Overview
Welcome to the programmatic interface! This is where you integrate Chunklet-py's chunking capabilities directly into your Python apps. Building RAG pipelines, data processing workflows, or custom AI solutions? We've got you covered.
-
Sentence Splitter
Precisely splits text into semantically meaningful sentences across 50+ languages with intelligent detection and complex structure handling.
Essential for preparing clean text data for NLP tasks, LLMs, and any application that needs accurate sentence boundaries.
-
Document Chunker
Transforms plain text and diverse document formats (
.pdf,.docx,.epub,.txt,.tex,.html,.hml,.md,.rst,.rtf,.odt,.csv, and.xlsx) into perfectly sized, context-aware chunks with flexible composable constraints and intelligent overlap for optimal LLM and embedding performance.Perfect for RAG systems, document analysis, and any workflow that needs smart text segmentation with full control over chunk sizes.
-
Code Chunker
Intelligently chunks source code while preserving logical structure and context and maintaining code semantics across functions, classes, and modules.
Language-agnostic and lightweight - ideal for code understanding and generation tasks, analysis, documentation, and AI model training.
-
Text Chunk Visualizer
Interactive web interface for real-time chunk visualization, parameter tuning, and exploring chunking results with live feedback.
Perfect for experimenting with chunking strategies, comparing different settings, and understanding how your text gets processed.
Pick a card below to get started! 📇