27 Sep 2024 • 4 min read
At JigsawStack, our mission is to simplify the development process by giving developers access to powerful AI tools without the usual complexity.
A key part of this effort is the Prompt Engine, an SDK designed to streamline the use of Large Language Models (LLMs) and automate workflows.
Today, we’re thrilled to announce our partnership with Groq, a leader in AI hardware acceleration. With Groq’s industry-leading speed, the JigsawStack Prompt Engine is now faster and more efficient, offering developers a cutting-edge solution for working with LLMs.
What is JigsawStack Prompt Engine?
The JigsawStack Prompt Engine is a developer-friendly SDK designed to simplify working with LLMs. One of our main goals is to make sure you don’t have to manually choose the right LLM or worry about optimizing prompts—our Prompt Engine automatically picks the best models and tunes your prompts for the best possible performance. This allows developers to focus on building great applications, not on managing the complexities of LLM selection or prompt adjustments.
With the addition of Groq’s powerful hardware, the Prompt Engine offers high performance and low-latency inference for real-time AI applications, making it easier than ever to build fast, efficient workflows.
Why Groq?
To achieve our vision of effortless AI integration, speed and efficiency are critical. That’s why we’ve partnered with Groq, the fastest in the business when it comes to LLM inference. Groq’s high-performance hardware ensures that your AI tasks run with minimal latency, which is essential for real-time applications. This integration allows the Prompt Engine to process and deliver results faster, enabling developers to build smarter, more responsive applications without the need to worry about hardware limitations.
How to Use JigsawStack’s Prompt Engine with Groq
Here’s a quick overview of how easy it is to use the Prompt Engine, with Groq handling the heavy lifting behind the scenes:
// Import JigsawStacks AI SDK
import { JigsawStack } from 'jigsawstack';
//Grab your free API key
const jigsaw = JigsawStack({ apiKey: 'your-api-key' });
//Create the prompt
const result = await jigsaw.prompt_engine.create({
prompt: "How to cook {dish}",
inputs: [{ key: "dish" }],
});
// Run the prompt
const resp = await jigsaw.prompt_engine.run({
id: result.prompt_engine_id,
input_values: { dish: "Singaporean chicken rice" },
});
With Groq’s hardware integrated under the hood, the Prompt Engine runs seamlessly, handling LLM inferencing faster than ever.
Build Without Worry: No Tokens , No GPUs, No Headaches
We understand that developers want simplicity and transparency. That’s why with JigsawStack, you don’t have to think about token-based pricing, managing GPUs, or rate limits. This way, you can focus on what matters most: building and scaling your applications.
Safety First: Llama Guard 3
In today’s AI landscape, ensuring the safety and integrity of AI outputs is crucial. That’s why we’ve incorporated Llama Guard 3, a powerful content moderation feature, into our Prompt Engine. Llama Guard 3 helps filter out harmful or inappropriate content—like hate speech, privacy violations, and election misinformation—ensuring your applications remain secure and trustworthy. It’s fully customizable, allowing you to fine-tune it to meet the needs of your project.
Future Integrations: Llama 3.2 on the Horizon
Exciting developments are on the way. Groq just announced the release of Llama 3.2, and we’re already preparing to integrate this next-generation model into JigsawStack. Llama 3.2 will be available not only in the Prompt Engine but also across all of JigsawStack’s APIs. This means even better performance and more flexibility for developers using our platform. Stay tuned as we roll out Llama 3.2 and continue to push the boundaries of what’s possible in AI automation.
Get Started with JigsawStack Today
We’re making it easier than ever for developers to integrate advanced AI capabilities into their applications. Sign up for a JigsawStack account, generate your API key, and start leveraging the power of our Groq-powered Prompt Engine. With safety features like Llama Guard 3 and future enhancements like Llama 3.2, there’s never been a better time to join the JigsawStack community.
Ready to elevate your AI-powered workflows? Head to JigsawStack and start building today!
Join the JigsawStack Community
We invite you to join our growing community of developers on Discord and Twitter. Share your projects, ask questions, and collaborate with others who are just as passionate about innovation as you are.