Laminar: a new serverless stream-based framework with semantic code search and code completion

Zaynab Zahra*, Zihao Li, Rosa Filgueira*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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 language 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.
Original languageEnglish
Title of host publication18th Workshop on Workflows in Support of Large-Scale Science
Subtitle of host publicationWORKS 2023
PublisherIEEE
Publication statusAccepted/In press - 8 Sept 2023
Event18th Workshop on Workflows in Support of Large-Scale Science (WORKS 2023) - Denver, United States
Duration: 12 Nov 202312 Nov 2023
Conference number: 18
https://works-workshop.org/

Conference

Conference18th Workshop on Workflows in Support of Large-Scale Science (WORKS 2023)
Abbreviated titleWORKS 2023
Country/TerritoryUnited States
CityDenver
Period12/11/2312/11/23
Internet address

Keywords

  • Serverless computing
  • Streaming applications
  • Semantic code search
  • Transformers
  • dispel4py
  • Code completion
  • Code summarization

Fingerprint

Dive into the research topics of 'Laminar: a new serverless stream-based framework with semantic code search and code completion'. Together they form a unique fingerprint.

Cite this