​
Laminar

Infrastructure-first approach to building LLM pipelines.

We provide a single platform to build, deploy, monitor, and evaluate LLM apps. Laminar offers an extensible set of tools to help you make reliable and cost-effective LLM apps, and bring them to production in seconds by deploying to our fast and scalable Rust infra.

​
First steps

To begin with, you can check our demo to get an overview of features available on Laminar.

After that, you can start with reading about how to create a pipeline. Try creating a simple pipeline by connecting Input node to LLM node, and then connecting LLM node to Output node.

Step by step, you’ll unveil various functionalities of our platform and make your LLM app ready for production.

​
Key features

  • Versatile pipeline builder: Build LLM pipeline using variety of nodes with required functionality provided out of the box
  • Endpoints and checks: Deploy your pipeline to an API endpoint in seconds, while protecting it with custom checks
  • Logging: Conveniently access the logs and see how users interact with your pipeline through endpoint
  • Evaluations: Evaluate your LLM pipeline with a broad set of metrics
  • Semantic Search: Cache data or upload it so that it can be quickly accessed based on semantic similarity
  • Semantic router: Direct the flow of pipeline by utilizing our semantic router

To see all features, you can read more in other sections.

We are adding new features every day. Feel free to contact us as founders@lmnr.ai for any feature requests.

Introduction