Examples for Jina

Table of Contents

• Adding Tests for Examples
• Community
• License

Start Here

First a little light background reading, and then let's jump in and build our first app!

	What is Neural Search? AI-powered search with less effort, more flexibility
	Jina 101: First Thing to Learn About Jina   English • 日本語 • français • Deutsch • Русский язык • 中文

Tutorials	Level
My First Jina App Brand new to neural search? Not for long! Use cookiecutter to search through Star Trek scripts using Jina	🐣

Search Text

Tutorials	Level
Build a NLP Semantic Search System with Transformers Upgrade from plain search to sentence search and practice your Flows and Pods by searching South Park scripts	🐣
Multilingual semantic search with Laser Language-agnostic search on WMTData	🐣
Search Lyrics with Transformers and PyTorch Get a better understanding of chunks by searching a lyrics database. Now with shiny front-end!	🐣

Search Images

Tutorials	Level
Search Flowers with TorchVision Build an image search system and define your own executors and run them in Docker	🐣
Google's Big Transfer Model in (Poké-)Production Use SOTA visual representation for searching Pokémon!	🚀
Object detection with fasterrcnn and MobileNetV2 Detect, index and query similar objects	🚀

Search Audio

Tutorials	Level
Search YouTube audio data with Vggish A demo of neural search for audio data based Vggish model.	🐣
Search audio based on Mel Frequency Cepstral Coefficients	🐣

Search Video

Tutorials	Level
Search Tumblr GIFs with KerasEncoder Use prefetching and sharding to improve the performance of your index and query flow when searching animated GIFs.	🐣

Cross Modal Search

Tutorials	Level
Search images from captions and vice-versa Use one modality (text) to search another (images)	🕊

Multi Modal Search

Tutorials	Level
Search images with 2 modalities in the query Use more than one modality (image+text) to search images	🕊

Miscellaneous

Tutorials	Level
Build complex logic, structures and filters with Query Language Create separate indexes and queries for different clothing in Fashion-MNIST	🐣
Search MNIST with Mindspore Search handwriting examples using Mindspore	🚀

Improve Performance and Scalability

Tutorials	Level
Video Semantic Search in Scale with Prefetching and Sharding Increase performance by using prefetching and sharding	🕊
Revisit "Hello, World!" in a Client-Server Architecture Run a Flow remotely and use a local client to connect to it	🕊
Distribute Your Workflow Remotely Run Jina on remote instances and distribute your workflow	🕊
Run Jina Pod via Docker Container Learn how Jina solves complex dependencies easily with Docker container	🕊
Index and query with FAISS Build a vector search engine that finds the closest vector in the database to a query.	🚀

Extend and Share Jina

Tutorials	Level
Extend Jina by Implementing Your Own Executor Implement your own ideas into Jina's plugin	🕊
Share Your Extension with the World Use Jina Hub and share your extensions with engineers around the globe	🚀

Adding Tests for Examples

You are highly encouraged to add a test for your example so that we will be alerted if it breaks in the future:

1. Put your test data in the tests folder. The test data can be a few text sentences, images or audio samples
2. Create test_[your_example].py in the tests folder. Add your test cases to the tests file with meaningful asserts depending on example input and output
3. Run the test locally to confirm before pushing with pytest
4. Add your example folder name to the path variable in matrix of .github/worflows/ci.yml. This will trigger your example test on creating a pull request.

Tips

• For reference, check out the tests folder from South Park example if your data is about text and object search example for images.
• Try using the original example function by importing them to the test. Avoid any modifications to original Flow or logic.
• Use the pytest fixture tmpdir for temporary directory

Community

• Slack channel - a communication platform for developers to discuss Jina
• LinkedIn - get to know Jina AI as a company and find job opportunities
• - follow us and interact with us using hashtag #JinaSearch
• Company - know more about our company, we are fully committed to open-source!

License

Copyright (c) 2020 Jina AI Limited. All rights reserved.

Jina is licensed under the Apache License, Version 2.0. See LICENSE for the full license text.