chore: update the README to reflect all input/output format and highlight the DoclingDocument data-structure.

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
This commit is contained in:
Peter Staar 2024-10-30 05:52:43 +01:00
parent dda2645d4c
commit c03d29d632

View File

@ -22,8 +22,9 @@ Docling parses documents and exports them to the desired format with ease and sp
## Features
* 🗂️ Multi-format support for input (PDF, DOCX etc.) & output (Markdown, JSON etc.)
* 🗂️ Multi-format support for input (PDF, DOCX, PPTX, HTML, AsciiDoc, MarkDown) and output (Markdown, JSON, YAML)
* 📑 Advanced PDF document understanding incl. page layout, reading order & table structures
* 🧩 Strongly typed Pydantic v2 data structure named [DoclingDocuyment](https://github.com/DS4SD/docling-core/blob/main/docling_core/types/doc/document.py#L945) which supports hierarchies and provides native iterators and chunkers.
* 📝 Metadata extraction, including title, authors, references & language
* 🤖 Seamless LlamaIndex 🦙 & LangChain 🦜🔗 integration for powerful RAG / QA applications
* 🔍 OCR support for scanned PDFs