IBM Docling Free and OpenSource Advanced Document Parser

In this video, we will discuss IBM Docling which is a great free and opensource document parser.

Timestamps
0:00 Introduction
2:11 Why Docling?
4:59 Tutorial overview
5:51 Installs and Imports
8:30 Simple usage of Docling
9:37 Go through parsing results.
12:04 Docling with local documents.
13:44 Docling pipelines
16:27 Get metadata from Docling
18:37 Iterate through text, table and image units
24:34 Save pages as images
27:43 Extract and save images of a document
29:32 Extract and save tables of a document
32:42 OCR examples with Docling
38:03 End Notes

If you learn something help me to buy a coffee :-) https://www.buymeacoffee.com/geekaven...

Contact me for your LLM based projects via Fiverr : https://www.fiverr.com/s/R7xWeax

Link to Notebook: https://buymeacoffee.com/geekavenueyt...
Link to Docling: https://github.com/DS4SD/docling




#langchain #chatgpt #openai #chromadb #langchainmultiplefiletypes #documentqna #docling #parser #vectordb
parses, RAG parsers, free parsers, langchain parsers