Laminar: A New Serverless Stream-based Framework with Semantic Code Search and Code Completion

TL;DR

Laminar is a serverless stream processing framework that integrates semantic code search and completion using large language models, simplifying streaming workflows and enhancing developer productivity.

Contribution

It introduces Laminar, a novel serverless framework based on dispel4py, with integrated semantic code search and code completion capabilities.

Findings

Efficient management of streaming workflows and components.

Enhanced code search and summarization using large language models.

Simplified execution of streaming computations.

Abstract

This paper introduces Laminar, a novel serverless framework based on dispel4py, a parallel stream-based dataflow library. Laminar efficiently manages streaming workflows and components through a dedicated registry, offering a seamless serverless experience. Leveraging large lenguage models, Laminar enhances the framework with semantic code search, code summarization, and code completion. This contribution enhances serverless computing by simplifying the execution of streaming computations, managing data streams more efficiently, and offering a valuable tool for both researchers and practitioners.