REVIEW 6 cited by
Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We introduce Docling, an easy-to-use, self-contained, MIT-licensed, open-source toolkit for document conversion, that can parse several types of popular document formats into a unified, richly structured representation. It is powered by state-of-the-art specialized AI models for layout analysis (DocLayNet) and table structure recognition (TableFormer), and runs efficiently on commodity hardware in a small resource budget. Docling is released as a Python package and can be used as a Python API or as a CLI tool. Docling's modular architecture and efficient document representation make it easy to implement extensions, new features, models, and customizations. Docling has been already integrated in other popular open-source frameworks (e.g., LangChain, LlamaIndex, spaCy), making it a natural fit for the processing of documents and the development of high-end applications. The open-source community has fully engaged in using, promoting, and developing for Docling, which gathered 10k stars on GitHub in less than a month and was reported as the No. 1 trending repository in GitHub worldwide in November 2024.
Forward citations
Cited by 6 Pith papers
-
HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding
A training-free, two-stage speculative decoding scheme accelerates VLM document parsers by ~2.8x end-to-end (up to 7x) while keeping parsing accuracy essentially unchanged.
-
The Hidden Threat in Plain Text: Attacking RAG Data Loaders
Invisible characters and formatting tricks in ingested documents survive popular RAG data loaders and can manipulate end-to-end RAG outputs.
-
Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence
Granite Vision is a ~3B parameter open-weights vision-language model that reaches state-of-the-art scores on document understanding benchmarks despite its small size.
-
Advancing Subsurface Discovery and Geothermal Monitoring with an Agentic Artificial Intelligence Framework
GAIA couples an LLM planning agent with retrieval-augmented search and standard seismological tools to automate geothermal monitoring, but no quantitative evaluation is reported.
-
Automated Evidence Extraction and Scoring for Corporate Climate Policy Engagement: A Multilingual RAG Approach
A multilingual RAG pipeline combining layout-aware parsing, Nomic embeddings, and few-shot prompting extracts and stance-classifies corporate climate lobbying evidence nearly as accurately as gold human snippets.
-
Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding
Using a multimodal model to chunk PDF pages in batches with cross-page context raised RAG answer accuracy from 0.78 to 0.89 on the authors' private benchmark.
Discussion (0). Continue with ORCID to comment.