mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: add architecture outline (#341)

Browse Source 
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
This commit is contained in:
Panos Vagenas
2024-11-15 12:52:41 +01:00
committed by GitHub
parent 835e077b02
commit 25fd149c38
7 changed files with 23 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
docs/concepts/architecture.md Normal file
View File

@@ -0,0 +1,19 @@
![docling_architecture](../assets/docling_arch.png)
In a nutshell, Docling's architecture is outlined in the diagram above.
For each document format, the *document converter* knows which format-specific *backend* to employ for parsing the document and which *pipeline* to use for orchestrating the execution, along with any relevant *options*.
!!! tip
While the document converter holds a default mapping, this configuration is parametrizable, so e.g. for the PDF format, different backends and different pipeline options can be used — see [Usage](../usage.md#adjust-pipeline-features).
The *conversion result* contains the [*Docling document*](./docling_document.md), Docling's fundamental document representation.
Some typical scenarios for using a Docling document include directly calling its *export methods*, such as for markdown, dictionary etc., or having it chunked by a *chunker*.
For more details on Docling's architecture, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869).
!!! note
The components illustrated with dashed outline indicate base classes that can be subclassed for specialized implementations.