refly-ai/refly

Support calling a model once for data cleaning using plugins

Open

#714 opened on Apr 16, 2025

View on GitHub
 (0 comments) (0 reactions) (0 assignees)TypeScript (7,331 stars) (712 forks)user submission
enhancementgood first issue

Description

Is your feature request related to a problem? Please describe. The user is requesting the ability to use a plugin to invoke a machine learning or AI model for data cleaning purposes in a single operation. This suggests a desire for a more streamlined and efficient data preprocessing workflow where a plugin can trigger a one-time model call to clean or transform data, potentially reducing the complexity of current data cleaning processes.

Describe the solution you'd like A clear and concise description of what you want to happen.

Describe alternatives you've considered A clear and concise description of any alternative solutions or features you've considered.

Additional context Add any other context or screenshots about the feature request here.

Contributor guide

Tech stack
typescript
Domain
datamachine learningai
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
unclear
Prerequisites
Basic plugin developmentTypeScript knowledgeUnderstanding of data cleaning
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40
Research direction
Examine the existing plugin architecture in the repository (likely in src/plugins or similar). Look for any prior discussions or PRs related to model invocation. Understand how plugins currently interact with data processing pipelines. Propose a minimal API for a one time model call, considering both local and remote model invocation. Check if there are any relevant issues or documentation on data cleaning workflows.