September 23, 2025

Guide: Getting started with Klu Python SDK

Stephen M. Walker II · Co-Founder / CEO

Step 1: Install the Klu SDK

First, you need to install the Klu SDK. You can do this by running the following command in your terminal:

pip install klu

Step 2: Import Klu

Next, you need to import the Klu module in your Python script:

from klu import Klu

Step 3: Initialize Klu

Now, you need to initialize Klu with your API key. You can find your API key in your Klu workspace settings.

klu = Klu('YOUR_API_KEY')

Step 4: Create an Action

To create an action, you need to define a prompt template, model config, and additional Klu-specific configurations. Here's an example:

action = klu.actions.create(
    name='Content Analyzer',
    description='Analyzes any given piece of text content',
    prompt_template='Analyze the following content: {{content}}',
    action_type="prompt",
    app_guid=app.guid,
    model_guid=models[0].guid
)

Step 5: Run the Action

Finally, you can run the action with your input:

result = klu.actions.prompt(action=action.guid,input={'content': 'Your text here'})
print(result)

This will print the generated text to the console.

And that's it! You've created and run your first Klu action using the Python SDK. Remember to replace 'YOUR_API_KEY' and 'Your text here' with your actual API key and the text you want to analyze, respectively.

If you want to learn more about the Klu Python SDK, you can check out the developer docs.

More articles

Continue exploring the Klu blog.

Fresh guides and product insights from teams building with Klu.

July 14, 2026

Fine-Tuning Guide: When It Is Worth It and How to Do It in 2026

A current decision framework and production workflow for fine-tuning LLMs, from prompting and RAG through datasets, evaluation, training, deployment, and monitoring.
Read article

July 14, 2026

Fine-Tuning OpenAI Models: What Still Works

OpenAI is winding down self-serve fine-tuning. Here are the models you can still fine-tune, the current API syntax, published pricing, and the decisions to make before the window closes.
Read article

It's time to build

Collaborate with your team on reliable Generative AI features.
Want expert guidance? Book a 1:1 onboarding session from your dashboard.

Talk to sales