mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-06 00:21:29 +00:00
8e6bc10ba1
To test: > cd docs && make html Changelogs: * Added verbiage about the cap limit and data usage for the Freemium AP * Added deprecated warning on Staging bricks * Added warning and code examples to use the SaaS API Endpoints using CLI-vs-SDKs * Fixed example page formatting * Added deprecation warning on ``model_name`` param in favor of ``hi_res_model_name`` * Added ``extract_images_in_pdf`` usage and code example in ``partition_pdf`` section * Reorganized and improved the documentation Intro section
18 lines
543 B
ReStructuredText
18 lines
543 B
ReStructuredText
Best Practices
|
|
==============
|
|
|
|
Unstructured offers a few strategies and models to extract document information. These best practices are intended to provide guidelines to configure the ``strategy`` and ``model`` configurations to optimize document information extraction.
|
|
|
|
High-level overview of available strategies and models in ``Unstructured`` library:
|
|
|
|
.. image:: imgs/strategy.png
|
|
:width: 1000
|
|
:alt: strategy
|
|
|
|
.. toctree::
|
|
:maxdepth: 1
|
|
|
|
best_practices/strategies
|
|
best_practices/models
|
|
best_practices/table_extraction_pdf
|