How to beginner · 3 min read

Semantic Kernel environment setup

Q: Semantic Kernel environment setup

Set up the semantic_kernel Python package by installing it via pip and configure an OpenAIChatCompletion service with your OpenAI API key. Initialize a Kernel instance, add the OpenAI service, and you are ready to run Semantic Kernel AI tasks.

Quick answer

Set up the semantic_kernel Python package by installing it via pip and configure an OpenAIChatCompletion service with your OpenAI API key. Initialize a Kernel instance, add the OpenAI service, and you are ready to run Semantic Kernel AI tasks.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install semantic-kernel openai

Setup

Install the semantic_kernel package along with openai for OpenAI API access. Set your OpenAI API key as an environment variable OPENAI_API_KEY before running your code.

bash

pip install semantic-kernel openai

Step by step

This example shows how to initialize the Semantic Kernel, add the OpenAI chat completion service, and run a simple prompt to get a response.

python

import os
import semantic_kernel as sk
from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion

# Ensure your OpenAI API key is set in environment variables
api_key = os.environ["OPENAI_API_KEY"]

# Create the kernel instance
kernel = sk.Kernel()

# Add OpenAI chat completion service with model gpt-4o-mini
kernel.add_service(OpenAIChatCompletion(
    service_id="chat",
    api_key=api_key,
    ai_model_id="gpt-4o-mini"
))

# Define a simple prompt
prompt = "Write a short poem about AI."

# Run the prompt through the kernel's chat service
response = kernel.run(prompt, service_id="chat")

print("Response:", response)

output

Response: AI weaves dreams in code and light,
Silent thinker through the night.
Endless knowledge, swift and bright,
Guiding futures, taking flight.

Common variations

Use different AI models by changing ai_model_id (e.g., gpt-4o or gpt-4o-mini).
For asynchronous calls, use await kernel.run_async(...) inside an async function.
Integrate other AI services by adding different connectors to the kernel.

Troubleshooting

If you see KeyError for OPENAI_API_KEY, ensure the environment variable is set correctly.
For authentication errors, verify your API key is valid and has access to the specified model.
If the kernel fails to run, check that semantic_kernel and openai packages are up to date.

✅

Key Takeaways

Install semantic_kernel and openai packages to start using Semantic Kernel in Python.
Configure the kernel by adding an OpenAI chat completion service with your API key and preferred model.
Use kernel.run() for synchronous calls and kernel.run_async() for async execution.
Always set your OPENAI_API_KEY environment variable before running your code.
Update packages regularly to avoid compatibility issues and access new features.

Verified 2026-04 · gpt-4o-mini

Verify ↗