app.py

import streamlit as st
import cohere
import os
import base64

st.set_page_config(page_title="Cohere Chat", layout="wide")

AI_PFP = "media/pfps/cohere-pfp.png"
USER_PFP = "media/pfps/user-pfp.jpg"
BANNER = "media/banner.png"

model_info = {
    "c4ai-aya-expanse-8b": {"description": "Aya Expanse is a highly performant 8B multilingual model, designed to rival monolingual performance through innovations in instruction tuning with data arbitrage, preference training, and model merging. Serves 23 languages.", "context": "4K", "output": "4K"},
    "c4ai-aya-expanse-32b": {"description": "Aya Expanse is a highly performant 32B multilingual model, designed to rival monolingual performance through innovations in instruction tuning with data arbitrage, preference training, and model merging. Serves 23 languages.", "context": "128K", "output": "4K"},
    "c4ai-aya-vision-8b": {"description": "Aya Vision is a state-of-the-art multimodal model excelling at a variety of critical benchmarks for language, text, and image capabilities. This 8 billion parameter variant is focused on low latency and best-in-class performance.", "context": "16K", "output": "4K"},
    "c4ai-aya-vision-32b": {"description": "Aya Vision is a state-of-the-art multimodal model excelling at a variety of critical benchmarks for language, text, and image capabilities. Serves 23 languages. This 32 billion parameter variant is focused on state-of-art multilingual performance.", "context": "16k", "output": "4K"},
    "command-a-03-2025": {"description": "Command A is our most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. Command A has a context length of 256K, only requires two GPUs to run, and has 150% higher throughput compared to Command R+ 08-2024.", "context": "256K", "output": "8K"},
    "command-r7b-12-2024": {"description": "command-r7b-12-2024 is a small, fast update delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps.", "context": "128K", "output": "4K"},
    "command-r-plus-04-2024": {"description": "Command R+ is an instruction-following conversational model that performs language tasks at a higher quality, more reliably, and with a longer context than previous models. It is best suited for complex RAG workflows and multi-step tool use.", "context": "128K", "output": "4K"},
}

with st.sidebar:
    st.image(BANNER, use_container_width=True)
    st.title("Settings")
    api_key = st.text_input("Cohere API Key", type="password")
    selected_model = st.selectbox("Model", options=list(model_info.keys()))
    if selected_model.startswith("c4ai-aya-vision"):
        uploaded_file = st.file_uploader("Upload image", type=["png", "jpg", "jpeg"])
        if uploaded_file:
            st.session_state.image_data = uploaded_file.read()
    if st.button("Clear Chat"):
        st.session_state.clear()
        st.session_state.image_data = None
        st.rerun()
    st.divider()
    st.subheader(selected_model)
    st.markdown(model_info[selected_model]["description"])
    st.caption(f"Context: {model_info[selected_model]['context']}")
    st.caption(f"Output: {model_info[selected_model]['output']}")
    st.markdown("Powered by Cohere's API")

if "messages" not in st.session_state:
    st.session_state.messages = []
if "first_message_sent" not in st.session_state:
    st.session_state.first_message_sent = False
if "image_data" not in st.session_state:
    st.session_state.image_data = None

if not st.session_state.first_message_sent:
    st.markdown("<h1 style='text-align:center;color:#4a4a4a;margin-top:100px;'>How can Cohere help you today?</h1>", unsafe_allow_html=True)

for msg in st.session_state.messages:
    with st.chat_message(msg["role"], avatar=USER_PFP if msg["role"] == "user" else AI_PFP):
        content = msg["content"]
        if isinstance(content, list):
            for item in content:
                if getattr(item, 'type', None) == "text":
                    st.markdown(item.text)
                elif getattr(item, 'type', None) == "image_url":
                    st.image(item.image_url.url)
        else:
            st.markdown(content)

if prompt := st.chat_input("Message..."):
    if not api_key:
        st.error("API key required! Please create one at https://dashboard.cohere.com/")
        st.stop()
    st.session_state.first_message_sent = True
    st.session_state.messages.append({"role": "user", "content": prompt})
    with st.chat_message("user", avatar=USER_PFP):
        st.markdown(prompt)
    co = cohere.ClientV2(api_key)
    content = [{"type": "text", "text": prompt}]
    if selected_model.startswith("c4ai-aya-vision") and st.session_state.image_data:
        data_url = "data:image/jpeg;base64," + base64.b64encode(st.session_state.image_data).decode('utf-8')
        content.append({"type": "image_url", "image_url": {"url": data_url}})
    response = co.chat(model=selected_model, messages=[*st.session_state.messages, {"role": "user", "content": content}], temperature=0.3)
    items = response.message.content
    reply = "".join(getattr(i, 'text', '') for i in items)
    with st.chat_message("assistant", avatar=AI_PFP):
        st.markdown(reply)
    st.session_state.messages.append({"role": "assistant", "content": items})
    st.session_state.image_data = None