Raiders of the Lost Dependency: Fixing Dependency Conflicts in Python using LLMs

2025-01-27

AI Summary

Manual resolution of module version conflicts and complex transitive dependencies in Python programs is inefficient and error-prone. Method: This paper introduces PLLM, the first LLM-driven closed-loop dependency repair framework for Python. PLLM integrates retrieval-augmented generation (RAG) with natural language error parsing to dynamically infer required modules and compatible versions, and employs an execution-feedback-enabled iterative testing environment to realize a “diagnose–generate–validate–optimize”闭环. Unlike traditional approaches relying on static dependency graphs or lookup tables, PLLM eliminates dependence on predefined rules or explicit dependency declarations. Results: Evaluated on the HG2.9K dataset, PLLM achieves 15.97% and 21.58% higher repair success rates than ReadPyE and PyEGo, respectively, with particularly notable improvements in cross-version compatibility for numerical computing and machine learning libraries.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Fixing Python dependency issues is a tedious and error-prone task for developers, who must manually identify and resolve environment dependencies and version constraints of third-party modules and Python interpreters. Researchers have attempted to automate this process by relying on large knowledge graphs and database lookup tables. However, these traditional approaches face limitations due to the variety of dependency error types, large sets of possible module versions, and conflicts among transitive dependencies. This study explores the potential of using large language models (LLMs) to automatically fix dependency issues in Python programs. We introduce PLLM (pronounced"plum"), a novel technique that employs retrieval-augmented generation (RAG) to help an LLM infer Python versions and required modules for a given Python file. PLLM builds a testing environment that iteratively (1) prompts the LLM for module combinations, (2) tests the suggested changes, and (3) provides feedback (error messages) to the LLM to refine the fix. This feedback cycle leverages natural language processing (NLP) to intelligently parse and interpret build error messages. We benchmark PLLM on the Gistable HG2.9K dataset, a collection of challenging single-file Python gists. We compare PLLM against two state-of-the-art automatic dependency inference approaches, namely PyEGo and ReadPyE, w.r.t. the ability to resolve dependency issues. Our results indicate that PLLM can fix more dependency issues than the two baselines, with +218 (+15.97%) more fixes over ReadPyE and +281 (+21.58%) over PyEGo. Our deeper analyses suggest that PLLM is particularly beneficial for projects with many dependencies and for specific third-party numerical and machine-learning modules. Our findings demonstrate the potential of LLM-based approaches to iteratively resolve Python dependency issues.

Problem

• Automatic Repair
• Python Dependencies
• Version Conflicts

Innovation

• Large Language Models
• Python Dependency Resolution
• Automated Code Repair