DS4SD/quackling
Build document-native LLM applications
ArchivedProvides Docling-powered PDF extraction with structured document models for RAG and retrieval tasks, offering plug-and-play adapters for LlamaIndex and LangChain. Features hierarchical document chunking that preserves native structure (tables, sections, bounding boxes) rather than plain text, and includes node parsers that maintain semantic relationships across document elements. Integrates seamlessly with vector stores like Milvus and supports hybrid retrieval combining dense and sparse embeddings.
No commits in the last 6 months.
Stars
56
Forks
2
Language
Python
License
MIT
Category
Last pushed
Sep 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/DS4SD/quackling"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR...
kreuzberg-dev/kreuzberg
A polyglot document intelligence framework with a Rust core. Extract text, metadata, and...
yfedoseev/pdf_oxide
The fastest PDF library for Python and Rust. Text extraction, image extraction, markdown...
opendataloader-project/opendataloader-pdf
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
NanoNets/docext
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking...