Skip to content

Make that logseq graph clean, tidy, and professional. Sanitize your brain dumps into an ADR that you can share.

Notifications You must be signed in to change notification settings

bigFin/logseq-tidy-graph

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Logseq Tidy Graph

A CLI tool to professionalize and enhance Logseq graph contents using AI.

Features

  • Smart Graph Processing

    • Interactive filesystem navigation for graph selection
    • Preserves #hashtags and [[page references]]
    • Maintains page relationships and knowledge structure
    • Processes both journal entries and pages
  • AI Enhancement

    • Rewrites content in professional tone using GPT-4
    • Context-aware processing using page references
    • Sample processing preview before full commit
    • Rate-limited API usage to stay within OpenAI limits
  • Safety & Control

    • Non-destructive: saves to new output directory
    • Preserves original graph structure
    • Estimates OpenAI API cost before processing
    • Progress tracking with error handling

Usage

  1. Install dependencies:
pip install -r requirements.txt
  1. Run the tool:
python cli.py tidy-graph
  1. Follow the interactive prompts to:
    • Select your Logseq graph
    • Review sample processing
    • Confirm full graph processing

Rate Limits

The tool automatically respects OpenAI's rate limits:

  • Tokens per minute (TPM): 200,000
  • Concurrent requests: Automatically managed
  • Built-in rate limiting and request queuing

Output

Processed files maintain the same structure as your original graph while providing:

  • Professional tone and clarity
  • Preserved links and references
  • Original Logseq formatting
  • Separate output directory for safety

About

Make that logseq graph clean, tidy, and professional. Sanitize your brain dumps into an ADR that you can share.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages