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

Zaynab  Zahra; Zihao  Li; Rosa Filgueira

doi:10.1145/3624062.3624280

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

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English
Title of host publication	Proceedings of the SC '23 workshops of the international conference on high performance computing, network, storage, and analysis (SC-W '23)
Subtitle of host publication	Nov 12-17, 2023 \| Denver, CO
Publisher	ACM
Pages	2009–2020
ISBN (Print)	9798400707858
DOIs	https://doi.org/10.1145/3624062.3624280
Publication status	Published - 1 Nov 2023
Event	18th Workshop on Workflows in Support of Large-Scale Science (WORKS 2023) - Denver, United States Duration: 12 Nov 2023 → 12 Nov 2023 Conference number: 18 https://works-workshop.org/

Conference

Conference	18th Workshop on Workflows in Support of Large-Scale Science (WORKS 2023)
Abbreviated title	WORKS 2023
Country/Territory	United States
City	Denver
Period	12/11/23 → 12/11/23
Internet address	https://works-workshop.org/

Keywords

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

Access to Document

10.1145/3624062.3624280

Zahra-2023-Laminar-SC23-AAM
Copyright © 2023 Association for Computing Machinery. This work has been made available online in accordance with publisher policies or with permission. Permission for further reuse of this content should be sought from the publisher or the rights holder. This is the author created accepted manuscript following peer review and may differ slightly from the final published version. The final published version of this work is available at https://doi.org/10.1145/3624062.3624280.
Accepted author manuscript, 2.48 MB

Cite this

Zahra, Z., Li, Z., & Filgueira, R. (2023). Laminar: a new serverless stream-based framework with semantic code search and code completion. In Proceedings of the SC '23 workshops of the international conference on high performance computing, network, storage, and analysis (SC-W '23): Nov 12-17, 2023 | Denver, CO (pp. 2009–2020). ACM. https://doi.org/10.1145/3624062.3624280

@inproceedings{593f13bddedc46a6998cfb5371bb5336,

title = "Laminar: a new serverless stream-based framework with semantic code search and code completion",

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.",

keywords = "Serverless computing, Streaming applications, Semantic code search, Transformers, dispel4py, Code completion, Code summarization",

author = "Zaynab Zahra and Zihao Li and Rosa Filgueira",

year = "2023",

month = nov,

day = "1",

doi = "10.1145/3624062.3624280",

language = "English",

isbn = "9798400707858",

pages = "2009–2020",

booktitle = "Proceedings of the SC '23 workshops of the international conference on high performance computing, network, storage, and analysis (SC-W '23)",

publisher = "ACM",

address = "United States",

note = "18th Workshop on Workflows in Support of Large-Scale Science (WORKS 2023), WORKS 2023 ; Conference date: 12-11-2023 Through 12-11-2023",

url = "https://works-workshop.org/",

}

Zahra, Z, Li, Z & Filgueira, R 2023, Laminar: a new serverless stream-based framework with semantic code search and code completion. in Proceedings of the SC '23 workshops of the international conference on high performance computing, network, storage, and analysis (SC-W '23): Nov 12-17, 2023 | Denver, CO. ACM, pp. 2009–2020, 18th Workshop on Workflows in Support of Large-Scale Science (WORKS 2023), Denver, Colorado, United States, 12/11/23. https://doi.org/10.1145/3624062.3624280

Laminar: a new serverless stream-based framework with semantic code search and code completion. / Zahra, Zaynab ; Li, Zihao ; Filgueira, Rosa.
Proceedings of the SC '23 workshops of the international conference on high performance computing, network, storage, and analysis (SC-W '23): Nov 12-17, 2023 | Denver, CO. ACM, 2023. p. 2009–2020.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Laminar: a new serverless stream-based framework with semantic code search and code completion

AU - Zahra, Zaynab

AU - Li, Zihao

AU - Filgueira, Rosa

N1 - Conference code: 18

PY - 2023/11/1

Y1 - 2023/11/1

N2 - 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.

AB - 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.

KW - Serverless computing

KW - Streaming applications

KW - Semantic code search

KW - Transformers

KW - dispel4py

KW - Code completion

KW - Code summarization

U2 - 10.1145/3624062.3624280

DO - 10.1145/3624062.3624280

M3 - Conference contribution

SN - 9798400707858

SP - 2009

EP - 2020

BT - Proceedings of the SC '23 workshops of the international conference on high performance computing, network, storage, and analysis (SC-W '23)

PB - ACM

T2 - 18th Workshop on Workflows in Support of Large-Scale Science (WORKS 2023)

Y2 - 12 November 2023 through 12 November 2023

ER -

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

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this