture of Agents",
    menu_items={
        'About': "## Groq Mixture-Of-Agents \n Powered by [Groq](https://groq.com)"
    },
    layout="wide"
)
valid_model_names = [
    'llama3-70b-8192',
    'llama3-8b-8192',
    'gemma-7b-it',
    'gemma2-9b-it',
    'mixtral-8x7b-32768'
]

st.markdown("<a href='https://groq.com'><img src='app/static/banner.png' width='500'></a>", unsafe_allow_html=True)
st.write("---")

# Initialize session state
if "messages" not in st.session_state:
    st.session_state.messages = []

set_moa_agent()

# Sidebar for configuration
with st.sidebar:
    st.title("MOA Configuration")
    with st.form("Agent Configuration", border=False):
        if st.form_submit_button("Use Recommended Config"):
            try:
                set_moa_agent(
                    main_model=rec_config['main_model'],
                    cycles=rec_config['cycles'],
                    layer_agent_config=layer_agent_config_rec,
                    override=True
                )
                st.session_state.messages = []
                st.success("Configuration updated successfully!")
            except Exception as e:
                st.error(f"Error updating configuration: {str(e)}")

        # Main model selection
        new_main_model = st.selectbox(
            "Select Main Model",
            options=valid_model_names,
            index=valid_model_names.index(st.session_state.main_model)
        )

        # Cycles input
        new_cycles = st.number_input(
            "Number of Layers",
            min_value=1,
            max_value=10,
            value=st.session_state.cycles
        )

        # Main Model Temperature
        main_temperature = st.number_input(
            label="Main Model Temperature",
            value=0.1,
            min_value=0.0,
            max_value=1.0,
            step=0.1
        )

        # Layer agent configuration
        new_layer_agent_config = st_ace(
            value=json.dumps(st.session_state.layer_agent_config, indent=2),
            language='json',
            placeholder="Layer Agent Configuration (JSON)",
            show_gutter=False,
            wrap=True,
            auto_update=True
        )

        if st.form_submit_button("Update Configuration"):
            try:
                new_layer_config = json.loads(new_layer_agent_config)
                set_moa_agent(
                    main_model=new_main_model,
                    cycles=new_cycles,
                    layer_agent_config=new_layer_config,
                    main_model_temperature=main_temperature,
                    override=True
                )
                st.session_state.messages = []
                st.success("Configuration updated successfully!")
            except Exception as e:
                st.error(f"Error updating configuration: {str(e)}")

# Main app layout
st.header("Mixture of Agents")
st.write("This project oversees implementation of Mixture of Agents architecture powered by Groq LLMs.")

# Display current configuration
with st.expander("Current MOA Configuration", expanded=False):
    st.markdown(f"**Main Model**: `{st.session_state.main_model}`")
    st.markdown(f"**Main Model Temperature**: `{st.session_state.main_temp:.1f}`")
    st.markdown(f"**Layers**: `{st.session_state.cycles}`")
    st.markdown("**Layer Agents Config:**")
    st_ace(
        value=json.dumps(st.session_state.layer_agent_config, indent=2),
        language='json',
        placeholder="Layer Agent Configuration (JSON)",
        show_gutter=False,
        wrap=True,
        readonly=True,
        auto_update=True
    )

# Chat interface
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

if query := st.chat_input("Ask a question"):
    async def handle_query():
        st.session_state.messages.append({"role": "user", "content": query})
        with st.chat_message("user"):
            st.write(query)

        moa_agent: MOAgent = st.session_state.moa_agent

        with st.chat_message("assistant"):
            message_placeholder = st.empty()
            messages = moa_agent.chat(query, output_format='json')
            async for response in stream_or_async_response(messages):
                message_placeholder.markdown(response)

        st.session_state.messages.append({"role": "assistant", "content": response})

    asyncio.run(handle_query())


# Add acknowledgment at the bottom
st.markdown("---")
st.markdown("""
###
This app is based on [Emmanuel M. Ndaliro's work](https://github.com/kram254/Mixture-of-Agents-running-on-Groq/tree/main).
""")