Skip to content
@DS4SD

IBM Deep Search

Developer tools for IBM Deep Search
README.md

Welcome to IBM Deep Search

Deep Search extracts and structures data from documents in four steps: Parse, Interpret, Index, and Integrate. Try out the first steps on our public system, where we have a live PDF to JSON inspector. With the inspector, you can see how your (programmatic) PDF documents get converted into JSON.

Deep Search also provides a programmatic access to the service, for easy integration with other tools or in order to do bulk conversion. Our python toolkit provides these functionalities both as a client and library. Our examples repository is very useful to get started.


Publications

Find here our extensive list of publications!

Gallery

Image extraction Table Understanding
image table
List resolution Math Formula
list math
Complex Layout Colored layout
complex complex

Pinned Loading

  1. docling docling Public

    🥚 Transform PDF to JSON or Markdown with ease and speed 🐣

    Python 466 46

  2. deepsearch-toolkit deepsearch-toolkit Public

    Interact with the Deep Search platform for new knowledge explorations and discoveries

    Python 120 18

  3. deepsearch-examples deepsearch-examples Public

    Examples using the Deep Search functionalities

    Python 35 14

  4. DocLayNet DocLayNet Public

    DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis

    235 15

Repositories

Showing 10 of 24 repositories
  • docling-core Public

    A python library to define and validate data types in Docling.

    DS4SD/docling-core’s past year of commit activity
    Python 12 MIT 1 2 1 Updated Sep 20, 2024
  • docling Public

    🥚 Transform PDF to JSON or Markdown with ease and speed 🐣

    DS4SD/docling’s past year of commit activity
    Python 466 MIT 46 8 5 Updated Sep 20, 2024
  • deepsearch-glm Public

    Create fast graph language models from converted PDF documents for knowledge extraction and Q&A.

    DS4SD/deepsearch-glm’s past year of commit activity
    C++ 10 MIT 2 1 3 Updated Sep 20, 2024
  • docling-ibm-models Public
    DS4SD/docling-ibm-models’s past year of commit activity
    Python 15 MIT 1 3 1 Updated Sep 20, 2024
  • docling-parse Public

    Simple package to extract text with coordinates from programmatic PDFs

    DS4SD/docling-parse’s past year of commit activity
    C++ 7 MIT 2 0 1 Updated Sep 20, 2024
  • ci-tester Public
    DS4SD/ci-tester’s past year of commit activity
    0 0 0 0 Updated Sep 20, 2024
  • DS4SD.github.io Public
    DS4SD/DS4SD.github.io’s past year of commit activity
    CSS 6 MIT 1 0 0 Updated Sep 18, 2024
  • docling-serve Public

    Running Docling as an API service

    DS4SD/docling-serve’s past year of commit activity
    Makefile 5 MIT 1 0 0 Updated Sep 13, 2024
  • quackling Public archive

    Build document-native LLM applications

    DS4SD/quackling’s past year of commit activity
    Python 47 MIT 1 0 0 Updated Sep 11, 2024
  • deepsearch-toolkit Public

    Interact with the Deep Search platform for new knowledge explorations and discoveries

    DS4SD/deepsearch-toolkit’s past year of commit activity
    Python 120 MIT 18 8 11 Updated Sep 9, 2024
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Most used topics

Loading…