app.py

import streamlit as st
from openai import OpenAI
import os
import sys
from dotenv import load_dotenv, dotenv_values
load_dotenv()

# initialize the client
client = OpenAI(
  base_url="https://api-inference.huggingface.co/v1",
  api_key=os.environ.get('HUGGINGFACEHUB_API_TOKEN')  # Replace with your token
)

# Create supported models
model_links = {
    "Mixtral-8x7B-Instruct-v0.1": "mistralai/Mixtral-8x7B-Instruct-v0.1",
    "Mistral-Nemo-Instruct-2407": "mistralai/Mistral-Nemo-Instruct-2407",
    "Nous-Hermes-2-Mixtral-8x7B-DPO": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
    "Mistral-7B-Instruct-v0.1": "mistralai/Mistral-7B-Instruct-v0.1",
    "Mistral-7B-Instruct-v0.2": "mistralai/Mistral-7B-Instruct-v0.2",
    "Mistral-7B-Instruct-v0.3": "mistralai/Mistral-7B-Instruct-v0.3",
    "Mistral-Small-Instruct-2409": "mistralai/Mistral-Small-Instruct-2409",
}

def reset_conversation():
    #st.session_state.conversation = []
    st.session_state.messages = []
    return None

def ask_assistant_stream(st_model, st_messages, st_temp_value, st_max_tokens):
    response=[]
    try:
        stream = client.chat.completions.create(
            model=st_model,
            messages=[
                {"role": m["role"], "content": m["content"]}
                for m in st_messages
            ],
            temperature=st_temp_value,
            stream=True,
            max_tokens=st_max_tokens,
        )
        response["stream"] = stream
    
    except Exception as e:
        pass

    return response

# Define the available models
models =[key for key in model_links.keys()]

# Create the sidebar with the dropdown for model selection
selected_model = st.sidebar.selectbox("Select Model", models)

# Create a temperature slider
temp_values = st.sidebar.slider('Select a temperature value', 0.0, 1.0, (0.5))

# Create a max_token slider
max_token_value = st.sidebar.slider('Select a max_token value', 1000, 9000, (5000))

#Add reset button to clear conversation
st.sidebar.button('Reset Chat', on_click=reset_conversation) #Reset button


# Create model description
st.sidebar.write(f"You're now chatting with **{selected_model}**")
st.sidebar.markdown("*Generated content may be inaccurate or false.*")
# st.sidebar.markdown("\n[TypeGPT](https://typegpt.net).")




if "prev_option" not in st.session_state:
    st.session_state.prev_option = selected_model

if st.session_state.prev_option != selected_model:
    st.session_state.messages = []
    # st.write(f"Changed to {selected_model}")
    st.session_state.prev_option = selected_model
    reset_conversation()



#Pull in the model we want to use
repo_id = model_links[selected_model]


st.subheader(f'{selected_model}')
# # st.title(f'ChatBot Using {selected_model}')

# Set a default model
if selected_model not in st.session_state:
    st.session_state[selected_model] = model_links[selected_model] 

# Initialize chat history
if "messages" not in st.session_state:
    st.session_state.messages = []


# Display chat messages from history on app rerun
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

if "retry" not in st.session_state:
    st.session_state.retry= False

def retry_click():
    st.session_state.retry= True


if st.session_state.retry:
    lastmessage = st.session_state.messages.pop()
    st.toast("popped msg: " + lastmessage["content"] + " // model: " + model_links[selected_model])
    response = get_assistant_aswer(model_links[selected_model], st.session_state.messages, temp_values, max_token_value)
    st.session_state.messages.append({"role": "assistant", "content": response})
    st.session_state.retry= False
    st.rerun()

if "remove" not in st.session_state:
    st.session_state.remove= False

def remove_click():
    st.session_state.remove= True

if st.session_state.remove:
    lastmessage = st.session_state.messages.pop()
    prelastmessage = st.session_state.messages.pop()
    st.toast("popped msg: " + lastmessage["content"] + " // model: " + model_links[selected_model])
    st.session_state.remove= False
    st.rerun()



# Accept user input
if prompt := st.chat_input(f"Hi I'm {selected_model}, ask me a question"):
    # Display user message in chat message container and Add user message to chat history
    with st.chat_message("user"):
        st.markdown(prompt)
    st.session_state.messages.append({"role": "user", "content": prompt})
    
    # Display assistant response in chat message container
    assistant = ask_assistant_stream(model_links[selected_model], st.session_state.messages, temp_values, max_token_value)
    st.write assistant
    if "stream" in assistant: 
        with st.chat_message("assistant"):
            response = st.write_stream(assistant["stream"])
    else:
        with st.chat_message("assistant"):
            response = st.write("Failure")

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

if len(st.session_state.messages)>0:
    col1, col2 = st.columns(2)
    col1.button("retry", key="retryButton", on_click=retry_click)
    col2.button("remove", key="removeButton", on_click=remove_click)