docling

Get your documents ready for gen AI

View on GitHub↗Upstream docling-project/docling↗

Builder

docling-project

docling-project • individual

Stars

56,953

Using upstream star count

Forks

3,861

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Jul 9, 2024

Project creation date

README Summary

Docling is a Python library that converts documents from various formats (PDF, DOCX, PPTX, images, HTML) into structured formats optimized for generative AI applications. It provides advanced PDF understanding capabilities including layout analysis, table structure recognition, and metadata extraction. The tool offers both programmatic APIs and CLI interfaces for seamless document processing workflows.

AI Dev Skills

Unmapped

Tags

Document ProcessingOptical Character Recognition (OCR)Computer Vision for Document AnalysisMulti-modal Content ExtractionRetrieval-Augmented Generation (RAG) PreprocessingDocument Layout AnalysisTable Structure RecognitionPDF ProcessingImage-to-Text ConversionImageDocument Digitization and ArchivalSelf-hostedFinancial ServicesRetrieval-Augmented Generation (RAG)RAG System Data PreparationTabularEnterprise Document ManagementMultimodal AIDocument Content Search and IndexingTextAutomated Document Processing PipelinesTable Data ExtractionDocument Question AnsweringDocker ContainersHealthcareEnterprise Knowledge Base CreationMultimodalResearch and AcademiaCompliance and AuditDocument AICompound AI SystemsCloud APIOn-premiseLegal TechMulti-format Document IngestionPythonCLI

Taxonomy

Recent Activity

Updated 24 days ago

7 Days

30 Days

90 Days

Quality

beta

Quality: high
Maturity: beta

PM Skills

Scale & ReliabilityDeveloper Platform

Languages

Python100.0%

Timeline

Project created: Jul 9, 2024
Forked: Mar 22, 2026
Your last push: 24 days ago
Upstream last push: 8 days ago
Tracked since: Mar 20, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…