> ## Documentation Index
> Fetch the complete documentation index at: https://docs.murnitur.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Loading Presets

In the Murnitur SDK, you can easily use presets configured in the Murnitur AI platform. These presets contain predefined settings like prompts and input variables, tailored for specific tasks. By using these presets in the SDK, you avoid the need to store configuration details in your code or repeat setup steps.

This simplifies integrating LLM functionality into applications, providing a straightforward way to access optimized configurations. It boosts productivity, ensures consistency, and speeds up development cycles. Whether adjusting prompts, selecting model versions, or specifying inputs, using presets in the SDK lets you focus on your application logic and innovation while benefiting from optimized configurations from the Murnitur AI platform.

## Example

<CodeGroup>
  ```python python theme={null}

  import murnitur
  from openai import OpenAI

  client = OpenAI()

  def customer_support(question: str):
      preset = murnitur.load_preset("customer_support")
      prompt = murnitur.format_prompt(
          messages=preset.active_version.messages,
          params={"question": question},
      )
      result = client.chat.completions.create(
          model="gpt-3.5-turbo",
          temperature=1,
          messages=prompt,
          max_tokens=300,
      )
      return result.choices[0].message.content


  if __name__ == "__main__":
      murnitur.set_api_key("mt-ey...")

      murnitur.init("murnix-trace", murnitur.Environment.DEVELOPMENT)
      print(customer_support("Do you offer discount on Hardware items?"))


  ```

  ```typescript typescript theme={null}
  import * as murnitur from "murnitur";
  import OpenAI from "openai";

  const client = new OpenAI();

  // Function to handle customer support questions
  async function customerSupport(question: string) {
    const preset = await murnitur.loadPreset("customer_support");

    const prompt = murnitur.formatPrompt(preset.PresetPrompts[0].prompts, {
      question,
    });

    const result = await client.chat.completions.create({
      model: "gpt-3.5-turbo",
      temperature: 1,
      messages: prompt,
      max_tokens: 300,
    });

    return result.choices[0].message.content;
  }

  // Main function to initialize murnitur and handle customer support query
  async function main() {
    murnitur.setApiKey("mt-ey...");

    murnitur.init("murnix-trace", murnitur.Environment.DEVELOPMENT);

    const response = await customerSupport(
      "Do you offer discount on Hardware items?"
    );
    console.log(response);
  }

  // Execute the main function
  main();
  ```
</CodeGroup>

## Helper functions

<CodeGroup>
  ```python python theme={null}
  preset = murnitur.load_preset("dev")

  # Get active version
  preset.active_version.messages

  # Load prompts by version
  preset.get_prompt_by_version(1).messages

  # Load prompts by name
  preset.get_prompt_by_name("dev_v2").messages

  ```
</CodeGroup>