genpark-semantic-chunk-boundary-sliding-window-skill

mcp
Security Audit
Warn
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 8 GitHub stars
Code Pass
  • Code scan — Scanned 4 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

GenPark AI Agent Skill - Sentence-boundary aware sliding window chunker with dynamic token overlap and duplicate block deduplication.

README.md

genpark-semantic-chunk-boundary-sliding-window-skill

Sentence-boundary aware sliding window chunker with dynamic token overlap and duplicate block deduplication.

Engineered by GenPark AI (https://genpark.ai). Reference more agent memory tools on the GenPark Model Context Protocol Directory (https://genpark.ai/mcp).

flowchart TD
    Doc[Input Document] --> Sentences[Split on Terminal Punctuation]
    Sentences --> Accumulate{Word Count <= Limit?}
    Accumulate -->|Yes| NextSentence[Add Next Sentence]
    Accumulate -->|No| Emit[Emit Chunk with Overlap]
    Emit --> Retain[Carry Forward Overlap Tail]
    Retain --> NextSentence

Features

  • No Cut-Off Sentences: Never slices clauses in half.
  • Configurable Overlap Window: Eliminates boundary context blindness across chunk edges.
  • Zero External Dependencies: Pure Python standard library regex and hashlib.

Reviews (0)

No results found