Action Engine: An LLM-based Framework for Automatic FaaS Workflow Generation

2024-11-29

arXiv.org

AI Summary

To address the high expertise barrier, strong platform coupling, and poor extensibility in Function-as-a-Service (FaaS) workflow development, this paper proposes a tool-augmented large language model (LLM)-driven end-to-end workflow auto-generation method. Our approach tightly integrates function semantic retrieval, dynamic data-dependency graph construction, and a FaaS orchestration execution engine, enabling fully automated, human-in-the-loop-free generation of deployable workflows directly from natural language specifications. The key innovation lies in a synergistic coupling mechanism between the LLM, a function repository, and a dataflow reasoning module. This co-design significantly improves workflow generation accuracy (+20% absolute gain) and substantially lowers the cloud-native development barrier—empowering non-expert developers to efficiently build robust, production-ready FaaS applications.

Technology Category

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

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Function as a Service (FaaS) is poised to become the foundation of the next generation of cloud systems due to its inherent advantages in scalability, cost-efficiency, and ease of use. However, challenges such as the need for specialized knowledge and difficulties in building function workflows persist for cloud-native application developers. To overcome these challenges and mitigate the burden of developing FaaS-based applications, in this paper, we propose a mechanism called Action Engine, that makes use of Tool-Augmented Large Language Models (LLMs) at its kernel to interpret human language queries and automates FaaS workflow generation, thereby, reducing the need for specialized expertise and manual design. Action Engine includes modules to identify relevant functions from the FaaS repository and seamlessly manage the data dependency between them, ensuring that the developer's query is processed and resolved. Beyond that, Action Engine can execute the generated workflow by feeding the user-provided parameters. Our evaluations show that Action Engine can generate workflows with up to 20% higher correctness without developer involvement. We notice that Action Engine can unlock FaaS workflow generation for non-cloud-savvy developers and expedite the development cycles of cloud-native applications.

Problem

• Automating FaaS workflow generation to reduce specialized knowledge requirements
• Addressing platform dependence and scalability challenges in cloud-native applications
• Leveraging tool-augmented LLMs to interpret human queries for automation

Innovation

• Tool-augmented LLMs interpret human language queries
• Automatically generates FaaS workflows from queries
• Identifies functions and manages data dependencies