Beginner Section

Jina AI equips developers with the tools to build end-to-end sophisticated search applications that can be easily scaled and deployed in the cloud.

Check out this video to understand how different products connect together in Jina Ecosystem to provide a holistic search experience:

The Neural Search Ecosystem from Jina AI

DocArray is a data structure for unstructured data. It can accommodate all kinds of data including text, images, audio, video, etc. You can get started right away with DocArray without any prerequisites since it is designed to work with Python intuitively.

To get started with DocArray, you can install it with the following command:

via PyPI

via Conda

pip install docarray

To install DocArray with all the external dependencies, use the following command:

pip install "docarray[full]"

Docs - DocArray

Interactive tutorial

DocArray also provides a safe and secure environment for collaborating with others. It lets you share a DocumentArray using the push/pull feature over the internet. You can push a pre-processed DocumentArray with a unique ID, and your colleague sitting in a different part of the world can just pull and use it. To understand more about this feature, check out the blog and documentation.

In the above section, we learned how Documents are the primary data type and can be used to contain any kind of data like text, images, audio, videos, tables, 3D Mesh, etc. We have designed a few tutorials for you to learn how to manipulate different data types in DocArray:

Text

Images

Audio

Video

Table

3D Mesh

A multimodal document consists of a mixture of data modalities such as text, image, audio, video, etc. For example, the article card from The Washington Post in the below figure can be viewed as a multimodal document as it consists of a sentence, an image, and some tags (i.e. author, column section).

DocArray provides dataclass as a high-level API for representing a multimodal document using nested Document structure. It follows the design of the standard Python dataclass, allowing users to represent a complicated multimodal document intuitively via the Document/DocumentArray API.

DocArray provides a decorator @dataclass and a set of multimodal types in docarray.typing, which allows the left multimodal document to be represented as the right code snippet:

 from docarray import dataclass, Document 
 from docarray.typing import Image, Text, JSON 
 @dataclass 
 class WPArticle: 
 banner: Image 
 headline: Text 
 meta: JSON 
 a = WPArticle( 
 banner='dog-cat-flight.png', 
 headline='Everything to know about flying with pets, from picking your seats to keeping your animal calm', 
 meta={ 
 'author': 'Nathan Diller', 
 'column': 'By the Way - A Post Travel Destination', 
 }, 
) 

Before moving further to build real-world applications with Jina, we recommend you join our community channels. So, even if you get stuck, there is no stopping!