Skip to content

Commit

Permalink
Fix documentation link, sentence grammar
Browse files Browse the repository at this point in the history
  • Loading branch information
MarkLindblad committed Oct 5, 2024
1 parent 3e70cd5 commit 0e69ef6
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions docs/source/index.rst
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@ Welcome to Aryn!
================
Aryn is an LLM-powered data preparation, processing, and analytics system for complex, unstructured documents like PDFs, HTML, presentations, and more. With Aryn, you can prepare data for GenAI and RAG applications, power high-quality document processing workflows, and run analytics on large document collections with natural language. It includes two components: The Aryn Partitioning Service and Sycamore.

The Aryn Partitioning Service (APS) is a serverless, GPU-powered API for segmenting and labeling PDF documents, doing OCR, and extracting tables and images. It returns the output in JSON. APS runs the Aryn Partitioner and its `state-of-the-art, open source deep learning AI model <https://huggingface.co/Aryn/deformable-detr-DocLayNet>`_ trained on 80k+ enterprise documents. You can use it to partition documents and extract information directly in your code, or use with Sycamore for additional processing. `Sign-up here for free <https://www.aryn.ai/get-started>`_ to get an API Key and use the `Aryn Playground <https://play.aryn.cloud/partitioning>`_ to visually see how it segments and processes your own documents. Or, watch the Aryn Partitioning Service in action in `this video <https://www.aryn.ai/?name=ArynPartitioningService_Intro>`_.
The Aryn Partitioning Service (APS) is a serverless, GPU-powered API for segmenting and labeling PDF documents, doing OCR, and extracting tables and images. It returns the output in JSON. APS runs the Aryn Partitioner and its `state-of-the-art, open source deep learning AI model <https://huggingface.co/Aryn/deformable-detr-DocLayNet>`_ trained on 80k+ enterprise documents. You can use it to partition documents and extract information directly in your code, or use it with Sycamore for additional processing. `Sign-up here for free <https://www.aryn.ai/get-started>`_ to get an API Key and use the `Aryn Playground <https://play.aryn.cloud/partitioning>`_ to visually see how it segments and processes your own documents. Or, watch the Aryn Partitioning Service in action in `this video <https://www.aryn.ai/?name=ArynPartitioningService_Intro>`_.

Sycamore is a document processing engine covered under the Apache v2.0 license. It's built for complex unstructured data, such as documents, presentations, transcripts, embedded tables, and internal knowledge repositories. Sycamore provides a declarative dataflow abstraction called a DocSet to make manipulating unstructured documents easy and scalable. It’s similar in style to Apache Spark and Pandas, but for collections of unstructured documents. DocSets can be used not only for extracting, enriching, summarizing, and cleaning unstructured data, but also for running powerful analytics on these datasets.

Expand Down Expand Up @@ -57,7 +57,7 @@ Next, you can:
..
You can specify additional options (e.g. table extraction), and a list of these options is :doc: `here </aryn_cloud/aryn_partitioning_service.html#specifying-options>`
You can specify additional options (e.g. table extraction), and a list of these options is :doc:`here </aryn_cloud/specifying_options>`.

|
Expand Down

0 comments on commit 0e69ef6

Please sign in to comment.