LLM4FaaS: No-Code Application Development using LLMs and FaaS

2025-02-20

AI Summary

Non-technical users lack the coding, deployment, and operational expertise required to leverage large language models (LLMs) for application development. Method: This paper proposes an LLM–FaaS deep-cooperation no-code development framework: users specify requirements in natural language; the system automatically invokes GPT-4o to generate function-level code and deploys it—without configuration—via open-source FaaS platforms (OpenFaaS/Knative), managing the full application lifecycle. Contribution/Results: By embedding FaaS abstraction *before* LLM code generation, the framework significantly reduces code complexity and error rates. Evaluated on real-world prompts from non-technical users, it achieves a 71.47% end-to-end application construction and deployment success rate—27.99 percentage points higher than a FaaS-free baseline. This work establishes the first fully automated, infrastructure-agnostic, zero-code application development paradigm enabled by tight LLM–FaaS integration.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Large language models (LLMs) are powerful tools that can generate code from natural language descriptions. While this theoretically enables non-technical users to develop their own applications, they typically lack the expertise to execute, deploy, and operate generated code. This poses a barrier for such users to leverage the power of LLMs for application development. In this paper, we propose leveraging the high levels of abstraction of the Function-as-a-Service (FaaS) paradigm to handle code execution and operation for non-technical users. FaaS offers function deployment without handling the underlying infrastructure, enabling users to execute LLM-generated code without concern for its operation and without requiring any technical expertise. We propose LLM4FaaS, a novel no-code application development approach that combines LLMs and FaaS platforms to enable non-technical users to build and run their own applications using only natural language descriptions. Specifically, LLM4FaaS takes user prompts, uses LLMs to generate function code based on those prompts, and deploys these functions through a FaaS platform that handles the application's operation. LLM4FaaS also leverages the FaaS infrastructure abstractions to reduce the task complexity for the LLM, improving result accuracy. We evaluate LLM4FaaS with a proof-of-concept implementation based on GPT-4o and an open-source FaaS platform, using real prompts from non-technical users. Our evaluation based on these real user prompts demonstrates the feasibility of our approach and shows that LLM4FaaS can reliably build and deploy code in 71.47% of cases, up from 43.48% in a baseline without FaaS.

Problem

• Enable non-technical users to develop applications
• Simplify code execution and deployment using FaaS
• Enhance LLM-generated code accuracy and reliability

Innovation

• LLMs generate code from natural language
• FaaS handles code execution and operation
• No-code app development via LLMs and FaaS