Overview
Welcome to the programmatic side of Chunklet-py! This is where you integrate Chunklet's intelligent text and code chunking capabilities directly into your Python applications. Whether you're building RAG pipelines, data processing workflows, or custom AI solutions, Chunklet provides a flexible and powerful API to meet your needs.
-
Sentence Splitter
Precisely split raw text into semantically meaningful sentences, fluently handling over 50 languages with intelligent detection and complex structures.
-
Plain Text Chunker
Process and chunk plain text documents into perfectly sized, context-aware segments. It offers flexible constraint-based chunking with intelligent overlap, optimizing text for downstream tasks like embedding and LLM input.
-
Document Chunker
Work with diverse document formats including
.pdf,.docx,.epub,.txt,.tex,.html,.hml,.md,.rst, and.rtf, transforming them into structured, chunked outputs. -
Code Chunker
Intelligently chunk source code, preserving its logical structure and context. This language-agnostic and lightweight tool is perfect for analysis, documentation, or AI model training.
Ready to get started? Click on any of the cards above to explore the specific chunker that fits your needs!