Skip to main content

Using Streamlit

Streamlit is a Python framework for building interactive web applications. This guide shows how to integrate Azerion Intelligence with Streamlit to create AI-powered applications.

What is Streamlit?​

Streamlit allows you to create web applications using simple Python scripts, with automatic UI generation and real-time updates.

Prerequisites​

Integration Steps​

1. Install Required Libraries​

pip install streamlit openai

2. Configure API Access​

Create .streamlit/secrets.toml file:

AZERION_API_KEY = "your_azerion_api_key_here"

3. Initialize Azerion Intelligence Client​

import streamlit as st
from openai import OpenAI

@st.cache_resource
def init_ai_client():
    return OpenAI(
        api_key=st.secrets["AZERION_API_KEY"],
        base_url="https://api.azerion.ai/v1"
    )

client = init_ai_client()

Basic Example: Simple Chatbot​

Create app.py with this chatbot implementation:

import streamlit as st
from openai import OpenAI

# Initialize Azerion Intelligence client
@st.cache_resource
def init_ai_client():
    return OpenAI(
        api_key=st.secrets["AZERION_API_KEY"],
        base_url="https://api.azerion.ai/v1"
    )

client = init_ai_client()

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

# App title
st.title("AI Assistant")

# Chat interface
def get_ai_response(user_input):
    response = client.chat.completions.create(
        model="meta.llama3-3-70b-instruct-v1:0",
        messages=[
            {"role": "system", "content": "You are a helpful AI assistant."},
            {"role": "user", "content": user_input}
        ],
        temperature=0.7,
        max_tokens=1024
    )
    return response.choices[0].message.content

# Chat input
if prompt := st.chat_input("Ask me anything..."):
    # Add user message
    st.session_state.messages.append({"role": "user", "content": prompt})
    
    # Get AI response
    with st.spinner("Thinking..."):
        response = get_ai_response(prompt)
    
    # Add AI response
    st.session_state.messages.append({"role": "assistant", "content": response})

# Display chat history
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.write(message["content"])

Run the application:

streamlit run app.py

Troubleshooting​

API Key Issues​

  • Ensure your API key is correctly set in .streamlit/secrets.toml
  • Verify the API key is valid and has proper permissions

Connection Errors​

  • Check your internet connection
  • Verify the base URL: https://api.azerion.ai/v1

Model Not Found​

  • Ensure you're using the correct model name: meta.llama3-3-70b-instruct-v1:0
  • Check if your account has access to the requested model

Rate Limiting​

  • Implement error handling for API rate limits
  • Add retry logic with exponential backoff
import time

def get_ai_response_with_retry(user_input, max_retries=3):
    for attempt in range(max_retries):
        try:
            response = client.chat.completions.create(
                model="meta.llama3-3-70b-instruct-v1:0",
                messages=[
                    {"role": "system", "content": "You are a helpful AI assistant."},
                    {"role": "user", "content": user_input}
                ]
            )
            return response.choices[0].message.content
        except Exception as e:
            if attempt < max_retries - 1:
                time.sleep(2 ** attempt)  # Exponential backoff
                continue
            st.error(f"AI service error: {str(e)}")
            return None