Docling

Open-source toolkit by IBM Research for parsing diverse document formats (PDF, DOCX, PPTX, HTML, XLSX, images, audio) into a unified structured representation ideal for GenAI and RAG workflows. Hosted by LF AI & Data Foundation.

document-parsing-frameworksRecently released
79
Hero Score
Popularity
76
Performance
70
Ecosystem
100
Maturity
76
Dev Experience
72
⭐ 60,752 stars⬇ 1.8M downloads/wkFirst release: Jul 2024Last release: Jun 2026
Async Support: YesPlugin Extensions: Very highSpeed: MediumDoc Quality: Very highLearning Curve: Medium

Pros

  • Parses many formats (PDF, DOCX, PPTX, HTML, XLSX, images, audio) into unified DoclingDocument model for AI/LLM use cases
  • Advanced PDF understanding including layout, reading order, table structures, OCR, and VLM support (GraniteDocling)
  • Native integrations with LangChain, LlamaIndex, Crew AI, Haystack, and MCP server for agentic applications

Cons

  • Some features require heavyweight optional dependencies (OCR backends, VLM models, ASR models)
  • Complex documents with unusual layouts may still need custom post-processing
  • Initial model download and setup can be time-consuming for full feature set

Alternatives in document-parsing-frameworks

Compare Python Packages with ease.