Skip to main content

Jupyter Notebooks Integration

Jupyter Notebooks provide an interactive computing environment that combines code, text, and visualizations. This guide shows how to integrate Azerion Intelligence with Jupyter Notebooks.

What are Jupyter Notebooks?​

Jupyter Notebooks are interactive documents that allow you to mix code execution, rich text, and data visualizations in a single environment, perfect for data analysis and experimentation.

Prerequisites​

Secure Your Credentials

Store your API key in environment variables. Never commit API keys to notebooks that might be shared publicly.

Integration Steps​

1. Environment Setup​

Create a .env file in your project directory:

AZERION_API_KEY=your_api_key_here
AZERION_BASE_URL=https://api.azerion.ai/v1

2. Configure Azerion Intelligence Client​

Add this setup cell to your notebook:

import os
from dotenv import load_dotenv
from openai import OpenAI

# Load environment variables
load_dotenv()

# Configure Azerion Intelligence client
client = OpenAI(
    api_key=os.getenv("AZERION_API_KEY"),
    base_url=os.getenv("AZERION_BASE_URL", "https://api.azerion.ai/v1")
)

print("✅ Azerion Intelligence configured successfully!")

3. Test Connection​

Verify your integration works:

def test_azerion_connection():
    try:
        response = client.chat.completions.create(
            model="meta.llama3-3-70b-instruct-v1:0",
            messages=[{"role": "user", "content": "Hello! Can you help me with data analysis?"}],
            max_tokens=100
        )
        return response.choices[0].message.content
    except Exception as e:
        return f"Connection failed: {e}"

# Test the connection
result = test_azerion_connection()
print(result)

Basic Example​

Here's a simple example of using Azerion Intelligence for data analysis assistance:

import pandas as pd

# Sample data analysis function
def analyze_dataset_with_ai(df, question):
    """
    Use Azerion Intelligence to analyze a pandas DataFrame
    """
    # Prepare dataset summary
    data_info = f"""
    Dataset Summary:
    - Shape: {df.shape}
    - Columns: {list(df.columns)}
    - Data types: {df.dtypes.to_dict()}
    - Missing values: {df.isnull().sum().to_dict()}
    """
    
    # Ask AI for analysis
    response = client.chat.completions.create(
        model="meta.llama3-3-70b-instruct-v1:0",
        messages=[
            {
                "role": "system", 
                "content": "You are a data analysis expert. Analyze the dataset information and provide insights."
            },
            {
                "role": "user", 
                "content": f"{data_info}\n\nQuestion: {question}"
            }
        ],
        temperature=0.3
    )
    
    return response.choices[0].message.content

# Example usage
# df = pd.read_csv('your_data.csv')
# analysis = analyze_dataset_with_ai(df, "What are the main patterns in this data?")
# print(analysis)

Troubleshooting​

Common Azerion AI Integration Issues​

1. Authentication Error

Error: Invalid API key
  • Verify your API key is correct in the .env file
  • Check that the environment variable is loaded properly
  • Ensure your API key has the necessary permissions

2. Connection Timeout

Error: Connection timeout
  • Check your internet connection
  • Verify the base URL is correct: https://api.azerion.ai/v1
  • Try reducing the max_tokens parameter if requests are too large

3. Model Not Available

Error: Model not found
  • Ensure you're using the correct model name: meta.llama3-3-70b-instruct-v1:0
  • Check if your API key has access to the specific model
  • Try using a different available model

4. Rate Limiting

Error: Rate limit exceeded
  • Add delays between API calls using time.sleep()
  • Implement retry logic with exponential backoff
  • Consider caching responses for repeated queries

5. Environment Variables Not Loading

Error: NoneType object
  • Make sure the .env file is in the correct directory
  • Verify the file contains: AZERION_API_KEY=your_key
  • Check that python-dotenv is installed and load_dotenv() is called