OPEN LINK ↗
// 3h agoOPENSOURCE RELEASE
Chunkr launches open-source document intelligence API for RAG pipelines
Chunkr is an open-source document intelligence API that handles layout analysis, OCR, and semantic chunking to convert complex documents into RAG-ready formats. It offers an AGPL release for self-hosting alongside a managed cloud version with customizable model configurations.
// ANALYSIS
Chunkr offers a robust open-source solution for one of the most tedious parts of RAG setup: document parsing and chunking. By tackling layout analysis and OCR directly, it can potentially save developers significant time.
- –Open-source (AGPL) with a managed cloud option provides flexibility for different usage scales.
- –Handles multiple complex document types (PDFs, PPTs, Word, images).
- –Customizable model configurations allow users to swap in different models as needed.
// TAGS
document-intelligenceocrragsemantic-chunkingopen-sourceapichunkr
DISCOVERED
3h ago
2026-06-30
PUBLISHED
5h ago
2026-06-30
RELEVANCE
8/ 10
AUTHOR
so_sthbryan