THIS WEEK IN JINA AI
Jina 3.3 drops, DocArray Dataclasses and more
Not to mention our upcoming office hours, tattoo search, CLIP-as-service examples, and more…
New Releases
DocArray 0.12
This new release introducesdataclass
support on multimodal data. Read up its design, usage, and examples with CLIP
CLIP-as-service
CLIP-as-service now has an example server for you to generate CLIP embeddings on the cloud. Simply pip install clip_client
and then
from clip_client import Client
c = Client('grpc://demo-cas.jina.ai:51000')
c.encode(your-data-to-embed)
Test it in your browser here
Jina 3.3
This release comes with a lot of improvements, some of which involve breaking changes. You can install it with:pip install -U jina
New features:
- Removed Head Pod when deploying non-sharded Executors
- Introduced shared Executors
- Improved support for workspace in Executors
- Added
volumes
to Docker Compose YAML - Added support for compression in GRPC communication
- Added TLS support for communication between client and Gateway
Breaking changes:
- In order to allow Load Balancing between the Executor replicas, a Service Mesh needs to be installed in the cluster
Read the full changelog here.
Community Showcase
Kevin Zehnder shared his project in the Jina AI slack community and we absolutely loved it. Kevin used Jina to build a text-to-image and image-to-image Neural Search for Tattoos.
Check out the code on GitHub and don’t forget to star it ⭐
Upcoming Events
Office Hours
If you have technical issues with Jina, we would love to discuss them all during our Office Hours on Thursday April 28 at 19:00 CET! (convert to your timezone)
Follow all our events on Meetup
Blog
Recent Events
Jina NOW at FOSSASIA
Our Solutions Lead, Florian Hönicke, presented at the FOSSASIA SUMMIT 2022! He explained how to use the open-source Jina NOW for various visual search cases such as — image NFTs, re-id, X-ray, photo apps, and customer data.
Engineering All Hands
Just like every second Tuesday of the month, we had our Engineering All Hands!
Connor Shorten joined us this time. He is the founder of Henry AI Labs and research scientist at SeMI Technologies. He discussed the crucial need for robustness in Deep Learning and how vector search can help you achieve it!
Office Hours
Community members who had technical issues came to discuss them during our recent Office Hours.
Contribute to our Good First Issues Repo
Our good first issues repo features some great issues for those looking to take their first steps into open source with Jina. Check them out here:
- Example: NFT/blockchain search engine
- Update Jina Hub Executors for Jina 3.0+
- React component for Jina
Get Jina Certified
Take our Learning Bootcamp quiz with beginner, intermediate and advanced tracks to etch your name in our Hall of Fame!
Join our Communities
- Slack: Our Slack community now boasts over 2,700 neural search enthusiasts. We would love to have you there!✨
- Meetup: Join our meetup group to stay updated with our latest events. Whether you’re AI engineers, Python Engineers, Data Scientists, CTO, Machine Learning Researchers, Open Source Evangelists, AI Product Managers, or just plain old interested, we’d love to meet up with you!
- Newsletter: Subscribe to our newsletter if you want to hear from us.