chore: update the with input formats and DoclingDocument (#188)

---------

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>

.github/workflows/cd-docs.yml

@@ -0,0 +1,14 @@
+name: "Run Docs CD"
+
+on:
+  push:
+    branches:
+      - "main"
+
+jobs:
+  build-deploy-docs:
+    uses: ./.github/workflows/docs.yml
+    with:
+      deploy: true
+    permissions:
+      contents: write

.github/workflows/cd.yml

@@ -10,12 +10,6 @@ env:
 jobs:
   code-checks:
     uses: ./.github/workflows/checks.yml
-  build-deploy-docs:
-    uses: ./.github/workflows/docs.yml
-    with:
-      deploy: true
-    permissions:
-      contents: write
   pre-release-check:
     runs-on: ubuntu-latest
     outputs:

.github/workflows/ci-docs.yml

@@ -0,0 +1,16 @@
+name: "Run Docs CI"
+
+on:
+  pull_request:
+    types: [opened, reopened, synchronize]
+  push:
+    branches:
+      - "**"
+      - "!gh-pages"
+
+jobs:
+  build-docs:
+    if: ${{ github.event_name == 'push' || (github.event.pull_request.head.repo.full_name != 'DS4SD/docling' && github.event.pull_request.head.repo.full_name != 'ds4sd/docling') }}
+    uses: ./.github/workflows/docs.yml
+    with:
+      deploy: false

.github/workflows/ci.yml

@@ -6,6 +6,7 @@ on:
   push:
     branches:
       - "**"
+      - "!main"
       - "!gh-pages"
 
 env:
@@ -16,8 +17,3 @@ jobs:
   code-checks:
     if: ${{ github.event_name == 'push' || (github.event.pull_request.head.repo.full_name != 'DS4SD/docling' && github.event.pull_request.head.repo.full_name != 'ds4sd/docling') }}
     uses: ./.github/workflows/checks.yml
-  build-docs:
-    if: ${{ github.event_name == 'push' || (github.event.pull_request.head.repo.full_name != 'DS4SD/docling' && github.event.pull_request.head.repo.full_name != 'ds4sd/docling') }}
-    uses: ./.github/workflows/docs.yml
-    with:
-      deploy: false

README.md

@@ -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.)
+* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, Images, HTML, AsciiDoc, Markdown) and exports to Markdown and JSON
-* 📑 Advanced PDF document understanding incl. page layout, reading order & table structures
+* 📑 Advanced PDF document understanding including page layout, reading order & table structures
+* 🧩 Unified, expressive [DoclingDocument](https://ds4sd.github.io/docling/concepts/docling_document/) representation format
 * 📝 Metadata extraction, including title, authors, references & language
 * 🤖 Seamless LlamaIndex 🦙 & LangChain 🦜🔗 integration for powerful RAG / QA applications
 * 🔍 OCR support for scanned PDFs

docs/concepts/docling_document.md

@@ -7,6 +7,8 @@ pydantic datatype, which can express several features common to documents, such
 * Layout information (i.e. bounding boxes) for all items, if available
 * Provenance information
 
+The definition of the Pydantic types is implemented in the module `docling_core.types.doc`, more details in [source code definitions](https://github.com/DS4SD/docling-core/tree/main/docling_core/types/doc).
+
 It also brings a set of document construction APIs to build up a `DoclingDocument` from scratch.
 
 ## Example document structures

docs/index.md

@@ -19,8 +19,9 @@ 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.)
+* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, Images, HTML, AsciiDoc, Markdown) and exports to Markdown and JSON
 * 📑 Advanced PDF document understanding incl. page layout, reading order & table structures
+* 🧩 Unified, expressive [DoclingDocument](./concepts/docling_document.md) representation format
 * 📝 Metadata extraction, including title, authors, references & language
 * 🤖 Seamless LlamaIndex 🦙 & LangChain 🦜🔗 integration for powerful RAG / QA applications
 * 🔍 OCR support for scanned PDFs